CN113825152A - Capacity control method, network management device, management arrangement device, system and medium - Google Patents
Capacity control method, network management device, management arrangement device, system and medium Download PDFInfo
- Publication number
- CN113825152A CN113825152A CN202010561024.XA CN202010561024A CN113825152A CN 113825152 A CN113825152 A CN 113825152A CN 202010561024 A CN202010561024 A CN 202010561024A CN 113825152 A CN113825152 A CN 113825152A
- Authority
- CN
- China
- Prior art keywords
- network
- capacity control
- capacity
- flow
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 77
- 230000009467 reduction Effects 0.000 claims description 44
- 238000013528 artificial neural network Methods 0.000 claims description 35
- 238000007781 pre-processing Methods 0.000 claims description 10
- 238000012217 deletion Methods 0.000 claims description 7
- 230000037430 deletion Effects 0.000 claims description 7
- 238000004140 cleaning Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- OOXMVRVXLWBJKF-DUXPYHPUSA-N n-[3-[(e)-2-(5-nitrofuran-2-yl)ethenyl]-1,2,4-oxadiazol-5-yl]acetamide Chemical compound O1C(NC(=O)C)=NC(\C=C\C=2OC(=CC=2)[N+]([O-])=O)=N1 OOXMVRVXLWBJKF-DUXPYHPUSA-N 0.000 claims 2
- 230000008859 change Effects 0.000 abstract description 8
- 230000010485 coping Effects 0.000 abstract description 5
- 238000007726 management method Methods 0.000 description 83
- 230000006870 function Effects 0.000 description 25
- 238000010586 diagram Methods 0.000 description 19
- 238000012549 training Methods 0.000 description 16
- 230000008602 contraction Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 4
- 230000008520 organization Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000004927 fusion Effects 0.000 description 3
- 230000010354 integration Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- YBJHBAHKTGYVGT-ZKWXMUAHSA-N (+)-Biotin Chemical compound N1C(=O)N[C@@H]2[C@H](CCCCC(=O)O)SC[C@@H]21 YBJHBAHKTGYVGT-ZKWXMUAHSA-N 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- FEPMHVLSLDOMQC-UHFFFAOYSA-N virginiamycin-S1 Natural products CC1OC(=O)C(C=2C=CC=CC=2)NC(=O)C2CC(=O)CCN2C(=O)C(CC=2C=CC=CC=2)N(C)C(=O)C2CCCN2C(=O)C(CC)NC(=O)C1NC(=O)C1=NC=CC=C1O FEPMHVLSLDOMQC-UHFFFAOYSA-N 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 239000004480 active ingredient Substances 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011038 discontinuous diafiltration by volume reduction Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/02—Arrangements for optimising operational condition
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention provides a capacity control method, network management equipment, management arrangement equipment, a system and a medium. The method comprises the steps that network flow data are collected through a VNF network element; predicting network traffic based on the trained prediction model according to the network traffic data; determining a network capacity control decision according to a prediction result of the network flow; sending a network capacity control instruction to a management orchestration MANO device to instruct the MANO device to perform the network capacity control decision. The technical scheme adaptively controls the network capacity by predicting the network flow, thereby coping with the change of the network flow, meeting the network service requirement and improving the flexibility of controlling the network capacity.
Description
Technical Field
Embodiments of the present invention relate to wireless communication networks, and for example, to a capacity control method, a network management device, a management arrangement device, a system, and a medium.
Background
Software Defined Network (SDN) is an open Network architecture, and has the characteristics of centralized control, openness, and programmability. The network management equipment can realize logic centralized control based on the SDN controller, obtain the global state view of the whole network and optimally control the whole network. Network Function Virtualization (NFV) is essentially Virtualization and clouding of Network devices, so as to implement software and hardware decoupling by Virtualization, implement sharing of software and hardware resources by clouding, and implement rapid deployment of Network devices without hardware differences. Under the fusion architecture of the SDN and the NFV, network traffic has a tidal effect, a holiday effect, burstiness, and the like, while network traffic that can be carried by fixed network devices is greatly limited, and a constant throughput and a network topology cannot flexibly cope with various characteristics of the network traffic, that is, network capacity is difficult to adapt to changes of network traffic, and service requirements are difficult to meet.
Disclosure of Invention
The embodiment of the invention provides a capacity control method, network management equipment, management arrangement equipment, a system and a medium, which are used for improving the flexibility of network capacity control.
The embodiment of the invention provides a capacity control method, which comprises the following steps:
collecting Network flow data through a Virtual Network Function (VNF) Network element;
predicting network traffic based on the trained prediction model according to the network traffic data;
determining a network capacity control decision according to the prediction result of the network flow;
sending a network capacity control instruction to a Management and organization (MANO) device to instruct the MANO device to execute the network capacity control decision.
The embodiment of the invention also provides another capacity control method, which comprises the following steps:
receiving a network capacity control instruction, wherein the network capacity control instruction comprises a network capacity control decision, and the network capacity control decision is determined by network management equipment according to a prediction result of network flow;
and reducing or expanding the network capacity according to the network capacity control instruction.
An embodiment of the present invention further provides a network management device, including:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a capacity control method as described above.
An embodiment of the present invention further provides a management arrangement device, including:
one or more processors;
storage means for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement another capacity control method as described above.
An embodiment of the present invention further provides a network capacity control system, including: a VNF network element, the above network management device, and the above management orchestration device;
and the VNF network element is used for receiving the data acquisition request of the network management equipment and returning network flow data to the network management equipment.
An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements one of the above capacity control methods.
Drawings
FIG. 1 is a flow chart of a capacity control method according to an embodiment;
FIG. 2 is a flow chart of a capacity control method according to another embodiment;
FIG. 3 is a schematic diagram of a back propagation neural network provided in one embodiment;
FIG. 4 is a schematic diagram illustrating controlling network traffic according to an embodiment;
fig. 5 is a schematic diagram illustrating interaction between network management equipment, a VNF network element, and a MANO in a capacity control process according to an embodiment;
FIG. 6 is a flow chart of a capacity control method according to yet another embodiment;
fig. 7 is a schematic structural diagram of a capacity control apparatus according to an embodiment;
fig. 8 is a schematic structural diagram of a capacity control device according to another embodiment;
fig. 9 is a schematic hardware structure diagram of a network management device according to an embodiment;
FIG. 10 is a diagram illustrating a hardware configuration of an orchestration device according to an embodiment;
FIG. 11 is a schematic diagram of a capacity control system according to an embodiment;
fig. 12 is a schematic diagram illustrating an implementation of capacity control according to an embodiment.
Detailed Description
The present application will be described with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the application and are not limiting of the application. It should be noted that the embodiments and features of the embodiments in the present application may be arbitrarily combined with each other without conflict. It should be further noted that, for the convenience of description, only some of the structures related to the present application are shown in the drawings, not all of the structures.
In the embodiment of the present invention, a capacity control method is provided, which is applicable to network management equipment, for example, an SDN controller. The network management equipment adaptively controls the network capacity by acquiring network traffic data and predicting the network traffic and interacting with MANO equipment with virtualized network functions, thereby responding to the change of the network traffic, meeting the network service requirements and improving the flexibility of controlling the network capacity.
Fig. 1 is a flowchart of a capacity control method according to an embodiment, as shown in fig. 1, the method according to the embodiment includes steps 110 and 140.
In step 110, network traffic data is collected by a virtual network function, VNF, network element.
In this embodiment, the Network management device may send a data acquisition instruction to the VNF Network element, and receive current Network traffic data returned by the VNF Network element, for example, acquire virtualized Network Function module Descriptor (VNFD) of the VNF Network element, and Key Performance Indicator (KPI) data of the NFV Network element, such as port, link, tenant-level traffic, and the like. The network flow data can be collected at regular time and periodically, the collected network flow data can be used as training data for training a prediction model, and the prediction model is trained to realize the prediction of the network flow in a machine learning mode; the collected network flow data can also be used as the basis for predicting the network flow, and the network flow data is input into a trained prediction model (various machine learning models such as a neural network) to automatically predict the network flow at a certain future moment or within a certain time period; in addition, the collected network traffic data may also be used to verify a previous prediction result of the current time, and if the previous prediction result is not consistent with the current actual network traffic, the prediction model needs to be updated or the network traffic control policy needs to be adjusted.
In step 120, network traffic is predicted based on the trained predictive model from the network traffic data.
In this embodiment, the network traffic is predicted by using a trained prediction model according to the collected network traffic data. According to the network traffic data in a past period of time, the network traffic at a certain time or in a certain period of time in the future can be predicted by combining influence factors (such as time characteristics of the network traffic, namely holidays or working days, peak hours or night hours, and regional, weather, service types, traffic and virtualized network element performance parameters). The network traffic prediction can be performed according to certain trigger conditions (for example, a prediction instruction is received, the collected network traffic data is accumulated to a sufficient data amount or spans a sufficiently long time period, influence factors are changed, and the like), so that the future network traffic can be predicted in advance, and a basis is provided for a network capacity control decision.
In one embodiment, the prediction period of the network traffic is longer than the period of collecting the network traffic data, and in this case, the frequency of collecting the network traffic data is higher than the prediction frequency, so that the historical data can be fully utilized, the characteristics and the variation trend of the network traffic data can be comprehensively analyzed, and the prediction accuracy can be improved.
In step 130, a network capacity control decision is determined based on the prediction of network traffic.
In this embodiment, it is determined whether to control the network capacity of the VNF network element (the network traffic that the VNF network element can support) and how to perform flexible capacity expansion or capacity reduction according to the prediction result, so as to cope with network congestion that may be encountered and avoid wasting unnecessary network resources. Optionally, the network capacity control decision is determined periodically according to the network traffic prediction result and in combination with performance parameters (such as an expansion threshold, a reduction threshold, and the like) of the VNF network element, or may be determined according to a certain trigger condition (such as receiving a decision instruction, obtaining a prediction result, and according to a certain period or frequency). The network capacity control decisions are for example: when the network flow at a future moment or within a certain time period is predicted to reach an expansion threshold, the capacity of the VNF network element needs to be expanded; if the capacity is lower than the capacity reduction threshold value, the VNF network element needs to be subjected to capacity reduction; if the predicted network flow is within the preset range, the original capacity of the VNF network element can be maintained unchanged. The network capacity control decision may be for the total amount of traffic that can be supported by the virtualized network element group (including at least two VNF network elements), or may be for the network traffic that can be supported by a single VNF network element.
In step 140, network capacity control instructions are sent to the management orchestration MANO device to instruct the MANO device to perform network capacity control decisions.
In this embodiment, the MANO device executes a corresponding network capacity control decision according to the network capacity control instruction of the network management device, for example, requests resources to create a new VNF instance to implement capacity expansion, thereby increasing network traffic that can be supported by the VNF network element, or terminates part of the VNF instance and releases corresponding resources to implement capacity reduction, thereby reducing network resource occupation and further implementing network capacity control on the VNF network element.
In the capacity control method of the embodiment, the network management equipment interacts with the MANO equipment with virtualized network functions by acquiring network traffic data and predicting the network traffic, so that the network capacity is adaptively controlled, the change of the network traffic is met, the network service requirement is met, and the flexibility of controlling the network capacity is improved.
In one embodiment, the method further comprises the step 150: and arranging the network service according to the controlled network capacity.
In this embodiment, after capacity expansion or capacity reduction is completed, the MANO device feeds back a message that network traffic control is completed to the network management device, and after receiving the message, the network management device may perform orchestration and deployment on network services according to the VNF network element after capacity expansion or capacity reduction, for example, interface configuration, route configuration, and the like of a newly added virtualized network element, and network service deployment of an associated device (e.g., TOR device); for the case of the capacity reduction, the gateway device also needs to clear the relevant network traffic corresponding to the terminated virtualized network element. On the basis of automatically controlling the network capacity, the network service is adaptively arranged, the consistency of the network flow and the network capacity of the VNF network element can be ensured, and the reliable operation of the network service and the efficient utilization of the network resource are considered.
Fig. 2 is a flowchart of a capacity control method according to another embodiment. As shown in fig. 2, the method provided in the present embodiment includes steps 210 and 260.
In step 210, network traffic data is collected by a virtual network function, VNF, network element.
In step 220, the network traffic data is pre-processed.
In this embodiment, after collecting the network traffic data, preprocessing, such as data cleaning, data integration, data normalization, etc., is further performed on the network traffic data to obtain data that is suitable for modeling or training and conforms to the input of the prediction model.
In one embodiment, the preprocessing of the network traffic data comprises at least one of: cleaning invalid data in the network flow data; storing the network traffic data to a data repository; and converting the network traffic data into a standard format.
In this embodiment, the network management device performs at least one of the following preprocessing on the acquired network traffic data: data cleaning, data integration and data conversion, wherein the data cleaning refers to removing invalid data in the acquired data, such as older historical data, repeated data, wrong data and the like, the duration of which is more than a certain threshold from the current time, and the data have no effect on the prediction of network traffic and even bring larger errors; the data integration refers to combining network traffic data from a plurality of data sources, uniformly storing the combined data and establishing a data warehouse, wherein the acquired network traffic data comprises the acquisition time or time period of the network traffic data, the control plane service type, the control plane service volume, the time characteristic, the forwarding plane traffic and the like, and data which can be used for modeling or training or accords with the input of a prediction model is extracted from the acquired network traffic data and stored in the data warehouse; data conversion refers to converting network traffic data into a standard format, for example, normalizing the network traffic data: within a time window, the network traffic value at a certain time can be converted into (the network traffic value at the time-the minimum value of the traffic within the time window)/(the maximum value of the traffic within the time window-the minimum value of the traffic within the time window), so that the network traffic value at each time is scaled to the [0, 1] interval, and data suitable for modeling or training or conforming to the input of a prediction model is obtained. Through preprocessing, the quality of input data of the prediction model is improved, and the prediction accuracy is improved.
In step 230, parameters of a Back Propagation (BP) neural network are initialized, and the parameters of the BP neural network are adjusted until the parameters of the BP neural network satisfy a condition, so as to obtain a trained BP neural network.
In this embodiment, taking the prediction model as the BP neural network as an example, the training data for training the BP neural network may be manually imported, may be data stored in a data warehouse, and may also be network traffic data (and preprocessed) acquired by the CNF network element. It should be noted that training (or updating) the BP neural network may be performed before acquiring the network traffic data, or after acquiring the network traffic data every time or every few times, or periodically, or according to a certain trigger condition (for example, receiving a training instruction, changing an influence factor, accumulating the acquired or stored network traffic data to a sufficient data amount, or obtaining a prediction result over a sufficient time period).
In the training process, the parameters to be initialized comprise the weight and the threshold from the input layer to the hidden layer and the weight and the bias from the hidden layer to the output layer, and the initialized parameters are continuously adjusted until the conditions are met, wherein the conditions are met, namely, the adjusted weight and the threshold from the input layer to the hidden layer and the adjusted weight and the adjusted bias from the hidden layer to the output layer can ensure that the deviation between the prediction result and the true value at the corresponding moment is small enough. For example, a loss function may be set to represent a deviation between the predicted result and a true value at a corresponding time, the deviation is recalculated after each parameter is adjusted, and each parameter is gradually adjusted and optimized in a direction of decreasing the deviation until the deviation is smaller than a set threshold value, or the deviation is stabilized within a certain range, and is not further decreased, reaches a minimum value, and the like.
Fig. 3 is a schematic diagram of a back propagation neural network according to an embodiment. Wherein (W)ij,θj) For the weights and thresholds from the input layer to the hidden layer, (Z)jω) are the weight and offset from hidden layer to output layer (i 1,2.. n, j 1,2.. m). The BP neural network input includes network traffic data of a past period of time, and also includes multifactor variables affecting the network traffic, such as time characteristics of the network traffic (holidays or working days, peak periods or night periods), regions, weather, traffic types, traffic volumes, virtualized network element performance parameters, and the like, and the output is predicted network traffic at a future time or within a certain period of time, specifically, a traffic peak value, a traffic valley value, an average value, and the like of the network traffic within a relevant period of time. The method comprises the steps of initializing parameters of the BP neural network, training or updating the BP neural network by using training data, calculating deviation between a predicted value and an actual value by using a loss function according to the training data, continuously adjusting parameters of the BP neural network if the deviation is large, and obtaining the trained BP neural network until the predicted deviation approaches to a minimum value or a preset loss threshold value or a certain range.
Illustratively, the principle of training the BP neural network is as follows: the input BP neural network flow data of the network is in a flow time sequence form and is expressed as: [ x ] of1,x2,x3...xn×m]Wherein m is the length of the unit time window, n is the number of the unit time windows, and the spanning time length of the input data is nxm. Flow valley and peak of network traffic and congestion or idle of network equipmentThe values are related, if the predicted traffic valley value is greater than a predetermined threshold (capacity expansion threshold) corresponding to the forwarding performance of the network device, network congestion may be caused, and capacity expansion is required in this case; if the flow peak value is smaller than a predetermined threshold (capacity reduction threshold) corresponding to the forwarding performance of the network equipment, the network resources are idle, and capacity reduction can be performed under the condition to save the resources. Extracting flow peak value and flow valley value y in unit time window (from time t to time m) from collected network flow datamax＝[xt-m,xt]max；ymin＝[xt-m,xt]minAnd performing normalization processing, where max is a maximum value of the forwarding performance of the device, min is a minimum value of the forwarding performance of the device, and is generally 0: then y is (y-min) ÷ (max-min). On this basis, normalized input data is obtained, and the flow peak-valley sequence within the unit time window m can be expressed as: y ═ Y1,y2,y3...yn]Each y is a sequence of flow peaks and flow troughs within the corresponding unit time window.
Correspondingly, the influence factors corresponding to the flow peak value and the flow valley value sequence are respectively: xi＝[x1,i,x2,i...xn,i]i ∈ (1,2,3.. p), where p is the number of influencing factors, different influencing factors need to be encoded separately, for example, for time characteristics, 0 may be used to represent weekday, 1 may represent weekend, 2 may represent holiday, and the like.
Establishing a nonlinear functional relation between the flow peak value and flow valley value sequence and the influence factor at the moment t: y ist＝F(xt,1,xt,2,xt,3,...xt,p) (ii) a The activation function can use a Sigmoid function, represented as:
the loss function can be expressed as: loss ═ yout-y |. When the loss function reaches the minimum value or is lower than a certain threshold value, the prediction result y is indicatedoutAnd if the deviation from the true value y is minimum, completing the training of the BP neural network.
In step 240, the network traffic data is input to the back propagation neural network, and the output of the back propagation neural network is used as the prediction result of the network traffic.
In this embodiment, the prediction result includes a traffic peak and a traffic valley of the network traffic in the prediction time period, and the network traffic data (including the influence factor) is input to the converged back propagation neural network, so as to predict the traffic peak or the traffic valley at a future time or in a time period, which is used as a basis for decision making.
In step 250, a network capacity control decision is determined based on the prediction of network traffic.
Fig. 4 is a schematic diagram of controlling network traffic according to an embodiment. As shown in fig. 4, when the peak value of the flow in the prediction result reaches the boundary (Pmax) of the expansion region, the expansion needs to be performed; when the flow valley value in the prediction result reaches the boundary (Pmin) of the capacity reduction area, capacity reduction is needed; if the flow peak value and the flow valley value in the prediction result are both located in the maintenance area, the original capacity can be maintained.
In step 260, network capacity control instructions are sent to the managing orchestration MANO device to instruct the MANO device to perform network capacity control decisions.
In an embodiment, step 250 specifically includes: if the flow peak value of the network flow of a single virtualized network element in the prediction time period is smaller than the capacity reduction threshold value of the single virtualized network element, determining that a network capacity control decision is as follows: reducing the network capacity of the single virtualized network element; if the flow valley value of the network flow of the single virtualized network element in the prediction time period is greater than or equal to the capacity expansion threshold value of the single virtualized network element, determining that a network capacity control decision is as follows: extending the network capacity of the single virtualized network element.
In this embodiment, the network capacity control decision is based on a single virtualized network element, and the decision is made according to the predicted traffic peak and traffic valley. Pmax、PminThe maximum network flow or the minimum network flow which can be supported and corresponds to the real forwarding performance is a threshold value, if the predicted flow peak value Z ismax≤S*Pmin(the capacity reduction threshold is the product of the scaling factor S and the minimum network flow which can be supported), the capacity reduction is carried outFor example, reducing computational resources on virtualized network elements, reducing processing performance and operating frequency, etc.; therefore, the flexibility of setting the capacity reduction threshold value is improved, the capacity reduction is controlled, meanwhile, the reservation and the standby of a certain proportion of network resources are ensured, the network resources are efficiently utilized, and the normal operation of network services is ensured; if the predicted flow valley Zmin≥S*Pmax(the capacity expansion threshold is the product of the scaling factor S and the maximum network traffic that can be supported), capacity expansion is performed, for example, the computational resources on the virtualized network element are increased, the processing performance and the operating frequency are improved, so that the flexibility of setting the capacity expansion threshold is improved, capacity expansion is performed when the network traffic is high, the situations of network congestion, sudden increase and the like are more flexibly dealt with, and the reliability of network capacity control is provided.
In an embodiment, step 250 specifically includes: if the sum of the flow peak values of the network flow of the virtualized network element group in the prediction period is less than or equal to the capacity reduction threshold value of the virtualized network element group, determining that a network capacity control decision is as follows: reducing a network capacity of the virtualized network element group; if the sum of flow valleys of the network flow of the virtualized network element group in the prediction period is greater than or equal to the capacity expansion threshold of the virtualized network element group, determining that a network capacity control decision is as follows: extending a network capacity of the virtualized network element group.
In this embodiment, the network capacity control decision is for a virtualized network element group, and the SDN controller has a global view of a network topology and can perform capacity expansion or capacity reduction for the virtualized network element group. Illustratively, there is n in a virtualized network element group0Each VNF network element calculates the sum of the flow peak values in the prediction result of each VNF network element
Then, it is determined whether the virtual network element group size is smaller than a capacity reduction threshold of the virtual network element group, where the capacity reduction threshold of the virtual network element group needs to be determined according to the comprehensive forwarding performance of each VNF network element, for example, the capacity reduction threshold is determined by
Wherein, each VNF network element is respectively corresponding to a proportional factorAnd (4) adding the active ingredients. If it is not
Then the capacity reduction is needed, and the total n is in the virtualized network element group after the capacity reduction1Individual VNF network elements, n1≤n0And after the volume reduction, the following requirements are met:
therefore, the number of VNF network elements is reduced and the network resources are saved under the condition that the network resources can meet the network service and the network flow.
Similarly, the sum of the flow valleys in the prediction result of each VNF network element is calculated
Then, it is determined whether the capacity expansion threshold of the virtualized network element group is greater than or equal to the capacity expansion threshold of the virtualized network element group, where the capacity expansion threshold of the virtualized network element group needs to be determined comprehensively according to the forwarding performance of each VNF network element, for example, the capacity expansion threshold of the virtualized network element group is determined comprehensively according to the forwarding performance of each VNF network element
Wherein each VNF network element is for a scaling factor. In some embodiments, the scaling factors used in calculating the capacity expansion threshold and the capacity reduction threshold of the virtualized mesh group may be the same or different. If (Z)1,min+Z2,min+...+Zn,min)≥(S1+S2+...+Sn)*PmaxThen, capacity expansion is needed, and the total number of n in the virtualized network element group after capacity expansion is n2And each VNF network element is subjected to capacity expansion and then meets the following requirements:
thus, the network resources can meet the requirements of network services and network traffic.
In an embodiment, the capacity expansion or capacity reduction is preferentially performed on the virtualized network element group; if the virtualized network element group is subjected to capacity expansion or capacity reduction for a certain number of times, a certain time consumption or a certain amplitude, the network flow which can be supported still cannot be controlled in the maintenance area, and then the single virtualized network element group is subjected to capacity expansion or capacity reduction.
In one embodiment, the method further comprises:
step 270: and when the predicted time is reached, comparing the predicted result with the true value of the predicted time, calculating the deviation, and if the deviation is greater than the set threshold, retraining the prediction model and adjusting the network capacity control decision.
Fig. 5 is a schematic diagram illustrating interaction between network management equipment, a VNF network element, and a MANO in a capacity control process according to an embodiment. As shown in fig. 5, the SDN controller sends a data acquisition instruction to the VNF network element, and the VNF network element returns network traffic data; preprocessing the received network flow data by the SDN controller, and training a prediction model; the SDN controller predicts network flow based on the trained prediction model and makes a network flow control decision; the SDN controller sends a network capacity control instruction to the MANO, instructs the MANO to execute a network capacity control decision and carries out capacity expansion and contraction linkage; the MANO performs capacity expansion or capacity reduction on the VNF network element according to the network flow control instruction, wherein the capacity expansion or capacity reduction comprises requesting resources and creating a VNF instance, or terminating the VNF instance and releasing corresponding resources; after capacity expansion or capacity reduction is completed, the MANO returns a network flow control result to the SDN controller; the SDN controller arranges network services and issues configuration to the VNF network elements based on the VNF network elements after capacity expansion or capacity reduction, and the network services are completed.
The capacity control method of the embodiment constructs a self-driven intelligent and automatic elastic system under a fusion framework of the SDN and the NFV. By combining SDN and NFV technologies, intelligent prediction, self-learning and continuous updating of network flow are realized, and the accuracy and reliability of prediction are improved; the automatic capacity expansion or capacity reduction of the network capacity and the automatic deployment of the network service are realized through the cloud network linkage. Through automatic capacity expansion, the probability of network congestion can be avoided; by automatic capacity reduction, the utilization rate of network resources can be improved, and the aim of saving energy is fulfilled; meanwhile, the whole expansion and contraction capacity and network service deployment process is completely automatic, manual intervention is avoided, manpower and expansion and contraction capacity deployment time are saved, and errors possibly caused by manual expansion and contraction capacity deployment are reduced.
The embodiment of the invention also provides a capacity control method which can be applied to the MANO. The MANO is linked with network management equipment (SDN controller), so that automatic capacity expansion or capacity reduction of network capacity is realized, and the utilization rate of network resources and reliable operation of network services are considered. It should be noted that the operations performed by the MANO in this embodiment correspond to the operations performed by the network management device in any of the above embodiments, and the technical details that are not described in detail in this embodiment may be referred to in any of the above embodiments.
Fig. 6 is a flowchart of a capacity control method according to yet another embodiment. As shown in fig. 6, the method provided by the present embodiment includes step 310 and step 320.
In step 310, a network capacity control instruction is received, where the network capacity control instruction includes a network capacity control decision, and the network capacity control decision is determined by the network management device according to the prediction result of the network traffic.
In step 320, the network capacity is reduced or expanded according to the network capacity control instruction.
In this embodiment, the MANO adaptively controls the network capacity according to a network capacity control decision obtained by predicting the network traffic by the network management equipment, thereby coping with the change of the network traffic, satisfying the network service requirement, and improving the flexibility of network capacity control.
In an embodiment, step 320 specifically includes:
determining a target VNF instance according to the network capacity control instruction, terminating the target VNF instance and releasing corresponding virtual resources; or acquiring virtual resources for creating the VNF instance according to the network capacity control instruction, and creating the VNF instance based on the virtual resources.
Illustratively, the MANO includes a number of components having different functions: network Function Virtualization Orchestrators (NFVO), Virtual Network Function Managers (VNFM), Virtualized Infrastructure device managers (VIM).
For example, after the SDN controller makes a decision to perform capacity expansion, a network capacity control instruction is sent to the NFVO, where the network capacity control instruction indicates the network capacity control decision and carries VNFD information; the NFVO sends an instance creating instruction to the VNFM; after receiving the instance creation instruction, the VNFM sends a virtual resource acquisition instruction to the VIM to request allocation of virtual resources for creating a VNF instance so as to create a VNF instance with a virtual network function; the VIM returns the distributed virtual resource information to the VNFM, the VNFM creates a VNF instance according to the virtual resource information, and the NFVO is notified after the VNF is successfully created; and the NFVO sends the expansion completion message to the SDN controller, and the SDN controller is accessed to the VNF network element to perform network service arrangement and realize flow load balance.
For another example, after the SDN controller makes a decision to perform capacity reduction, a network capacity control instruction is sent to the NFVO, where the network capacity control instruction indicates the network capacity control decision and carries information of a target VNF instance to be deleted; the NFVO sends an instance deletion instruction to the VNFM; after receiving the instance deletion instruction, the VNFM terminates the target VNF instance and notifies the VIM to release corresponding virtual resources, so that the target VNF instance is deleted; and after the target VNF instance is successfully deleted, the NFVO sends a capacity reduction completion message to the SDN controller, and the SDN controller is accessed to the VNF network element to perform network service arrangement and realize flow load balancing.
The network capacity control method applied to the MANO device in the embodiment belongs to the same inventive concept as the capacity control method applied to the network management device proposed in the above embodiment, and the technical details not described in detail in the embodiment can be referred to any of the above embodiments, and the embodiment has the same beneficial effects as the execution of the capacity control method applied to the network management device.
The embodiment of the invention also provides a capacity control device. Fig. 7 is a schematic structural diagram of a capacity control device according to an embodiment. As shown in fig. 7, the capacity control device includes: an acquisition module 410, a prediction module 420, a decision module 430, and an indication module 440.
An acquisition module 410 configured to acquire network traffic data via a virtual network function VNF network element;
a prediction module 420 configured to predict network traffic based on the trained prediction model based on the network traffic data;
a decision module 430 configured to determine a network capacity control decision based on the prediction of network traffic;
an instructing module 440 configured to send a network capacity control instruction to a management orchestration, MANO, device to instruct the MANO device to execute the network capacity control decision.
The capacity control device of the embodiment adaptively controls the network capacity by predicting the network traffic, thereby coping with the change of the network traffic, satisfying the network service requirement, and improving the flexibility of controlling the network capacity.
In one embodiment, the predictive model includes a back propagation neural network;
the prediction module 420 is specifically configured to:
inputting the network traffic data into a back propagation neural network;
and taking the output of the back propagation neural network as a prediction result of the network traffic, wherein the prediction result comprises a traffic peak value and a traffic valley value of the network traffic in a prediction period.
In one embodiment, the method further comprises:
a machine learning module configured to initialize parameters of the back propagation neural network and adjust the parameters of the back propagation neural network until the parameters of the back propagation neural network satisfy a condition before predicting network traffic based on a trained prediction model according to the network traffic data, to obtain a trained back propagation neural network;
wherein the parameters include weights and thresholds from the input layer to the hidden layer, and weights and biases from the hidden layer to the output layer.
In one embodiment, the decision module 430 is configured to:
if the flow peak value of the network flow of a single virtualized network element in the prediction time period is smaller than the capacity reduction threshold value of the single virtualized network element, determining that the network capacity control decision is as follows: reducing the network capacity of the single virtualized network element;
if the flow valley value of the network flow of the single virtualized network element in the prediction time period is greater than or equal to the capacity expansion threshold value of the single virtualized network element, determining that the network capacity control decision is as follows: extending the network capacity of the single virtualized network element.
In one embodiment, the decision module 430 is configured to:
if the sum of the flow peak values of the network flow of the virtualized network element group in the prediction period is smaller than the capacity reduction threshold value of the virtualized network element group, determining that the network capacity control decision is as follows: reducing a network capacity of the virtualized network element group;
if the sum of flow valleys of the network flow of the virtualized network element group in the prediction period is greater than or equal to the capacity expansion threshold of the virtualized network element group, determining that the network capacity control decision is as follows: extending a network capacity of the virtualized network element group.
In one embodiment, the method further comprises:
the preprocessing module is used for preprocessing the network flow data;
the preprocessing module is specifically set as at least one of the following:
cleaning invalid data in the network traffic data;
storing the network traffic data to a data repository;
and converting the network traffic data into a standard format.
In one embodiment, the method further comprises:
and the service arranging module is arranged for arranging the network service according to the controlled network capacity.
The capacity control device proposed in this embodiment is the same as the capacity control method applied to the network management equipment proposed in the above embodiment, and the technical details that are not described in detail in this embodiment can be referred to any of the above embodiments, and this embodiment has the same beneficial effects as executing the capacity control method applied to the network management equipment.
The embodiment of the invention also provides a capacity control device. Fig. 8 is a schematic structural diagram of a capacity control device according to another embodiment. As shown in fig. 8, the capacity control device includes: an instruction receiving module 510 and a capacity control module 520.
An instruction receiving module 510 configured to receive a network capacity control instruction, where the network capacity control instruction includes a network capacity control decision, and the network capacity control decision is determined by the network management device according to a prediction result of the network traffic;
and a capacity control module 520 configured to reduce or expand the network capacity according to the network capacity control instruction.
The capacity control device of the embodiment adaptively controls the network capacity according to the network capacity control decision obtained by predicting the network traffic, thereby coping with the change of the network traffic, meeting the network service requirement, and improving the flexibility of network capacity control.
In one embodiment, the capacity control module 520 is specifically configured to:
determining a target VNF instance according to the network capacity control instruction, terminating the target VNF instance and releasing corresponding virtual resources; or,
and acquiring virtual resources for creating the VNF instance according to the network capacity control instruction, and creating the VNF instance based on the virtual resources.
The capacity control apparatus proposed by the present embodiment is the same as the capacity control method applied to the management orchestration device proposed by the above embodiments, and technical details that are not described in detail in the present embodiment can be referred to any of the above embodiments, and the present embodiment has the same advantageous effects as the capacity control method applied to the management orchestration device is performed.
The embodiment of the invention also provides network management equipment. The capacity control method may be executed by a capacity control device, which may be implemented in software and/or hardware and integrated in the network management apparatus. The network management equipment is an SDN controller.
Fig. 9 is a schematic hardware structure diagram of a network management device according to an embodiment. As shown in fig. 9, the network management device provided in this embodiment includes: a processor 610 and a storage device 620. The number of the processors in the network management device may be one or more, one processor 610 is taken as an example in fig. 9, the processor 610 and the storage 620 in the device may be connected by a bus or in another manner, and the processor 610 and the storage 620 in fig. 9 are taken as an example of being connected by a bus.
The one or more programs are executed by the one or more processors 610, so that the one or more processors implement the capacity control method applied to the network management device according to any of the above embodiments.
The storage device 620 in the network management equipment, as a computer-readable storage medium, can be used to store one or more programs, which may be software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the capacity control method applied to the network management equipment in the embodiment of the present invention (for example, the modules in the capacity control device shown in fig. 7 include the acquisition module 410, the prediction module 420, the decision module 430, and the indication module 440). The processor 610 executes various functional applications and data processing of the network management device by running the software program, instructions and modules stored in the storage device 620, that is, the capacity control method applied to the network management device in the above method embodiment is implemented.
The storage device 620 mainly includes a storage program area and a storage data area, wherein the storage program area can store an operating system and an application program required by at least one function; the storage data area may store data created according to the use of the device, etc. (such as network traffic data, network capacity control decisions, etc. as in the above-described embodiments). Further, the storage 620 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, the storage 620 may further include memory located remotely from the processor 610, which may be connected to the network management device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
And, when one or more programs included in the above network management device are executed by the one or more processors 610, the following operations are implemented: collecting network flow data through a virtual network function VNF network element; predicting network traffic based on the trained prediction model according to the network traffic data; determining a network capacity control decision according to a prediction result of the network flow; sending a network capacity control instruction to a management orchestration MANO device to instruct the MANO device to perform the network capacity control decision.
The network management device proposed in this embodiment and the capacity control method applied to the network management device proposed in the above embodiment belong to the same inventive concept, and the technical details that are not described in detail in this embodiment can be referred to any of the above embodiments, and this embodiment has the same beneficial effects as executing the capacity control method applied to the network management device.
The embodiment of the invention also provides a management arrangement device. The capacity control method may be performed by capacity control means, which may be implemented in software and/or hardware, and integrated in the management orchestration device. Fig. 10 is a schematic hardware structure diagram of a management orchestration device according to an embodiment. As shown in fig. 10, the management orchestration device according to the present embodiment includes: a processor 710 and a storage device 720. The number of the processors in the management orchestration device may be one or more, and fig. 10 illustrates one processor 710, and the processor 710 and the storage 720 in the device may be connected by a bus or in other ways, and fig. 10 illustrates a connection by a bus.
The one or more programs are executed by the one or more processors 710, so that the one or more processors implement the capacity control method applied to the management orchestration device according to any one of the above embodiments.
The storage 720 of the managing and arranging device is used as a computer readable storage medium for storing one or more programs, which may be software programs, computer executable programs, and modules, such as program instructions/modules corresponding to the capacity control method applied to the managing and arranging device in the embodiment of the present invention (for example, the modules in the capacity control apparatus shown in fig. 7, including the transmission mechanism determining module 210 and the transmission module 220). The processor 710 executes various functional applications and data processing of the management orchestration device by running software programs, instructions and modules stored in the storage 720, i.e. implements the capacity control method applied to the management orchestration device in the above method embodiments.
The storage device 720 mainly includes a storage program area and a storage data area, wherein the storage program area can store an operating system and an application program required by at least one function; the storage data area may store data created according to the use of the device, etc. (such as network capacity control instructions, network capacity control decisions, etc. in the above-described embodiments). Additionally, the storage 720 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, storage 720 may further include memory located remotely from processor 710, which may be connected to the managing orchestration device through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
And, when one or more programs included in the above-described management orchestration device are executed by the one or more processors 710, the following operations are implemented: receiving a network capacity control instruction, wherein the network capacity control instruction comprises a network capacity control decision, and the network capacity control decision is determined by network management equipment according to a prediction result of network flow; and reducing or expanding the network capacity according to the network capacity control instruction.
The management and organization apparatus proposed by the present embodiment is the same inventive concept as the capacity control method applied to the management and organization apparatus proposed by the above embodiments, and technical details that are not described in detail in the present embodiment can be referred to any of the above embodiments, and the present embodiment has the same advantageous effects as the capacity control method applied to the management and organization apparatus.
The embodiment of the invention also provides a capacity control system. Fig. 11 is a schematic structural diagram of a capacity control system according to an embodiment. As shown in fig. 11, the system includes: a VNF network element 810, a network management device 820, and a management orchestration device 830; the VNF network element 810 is configured to receive a data collection request of the network management device 820 and return network traffic data to the network management device 810.
The capacity control system of the embodiment adaptively controls the network capacity by predicting the network traffic, thereby coping with the change of the network traffic, meeting the network service requirement and improving the flexibility of controlling the network capacity.
In one embodiment, managing orchestration device 830 comprises: NFVO, VNFM and VIM;
the NFVO is used for receiving a network capacity control instruction and sending an instance creating instruction or an instance deleting instruction to the VNFM;
the VNFM is used for sending a virtual resource acquisition instruction to the VIM according to the instance creation instruction or terminating the target VNF instance according to the instance deletion instruction;
and the VIM is used for acquiring the virtual resources used for creating the VNF instances according to the virtual resource acquisition instructions, or releasing the virtual resources corresponding to the target VNF instances.
Fig. 12 is a schematic diagram illustrating an implementation of capacity control according to an embodiment. As shown in fig. 12, in the present embodiment, the MANO device is provided with three functional components: NFVO, VNFM, VIM.
Taking the capacity expansion situation as an example, after the SDN controller makes a decision to perform capacity expansion, sending a network capacity control instruction to the NFVO, where the network capacity control instruction indicates the network capacity control decision and carries VNFD information; the NFVO sends an instance creating instruction to the VNFM; after receiving the instance creation instruction, the VNFM sends a virtual resource acquisition instruction to the VIM to request allocation of virtual resources for creating a VNF instance so as to create a VNF instance with a virtual network function; the VIM returns the distributed virtual resource information to the VNFM, the VNFM creates a VNF instance according to the virtual resource information, and the NFVO is notified after the VNF is successfully created; and the NFVO sends the expansion completion message to the SDN controller, and the SDN controller is accessed to the VNF network element to perform network service arrangement and realize flow load balance.
Taking the case of capacity reduction as an example, after the SDN controller makes a decision to perform capacity reduction, sending a network capacity control instruction to the NFVO, where the network capacity control instruction indicates the network capacity control decision and carries information of a target VNF instance to be deleted; the NFVO sends an instance deletion instruction to the VNFM; after receiving the instance deletion instruction, the VNFM terminates the target VNF instance and notifies the VIM to release corresponding virtual resources, so that the target VNF instance is deleted; and after the target VNF instance is successfully deleted, the NFVO sends a capacity reduction completion message to the SDN controller, and the SDN controller is accessed to the VNF network element to perform network service arrangement and realize flow load balancing.
The network capacity control system of the embodiment provides a cloud network linkage interaction mode under the framework of fusion of an SDN and an NFV cloud network, so as to realize automatic expansion and contraction of network devices and automatic deployment of network services; by predicting the network flow change, capacity reduction or capacity expansion is adopted in advance, so that the resource utilization rate is improved, and network congestion is avoided; network flow performance in the equipment is collected, a flow prediction model is continuously perfected, and prediction accuracy is improved; through automatic decision making and execution, a self-driven intelligent and automatic elastic network is realized.
The capacity control system proposed by this embodiment is the same as the capacity control method applied to the network management device or the capacity control method applied to the management orchestration device proposed by the above embodiments, and the technical details that are not described in detail in this embodiment can be referred to any of the above embodiments, and this embodiment has the same beneficial effects as the execution of the capacity control method applied to the network management device or the capacity control method applied to the management orchestration device.
Embodiments of the present invention also provide a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform a capacity control method applied to a network management device or a capacity control method applied to a management orchestration device.
The capacity control method applied to the network management equipment comprises the following steps: collecting network flow data through a virtual network function VNF network element; predicting network traffic based on the trained prediction model according to the network traffic data; determining a network capacity control decision according to a prediction result of the network flow; sending a network capacity control instruction to a management orchestration MANO device to instruct the MANO device to perform the network capacity control decision.
The capacity control method applied to the management arranging device comprises the following steps: receiving a network capacity control instruction, wherein the network capacity control instruction comprises a network capacity control decision, and the network capacity control decision is determined by network management equipment according to a prediction result of network flow; and reducing or expanding the network capacity according to the network capacity control instruction.
From the above description of the embodiments, those skilled in the art will appreciate that the present invention can be implemented by software, general hardware, or hardware. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, and the computer software product may be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes a plurality of instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the method according to any embodiment of the present invention.
The above description is only an exemplary embodiment of the present invention, and is not intended to limit the scope of the present invention.
Any logic flow block diagrams in the figures of the present invention may represent program steps, or may represent interconnected logic circuits, modules, and functions, or may represent a combination of program steps and logic circuits, modules, and functions. The computer program may be stored on a memory. The memory may be of any type suitable to the local technical environment and may be implemented using any suitable data storage technology, such as, but not limited to, Read Only Memory (ROM), Random Access Memory (RAM), optical storage devices and systems (digital versatile disks, DVDs, or CD discs), etc. The computer readable medium may include a non-transitory storage medium. The data processor may be of any type suitable to the local technical environment, such as but not limited to general purpose computers, special purpose computers, microprocessors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), programmable logic devices (FGPAs), and processors based on a multi-core processor architecture.
The foregoing has provided by way of exemplary and non-limiting examples a detailed description of exemplary embodiments of the invention. Various modifications and adaptations to the foregoing embodiments may become apparent to those skilled in the relevant arts in view of the following drawings and the appended claims without departing from the scope of the invention. Therefore, the proper scope of the invention is to be determined according to the claims.
Claims (14)
1. A capacity control method, comprising:
collecting network flow data through a virtual network function VNF network element;
predicting network traffic based on the trained prediction model according to the network traffic data;
determining a network capacity control decision according to the prediction result of the network flow;
sending a network capacity control instruction to a management orchestration MANO device to instruct the MANO device to perform the network capacity control decision.
2. The method of claim 1, wherein the predictive model comprises a back propagation neural network;
predicting network traffic based on the trained prediction model according to the network traffic data comprises:
inputting the network traffic data into the back propagation neural network;
and taking the output of the back propagation neural network as a prediction result of the network traffic, wherein the prediction result comprises a traffic peak value and a traffic valley value of the network traffic in a prediction period.
3. The method of claim 2, further comprising, prior to predicting network traffic based on the trained predictive model from the network traffic data:
initializing parameters of the back propagation neural network, and adjusting the parameters of the back propagation neural network until the parameters of the back propagation neural network meet conditions to obtain a trained back propagation neural network;
wherein the parameters include weights and thresholds from the input layer to the hidden layer, and weights and biases from the hidden layer to the output layer.
4. The method of claim 2, wherein determining a network capacity control decision based on the network traffic prediction comprises:
if the flow peak value of the network flow of a single virtualized network element in the prediction time period is smaller than the capacity reduction threshold value of the single virtualized network element, determining that the network capacity control decision is as follows: reducing the network capacity of the single virtualized network element;
if the flow valley value of the network flow of the single virtualized network element in the prediction time period is greater than or equal to the capacity expansion threshold value of the single virtualized network element, determining that the network capacity control decision is as follows: extending the network capacity of the single virtualized network element.
5. The method of claim 2, wherein determining a network capacity control decision based on the network traffic prediction comprises:
if the sum of the flow peak values of the network flow of the virtualized network element group in the prediction period is smaller than the capacity reduction threshold value of the virtualized network element group, determining that the network capacity control decision is as follows: reducing a network capacity of the virtualized network element group;
if the sum of flow valleys of the network flow of the virtualized network element group in the prediction period is greater than or equal to the capacity expansion threshold of the virtualized network element group, determining that the network capacity control decision is as follows: extending a network capacity of the virtualized network element group.
6. The method of any one of claims 1-5, further comprising: preprocessing the network flow data;
the preprocessing the network traffic data includes at least one of:
cleaning invalid data in the network traffic data;
storing the network traffic data to a data repository;
and converting the network traffic data into a standard format.
7. The method of any one of claims 1-5, further comprising:
and arranging the network service according to the controlled network capacity.
8. A capacity control method, comprising:
receiving a network capacity control instruction, wherein the network capacity control instruction comprises a network capacity control decision, and the network capacity control decision is determined by network management equipment according to a prediction result of network flow;
and reducing or expanding the network capacity according to the network capacity control instruction.
9. The method of claim 8, wherein the scaling down or scaling up network capacity according to the network capacity control instruction comprises:
determining a target VNF instance according to the network capacity control instruction, terminating the target VNF instance and releasing corresponding virtual resources; or,
and acquiring virtual resources for creating the VNF instance according to the network capacity control instruction, and creating the VNF instance based on the virtual resources.
10. A network management device, comprising:
at least one processor;
storage means for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement the capacity control method of any one of claims 1-7.
11. A management orchestration device, comprising:
at least one processor;
storage means for storing at least one program;
when executed by the at least one processor, cause the at least one processor to implement the capacity control method of any one of claims 8-9.
12. A network capacity control system, comprising: a VNF network element, a network management device according to claim 10 and a management orchestration device according to claim 11;
and the VNF network element is used for receiving the data acquisition request of the network management equipment and returning network flow data to the network management equipment.
13. The system of claim 12, wherein the management orchestration device comprises: a network function virtualization orchestrator NFVO, a virtual network function manager VNFM, and a virtualization infrastructure device manager VIM;
the NFVO is used for receiving a network capacity control instruction and sending an instance creation instruction or an instance deletion instruction to the VNFM;
the VNFM is used for sending a virtual resource acquisition instruction to the VIM according to the instance creation instruction or terminating the target VNF instance according to the instance deletion instruction;
and the VIM is used for acquiring virtual resources used for creating the VNF instance according to the virtual resource acquisition instruction, or releasing the virtual resources corresponding to the target VNF instance.
14. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the network traffic control method according to any one of claims 1 to 7 or the network traffic control method according to any one of claims 8 to 9.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010561024.XA CN113825152A (en) | 2020-06-18 | 2020-06-18 | Capacity control method, network management device, management arrangement device, system and medium |
| PCT/CN2021/100216 WO2021254354A1 (en) | 2020-06-18 | 2021-06-15 | Capacity control method, network management device, management and orchestration device, system and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010561024.XA CN113825152A (en) | 2020-06-18 | 2020-06-18 | Capacity control method, network management device, management arrangement device, system and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113825152A true CN113825152A (en) | 2021-12-21 |
Family
ID=78911843
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010561024.XA Pending CN113825152A (en) | 2020-06-18 | 2020-06-18 | Capacity control method, network management device, management arrangement device, system and medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113825152A (en) |
| WO (1) | WO2021254354A1 (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114501500A (en) * | 2022-01-28 | 2022-05-13 | 吕则东 | Network arrangement method, device and system based on network tide |
| CN114827079A (en) * | 2022-03-25 | 2022-07-29 | 阿里云计算有限公司 | Capacity expansion method, equipment and storage medium for network address conversion gateway |
| CN115051920A (en) * | 2022-06-02 | 2022-09-13 | 北京邮电大学 | Method and system for capacity expansion of NFV capacity network element under capacity open architecture |
| CN115955407A (en) * | 2022-09-30 | 2023-04-11 | 中国联合网络通信集团有限公司 | Instance management method, device, equipment and storage medium |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115002042B (en) * | 2022-05-25 | 2023-06-20 | 中国平安财产保险股份有限公司 | Special line flow control method and device based on machine learning and computer equipment |
| CN115426201B (en) * | 2022-11-03 | 2023-01-17 | 湖南大佳数据科技有限公司 | Data acquisition method and system for network shooting range |
| CN116414663A (en) * | 2023-04-24 | 2023-07-11 | 山东溯源安全科技有限公司 | Capacity expansion prompting method, device and storage medium based on capacity use prediction |
| CN118394534B (en) * | 2024-06-28 | 2024-09-27 | 济南浪潮数据技术有限公司 | Method, system, product, device and medium for expanding and shrinking volume of cluster application service |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200153702A1 (en) * | 2017-06-20 | 2020-05-14 | Telefonaktiebolaget Lm Ericsson (Publ) | Methods and network nodes enabling a content delivery network to handle unexpected surges of traffic |
| CN110213780A (en) * | 2018-02-28 | 2019-09-06 | 中兴通讯股份有限公司 | Management method, management and the layout entity and storage medium of network slice |
| EP3834372A1 (en) * | 2018-08-08 | 2021-06-16 | Telefonaktiebolaget Lm Ericsson (Publ) | Towards network slice availability |
| CN109995583B (en) * | 2019-03-15 | 2021-08-06 | 清华大学深圳研究生院 | Delay-guaranteed NFV cloud platform dynamic capacity expansion and contraction method and system |
-
2020
- 2020-06-18 CN CN202010561024.XA patent/CN113825152A/en active Pending
-
2021
- 2021-06-15 WO PCT/CN2021/100216 patent/WO2021254354A1/en active Application Filing
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114501500A (en) * | 2022-01-28 | 2022-05-13 | 吕则东 | Network arrangement method, device and system based on network tide |
| CN114501500B (en) * | 2022-01-28 | 2022-12-09 | 吕则东 | Network arrangement method, device and system based on network tide |
| CN114827079A (en) * | 2022-03-25 | 2022-07-29 | 阿里云计算有限公司 | Capacity expansion method, equipment and storage medium for network address conversion gateway |
| CN114827079B (en) * | 2022-03-25 | 2024-04-30 | 阿里云计算有限公司 | Capacity expansion method, device and storage medium of network address translation gateway |
| CN115051920A (en) * | 2022-06-02 | 2022-09-13 | 北京邮电大学 | Method and system for capacity expansion of NFV capacity network element under capacity open architecture |
| CN115051920B (en) * | 2022-06-02 | 2023-07-18 | 北京邮电大学 | Method and system for expanding NFV capacity network element under capacity open architecture |
| CN115955407A (en) * | 2022-09-30 | 2023-04-11 | 中国联合网络通信集团有限公司 | Instance management method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021254354A1 (en) | 2021-12-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113825152A (en) | Capacity control method, network management device, management arrangement device, system and medium | |
| CN107766889B (en) | Cloud edge computing fused deep learning computing system and method | |
| CN110347500B (en) | Task unloading method for deep learning application in edge computing environment | |
| CN107871164B (en) | Fog computing environment personalized deep learning method | |
| CN102622303B (en) | A kind of method of internal memory premature beats and device | |
| CN109324875B (en) | Data center server power consumption management and optimization method based on reinforcement learning | |
| US11074105B2 (en) | Systems and methods for digital workforce intelligent orchestration | |
| TWI725744B (en) | Method for establishing system resource prediction and resource management model through multi-layer correlations | |
| KR20220030050A (en) | Method and server for adjusting the allocation of computing resources to a plurality of vnf(virtualized network function) | |
| Munir et al. | Intelligent service fulfillment for software defined networks in smart city | |
| CN116643844B (en) | Intelligent management system and method for automatic expansion of power super-computing cloud resources | |
| CN117591285A (en) | Computing power resource scheduling and distributing system and method | |
| CN117880291A (en) | Multi-cloud resource load balancing method, device, equipment and medium based on GPT technology | |
| Tekiyehband et al. | An efficient dynamic service provisioning mechanism in fog computing environment: A learning automata approach | |
| CN103442087A (en) | Web service system access volume control device and method based on response time trend analysis | |
| CN117972367B (en) | Data storage prediction method, data storage subsystem and intelligent computing platform | |
| CN115562841B (en) | Cloud video service self-adaptive resource scheduling system and method | |
| CN116760722A (en) | Storage auxiliary MEC task unloading system and resource scheduling method | |
| CN117687784A (en) | Docker container intelligent dynamic allocation method and device based on machine learning | |
| CN114301911B (en) | Task management method and system based on edge-to-edge coordination | |
| CN116109058A (en) | Substation inspection management method and device based on deep reinforcement learning | |
| CN116684472A (en) | Service deployment system and service deployment method for terminal-side computing network | |
| KR20240016572A (en) | Cloud-Multiple Edge Server Collaboration System and Method Based on Service Classification in Intelligent Video Security Environments | |
| Caux et al. | Smart datacenter electrical load model for renewable sources management | |
| CN113297415A (en) | Intelligent service method and system for edge video analysis facing power edge side |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |