WO2011144178A1 - 联合优化的方法、装置和系统 - Google Patents
联合优化的方法、装置和系统 Download PDFInfo
- Publication number
- WO2011144178A1 WO2011144178A1 PCT/CN2011/075388 CN2011075388W WO2011144178A1 WO 2011144178 A1 WO2011144178 A1 WO 2011144178A1 CN 2011075388 W CN2011075388 W CN 2011075388W WO 2011144178 A1 WO2011144178 A1 WO 2011144178A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- bandwidth
- subnet
- server
- information
- external port
- Prior art date
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0876—Network utilisation, e.g. volume of load or congestion level
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0896—Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/60—Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources
- H04L67/63—Routing a service request depending on the request content or context
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/12—Discovery or management of network topologies
Definitions
- the present invention relates to the field of communications technologies, and in particular, to a method, apparatus, and system for joint optimization.
- the role of the ISP Internet Service Provider
- ISP Internet Service Provider
- TE Traffic Engineering
- CP Content Provider
- SS Server Selection
- the joint optimization mathematical model of TE and SS established by NBS is a constrained convex optimization problem.
- the network-wide status information uses a centralized approach to obtain the optimal solution of the system, and applies the optimal solution to the network, thereby implementing a routing change strategy and a new server selection strategy.
- the scalability of the solution is poor. As the network scale expands, the time spent collecting information and computing will increase dramatically. If joint optimization is to be applied to larger networks, such as the entire metropolitan area network or even the national backbone network, The real-time performance of the existing joint optimization method on the network will be difficult to guarantee.
- the embodiments of the present invention provide a method, a device, and a system for jointly optimizing, which effectively reduce the computational complexity and complexity of the joint optimization, and improve the performance and efficiency of the entire network.
- Joint optimization methods including: Obtaining link information, server and bandwidth information, and user requirement information of the subnet; the server and bandwidth information includes a virtual server bandwidth of each external port of the subnet, where the virtual server bandwidth is the subnet pass The bandwidth required by the external port to the server outside the subnet;
- An embodiment of the present invention provides a joint optimization computing device, including:
- a parameter collection module configured to obtain link information, server and bandwidth information, and user requirement information of the subnet;
- the server and bandwidth information includes virtual server bandwidth of each external port of the subnet, and the virtual server The bandwidth is the bandwidth requirement of the subnet through the external port to the server outside the subnet;
- the calculation module is configured to obtain an optimal routing parameter and a server selection parameter of the subnet according to link information, server and bandwidth information, and user requirement information, and obtain each subnet of the subnet according to an optimal routing parameter and a server selection parameter. Optimized ingress bandwidth of the port;
- Output module used to compare the optimized ingress bandwidth and the virtual server bandwidth of each external port. If the comparison result of the optimized ingress bandwidth and the virtual server bandwidth of all the external ports is less than the setting error, the application is performed in the subnet. Optimal routing parameters and server selection parameters, and outputting the optimal routing parameters and server selection parameters.
- the embodiment of the invention provides a communication network, including:
- the joint optimization system obtains link information, server and bandwidth information, and user demand information of the subnet; and the server and bandwidth information includes a virtual server bandwidth of each external port of the subnet;
- An embodiment of the present invention provides a joint optimization system, including:
- the joint optimization computing device is configured to collect link information, server and bandwidth information, and user demand information; obtain routing parameters and server selection parameters, obtain optimized ingress bandwidth and optimize export bandwidth of each external port;
- the content routing engine is configured to convert the routing parameters and server selection parameters obtained by the joint optimization computing device into routing parameters and server selection parameters of the network in which the application is located.
- the embodiment of the present invention compares the servers outside the subnet to the virtual server on the device at the entrance of the subnet by performing joint optimization calculation in parallel in each subnet.
- the bandwidth of this virtual server is the smaller of the optimized egress bandwidth calculated by the port to the terminal network joint optimization and the ingress bandwidth on the subnet minus the ingress background traffic, and the bandwidth through the virtual server is also between the subnets.
- Bandwidth coupling, joint optimization calculations are performed on each subnet to obtain the routing policy and server selection policy of the network. Applying this routing policy and server selection strategy in the network makes the performance and utilization of the network the highest.
- Figure 1 illustrates an embodiment in which a jointly optimized network is decomposed into two layers
- Figure 2 illustrates an embodiment in which a jointly optimized network is decomposed into three layers
- FIG. 5 is an embodiment of a network-wide joint optimization execution process
- Figure 6 is an embodiment of a joint optimization control system.
- Figure 1 shows the network that performs joint optimization into two layers.
- the first layer is the access layer.
- the subnet is divided into BAS (Broadband Access Server), that is, the BAS and the switch connected to it, DSLAM. ( , Digital Subscriber Line Access Multiplexer, etc.) form a subnet, and the BAS and the Border Router (BR) connected to it and the core router (CR, Core Router) form an upper layer.
- BAS Broadband Access Server
- DSLAM Digital Subscriber Line Access Multiplexer, etc.
- BR Border Router
- CR Core Router
- Subnet At the access layer, subnetting in units of BAS is a method of subnetting. It can also be subnetted by an edge router or other device.
- the second is an embodiment in which a network performing joint optimization is divided into three layers.
- the first layer is an access layer, which is divided into multiple subnets by BAS and edge routers, and is divided into different areas by region in the middle layer.
- the subnet, the uppermost layer is a subnet, including network nodes such as egress routers.
- the decomposition of the network is not limited to two or three layers, and may be decomposed into multiple layers.
- the bottom layer may be referred to as a first layer subnet and a second layer subnet.
- the third layer subnet, ..., the M layer subnet, the uppermost layer network can also be called the upper layer subnet, and the first layer subnet can also be called the bottom layer subnet.
- 3 is an embodiment of a joint optimization computing device including a parameter collection module, a calculation module, and an output module.
- the parameter collection module is responsible for collecting network status information, server information, user demand information, and optimized output bandwidth of the adjacent subnet output, and providing the collected input to the calculation module; wherein the network status information includes link bandwidth and link
- the user demand information includes a collection of users, a user's demand for content, etc.
- the server information includes a server set, a server bandwidth, and the server set includes a server in the subnet and an entrance of the adjacent subnet.
- the virtual server, the optimized egress bandwidth output by the neighboring subnet is the egress bandwidth that can be provided by the adjoining subnet for joint optimization calculation. This bandwidth is used as the bandwidth of the virtual server at the entrance of the adjacent subnet.
- the calculation module receives the network state information collected by the parameter collection module, the server information, the user information, and the optimized output bandwidth of the neighboring subnet output, performs a joint optimization algorithm calculation, and calculates the egress bandwidth and the required ingress bandwidth that the subnet can provide. And the corresponding routing policy and server selection policy, the results are provided to the output module.
- the output module receives the optimal result calculated by the calculation module and calculates the calculation result of the module, and compares Compared with the ingress bandwidth required by the subnet and the egress bandwidth that the adjacent subnet can provide, if the difference between the two is within the error range, a routing policy and a server selection policy are provided to the content routing engine. Also provide the egress bandwidth that this subnet can provide to the content routing engine.
- Users in a subnet may download content from servers on this subnet, or may download content from servers on other subnets or upper subnets. Users in subnets request servers outside the subnet to pass through this subnet and other subnets.
- the outlet of the network connection so in terms of a subnet, it can be considered that the server outside the subnet is the virtual server on the device at the entrance of the subnet, and the sum of the bandwidths that all servers in the subnet can provide.
- the smallest of the maximum egress bandwidth of the neighboring subnet and the maximum ingress bandwidth of the subnet which is the bandwidth that the virtual server at the entrance of the subnet can provide.
- the maximum egress bandwidth of the subnet refers to the value of the subnet's egress bandwidth minus the egress background traffic.
- the maximum ingress bandwidth of the subnet refers to the subnet's ingress bandwidth minus the entry background. The value after the flow.
- the user set T is a collection of all users in the subnet requesting CP content
- the server set S is a collection of all servers in the subnet and virtual servers on the devices at the ingress.
- the bandwidth of the server in the subnet is the bandwidth that the server can provide, and the bandwidth of the virtual server on the device at the ingress is not greater than the value of the ingress bandwidth of the subnet minus the background traffic of the portal.
- the value is According to the statistical prediction of network information, when the neighboring subnet outputs optimized outlet bandwidth, the virtual server bandwidth on the device at the ingress is the minimum of the neighboring subnet output optimized outlet bandwidth, the subnet entry bandwidth minus the entrance background traffic.
- the starting node set I of the background stream is a set of those nodes requesting the background stream in the subnet
- the terminating node set J is the egress node of the metropolitan area network
- the station is also assumed to have a device on the device at the entrance point.
- the virtual background stream terminates the node.
- the mathematical model of the joint optimization algorithm is established by using the convex optimization technique and the NBS (Nash Bargaining Solution) of the game theory, that is, the constraints such as link information, server and bandwidth information, and user demand information are considered.
- NBS Network Bargaining Solution
- the optimization problem is solved to obtain a set of optimal values, which reflect the optimal routing change strategy of the TE and the optimal server selection strategy of the SS.
- the user-to-server band can be calculated.
- Wide demand which also includes the bandwidth requirement for the server outside the subnet, that is, the bandwidth requirement of the virtual server on the device at the entrance, the bandwidth requirement and the maximum ingress bandwidth of the subnet on the port minus the background traffic.
- the smaller value is used as the optimized ingress bandwidth for this subnet on this port. According to the set of optimal values, the remaining bandwidth that can be provided by the server in the subnet through the port can be calculated, and the bandwidth and the maximum egress bandwidth of the subnet on the port are subtracted from the background traffic. The small value is used as the optimized exit bandwidth for this subnet on this port.
- the SS-drawn TE-NBS sub-problem after the first-stage decomposition of the joint optimization original problem is further advanced in the angle of the link, the server, and the background flow end point.
- the level is decomposed to decompose it into smaller problem solvers, reducing the time it takes for the algorithm to execute.
- the decomposition principle is as follows:
- the joint optimization mathematical model of the network is decomposed into the first-level decomposition according to the dual decomposition method, which is decomposed into two sub-problems of SS-NBS and TE-NBS, and the main problem of DualTE-SS, and the main problem ⁇ > ⁇ /73 ⁇ 4 -
- the price variables, and introduced by the decomposition method control the two sub-problems -A ⁇ and 73 ⁇ 4-A3 ⁇ 4. Since the two sub-problems - ⁇ ⁇ and 73 ⁇ 4-A3 ⁇ 4 are still constrained optimization problems, further decomposition is necessary.
- the second-level decomposition is performed in units of link/server S, and is decomposed into two sub-problems of SS-NBS-L and SS-NBS-S, and the DimlSS-NBS master and
- the main problem wa/ -A ⁇ controls the two sub-problems of SS-NBS-L and SS-NBS-S by the price variables introduced by the second-level decomposition, and . Since the two sub-problems SS-NBS-L and SS-NBS-S are the smallest solvable problems, it is not necessary to continue the decomposition. Otherwise, it is still necessary to continue the decomposition with a similar decomposition method until the minimum solvable problem is obtained.
- the second level decomposition is performed in the unit of link 1 and background flow end j, and is decomposed into two sub-problems of TE-NBS-L and TE-NBS-J, and the main problem of DiialTE-NBS.
- DiialTE-NBS controls the two sub-problems TE-NBS-L and 73 ⁇ 4-A3 ⁇ 4 -J through the price variables introduced by the second-level decomposition.
- the equation can be decomposed into SS-NBS, and two sub-problems SS-NBS, wherein the two sub-problems acceptor question D Ma / r £ _ ss ( 4, ⁇ , ⁇ ,) control.
- G( ,v,) log(rE 0 +f )) + ⁇ ( l fl ,g ' -vj - )
- V(s,t)eSxT; f t represents the set of users served by the server, s (o represents a collection of servers served by a user.
- the last constraint indicates that for non-servers and users
- the intermediate node V the flow rate into V is equal to the flow flow from V, that is, the flow conservation law is satisfied for the intermediate node V.
- the establishment of this formula is obvious, so it is not considered when generating the Lagrangian expression.
- / eJ L(w) represents the link from the server s to the user.
- Layer 5 sub-problems are divided into two sub-problems based on link I and server S ⁇ -N ⁇ S- and
- the TE-NBS subproblem in ( 1. 2 ) rE _ NBS(r; j , can be further expressed as follows
- I e L ⁇ i,j represents the link from i to j.
- the rE-Nas subproblem is divided into two sub-problems rE-N ⁇ s - and according to the link I and the background flow end point.
- the Variable ⁇ , r t calculation module decomposes the original problem into two sub-problems with less computation according to the above decomposition process. After calculating the optimal result, it will feed back to the output module, and the output module outputs the calculation result to the content routing engine.
- the result on the network will change the routing policy and server selection policy.
- the routing change policy will allocate traffic to each path in an optimal manner to solve the traffic engineering problem; the server selection policy will be applied to the server (including the virtual server in the subnet), specifying the bandwidth that the server can allocate and the server to serve. New user collection.
- Figure 5 is the execution flow of the joint optimization of the whole network.
- the network to be jointly optimized is decomposed into multiple subnets, and the joint optimization is solved separately in each subnet. If the subnets are not solved from the adjacent network in the first solution,
- the bandwidth value is set to an initial value of the virtual server bandwidth on the device at the entry. The initial value is not greater than the subnet entry bandwidth minus the entry background traffic.
- the value can be predicted according to the network information. Alternatively, a value can be arbitrarily selected within this range, such as the subnet entry bandwidth minus one-half of the ingress background traffic. If an optimized egress bandwidth value is obtained from the neighboring network, the neighboring network is selected to optimize the egress bandwidth, the subnet. The minimum of the ingress bandwidth minus the ingress background traffic is used as the virtual server bandwidth on the device at the set entry.
- the joint optimization described above is performed on each subnet in an iterative manner, and the optimization problems of all the subnets and upper subnets are finally converged to the optimal value, thereby achieving Pareto optimality.
- the route change policy and the server selection policy after the system convergence are sent to the relevant network elements in the network.
- Step 1 Set an initial hypothetical ingress bandwidth for each subnet in the lower layer network, and the parameter collection module collects network status information (such as link information, etc.), server and bandwidth information, and user requirement information of the subnet, and calculates The module solves the optimal routing parameters and server of this subnet according to the decomposition method of FIG. Parameters.
- the optimal egress bandwidth that this subnet can provide is derived, where the optimized egress bandwidth is the smallest of the port's maximum egress bandwidth and the maximum bandwidth that the server within the subnet can provide.
- the optimized ingress bandwidth of this subnet is obtained, that is, the bandwidth provided by the server outside the subnet is required;
- Step 2 If there is a non-top layer intermediate layer subnet, the parameter collection module of the joint optimization system of the middle layer subnet collects the optimized exit bandwidth calculated by the adjacent lower layer subnet, and the intermediate layer subnet Network status information (such as link information, etc.), server and bandwidth information, user demand information, set initial intermediate layer subnet and hypothetical ingress bandwidth of the upper subnet interface, and the calculation module solves according to the decomposition method of FIG.
- the optimal routing parameters and server parameters for this middle tier subnet The optimized egress bandwidth provided by the subnet in the upper layer network and the subnet in the lower layer network, where the optimized egress bandwidth refers to the smallest of the maximum egress bandwidth of the port and the maximum bandwidth that the server in the subnet can provide. .
- the optimized ingress bandwidth of this subnet is obtained, that is, the bandwidth provided by the server outside the subnet is required;
- Step 3 Optimize the egress bandwidth calculated by the parameter collection module of the joint optimization system of the uppermost subnet and the subnet, and the network state information (such as link information, etc.) calculated by the adjacent subnet. ), server and bandwidth information, the calculation module solves the optimal routing parameters and server parameters of the subnet according to the decomposition method of FIG. 4 .
- the optimal egress bandwidth provided by the subnet in the lower layer network of this subnet is obtained, where the optimized egress bandwidth is the smallest of the maximum egress bandwidth of the port and the maximum bandwidth that the server within the subnet can provide.
- the optimized ingress bandwidth of this subnet is obtained, that is, the bandwidth provided by the server outside the subnet is required;
- Step 4 Replace the optimized assumed egress bandwidth calculated in step 3 with the lower subnet interface with the initial hypothetical ingress bandwidth set in step 2, and perform step 2, using step 2 to calculate the optimized egress bandwidth of the subnet interface.
- the initial hypothetical ingress bandwidth is set in step 1
- the first step is performed. If the calculated hypothetical ingress bandwidth and the optimized ingress bandwidth are within the error range, the optimal routing parameters and server parameters are output and act on the corresponding subnet. Otherwise, repeat step 1, step 2, step 3, and step 4 again.
- the joint optimization system includes a content routing engine, a joint optimization computing device, and a composition of the joint optimization computing device.
- FIG. 3 further includes a joint optimization system and a proxy module, and a name is also included.
- Proxy As a proxy for the user, it establishes a bridge between the user terminal and the joint optimization system, and can also be used to aggregate the user's request. It can be deployed at the edge of the network, such as on a DSLAM.
- Content Routing Engine It determines how to get the content you need. When it finds that the required content is not on the local cache device, it uses the Name Resolution Engine to get a list of nodes that own the content, which is input as server information to the parameter collection module.
- the content routing engine obtains the routing change policy and the server selection policy from the output module of the joint optimization computing device, and converts it into a deployable implementation routing change policy and a server selection policy, the former being input to the transmission/retransmission engine to execute the underlying routing policy, and then The input is to the topology maintenance module to perform server selection at the content layer.
- Name Resolution Engine Mainly returns a list of suitable nodes with the content the user wants.
- Content GET/PUT Adapter It requests the content of the content routing engine from the local cache device and returns it to the content routing engine so that the content routing engine routes the content to the destination user.
- Traffic Statistics Collector summarizes background traffic information, link information, etc., and reports them to the parameter collection module.
- Requests Statistics Collector Aggregates user requirements and sends them to the parameter collection module.
- For the terminal network joint optimization system obtain the optimized exit bandwidth calculated by the subnet joint optimization computing device, and use the optimized egress bandwidth for the terminal network to obtain the hypothetical ingress bandwidth required for performing joint optimization, which is virtualized on the device at the entrance.
- the bandwidth of the server The bandwidth of the server.
- Parameter collection module It mainly collects user requests, server list information, dynamic characteristics of traffic, and optimized export bandwidth information for the terminal network.
- Calculation module Using the optimal decomposition theory to calculate the optimal (user, server) pair, and at the same time, derive the end-to-end path and the flow ratio on each path for each (user, server) pair.
- Output module The output module is responsible for receiving the optimal calculation result of the calculation module and inputting it to the content routing engine.
- Transmission/Forwarding Engine Receives the IP layer of the content routing engine, performs traffic transmission, and implements the optimal routing of the underlying layer.
- Topology maintenance module Receives the application layer instructions of the content routing engine, performs server selection, and implements content layer routing.
- the interaction process of the joint optimization system is as follows:
- the proxy module completes the client user's request collection of content
- the naming parsing engine performs content parsing according to the requested content name, and knows the user's demand information for the content and inputs it to the request generator;
- the content routing engine obtains the server information, first obtains the server information of the local cache device through the content GET/PUT adapter, and when the local cache device does not have the required content, obtains the node list information with the content required by the user through the naming parsing engine. ;
- the parameter collection module obtains the user's request information from the request generator, obtains the server information from the content routing engine, obtains network status information (such as background flow information, link information, etc.) from the traffic generator, and the slave terminal network.
- the interface obtains the egress bandwidth information and the ingress bandwidth information of the terminal network;
- the calculation module uses the information obtained by the parameter collection module to perform the joint optimization calculation using the optimization decomposition theory, and obtains the optimal (user, server) pair, and at the same time, the end-to-end formed by each (user, server) pair is obtained.
- the output module inputs the optimal calculation result of the calculation module to the content routing engine
- the content routing engine obtains the optimal solution from the output module and converts it into a deployable implementation of the route change policy and the server selection policy.
- the former is input to the transport/forward engine to execute the underlying routing policy, and the latter is input to the topology maintenance module.
- the relevant information required to update the egress bandwidth and the ingress bandwidth is input to the terminal network;
- the transport/forward engine receives a routing change policy from the content routing engine to modify the underlying route and perform a routing change policy at the IP layer;
- the topology maintenance module receives a server selection policy from the content routing engine to perform server selection at the application layer, thereby establishing a mapping relationship between the user and the server.
- a global network optimization problem is equivalently converted into several subnet optimization problems.
- the joint optimization model variables and constraints in the subnet are relatively small and the calculation amount is small.
- the embodiment also discloses a method for solving the joint optimization model in the subnet, and decomposes the original mathematical model according to the link, the server and the background flow end point, and decomposes it into a smaller solvable problem, and reduces the execution time of the algorithm. Since the subnets are only coupled by bandwidth, the coupling relationship is loose. Solve the problem of optimization.
- the foregoing program may be stored in a computer readable storage medium, and the program is executed when executed.
- the foregoing steps include the steps of the foregoing method embodiments; and the foregoing storage medium includes: a medium that can store program codes, such as a ROM, a RAM, a magnetic disk, or an optical disk.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Environmental & Geological Engineering (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
Description
Claims
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP11783095.0A EP2515478B1 (en) | 2010-10-30 | 2011-06-07 | Method, apparatus and system for joint optimizations |
RU2012137874/08A RU2520354C2 (ru) | 2010-10-30 | 2011-06-07 | Способ, устройство и система для совместной оптимизации |
BR112012022286A BR112012022286A2 (pt) | 2010-10-30 | 2011-06-07 | método, aparelho e sistema para otimização de ligação. |
US13/721,530 US9003029B2 (en) | 2010-10-30 | 2012-12-20 | Method, apparatus and system for joint optimization |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201010525399.7 | 2010-10-30 | ||
CN201010525399.7A CN102130824B (zh) | 2010-10-30 | 2010-10-30 | 网络联合优化方法和装置 |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US13/721,530 Continuation US9003029B2 (en) | 2010-10-30 | 2012-12-20 | Method, apparatus and system for joint optimization |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2011144178A1 true WO2011144178A1 (zh) | 2011-11-24 |
Family
ID=44268718
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2011/075388 WO2011144178A1 (zh) | 2010-10-30 | 2011-06-07 | 联合优化的方法、装置和系统 |
Country Status (6)
Country | Link |
---|---|
US (1) | US9003029B2 (zh) |
EP (1) | EP2515478B1 (zh) |
CN (1) | CN102130824B (zh) |
BR (1) | BR112012022286A2 (zh) |
RU (1) | RU2520354C2 (zh) |
WO (1) | WO2011144178A1 (zh) |
Families Citing this family (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9686232B2 (en) * | 2012-06-25 | 2017-06-20 | Connectify, Inc. | Network address translating router for mobile networking |
CN103974082B (zh) * | 2013-01-25 | 2018-09-21 | 华为技术有限公司 | 子节点、父节点以及用于多层次视频网络的缓存方法及系统 |
US9386353B2 (en) | 2013-01-25 | 2016-07-05 | Huawei Technologies Co., Ltd. | Child node, parent node, and caching method and system for multi-layer video network |
EP2963970B1 (en) | 2013-03-28 | 2022-01-05 | Huawei Technologies Co., Ltd. | Method and device for allocating bandwidth, user equipment and base station |
CN103200113B (zh) * | 2013-04-02 | 2016-04-06 | 北京邮电大学 | 兼顾运营成本和传输性能双优化的域间流量工程的实现方法 |
US10313232B2 (en) * | 2015-03-06 | 2019-06-04 | Nec Corporation | Network control device, network control method, and recording medium for program |
CN106293897B (zh) * | 2015-05-15 | 2021-11-30 | 株式会社日立制作所 | 组件自动化调度系统 |
CN105515831A (zh) * | 2015-11-27 | 2016-04-20 | 小米科技有限责任公司 | 网络状态信息展示方法及装置 |
CN107438013B (zh) * | 2016-05-27 | 2022-05-17 | 中兴通讯股份有限公司 | 一种端口优化方法、装置及系统 |
CN106302221B (zh) * | 2016-09-12 | 2019-09-10 | 中国联合网络通信集团有限公司 | 基于端局云化的流量调度方法和系统 |
RU2680764C1 (ru) * | 2018-03-06 | 2019-02-26 | Федеральное государственное казенное военное образовательное учреждение высшего образования Академия Федеральной службы охраны Российской Федерации | Способ, устройство и система для оптимизации транспортной сети связи |
CN111884854B (zh) * | 2020-07-29 | 2022-09-02 | 中国人民解放军空军工程大学 | 基于多模式混合预测的虚拟网络流量迁移方法 |
CN113630456B (zh) * | 2020-08-05 | 2022-07-05 | 北京航空航天大学 | 基于拉格朗日对偶分解和纳什议价博弈的域间合作缓存方法 |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1688133A (zh) * | 2005-04-11 | 2005-10-26 | 西安电子科技大学 | 传送网的资源利用优化方法 |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7403482B2 (en) * | 2000-10-30 | 2008-07-22 | Nec Corporation | Path provisioning for service level agreements in differentiated service networks |
JP5138847B2 (ja) * | 2001-08-31 | 2013-02-06 | 富士通株式会社 | ネットワークシステム、ネットワーク中継装置、ネットワーク中継監視装置およびネットワーク運用方法 |
SE523714C2 (sv) | 2002-07-05 | 2004-05-11 | Packetfront Sweden Ab | Ett filter i ett gränssnitt inom ett öppet system av typ skikt2 för trafikseparation i minst en router för åtkomstomkoppling inom ett nät, och ett förfarande för detta |
US7292542B2 (en) * | 2003-03-05 | 2007-11-06 | At&T Bls Intellectual Property, Inc. | Method for traffic engineering of connectionless virtual private network services |
CN101541025B (zh) * | 2009-04-28 | 2011-01-19 | 北京邮电大学 | 具有认知功能的无线通信网络系统 |
CN101707788B (zh) * | 2009-10-27 | 2014-04-02 | 北京邮电大学 | 基于差异化定价策略的多层网络业务动态规划方法 |
CN101753450B (zh) * | 2009-12-21 | 2012-09-05 | 西安电子科技大学 | 三层网络联合资源优化方法 |
US8688775B2 (en) * | 2010-05-28 | 2014-04-01 | Juniper Network, Inc. | Application-layer traffic optimization service spanning multiple networks |
-
2010
- 2010-10-30 CN CN201010525399.7A patent/CN102130824B/zh not_active Expired - Fee Related
-
2011
- 2011-06-07 BR BR112012022286A patent/BR112012022286A2/pt active Search and Examination
- 2011-06-07 RU RU2012137874/08A patent/RU2520354C2/ru not_active IP Right Cessation
- 2011-06-07 WO PCT/CN2011/075388 patent/WO2011144178A1/zh active Application Filing
- 2011-06-07 EP EP11783095.0A patent/EP2515478B1/en not_active Not-in-force
-
2012
- 2012-12-20 US US13/721,530 patent/US9003029B2/en not_active Expired - Fee Related
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1688133A (zh) * | 2005-04-11 | 2005-10-26 | 西安电子科技大学 | 传送网的资源利用优化方法 |
Non-Patent Citations (3)
Title |
---|
D. DIPALANTINO ET AL.: "Traffic Engineering vs. Content Distribution: A Game Theoretic Perspective", PROC. IEEE INFOCOM 2009, 30 December 2009 (2009-12-30) * |
See also references of EP2515478A4 * |
W. JIANG ET AL.: "Cooperative Content Distribution and Traffic Engineering in an ISP network", SIGMETRICS/PERFORMANCE'09, JUNE 15-19,2009, 19 June 2009 (2009-06-19), SEATTLE, WA, USA * |
Also Published As
Publication number | Publication date |
---|---|
EP2515478A4 (en) | 2012-11-28 |
US20130117443A1 (en) | 2013-05-09 |
RU2520354C2 (ru) | 2014-06-20 |
EP2515478A1 (en) | 2012-10-24 |
CN102130824A (zh) | 2011-07-20 |
BR112012022286A2 (pt) | 2018-05-15 |
US9003029B2 (en) | 2015-04-07 |
RU2012137874A (ru) | 2014-03-10 |
EP2515478B1 (en) | 2016-04-27 |
CN102130824B (zh) | 2014-09-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2011144178A1 (zh) | 联合优化的方法、装置和系统 | |
Xu et al. | Incremental deployment and throughput maximization routing for a hybrid SDN | |
EP3005620B1 (en) | A method and system of bandwidth-aware service placement for service chaining | |
JP5975083B2 (ja) | 通信システム、制御装置、パケット転送経路の制御方法およびプログラム | |
He et al. | Achieving near-optimal traffic engineering in hybrid software defined networks | |
WO2019218812A1 (zh) | 物理光网络虚拟化映射方法、装置、控制器及存储介质 | |
JP2019122040A (ja) | ネットワークソースリユース及びソフトウェアによりマルチソースを定義するルーティングメカニズム | |
Nguyen et al. | Environment-aware virtual slice provisioning in green cloud environment | |
Attia et al. | QoS-aware software-defined routing in smart community network | |
He et al. | Performance of multipath in fiber-wireless (FiWi) access network with network virtualization | |
Ndikumana et al. | Federated learning assisted deep Q-learning for joint task offloading and fronthaul segment routing in open RAN | |
Shirmarz et al. | A novel flow routing algorithm based on non-dominated ranking and crowd distance sorting to improve the performance in SDN | |
CN109286563B (zh) | 一种数据传输的控制方法和装置 | |
Huang et al. | Utility-optimized flow-level bandwidth allocation in hybrid SDNs | |
CN103200113B (zh) | 兼顾运营成本和传输性能双优化的域间流量工程的实现方法 | |
Elzain et al. | QoS-aware topology discovery in decentralized software defined wireless mesh network (D-SDWMN) architecture | |
Oki et al. | F-TPR: Fine two-phase IP routing scheme over shortest paths for hose model | |
García et al. | Multicast routing and virtual network function placement in NFV-SDN networks: A genetic algorithms approach | |
CN115102831A (zh) | 一种分布式bgp服务的部署方法和系统 | |
Zhang et al. | Q-SR: An extensible optimization framework for segment routing | |
ELseuofi | Quality of service using PSO algorithm | |
Zhao et al. | Hybrid routing by joint optimization of per-flow routing and tag-based routing in software-defined networks | |
Li et al. | Self-adaptive genetic algorithm for LTE Backhaul network | |
Xu et al. | An implementation of an intelligent PCE-agent-based multi-domain optical network architecture | |
Zhang et al. | Multi-AS cooperative incoming traffic engineering in a transit-edge separate internet |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 11783095 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 1761/KOLNP/2012 Country of ref document: IN Ref document number: 2011783095 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2012137874 Country of ref document: RU |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
REG | Reference to national code |
Ref country code: BR Ref legal event code: B01A Ref document number: 112012022286 Country of ref document: BR |
|
ENP | Entry into the national phase |
Ref document number: 112012022286 Country of ref document: BR Kind code of ref document: A2 Effective date: 20120904 |