KR20190060562A - Method and apparatus for controlling multi-resource infrastructures - Google Patents

Abstract

According to various embodiments of the present invention, provided are a method and an apparatus for managing multi-resource infrastructures, wherein the method for managing multi-resource infrastructures defines a set of candidate paths for each of services in a network environment including multiple physical nodes and multiple links where networking and processing resources coexist, and provides a service by selecting a plurality of paths with high efficiency among the defined candidate paths, thereby improving service quality while reducing system costs.

Description

[0001] METHOD AND APPARATUS FOR CONTROLLING MULTI-RESOURCE INFRASTRUCTURES [

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates generally to a method and apparatus for managing multiple resource infrastructures and, more particularly, to network function virtualization (QoS) including a general networking service in a multiple resource infrastructure environment including networking resources and processing resources. (NFV) service and computation offloading (CO) service.

The following description merely provides the background information related to the embodiments of the present invention and does not constitute the prior art.

In conventional network environments, network functions such as deep packet inspection (DPI), intrusion detection system (IDS), firewall and charging have been implemented only on special hardware, Accordingly, a service that requires a network function must pass through hardware that supports the function.

1 is a conceptual diagram illustrating a conventional network routing environment.

For example, in a cellular network, all packets have to go through a packet data network gateway (P-GW) to support billing because all packets have to be billed.

However, as virtualization technology has been introduced in recent years, various services using networking resources and processing resources have become possible. One of them is network function virtualization (NFV) service.

2 is a conceptual diagram illustrating a conventional NFV service routing environment.

NFV has virtualized these network functions based on software so that they can be implemented in various nodes. Network function virtualization has the advantage of improving resource efficiency, manageability, scalability, and applicability by using network service chaining. US leading network operators AT & T and Verizon also began applying NFV technology for network operation starting in 2016.

Another example of using networking and processing resources together is computation offloading (CO) services.

3 is a conceptual diagram illustrating a conventional CO service routing environment.

Examples of computation functions include transcoding, voice and image processing, and the like. In the past, the computation functions required by the end host had to be handled directly by the host node, but now the CO service can be used to offload the computation functions to the near-edge cloud or remote cloud in the distance, instead of processing them.

With this technique, end hosts can reduce the energy consumption and processing delay of the node, and can improve the service quality by performing the computation function with higher throughput. Currently, various IT companies such as Amazon, Windows, Google and Microsoft support CO services.

The above-mentioned NFV service and CO service both use the networking resource and the processing resource together and have the following common features. In the network environment where the NFV service and the CO service are provided, there are a plurality of physical nodes that can perform a given virtual function, and an end host of each service selects which resource is used to perform the corresponding function . This is similar to network routing, but also takes into account networking resources, that is, link capacity as well as processing resources, that is, CPU capacity. For example, no matter how rich the networking resources are, if the processing resources of the corresponding route nodes are insufficient, the service quality is degraded. Also, a path defined as a set of networking resources is defined as a set of networking resources and processing resources. In this case, the characteristics such as cost, delay, and throughput vary depending on the route through which the service is provided, and the efficiency of the resource utilization and the quality of the service are changed. Also, if one service can use multiple given candidate paths at the same time, it can be expected to improve the quality of service or decrease system cost.

Existing studies have been conducted in NFV environments and CO environments only in their respective environments, and none of them have been studied in a single framework. However, in a real network environment, NFV service and CO service coexist, including general network service, and these services share networking resources and processing resources.

Therefore, there is a need for a resource management method that can manage these services together in a network environment where various resources such as networking resources and processing resources coexist.

Embodiments of the present invention provide a method and apparatus for managing multiple resource infrastructures that can reduce system cost while improving service quality in a network environment including a plurality of physical nodes and a plurality of links in which networking resources and processing resources coexist The main purpose is to do.

One embodiment of the present invention is a multi-resource infrastructure (e.g., a multi-resource infrastructure) comprising at least two nodes using processing resources and at least one link using networking resources. managing at least one service provided based on at least one path formed by connecting at least one first end node selected from each of the at least two nodes and at least one second end node in a resource infrastructure A candidate path set defining process for defining a set of candidate paths for the at least one service among the at least one path; And a multipath forming step of forming a multipath by dividing an input transmission rate for the at least one service by the set of the candidate paths.

One embodiment of the present invention is directed to a method and system for providing at least one link using at least two nodes using a processing resource and a first end node and a second end node that are networking resources, link, and at least one path connecting the first end node and the second end node via the at least one link, wherein in the multi-resource infrastructure, A candidate path set defining unit that defines a set of candidate paths for at least one service; A multipath forming unit for forming a multipath by dividing an input transmission rate for the at least one service by the set of the candidate paths; And a transmission rate determiner for defining a dual variable for each of the processing resource and the networking resource and for determining a transmission rate of the dual resource by updating the pair variable, Thereby providing an infrastructure management apparatus.

According to an embodiment of the present invention, a method and apparatus for managing a network function virtualization service and a computation offloading service together can be provided.

According to another aspect of the present invention, there is an effect that resource utilization efficiency and service quality can be improved in a network environment in which networking resources and processing resources coexist.

1 is a conceptual diagram illustrating a conventional network routing environment.
2 is a conceptual diagram illustrating a conventional NFV service routing environment.
3 is a conceptual diagram illustrating a conventional CO service routing environment.
4 is a conceptual diagram of a multi-resource infrastructure management apparatus according to an embodiment of the present invention.
5 is a flowchart illustrating a multi-resource infrastructure management method according to an exemplary embodiment of the present invention.
FIG. 6 illustrates two examples of topologies for explaining the results of applying the multi-resource infrastructure management method according to an embodiment of the present invention.
FIG. 7 is a graph illustrating service utilization and system cost when a multiple resource infrastructure management method according to an embodiment of the present invention is applied to Case 1 of FIG.
FIG. 8 is a graph illustrating the effect of the multiple resource infrastructure management method according to an exemplary embodiment of the present invention on resource availability when the case 1 of FIG. 6 is applied.
FIG. 9 is a graph illustrating the effect of the multiple resource infrastructure management method according to an exemplary embodiment of the present invention on service characteristics in case 2 of FIG. 6.
Figure 10 shows a real Internet topology in the United States.
11 is a graph showing simulation results obtained by applying a multi-resource infrastructure management method according to an embodiment of the present invention to actual large-scale cases.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. It should be noted that, in the drawings, like reference numerals are used to denote like elements in the drawings, even if they are shown in different drawings. In the following description of the present invention, detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present invention rather unclear.

In describing the components of the embodiments according to the present invention, the first, second, i), ii), a), b) and the like can be used. Such a code is intended to distinguish the constituent element from other constituent elements, and the nature of the constituent element, the order or the order of the constituent element is not limited by the code. It is also to be understood that when a component is referred to as being "comprising" or "comprising," it should be understood that it is not intended to exclude other components, it means.

Hereinafter, a method and apparatus for managing multiple resource infrastructures according to embodiments of the present invention will be described with reference to the accompanying drawings.

4 is a conceptual diagram of a multi-resource infrastructure management apparatus according to an embodiment of the present invention.

The multi-resource infrastructure management apparatus 400 according to an exemplary embodiment of the present invention includes a candidate path set defining unit 410, a multipath forming unit 420, and a transmission rate determining unit 430.

To help explain the multi-resource infrastructure management apparatus 400, the multi-resource infrastructure management apparatus 400 first defines a typical network environment in which the apparatus 400 can be implemented. The network environment includes at least one link ( l ) included in a set of networking resources ( L ) and at least one node ( k ) included in a set of processing resources ( K ). The set of networking resources and the set of processing resources can be expressed by Equation (1), respectively.

The available capacity of the networking resource l and the processing resource k can be expressed as C _l (bits / s) and C _k (cycles / s), respectively. Each processing resource supports a set of virtualization functions, for example, network functions for NFV services and computation functions for CO services. Furthermore, the network environment comprises at least one of a set of co-existing service W, each service source node (source node, s _w) path (s _w, d _w, leading to a destination node (destination node, d _w) in the ) And virtual functions to be processed. Here, a node refers to a network entity that performs or processes at least one function using a processing resource. Among the various nodes, there are a source node serving as a service source and a destination node serving as a service destination. There can be multiple links between the source node and the destination node, and various paths connecting the nodes through the various nodes.

The candidate path set definition unit 410 of the multi-resource infrastructure management apparatus 400 according to an embodiment of the present invention may consider the same service as the source node and the destination node. There may be a CO service in which the source node and the destination node have the same service processed as an example of the same service, and the function is consumed by the source node of the corresponding service. The candidate path set defining unit 410 defines multiple candidate paths by P _w for each service w ∈ W. Here, each path p ∈ P _w includes a networking resource set L _p and a processing resource set K _p . The networking resources included in the networking resource set L _p connect the source node s _w and the destination node d _w and the processing resources belonging to the processing resource set K _p support the virtual functions provided by the service w . That is, the candidate path set definition unit 410 defines a set of candidate paths for at least one service among at least one path (S510). The entire candidate path set P is defined by Equation (2).

The multi-path forming unit 420 of the multi-resource infrastructure management apparatus 400 according to an embodiment of the present invention may be configured such that the source node of the service has a transmission rate (Transmission rate) R _w is limited to R _w ≥ 0 and the transmission rate is divided into multiple candidate paths (S 520). Here, x _p means the transmission rate assigned to the path p . That is, the transmission speed of the service w divided by the multipath forming unit 420 is expressed by Equation 3, which is the sum of the transmission speeds assigned to the candidate paths.

The processing resource k is used by multiple candidate paths of coexisting services, and the virtual functions performed by processing resource k may be different for each path p .

For example, some paths may use processing resource k for video transcoding while the remaining paths may use the same processing resource k for DPI. In order to reflect this heterogeneity, we define the processing density ρ _{k, p} (cycles / bit) as the CPU cycles required in the processing resource k for processing the unit bits of the work on path p . Therefore, the load (cycles / s) for processing resource k for path p is ρ _{k, p} x _p . Depending on the functions performed on processing resource k for path p , the output transmission rate (bit rate) after performing processing resource k may be different. For example, if a function is only for verification of data accounting and virus scanning, then the output transmission rate will be equal to the input transmission rate. On the other hand, if the function includes a function of converting input data such as encryption, transcoding, packet aggregation, etc., the output transmission rate may be different from the input transmission rate. The change in transmission rate that is confirmed after processing is confirmed only on links that are successors to processing resources on that path. Define σ _{l, p} as the bit conversion ratio identified in networking resource 1 to account for the change in transmission rate after processing. Thus, the load (bit / s) on networking resource l for path p is σ _{l, p} x _p . For a transmission rate assigned to all paths p ∈ P , the total load for networking resource l may be denoted by F _l , and the total load for processing resource k may be denoted by F _k , Equation 5 is as follows.

Where P _l and P _k are a set of paths to which the networking resource l belongs and a set of paths to which the processing resource k belongs, respectively.

To account for the cost, delay, energy or throughput affecting network operation, we define a cost function D _l (F _l ) for the networking resource l and a cost function D _k (F _k ) for the processing resource k , respectively . Here, D _l (F _l ) and D _k (F _k ) are convex, and F _l And F _k increases, and has a bounded second derivative. U _w (R _w) is a function of the utilization of services w (utility function) That is, the satisfaction of the service that is determined by the input transmission rate of the service w, convex, and increases as the transmission rate R _w is increased.

Routing in the conventional network routing environment shown in FIG. 1 includes transmitting data from the source node 110 to the destination node 130 without any functional requirement, including the different source node 110 and the destination node 130 do. At this time, data may be transmitted through the various hardware routers 122, 124, and 126. Routing for a conventional routing service is therefore defined as determining the path from the source node 110 to the destination node 130. Applying this to the multi-resource infrastructure management apparatus 400 according to an embodiment of the present invention, ρ _{k, p} = _{k for} all k ∈ K _p , l ∈ L _p , p ∈ P _w and s _w ≠ d _w , 0 ,? _{1, p} = 1.

The NFV service in the conventional NFV service routing environment shown in FIG. 2 includes the source node 210 and the destination node 230, and virtualizes them in the nodes 222, 224, and 226 of the corresponding network. Thus, the routing of the NFV service is defined as determining the path connecting the source node 210 and the destination node (30) and performing the required network functions. When applying them to one embodiment a multi-resource infrastructure management apparatus 400 according to the present _invention, ρ _{k, p} ≠ 0 in all p ∈ P _w while the k ∈ K _p for a s _w ≠ d _w condition k Is present. Here, even if the network paths are the same, the networking resources and the processing resources may be different depending on the functions assigned to the nodes 222, 224, and 226 included in the paths.

The CO service in the CO service routing environment shown in FIG. 3 includes the same source node 310 and the destination node 310, and provides a computation function. Typically, nodes for executing computation functions include, but are not limited to, an end host, an edge cloud, and a remote cloud. Therefore, the routing of the CO service can be defined as determining the computation offloading policy among multiple processing resources. When the computation functions are performed locally, that is, when the computation functions are performed in the end host, the service does not require any networking resources, and there is a restriction on the processing resources of the end hosts. As computation functions are offloaded to the edge cloud 340 or the remote cloud 350, more powerful processing resources may be used, but additional networking resources may be consumed. Of this, when applied to a multi-resource infrastructure management apparatus 400 according to an embodiment of the present _invention, ρ _{k, p} ≠ 0 in all p ∈ P _w while s _w = d _w for the condition k ∈ K _p k Is present. Computation functions of a service can be performed through multiple processing resources. For example, intermediate stage processing may be performed in the edge cloud 340 before proceeding to the main processing at the remote cloud 350.

Meanwhile, the transmission rate determination unit 430 of the multi-resource infrastructure management apparatus 400 according to an exemplary embodiment of the present invention minimizes the total cost of networking resources and processing resources and maximizes the service satisfaction, that is, A dual variable for each of the processing and networking resources is defined. The transmission rate determination unit 430 updates the defined twin variables to determine a transmission rate at which data is to be transmitted through the multiple paths formed by the multipath forming unit 420. [

5 is a flowchart illustrating a multi-resource infrastructure management method according to an exemplary embodiment of the present invention.

The multi-resource infrastructure management method according to an embodiment of the present invention includes a candidate path set defining step S510 and a multipath forming step S520. The candidate path set definition process (S510) and the multipath formation process (S520) are as described with reference to the multiple resource infrastructure management apparatus 400 of FIG.

The multi-resource infrastructure management method according to an embodiment of the present invention may further include an objective function calculation step (S530).

In the objective function calculation process (S530), a problem for maximizing the service utilization, that is, the sum of the satisfaction levels of the services, is defined and calculated while reducing the cost incurred in the network environment. The multi-resource infrastructure management method according to an exemplary embodiment of the present invention is based on a networking cost to be generated using networking resources, a processing cost to be generated using processing resources, and a service satisfaction, which is satisfaction with at least one service Calculate the objective function. Here, the problem, that is, the objective function G (x) is expressed by Equation (6 ) .

를 원 변수(primal variable)로 정의한다. 상수 V는 전체 비용 최소화와 서비스 활용도 최대화 사이에서 발생하는 상충 관계 파라미터(trade-off parameter)이다. 이 목적함수 G(x)는 x에 대해 "엄격하게(strictly)" 볼록하지 않으며, 그에 따라 동일한 목적값을 얻을 수 있는 여러 최적해가 존재할 수 있다.here,

Is defined as a primal variable. The constant V is a trade-off parameter that occurs between minimizing total cost and maximizing service utilization. This objective function G (x) is not " strictly " convex to x , so there may be several optimal solutions to achieve the same objective value.

The constraint in the objective function calculation step (S530) is the available capacity for the usage amount of each of the networking resource 1 and the processing resource p . The multi-resource infrastructure management method according to an embodiment of the present invention first defines an available capacity of each of at least one networking resource and an available capacity of each of at least two processing resources. In order to optimize this problem, the input transmission rate R _w of each service is determined and multi-path routing is performed by dividing the input transmission rate R _w by a plurality of candidate paths x _p given to the corresponding service.

인 x ^* 를 목적함수 G(x)에 대한 최적 원 해(optimal primal solution) 집합 X ^* 에 속하는 특정 속도 할당 벡터로 정의한다.here,

Which defines the x ^* as the objective function G (x) to the optimum source (optimal primal solution) specific rate assigned belongs to the set X ^* vector for.

On the other hand, the Lagrangian dual problem for eliminating constraints can be expressed as Equation (7).

를 쌍대 변수로 정의한다.

은 수학식 8로 정의되는 라그랑주 함수이다.here,

Is defined as a pair variable.

Is a Lagrange function defined by equation (8).

인 λ ^* 를 수학식 7에 대한 최적 쌍대 해(optimal dual solution) 집합 Λ ^* 에 속하는 특정 벡터로 정의함으로써, 커플링 문제를 일으키는 가용 용량 제약사항을 제거할 수 있다. 그러나 그래디언트 프로젝션 알고리즘(gradient projection algorithm)은 원 목적함수가 엄격히 볼록인 경우에만 적용할 수 있기 때문에, 안장점 정리(saddle point theorem)를 이용하여 목적함수를 변동부등식(variational inequality)으로 변경할 수 있다. 수학식 7에 대한 최적 원 쌍대 해(optimal primal and dual solution)를 찾는 것은 수학식 9를 만족시키는

를 구하는 안장점 정리 문제를 푸는 것과 등가하다. 이때, 수학식 9는 아래와 같이 나타낼 수 있다.here,

By defining λ ^* as a specific vector belonging to the optimal dual solution set Λ ^* for Equation 7, it is possible to eliminate the usable capacity constraint that causes coupling problems. However, since the gradient projection algorithm can be applied only when the original objective function is strictly convex, the objective function can be changed to a variational inequality using the saddle point theorem. Finding the optimal primal and dual solution for Equation (7) can be expressed as Equation

It is equivalent to solving the problem of solving the problem. At this time, equation (9) can be expressed as follows.

를 구하는 것은

와 수학식 10을 만족시키는 변동부등식과 등가하다.By substituting Equation (7) into Equation (9), it is possible to consider a twin variable λ that does not depend on the original variable x . The advantage of satisfying Equation (9)

To obtain

And Equation (10).

와 수학식 11을 만족시킨다.Where f is

And Equation (11).

The method of managing multiple resource infrastructures according to an embodiment of the present invention is a method of managing the variable inequality described above in an extragradient-based manner so that the solution of the above-described fluctuation inequality can be converged to an optimal solution in the objective function calculation step (S530) Algorithm.

A method for managing multiple resource infrastructures according to an exemplary embodiment of the present invention includes defining at least one networking resource and at least two processing resources to calculate a networking cost and a processing cost, Calculate the usage of each of the at least two processing resources.

The multi-resource infrastructure management method according to an exemplary embodiment of the present invention may include calculating a set of candidate paths using each of at least one networking resource, calculating a set of candidate paths using each of the at least two processing resources, do.

The objective function calculation process (S530) comprises checking the current usage of each of the at least two processing resources to update each of the at least two processing resources. In addition, the objective function calculation process (S530) includes checking the current usage of each of the at least one networking resource to update each of the at least one networking resource.

,

및 x _p 를 출력하며, 그 과정을 정리하면 표 1과 같다. 여기서, τ 및 γ는 각각 반복되는 업데이트 회차(1, 2, 3, ...) 및 업데이트 간격(step size)를 의미한다.The multi-resource infrastructure management method according to the embodiment of the present invention updates x _p

,

And x _p . The process is summarized in Table 1. Here, τ and γ mean the repeated update times (1, 2, 3, ...) and the update interval (step size), respectively.

number process Equation One

를 업데이트After allowing each processing resource k to check its current usage of its resources,

Update

2 After each networking resource l has checked its current usage of its resources,

Update

3 The end node of each service w updates x _p for each candidate path p ∈ P given to itself Equation 12

Here, Equation (12) in Table 1 is as follows.

FIG. 6 illustrates two examples of topologies for explaining the results of applying the multi-resource infrastructure management method according to an embodiment of the present invention.

In case 1, the network includes three nodes 611, 613, 622 and four links 632, 634, 636, 638. The first SC1 node 611 and the second SC1 node 613 are nodes that contain processing resources and the third SC1 node 622 is a node that does not contain processing resources. In case 1, the source node and the other two services with different destination nodes, such as the NFV service, require virtual functions in the triangle topology. Each service may use a one-hop path using two resources and a two-hop path using three resources.

In case 2, the network includes three nodes 612, 614, 616 and four links 631, 633, 635, 637. The first SC2 node 612, the second SC node 614, and the third SC node 616 all include processing resources. In this case, one service having the same source node and destination node, for example, a CO service, requires virtual functions in a serially connected topology. Route using only processing resources k ₁ is the path using the case of a local computing work, and processing resources k ₂ may be a computation offloaded using the edge cloud, path using a processing resource k ₃ is a computation-off using the remote cloud Lt; / RTI &gt; In this case, the cloud node has the highest processing usable capacity. That is, C _k1 < C _k2 < C _k3 . However, it consumes the least cost for the same processing load. That is, D _k1 (F) > D _k2 (F) > D _k3 (F) .

Table 2 summarizes the above two cases, the details of Case 1 and Case 2.

Case 1 Case 2 Relationship between source node and destination node Different equivalence Number of services | W | = 1 | W | = 1 Candidate path p ₁₁ : k ₁ ? l ₃
p ₁₂ : l ₂ ? k ₂ ? l ₄
p ₂₁ : k ₂ → l ₄
p ₂₂ : l ₁ ? k ₁ ? l ₃ p ₁₁ : k ₁
p ₁₂ : l ₁ ? k ₂ ? l ₂
p ₁₃ : l ₁ ? l ₃ ? k ₃ ? l ₄ ? l ₂ Available Capacity (Mbps or GHz) C _l = 2, ∀ l ∈ L
C _k1 ∈ {1.3, 1.4, ... , 2.3}, C _k2 = 2 C _l = 2, ∀ l ∈ L
C _k1 = 2 , C _k2 = 20 , C _k3 = 40 Resource cost D _l (F _l ) = F _l , ∀ l ∈ L
D _k ( F _k ) = F _k , ∀ k ∈ K D _l (F _l ) = F _l , ∀ l ∈ L
D _k1 ( F _k1 ) = F _k1 , D _k2 ( F _k2 ) = ½ F _k2 , D _k3 ( F _k3 ) = 1/3 F _k3 , Service utilization U _w ( R _w ) = log (0.1 + R _w ) - log (0.1) U _w ( R _w ) = log (0.1 + R _w ) - log (0.1) Processing density (Kcycles / bit) ρ _{k, p} = 1, ∀ k ∈ Kp , p ∈ P ρ ∈ {1, 2, ... , 20}
ρ _{k, p} = ρ , ∀ k ∈ Kp , p ∈ P Bit conversion ratio (bits / bit) σ _{l, p} = 1, ∀ l ∈ Lp , p ∈ P σ ∈ {0.05, 0.1, ... ,One}
σ _{l1, p12} = 1, σ _{l2, p12} = σ
? _{1, p13} = 1 ,? _{13, p13} = 1,
σ _{l4, p13} = σ , σ _{l2, p13} = σ

In order to examine the effect of resource management considering cost, a cost-utility-minimal algorithm to which a multi-resource infrastructure management method according to an embodiment of the present invention is applied, And compared with the utility-maximal algorithm. That is, D _l (F) = D _k ( F _k ) = 0 for all l ∈ L and k ∈ K.

FIG. 7 is a graph illustrating service utilization and system cost when a multiple resource infrastructure management method according to an embodiment of the present invention is applied to Case 1 of FIG.

Of Figure 7 (a) is C _k1 = 2 GHz, (b) is and (b) of Fig. 7 of V = 20 and γ = 0.005 be when denotes hwalyongdoeul services according to the number of iterations, Figure 7 is C _k1 = 2 GHz , V = 20 and γ = 0.005, respectively. The initial transmission rate allocation value x ^{0 is set} to x ⁰ Consider the following four assumptions: ∈ {(0, 0, 0, 0), (0,1,0,1), (1,2,1,2), .

Both algorithms converge to the maximum utilization regardless of the initial transmission rate allocation value. The maximum utilization is achieved when the transmission rate of each service is 2 Mbps, that is, R ₁ = R ₂ = 2 Mbps. Referring to FIG. 7 (b), when the multi-resource infrastructure management method according to an embodiment of the present invention is applied, when two services do not share any resources, x _p11 = x _p21 = 2 Mbps, and when x _p12 = x _p22 = 0, it can be confirmed that the system converges to the minimum system cost.

On the other hand, it can be seen that the utilization-maximum algorithm converges to a system cost value other than the minimum value according to the change of the initial transmission rate allocation value.

FIG. 8 is a graph illustrating the effect of the multiple resource infrastructure management method according to an exemplary embodiment of the present invention on resource availability when the case 1 of FIG. 6 is applied.

For this, the optimal transmission rate allocation value was calculated while changing the available capacity of the processing resource k ₁ , that is, C _k1 from 1.3 GHz to 2.3 GHz. If C _k1 is between 1.3 GHz and 1.8 GHz, then service 1 uses both p ₁₁ and p ₁₂ candidate paths, and processing resource k ₂ and networking resource l ₄ are shared by both services . When each service uses only the 1-hop path of the service, that is, p ₁₁ and p ₂₁ , the transmission speed between the two services shows a large difference. The two-hop path p ₁₂ causes a higher cost than the one-hop path p ₂₁ , and the transmission rate assignment value for service 2 is larger than the transmission rate assignment value for service 1.

In order to investigate the effect of different service parameters on service throughput, we examined the behavior according to service parameters while changing the processing density ( ρ ) and bit conversion ratio ( σ ).

FIG. 9 is a graph illustrating the effect of the multiple resource infrastructure management method according to an exemplary embodiment of the present invention on service characteristics in case 2 of FIG. 6.

As the processing density ( rho ) and the bit conversion ratio ( ? ) Increased, the total throughput was found to decrease. This is because a large processing density p and bit conversion ratio sigma require higher system cost to achieve the same utilization. If it has a low processing density value, it can be seen that each service is provided by local computing. Having a low processing density value can adequately handle computation functions with local processing resources and achieve high throughput without relying on edge clouds and remote clouds requiring excessive networking costs.

In order to apply the multi-resource infrastructure management method according to an embodiment of the present invention to a large-scale case similar to the actual one, simulation was performed using MCI's actual Internet topology of the United States provided in 2011.

Figure 10 shows a real Internet topology in the United States.

This data set includes 19 nodes and 45 wired links. Since this dataset is not specific to the processing resources, we have arbitrarily calculated the processing resources.

11 is a graph showing simulation results obtained by applying a multi-resource infrastructure management method according to an embodiment of the present invention to actual large-scale cases.

As the number of candidate paths increases, the transmission rate may increase, but the cost may increase. Therefore, the transmission rate assignment for each candidate path should be carefully determined. This result means that a multi-resource infrastructure management method according to an embodiment of the present invention can utilize multipath to increase service utilization while keeping system cost low.

In FIG. 5, it is described that each process is sequentially executed, but it is not limited thereto. In other words, it is applicable that the process described in FIG. 5 is changed or executed by one or more processes in parallel, so that FIG. 5 is not limited to a time series order.

Meanwhile, each step of the flowchart shown in FIG. 5 can be implemented as a computer-readable code in a computer-readable recording medium. A computer-readable recording medium includes all kinds of recording apparatuses in which data that can be read by a computer system is stored. That is, a computer-readable recording medium includes a magnetic storage medium (e.g., ROM, floppy disk, hard disk, etc.), an optical reading medium (e.g., CD ROM, And the like). In addition, the computer-readable recording medium may be distributed over a network-connected computer system so that computer-readable code can be stored and executed in a distributed manner.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit or scope of the inventive concept. Various modifications and variations will be possible. Therefore, the embodiments according to the present invention are intended to illustrate rather than limit the technical idea of the embodiments, and the scope of the technical idea of the embodiments is not limited by these embodiments. The scope of protection of embodiments according to the present invention should be construed according to the following claims, and all technical ideas within the scope of equivalents should be interpreted as being included in the scope of the embodiments of the present invention.

110, 210, 310: source node 122, 124, 126: hardware router
130, 230, 310: destination node 222, 224, 226: NFV supporting node
340: Edge Cloud 350: Remote Cloud
400: Multiple resource infrastructure management device
410: candidate path set defining unit 420: multipath forming unit
430: transmission speed determination unit

Claims (11)

In a multi-resource infrastructure comprising at least two nodes using processing resources and at least one link using networking resources, the at least two A method for managing at least one service provided based on at least one route formed by connecting at least one first end node and at least one second end node respectively selected from among a plurality of nodes,
A candidate path set defining process for defining a set of candidate paths for the at least one service among the at least one path; And
A multipath forming step of forming a multipath by dividing an input transmission rate for the at least one service by the set of the candidate paths,
Wherein the plurality of resource infrastructure management methods include: The method according to claim 1,
A method for calculating an objective function based on a networking cost to be generated using networking resources, a processing cost to be generated by using processing resources, and a satisfaction degree of the at least one service, Wherein the method further comprises a function calculation process. 3. The method of claim 2,
The objective function calculation process includes:
The method comprising: defining at least one networking resource and at least two processing resources to calculate the networking cost and the processing cost, respectively, calculating a usage amount of each of the at least one networking resource and a usage amount of each of the at least two processing resources A resource definition and a calculation process. The method of claim 3,
The resource definition and calculation process includes:
Calculating a set of candidate paths using each of the at least one networking resource and calculating a set of candidate paths using each of the at least two processing resources. 5. The method of claim 4,
The objective function calculation process includes:
And defining an available capacity of each of the at least one networking resource and an available capacity of each of the at least two processing resources. 6. The method of claim 5,
The objective function calculation process includes:
The method of claim 1, further comprising: calculating a set of networking resources used by each of paths included in the set of candidate paths using each of the at least one networking resource, and each of paths included in a set of candidate paths using each of the at least two processing resources And calculating a set of processing resources to be used in the multi-resource infrastructure management method. The method of claim 3,
The objective function calculation process includes:
Defining a dual variable for each of the at least one networking resource and defining a dual variable for each of the at least two processing resources. 8. The method of claim 7,
The objective function calculation process includes:
Checking the current usage of each of the at least two processing resources to update each of the at least two processing resources and checking the current usage of each of the at least one networking resource to update each of the at least one networking resource Wherein the multi-resource infrastructure management method comprises: At least one link that uses a networking resource, a first end node and a second end node that are at least two nodes that use processing resources, at least one link that uses a networking resource, In a multi-resource infrastructure comprising at least one path connecting the first end node and the second end node via a link,
A candidate path set defining unit that defines a set of candidate paths for the at least one service among the at least one path;
A multipath forming unit for forming a multipath by dividing an input transmission rate for the at least one service by the set of the candidate paths; And
A transmission rate determination unit for defining a dual variable for each of the processing resource and the networking resource and for determining a transmission rate of the dual resource by updating the pair variable,
Wherein the plurality of resource infrastructure management apparatuses are managed by the plurality of resource infrastructure management apparatuses. 10. The method of claim 9,
Wherein the at least one path may include a plurality of nodes and the plurality of nodes are configured to be capable of processing some or all of the functions requested by one of the first end node and the second end node Multiple resource infrastructure management device. 11. The method of claim 10,
And an objective function calculator for calculating an objective function based on a networking cost to be generated using the networking resource, a processing cost to be generated using the processing resource, and a service satisfaction, which is satisfaction with the at least one service. Wherein the resource management unit comprises:

Images