CN-116781532-B - Optimization mapping method of service function chains in converged network architecture and related equipment

CN116781532BCN 116781532 BCN116781532 BCN 116781532BCN-116781532-B

Abstract

The application provides an optimization mapping method of a service function chain in a converged network architecture and related equipment. The method comprises the steps of obtaining a service function chain request and resource information of each server node, wherein the service function chain request comprises demand information of a plurality of virtual network functions in a service function chain, constructing a Markov decision process model according to the resource information and the demand information, wherein the Markov decision process model characterizes a mapping relation between the server nodes and the virtual network functions, solving the Markov decision process model to obtain a mapping strategy, and executing the mapping strategy. The scheme of the application can more flexibly cooperatively schedule network resources, reduce the resource blocking of the network, and meet the power business requirements of low time delay, high reliability, large bandwidth and the like.

Inventors

OU QINGHAI
YANG LINQING
LIU HUI
ZHANG JIE
SU LILI
GUO SHAOYONG
LIU JUNYU
HE HAIYANG
CHEN WENWEI
YANG YINGQI
ZHANG NINGCHI
ZHU HONG
WANG YANRU
WANG WENDI
MA WENJIE
SHAO SUJIE
ZHANG LIN
Song Jigao

Assignees

北京中电飞华通信有限公司
国网江苏省电力有限公司南京供电分公司
国网江苏省电力有限公司
国网信息通信产业集团有限公司
北京邮电大学
国家电网有限公司

Dates

Publication Date: 20260512
Application Date: 20230323

Claims (11)

1. The optimizing mapping method of the service function chain in the converged network architecture is characterized in that the converged network architecture comprises a plurality of server nodes, a 5G-based power converged access layer and a 5G-MEC multi-access edge computing layer; the method comprises the following steps: acquiring a service function chain request and resource information of each server node, wherein the service function chain request comprises the requirement information of a plurality of virtual network functions in a service function chain; Constructing a Markov decision process model according to the resource information and the demand information, wherein the Markov decision process model characterizes the mapping relation between the server node and the virtual network function; Determining a priority policy and a reward function according to the power service type of the service function chain request, wherein the power service type comprises a time delay sensitive service and a time delay tolerant service, the priority policy comprises that the power service type of the service function chain request is determined to be the time delay sensitive service, the priority policy comprises that each neighbor node in a sub-network based on a 5G power fusion access layer is mapped from a predecessor node, a cluster head node in the sub-network based on the 5G power fusion access layer is mapped from the predecessor node, each node in a 5G-MEC multi-access edge computing layer is mapped from the predecessor node, the priority policy comprises that each node in the sub-network based on the 5G power fusion access layer is mapped from the predecessor node in response to the determination that the power service function chain request is the time delay tolerant service, and the priority policy comprises that each node in the sub-network based on the 5G power fusion access layer is mapped from the predecessor node, each node in the 5G-MEC multi-access edge computing layer is characterized by the predecessor node when the predecessor node is mapped successfully; The method comprises the steps of establishing constraint conditions corresponding to resource information, constructing a joint optimization target model according to the constraint conditions, screening feasible nodes in a fusion network architecture based on a priority strategy and the constraint conditions, solving the joint optimization target model by using the Markov decision process model with the aim of maximizing a reward function in the feasible nodes to obtain a solving result, and determining a mapping strategy according to the solving result and the reward function; And executing the mapping strategy.
2. The method of claim 1, wherein the resource information comprises a total amount of computing resources, a total amount of storage resources, and a total amount of bandwidth resources of the server node; The establishing of the constraint condition corresponding to the resource information and the construction of the joint optimization target model according to the constraint condition comprise the following steps: Establishing a time delay constraint condition, a residual calculation resource constraint condition, a residual storage resource constraint condition and a residual bandwidth resource constraint condition according to the total calculation resource, the total storage resource and the total bandwidth resource of the server node; constructing a joint optimization target model according to the time delay constraint condition, the residual computing resource constraint condition, the residual storage resource constraint condition and the residual bandwidth resource constraint condition; the time delay constraint condition is as follows: ; Wherein, the Representing a tolerant delay of the service function chain; representing the total response delay, representing the sum of the communication delay of a physical link formed by server nodes mapped by a service function chain and the processing delay of virtual network functions on all the server nodes of the physical link; representing a set of service function chains; the remaining computing resource constraints are: ; Wherein, the Is shown in time slot Server node Is a residual computing resource of (1); Representing server nodes Is calculated by the total amount of resources; Representing a set of virtual network functions; Is shown in time slot Server node On which virtual network functions are mapped Is the number of (3); representing computing resource requirements of virtual network functions; representing a server node set of a 5G-based power fusion access layer and a 5G-MEC multi-access edge computing layer; the constraint conditions of the residual storage resources are as follows: ; Wherein, the Is shown in time slot Server node Is a residual storage resource of (1); Representing server nodes Is a total amount of storage resources; Representing storage resource requirements of virtual network functions; the constraint conditions of the residual bandwidth resources are as follows: ; Wherein, the Is shown in time slot Residual bandwidth resources of the server node; Representing the total amount of bandwidth resources of the server node; Representing service function chains Whether mapping is successful; Representing service function chains Is not required by the bandwidth requirements of the system; Is shown in time slot Server node Whether or not to map virtual network functions 。
3. The method of claim 2, wherein the screening out viable nodes in the converged network architecture based on the priority policy and the constraint comprises: And searching feasible nodes in the converged network architecture based on the priority strategy to obtain the feasible nodes, wherein the feasible nodes meet the time delay constraint condition, the residual computing resource constraint condition, the residual storage resource constraint condition and the residual bandwidth resource constraint condition.
4. The method according to claim 2, wherein the joint optimization objective function of the joint optimization objective model is: Wherein, the Representing the computational cost of the server resource units; representing processing costs for the server resource units; Representing the unit cost of consuming bandwidth.
5. The method of claim 2, wherein the reward function is: Wherein, the Representing that the power service type requested by the service function chain is a reward function which is time delay sensitive service and is successfully mapped; Representing that the power service type requested by the service function chain is a reward function of delay sensitive service and mapping failure; Representing that the power service type requested by the service function chain is a delay tolerant service and is mapped successfully to a reward function; Representing that the power service type requested by the service function chain is a delay tolerant service and mapping failure rewarding function; representing a first weight coefficient; Representing a second weight coefficient; representing a third weight coefficient; Is that Is an evaluation index of (2) Representing a first number, and representing the number of server nodes where the virtual network functions are successfully mapped in the 5G-based power fusion access layer; Representing a second number, representing the number of server nodes where the virtual network functions are successfully mapped at the 5G-MEC multi-access edge computing layer; Is determined for the type of power traffic requested from the service function chain.
6. The method of claim 2, wherein said constructing a markov decision process model comprises: For each of the feasible nodes, determining a corresponding state and action; taking a set formed by the states of all feasible nodes as a state space and taking a set formed by the actions as an action space; Constructing a Markov decision process model according to the state space and the action space; The state space is that for each state ; Wherein, the Is shown in time slot Remaining computing resources of all server nodes; Is shown in time slot Remaining storage resources of all server nodes; Is shown in time slot Residual bandwidth resources of all server nodes; Representing the remaining delay space of the current service function chain, wherein Is shown in time slot Service function chain Is a total response delay of (2); Representing service function chains Including the service function chain Ordered set of server nodes, bandwidth requirements, tolerance delays and time slots; Representing a mapping predecessor node; The action space is Wherein, the Representing server nodes Whether or not to map a service function chain Is provided with a virtual network function in the network, A tuple representing the action space.
7. The method of claim 5, wherein in the feasible nodes, with the objective of maximizing the reward function, solving the joint optimization objective model by using the markov decision process model to obtain a solution result, and determining a mapping strategy according to the solution result and the reward function, wherein the method comprises: in the feasible nodes, aiming at maximizing the rewarding function, solving the joint optimization target model by using the Markov decision process model based on a deep reinforcement learning method to obtain a solving result, wherein the solving result represents real-time rewarding; and according to the solving result, calculating the first number and the second number based on the reward function, and obtaining a mapping strategy according to the first number and the second number.
8. An optimization mapping device of a service function chain in a converged network architecture is characterized in that the converged network architecture comprises a plurality of server nodes, a 5G-based power converged access layer and a 5G-MEC multi-access edge computing layer; the device comprises: the acquisition module is configured to acquire a service function chain request and resource information of each server node, wherein the service function chain request comprises the requirement information of a plurality of virtual network functions in a service function chain; The construction module is configured to construct a Markov decision process model according to the resource information and the demand information, wherein the Markov decision process model characterizes the mapping relation between the server node and the virtual network function; The solution module is configured to determine a priority policy and a reward function according to the electric service type of the service function chain request, wherein the electric service type comprises a time delay sensitive service and a time delay tolerant service, the priority policy is determined according to the electric service type of the service function chain request, the priority policy comprises that in response to determining that the electric service type of the service function chain request is the time delay sensitive service, the priority policy comprises that each neighbor node in a sub-network based on a 5G electric power fusion access layer is from a mapping predecessor node, a cluster head node from the mapping predecessor node to the sub-network based on the 5G electric power fusion access layer is selected from the mapping predecessor node to each node in the 5G-MEC multi-access edge computing layer, in response to determining that the electric service type of the service function chain request is the time delay tolerant service, the priority policy comprises that in response to determining that each cluster head node from the mapping predecessor node to the sub-network based on the 5G electric power fusion access layer is the time delay tolerant service, in response to the mapping predecessor node to each neighbor node in the 5G-MEC multi-access edge computing layer, the current constraint model can be optimized according to the current constraint model, the constraint policy can be obtained by constructing the combined constraint policy in a combined constraint model and the combined constraint model according to the optimal result, the combined constraint policy can be obtained by using the optimal result, determining a mapping strategy and executing the mapping strategy.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable by the processor, wherein the processor implements the method of any of claims 1-7 when executing the computer program.
10. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1-7.
11. A computer program product comprising computer program instructions which, when run on a computer, cause the computer to perform the method of any of claims 1-7.

Description

Optimization mapping method of service function chains in converged network architecture and related equipment Technical Field The present application relates to the field of communications technologies, and in particular, to an optimization mapping method and related devices for a service function chain in a converged network architecture. Background Network function virtualization technology (Network Function Virtualization, NFV), i.e. transferring hardware devices into virtual machines, thereby improving flexibility of services and network openness. In network function virtualization, a service function chain (Service Function Chains, SFC) consists of ordered virtual network functions (Virtual Network Function, VNF) that provide flexibility by enabling dynamic deployment and interconnection of network functions to implement SFC. The effective SFC mapping can flexibly process mass data flow and filter, learn, use, compress and process, and provide high-efficiency, expandable and economic network service for terminal Internet of things users. However, under the requirements of low-latency and high-reliability power network service, NFV-based networks have higher usability requirements than conventional networks, and the mapping schemes of service function chains in the related art cannot meet the requirements. Disclosure of Invention In view of the above, the present application is directed to an optimization mapping method and related devices for fusing service function chains in a network architecture, so as to solve or partially solve the above-mentioned problems. The first aspect of the present application provides an optimization mapping method for a service function chain in a converged network architecture, where the converged network architecture includes a plurality of server nodes; the method comprises the following steps: acquiring a service function chain request and resource information of each server node, wherein the service function chain request comprises the requirement information of a plurality of virtual network functions in a service function chain; Constructing a Markov decision process model according to the resource information and the demand information, wherein the Markov decision process model characterizes the mapping relation between the server node and the virtual network function; and solving the Markov decision process model to obtain a mapping strategy, and executing the mapping strategy. Optionally, the solving the markov decision process model to obtain the mapping policy includes: Determining a priority strategy and a reward function according to the power service type requested by the service function chain; Establishing constraint conditions corresponding to the resource information, and constructing a joint optimization target model according to the constraint conditions; based on the priority policy and the constraint condition, screening out feasible nodes in the converged network architecture; and in the feasible nodes, aiming at maximizing the reward function, solving the combined optimization target model by using the Markov decision process model to obtain a solving result, and determining a mapping strategy according to the solving result and the reward function. Optionally, the fusion network architecture comprises a 5G-based power fusion access layer and a 5G-MEC multi-access edge computing layer, wherein the power service types comprise delay sensitive services and delay tolerant services; the determining the priority policy according to the power service type requested by the service function chain comprises the following steps: in response to determining that the power traffic type of the service function chain request is a delay sensitive traffic, the priority policy is: The system comprises a mapping predecessor node, a cluster head node, a 5G-MEC multi-access edge computing layer, a power fusion access layer and a power fusion access layer, wherein the mapping predecessor node is connected with each neighbor node in the sub-network of the 5G-based power fusion access layer; in response to determining that the power traffic type of the service function chain request is a delay tolerant traffic, the priority policy is: From the mapping predecessor node to each node in the 5G-MEC multi-access edge computing layer; Wherein the predecessor node characterizes a previous node that was mapped successfully when the current node was mapped. Optionally, the resource information comprises the total computing resource, the total storage resource and the total bandwidth resource of the server node, and the demand information comprises the computing resource demand, the storage resource demand and the bandwidth resource demand of the virtual network function; The establishing of the constraint condition corresponding to the resource information and the construction of the joint optimization target model according to the constraint condition comprise the following ste