Service function chain low-cost intelligent deployment method based on environmental perception

Abstract

The invention relates to a service function chain low-cost intelligent deployment method based on environmental perception, and belongs to the technical field of mobile communication. The method comprises the following steps: S1, taking a wireless rate reachable by a user wireless terminal as a basis of SFC resource allocation, jointly considering SFC deployment and wireless subcarrier allocation,and establishing an SFC deployment cost minimization model under user delay requirements, wireless rate requirements and resource constraints; S2, converting the optimization problem into a Markov decision process with a continuous state space and a high-dimensional action space in discrete time; and S3, finally, considering the high dimensionality of the MDP problem, and obtaining a joint optimization strategy of SFC deployment and subcarrier allocation by utilizing a DDPG reinforcement algorithm, thereby achieving the purposes of reducing resource consumption and reducing SFC deployment cost. According to the method, the total cost of SFC deployment can be effectively reduced while the user delay requirement and the wireless rate requirement are ensured; and subcarrier allocation and SFC deployment strategies enabling the deployment cost to be lowest can be made in each time slot according to the current environment.

Description

Technical field [0001] The invention belongs to the field of mobile communication technology, and relates to a low-cost intelligent deployment method of a service function chain based on environment perception. Background technique [0002] In order to solve how to simultaneously support diversified business scenarios on the same physical network, "network slicing" is generally considered by the industry as an ideal network model. Network slicing refers to isolated logical networks that are segmented according to different business needs on a common and shared underlying network infrastructure. NFV is one of the key technologies supporting network slicing. NFV technology uses cloud computing and virtualization technology to orchestrate different virtual network functions (VNFs), and map them to general physical server equipment to complete the corresponding network functions. A complete service request is composed of multiple VNFs connected in order to form a service function c...

AI Technical Summary

Problems solved by technology

Secondly, in the traditional SFC deployment problem, usually a flow rate is specified for one SFC, or the required resource consumption is specified for each VNF and virtual link in the SFC. The achievable wireless rate does not match, resulting in a large waste of core network resources

Furthermore, the heuristic algorithm is less than considering the dynamics of the wireless environment to optimize the network performance in a single time slot. Facing the complex and changeable network environment, such a heuristic algorithm is difficult to achieve the ideal optimization effect

Images