Access network service function chain deployment method based on random learning

Abstract

The invention relates to an access network service function chain deployment method based on random learning, and belongs to the technical field of wireless communication. The method comprises the steps that an access network service function chain deployment scheme based on partially observable Markov decision process partial perception topology is established for the problem of high delay causedby the physical network topology change under the 5G cloud access network scene. According to the scheme, the underlying physical network topology change is perceived through the heartbeat packet observation mechanism under the 5G access network uplink condition and the complete true topology condition cannot be acquired because of the observation error so that deployment of the service functionchain deployment of the access network slice is adaptively and dynamically adjusted by using partial perception and random learning based on the partially observable Markov decision process and the delay of the slice on the access network side can be optimized. Dynamic deployment is realized by deciding the optimal service function chain deployment mode by partially perceiving the network topologychange based on the partially observable Markov decision process so that the delay can be optimized and the resource utilization rate can be enhanced.

Description

technical field [0001] The invention belongs to the technical field of mobile communication, and relates to a method for deploying access network service function chains based on random learning. Background technique [0002] Network Slicing (NS) refers to the establishment of several isolated logical networks on a physical network infrastructure, and each logical network serves a specific application scenario. On the one hand, network slicing technology can meet the diversified service requirements of future mobile communications. On the other hand, it can also enable operators to reduce network infrastructure construction costs and deploy networks more flexibly. Therefore, it is regarded as one of the key technologies of 5G. There are still many problems in the process of promoting the commercial use of slicing technology, such as slice resource management, slice isolation, slice mobility management, and slice security. The problem of slice resource management is mainly d...

AI Technical Summary

Problems solved by technology

Find a fixed resource allocation strategy for each service function chain based on the approximate Markov model. In fact, the arrival of SFC data packets will change with time, and the static deployment strategy cannot guarantee QoS in real time.

The resource allocation model based on genetic algorithm realizes the dynamic deployment of SFC in the core network to adapt to the changing data arrival volume, but this algorithm is limited to the situation where the topology of the physical network remains unchanged, and the physical network may be affected by random environmental factors in actual scenarios However, the dynamically changing network topology may cause problems such as SFC failure, high delay, and low resource utilization.

At the same time, the solutions in the above documents only support core network slicing. Since the 5G access network adopts the C-RAN architecture, it cannot directly support SFC deployment in access network slicing.

Images