Resource-Aware Reliability Assurance of Service Function Chain

Abstract

AbstractAlthough new technologies as Network Function Virtualization (NFV) and Service Function Chain (SFC) technology improve the deployment efficiency of network functions and the speed of service delivery, the reliability of the nodes in the service function chain will be reduced. With the increase of the length of the service function chain, the overall reliability will be greatly reduced. In order to improve the reliability of service function chain and reduce resource consumption, this paper realizes the reliability guarantee of resource-aware service function chain. Firstly, the reliability calculation model is realized based on the neural network, and the model is trained with the randomly generated service function chain data. The reliability of the model is verified by comparing the calculated data with the approximate calculated data. Then greedy shared backup is adopted to guarantee the service function chain and the node with the optimal improvement rate is selected as the newly added backup node. The simulation results verify that the proposed algorithm can effectively reduce the consumption of backup resources and improve resource utilization.KeywordsNFVService function chainResource-awareNeural networks