Abstract:

As a new network architecture,the space air terrestrial integrated network has the advantages of wide network coverage and ubiquitous seamless access ability,but it also faces the contradiction between increasing users’ demands and limited network service resources.Introducing edge computing into space air terrestrial integrated networks can greatly improve the system’s business processing capability.Meanwhile,first,in order to improve the resources utilization of Space Air Terrestrial aided Mobile-access Edge Cloud (SAT-MEC) networks,and provide users with diversified and high-quality network services,we connect a group of virtual network functions according to a certain business logic,which forms a dynamic and reconfigurable service function chain.Considering the high dynamic and heterogeneous characteristics of the SAT-MEC network,the efficient scheduling method for its dynamic service function chain is studied,and the system model of the SAT-MEC network is designed.On this basis,the objective function of end-to-end delay optimization constrained by network resources and service requests is constructed.Second,combining the advantages of efficient parallel computing of Quantum Machine Learning,the path selection problem of the service function chain is modeled as a Hidden Markov Model based on Open Quantum Random Walk,with the model solved by the Quantum Backtrack Decoding method.Compared with the traditional precise solution and heuristic methods,simulation results show that the proposed method can improve the success rate of service request and reduce the end-to-end average delay under the condition of a high network traffic load.

Key words: space air terrestrial network, edge cloud network, SDN/NFV, quantum machine learning