Satellite Network Load Balancing Strategy for SDN/NFV Collaborative Deployment

In order to solve the problem of load imbalance caused by the changing topology and real-time changes of service requests in SDN/NFV cooperative deployment satellite networks, the load balancing optimization algorithm based on Viterbi algorithm for minimum migration cost (MLB-Viterbi) is proposed. This method establishes the mapping process of SFC as a hidden Markov model. Considering the migration cost and the constraints in migration, the MLB-Viterbi algorithm is used to migrate the VNF resources of the overloaded nodes to other suitable nodes and adds a migration cost function to the state transition matrix, so as to multi-objective optimization. The results show that MLB-Viterbi algorithm has better convergence than MRLB algorithm in load balancing performance. With the increase of the number of reconstructed service chains, MLB-Viterbi algorithm has more advantages than multi-steps in the cost of migration. The cost of updating the service chain depends on the number of service chains in a linear way. The algorithm can effectively achieve load balancing and ensures the minimum migration cost.