A large-scale multiobjective satellite data transmission scheduling algorithm based on SVM plus NSGA-II

摘要

The satellite data transmission traffic appears a considerable growth tendency with the increase in the number of satellites and the client requirements, so how to solve the large-scale multiobjective satellite data transmission scheduling problem (SDTSP) within a valid period of time has become more and more important. In this context, a multiobjective satellite data transmission model is developed for the practical application, and a novel SVM + NSGA-II algorithm is proposed based on the periodicity of resource confliction in satellite data transmission, the large-scale characteristic of SDTSP and the multidimensional characteristic of the optimization objectives. Experimental results have demonstrated that SVM + NSGA-II can efficiently solve the large-scale multiobjective SDTSP in a very short period of time on the basis of ensuring the satisfactory optimization objectives by comparing with the other four state-of-the-art MOEAs.