Author(s)

Junhong Ni, Dan Guo

Corresponding Author

Dan Guo

Abstract

In this paper, a wireless heterogeneous environment system model is constructed. In the process of task offloading, queuing theory is considered to offload it to edge nodes and edge clouds. In addition, solar panels are deployed in roadside units, the use of green energy can reduce system grid energy consumption. Since the optimization objective is a multi-objective non-convex NP-Hard problem, and the application scenario of multiple edge nodes makes it difficult to solve this problem, this paper solves the problem by improving the selection and crossover links of the genetic algorithm, and establishes an external file to speed up the convergence of the population. The simulation results show that the improved genetic algorithm can effectively reduce the system cost and the use of traditional electric energy.

Keywords

Task offloading, Queuing theory, Solar resource, Genetic algorithm