Cost-Efficient Tasks Scheduling for Smart Grid Communication Network with Edge Computing System

Abstract

The smart grid, as a solution to meet the increasing electricity demand of modern cities, has gained great attention. The analysis of the real-time power data collected by smart devices in the smart grid environment is one of the most challenging tasks. The edge computing paradigm can well carry the data analysis from smart devices with a low latency. A key issue in edge computing system is how to reduce the cost while completing the offloaded tasks. In this paper, we focus on the cost optimization for task scheduling in smart grid scenarios. The task scheduling is planned to minimize the cost of the edge computing system while satisfying the task completion needs. To solve this optimization problem, a greedy-based algorithm, called Green Greedy, is proposed. The effectiveness of the proposed Green Greedy algorithm is validated by comparing with the RANDOM algorithm(a baseline strategy: random scheduling strategy) and the EARS [21] algorithm under various parameters including the number of input tasks, transmission data size and delay requirement. Simulation results show that the proposed algorithm can reduce the cost up to 50% compared with the other two algorithms and achieve excellent performance.