Smart Grid Resource Scheduling Algorithm Based on Reinforcement Learning for Edge Computing

Abstract

Smart grid is a power system that enables intelligent management and optimization. Network virtualization technology can effectively improve the resource utilization and reliability of smart grid and meet the differentiated needs of different users. In the case of limited resources, traditional virtual network mapping algorithms cannot dynamically adjust the allocation and mapping of virtualized resources based on the resource usage and user demands of the power system. To address this issue, we combined edge computing and virtualization technology, and introduced a reinforcement learning-based virtual network resource scheduling algorithm. Simulation results show that our virtual resource scheduling algorithm performs better than the other three scheduling algorithms in improving the reliability and resource utilization of the power grid.