Reliable Scheduling Method for Sensitive Power Business Based on Deep Reinforcement Learning

Abstract

The main function of the power communication business is to monitor, control and manage the power communication network to ensure normal and stable operation of the power communication network. Communication services related to dispatching data networks and the transmission of fault information or feeder automation have high requirements for delay. If processing time is prolonged, a power business cascade reaction may be triggered. In order to solve the above problems, this paper establishes an edge object-linked agent business deployment model for power communication network to unify the management of data collection, resource allocation and task scheduling within the system, realizes the virtualization of object-linked agent computing resources through Docker container technology, designs the target model of network latency and energy consumption, and introduces A3C algorithm in deep reinforcement learning, improves it according to scene characteristics, and sets corresponding optimization strategies. Minimize network delay and energy consumption; At the same time, to ensure that sensitive power business is handled in time, this paper designs the business dispatch model and task migration model, and solves the problem of server failure. Finally, the corresponding simulation program is designed to verify the feasibility and validity of this method, and to compare it with other existing mechanisms.