Deep reinforcement learning emergency control strategy extraction method for power system

Abstract

The invention provides a deep reinforcement learning emergency control strategy extraction method for a power system. The method comprises: constructing observation data by introducing feature data of a power system node model at a plurality of historical moments; further constructing a deep Q learning network model, and performing optimization training by adopting a stochastic gradient descent optimization algorithm to obtain a power system emergency control deep reinforcement learning model; generating a data set in a specific fault scene based on the trained deep Q learning network model; training a weighted tilt decision tree model based on an information gain ratio on the data to complete strategy extraction; and setting a strategy fidelity index, a strategy actual control performance index and a model complexity index to evaluate model performance under different hyper-parameters, so that an optimal model is selected according to actual requirements and is used in the field of power system emergency control.

Description

technical field [0001] The invention belongs to the intersecting field of artificial intelligence and electric power system, and in particular relates to a method for extracting emergency control strategies by deep reinforcement learning of electric power system. Background technique [0002] Some major blackouts that occurred around the world, such as the blackout in the United States and Canada in 2003, caused huge social and economic losses, warning us that we urgently need to build a safer and more reliable power system. However, the current power system protection and control mechanisms are all designed offline based on some typical scenarios, and cannot adapt to unknown changes in the power system. At the same time, with the development of artificial intelligence (AI) technology in natural language processing technology, computer vision, automatic driving and other fields, these technologies have also been successfully applied in power systems, such as load forecasting...

AI Technical Summary

Problems solved by technology

However, these works have only verified their feasibility in some simple game scenarios, and the research and effectiveness of related work in power system control problems have not yet been carried out.

Images