Fully distributed intelligent power grid economic dispatching method based on deep reinforcement learning

Abstract

The invention relates to a fully distributed intelligent power grid economic dispatching method based on deep reinforcement learning. The fully distributed intelligent power grid economic dispatchingmethod comprises the following steps: 1), obtaining a network topological structure, and building an economic dispatching model based on load distribution and unit combination; 2) obtaining a local optimal solution of the economic dispatch model through the deep reinforcement learning model to serve as a first Q function table; 3) loading the first Q function table into a pre-trained deep convolutional neural network to obtain a second Q function table; and 4) initializing the power of each unit according to the second Q function table, loading a unit power solving model, and updating the second Q function table according to the network topology structure to obtain a globally optimal solution. Compared with the prior art, the fully distributed intelligent power grid economic dispatching method has the advantages that economic dispatch optimization can be realized in an intelligent power grid environment with large data volume and complex network structure, and the fully distributed intelligent power grid economic dispatching method does not depend on a clear target function, can adapt to the plug-and-play characteristic of distributed energy, and has a good application prospect.

Description

technical field [0001] The invention relates to the field of fully distributed smart grid economic scheduling, in particular to a fully distributed smart grid economic scheduling method based on deep reinforcement learning. Background technique [0002] With the vigorous development of renewable energy, the smart grid (Smart Grid) containing high-density intermittent energy has gradually developed into a new energy structure. Due to the popularity of large-scale intermittent renewable energy, sufficient controllable resources are required to ensure the safe and reliable operation of the power system. In addition to traditional controllable generators, flexible loads also play an important role in keeping the system balanced. Therefore, how to manage large-scale and decentralized demand response, and achieve global optimization and win-win results for all parties, has attracted great attention under the comprehensive consideration of the connection between various parts of "...

AI Technical Summary

Problems solved by technology

Although the above literature can solve the Pareto optimal solution set problem of multi-objective optimization through deep reinforcement learning, but in the face of the "plug and play" characteristics of distributed energy and the problems of dealing with continuous variables, the deep reinforcement learning algorithm seems somewhat powerless

Images