Adaptive new energy ultra-short-term power prediction method and device based on reinforcement learning

Abstract

The invention relates to an adaptive new energy ultra-short-term power prediction method and device based on reinforcement learning. The method comprises the following steps: acquiring an environment variable, an action space and a reward function for constructing an adaptive agent; wherein the environment variable is an environment variable index reflecting environment characteristics, the action space is an action function set adopted by the agent decision, and the reward function is an evaluation result of corresponding change of the environment variable after the agent action is executed; constructing a self-adaptive agent according to the environment variable and a reward function; and processing the environment variable, and training the adaptive agent by using the processed environment variable to obtain an adaptive prediction agent. The prediction result of the single-class prediction method most matched with the external environment is adaptively selected according to the environment variable, so that the accuracy of the prediction result is improved to the maximum extent. The method provided by the invention is simple in implementation process and has a relatively strong application prospect.

Description

technical field [0001] The invention belongs to the field of electric power technology, and in particular relates to an adaptive new energy ultra-short-term power prediction method and device based on reinforcement learning. Background technique [0002] In recent years, new energy sources, mainly wind power and photovoltaics, have developed rapidly, and their scale in the power grid is increasing. New energy power prediction technology is the basic data for power grid operation control. At present, my country proposes to build a new power system with new energy as the main body. It is foreseeable that the scale of new energy in the power system will increase rapidly in the future. In the context of the increasing scale of new energy sources, the impact of its prediction accuracy on the power grid operation efficiency has become increasingly prominent and has become the focus of current research. [0003] At present, there have been a lot of researches on new energy power ...

AI Technical Summary

Problems solved by technology

[0011] In view of this, the purpose of the present invention is to overcome the deficiencies of the prior art and provide an adaptive new energy ultra-short-term power prediction method and device based on reinforcement learning to solve the problem of low accuracy of new energy power prediction in the prior art. question

Images