Practical reinforcement learning automaton method for quotation optimization of power generator under limited information

Abstract

The invention provides a practical reinforcement learning automaton method for quotation optimization of a power generator under limited information. The method comprises the following steps: S1, initializing an action space probability density function and a historical income cache region of the power generation capacity of the power generator; S2, discretizing the probability density function into a discrete probability density function to obtain a plurality of sub-intervals, selecting an action corresponding to the sub-interval where the random number is located according to the cumulativeprobability of the sub-intervals, and submitting the selected action; S3, evaluating the environmental feedback, calculating clearing income, executing enhanced signal evaluation according to the clearing income, and storing the clearing income into the historical income cache region; S4, updating the discrete probability density function as linear operation of discrete values of the discrete probability density function and the discrete Gaussian neighborhood function at the end points of the subintervals; and S5, judging whether an iteration stopping standard is reached or not, if not, returning to the step S2, and if so, ending the optimization process.

Description

technical field [0001] The invention relates to the technical field of electric power system data processing, in particular to a practical reinforcement learning automaton method for power supplier quotation optimization under limited information. Background technique [0002] The electricity market is a typical imperfect competition market, and power generators can increase their own profits through strategic bidding. However, in many countries, the electricity market is still in the initial stage, and the external market information that power generators can obtain is extremely limited, which makes it difficult for power generators to optimize their strategies. [0003] The Cournot model is a classic model describing the game of power market participants. A market based on the Cournot model usually includes three main parts: generators, users and market operators. [0004] Such as figure 1 As shown in , generators and users submit output and utility functions to the mar...

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to provide a practical reinforcement learning automaton method for power supplier quotation optimization under limited information, to solve the complex optimization process existing in the existing technology when applying continuous action reinforcement learning automata, which is difficult to implement in practice Medium application, difficult to solve, poor practicability

Images