Household energy scheduling method and device and computer readable storage medium

Abstract

The invention discloses a household energy scheduling method and device and a computer readable storage medium. An electric energy scheduling system, an evaluation network and an execution network areconstructed, a neural network, the adaptive evaluation design, reinforcement learning, classic dynamic planning and the like are combined, mutual iterative approximation is performed in the evaluation network and the execution network by adopting a nonlinear function fitting method on the basis of approximate dynamic planning, and an optimal performance index and an optimal control solution are obtained, so that the problem that uncertainty and dynamic parameters are difficult to accurately model in household electric energy optimization control is effectively solved, and a feasible method isprovided for the optimal control of a high-dimensional complex nonlinear system. Under the condition that direct influence factors are not completely clear, the minimum cumulative electricity price can be obtained by controlling the charging and discharging efficiency of an energy storage device, and the effects of peak clipping and valley filling of electric power requirements, improving the power supply efficiency, relieving the power shortage pressure and reducing the power supply cost and the power utilization cost, can be achieved.

Description

technical field [0001] The present invention relates to the technical field of electric energy optimization management, in particular to a family energy scheduling method, device and computer-readable storage medium. Background technique [0002] Household energy optimal dispatch is an important link in the demand side management of the power system and an important part of the smart grid optimization. The role of power supply and demand balance, through demand-side optimization management and two-way interaction with users, ultimately achieves the goal of improving the grid’s ability to accept renewable energy, improving asset utilization efficiency, delaying the need for grid expansion investment, and improving power quality and power supply reliability. It can achieve a win-win situation for both power suppliers and consumers, and can also achieve the sustainable development goals of low-carbon electricity and environmental protection. [0003] However, the user's demand...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve at least one of the technical problems in the prior art, and provide a family capacity scheduling method, device and computer-readable storage medium, which can effectively solve the problem of uncertain and dynamic parameters in the optimal control of household electric energy. Accurate modeling problems provide a practical theory and method for the optimal control of high-dimensional complex nonlinear systems

Images