Expandable deep-width adaptive dynamic programming intelligent power generation control method

Abstract

The invention provides an expandable deep-width adaptive dynamic programming intelligent power generation control method, which combines an expandable deep-width adaptive dynamic programming algorithmwith a learning rate adaptive algorithm, and is suitable for 'source-load ' three-state energy active control of a future integrated energy interconnection system (FIEIS) under a unified time scale.According to the method, the problem that traditional power generation control is difficult to adapt to real-time flexible control of active frequency under high permeability of three-state energy andintermittent energy of a power system is solved; the robustness and stability of the method are high, and the iterative convergence speed and accuracy are improved. According to the method, the depthand the width of a deep neural network are adaptively changed according to the type and the number of the three-state energy accessed to the network on the framework, so that the real-time performance, the accuracy and the stability of active control are enhanced. A deep width model prediction network, an evaluation network and an execution network of the method can effectively replace a traditional multi-time-scale combined active control algorithm.

Description

technical field [0001] The invention relates to an intelligent power generation control method capable of expanding depth-width self-adaptive dynamic planning, which belongs to the field of intelligent power generation dispatching and control in electric power systems, and is applied to the three-state energy sources of "source and load" under the unified time scale of the future comprehensive energy interconnection system Active frequency control. Background technique [0002] As the penetration rate of intermittent new energy sources such as wind power and photovoltaic power generation increases, the economically optimal allocation and stable regulation of the active frequency of the power grid are facing challenges. In order to ensure the safe and economical operation of the power grid and solve the problem of output active power frequency difference, in addition to regulating active power output by traditional power generation methods such as hydropower and thermal power...

AI Technical Summary

Problems solved by technology

[0005] The present invention proposes an intelligent power generation control method capable of expanding depth-width self-adaptive dynamic planning, which is dedicated to solving the problem that it is difficult to achieve high-quality control of active power and frequency in the traditional combined power generation control mode after FIEIS grid-connected power generation

Images