Flywheel array auxiliary frequency modulation method for thermal power generating unit based on TD3 algorithm

By optimizing the control strategy of the flywheel array through deep reinforcement learning and global self-attention mechanism based on the TD3 algorithm, the problems of slow response speed and poor coordination of traditional flywheel arrays are solved, realizing fast and flexible power distribution and coordinated action, and improving the frequency regulation capability of the power grid.

CN122600129APending Publication Date: 2026-08-18INST OF ENGINEERING THERMOPHYSICS - CHINESE ACAD OF SCI
0 Cites 0 Cited by

Patent Information

Application Number
CN202610724776.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-05-25
Publication Date
2026-08-18

AI Technical Summary

Technical Problem

Traditional flywheel array control strategies suffer from slow response speed, inflexible power allocation, and poor coordination among flywheels, making it difficult to effectively suppress frequency fluctuations in power systems with a high proportion of renewable energy integration.

Method used

A deep reinforcement learning model based on the TD3 algorithm is adopted, combined with a global self-attention mechanism, to construct a Markov decision process for the flywheel array, realizing the coordinated action between individual flywheels and the array. Through the dual-Q network of the TD3 algorithm and the target policy smoothing regularization, the power allocation and response speed are optimized.

Benefits of technology

It significantly improves the frequency regulation response speed and stability of the flywheel array, realizes rapid power distribution and inter-flywheel coordination, and enhances the dynamic performance and robustness of the power grid.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The present application belongs to the technical field of power system auxiliary frequency modulation, and particularly relates to a flywheel array auxiliary thermal power unit frequency modulation method based on a TD3 algorithm, comprising the following steps: S1, modeling a flywheel array auxiliary thermal power unit frequency modulation system as a Markov decision process; S2, constructing a deep reinforcement learning model based on the TD3 algorithm, describing the control action of the flywheel array as a continuously changing action space, training the model to learn the state space of the flywheel array, and finding the optimal control strategy; S3, introducing a global self-attention mechanism into the TD3 model; S4, inputting real-time power grid operation data into the trained TD3 model, outputting the continuous power instructions of each flywheel unit from the model, and realizing the dynamic assistance of the flywheel array to the frequency modulation of the thermal power unit. The present scheme can significantly improve the response speed, training stability and power distribution flexibility of the thermal power-flywheel combined frequency modulation system.
Need to check novelty before this filing date? Find Prior Art