Micro-grid frequency control method and system based on depth deterministic strategy gradient

Abstract

The invention discloses a micro-grid frequency control method and system based on depth deterministic strategy gradient, and belongs to the field of power system frequency control. Comprising the following steps: taking a frequency deviation of a micro-grid system and an integral thereof as training data, and training an intelligent agent by adopting a double-delay depth deterministic strategy gradient algorithm; the trained intelligent agent is applied to a micro-grid system with new energy, the state information of the current system is input into an AC framework, and the optimal action is selected and converted into an actual instruction for synchronizing the valve opening degree of a regulator of a generator and controlling the frequency of the micro-grid. According to the method, a model-free deep reinforcement learning algorithm is utilized, the intelligent agent is trained to adaptively learn the frequency change of the power grid, and the microgrid containing the new energy has the characteristics of randomness and intermittency, so that the method does not need to depend on an ideal mathematical model which has relatively large deviation with a real environment; and only the input of the system and the reward value need to be continuously learned and iterated, so that a better control effect on the micro-grid is achieved.

Description

technical field [0001] The present invention relates to the field of frequency control of power systems, and more particularly, to a method and system for frequency control of a microgrid based on a deep deterministic policy gradient. Background technique [0002] With the development of power system frequency control, new energy sources and their continuous introduction into the power system, new frequency control methods are required to meet this challenge and achieve frequency stability in the power system within the specified 50±0.2Hz range, which encourages A large number of scientific researchers are engaged in the research work of power system frequency control related topics. [0003] However, due to the complexity of the power system environment, most researchers use a simple linear approximation to simulate the power grid environment when designing the controller, which will cause some indescribable power grid characteristics to be mathematically modeled or lineari...

AI Technical Summary

Problems solved by technology

[0003] However, due to the complexity of the power system environment, most researchers use simple linear approximations to simulate the grid environment when designing controllers, which will lead to some indescribable grid characteristics being mathematically modeled or linearized, resulting in large error

On the other hand, with the continuous development of the "dual carbon" strategy, a certain proportion of new energy power generation equipment has been introduced into the microgrid system. Difficulties

[0004] In the current frequency control method, the mathematical modeling of the power system is too simple, the characteristics of the new energy in the system are not considered, or the traditional control method cannot adaptively learn the changes of the system parameters, etc. The method that does not depend on the system model and can make adaptive adjustments to the parameter changes in the system is particularly important

Images