Offshore wind power plant reactive power-voltage coordination control method based on deep reinforcement learning

Abstract

The invention relates to an offshore wind power plant reactive power-voltage coordination control method based on deep reinforcement learning, and belongs to the technical field of wind power generation. The method comprises the following steps: S1, establishing an offshore wind power plant reactive power-voltage coordination control model; S2, establishing a Markov decision process model based on a wind power plant reactive power-voltage control strategy, and defining a state action and a reward function of the system; S3, training the reactive power-voltage coordination control model based on a depth deterministic gradient strategy in combination with unit random output data to realize mapping from a wind turbine unit state to a reactive power instruction; and S4, achieving an online deployment process of the offshore wind power plant reactive power-voltage coordination control strategy. Compared with a traditional method, the method does not depend on system accurate modeling, can effectively reduce the voltage deviation of the wind power plant, and has better model solving precision and instant response speed.

Description

technical field [0001] The invention belongs to the technical field of wind power generation, and relates to a reactive power-voltage coordinated control method of an offshore wind farm based on deep reinforcement learning. Background technique [0002] At present, offshore wind farms are mainly connected to the grid through AC transmission. Due to the capacitive effect of the AC submarine cable, a large amount of charging power has raised the voltage at the end of the cable, and the closer to the end of the feeder, the higher the risk of the wind turbine voltage exceeding the limit. In addition, it is difficult to install reactive power compensation equipment due to the harsh offshore environment, so the reactive power-voltage regulation and control function of wind turbines is more prominent and has higher economic efficiency. However, the adjustment ability of a single unit is limited, and the geographical location and operating status of the units are different. How to c...

AI Technical Summary

Problems solved by technology

However, the adjustment ability of a single unit is limited, and the geographical location and operating status of the units are different. How to coordinate the operating status of all units to achieve reactive power-voltage coordinated control is a research hotspot.

[0003] Most of the current methods need to rely on the parameters of the wind farm structure model, and each new scenario needs to be solved repeatedly, and the immediate response ability needs to be further improved

Images