100MW energy storage power control method and system based on adaptive dynamic programming

Abstract

The present invention provides a 100-megawatt energy storage power control method and system based on adaptive dynamic programming. The method includes the following steps: setting the structure of the adaptive dynamic programming control system and setting its parameters; initializing the parameters and importing the parameters of the controlled object Initial state; initial training execution module and evaluation module; calculating the charging and discharging power of the 100MW energy storage system; sequentially training the evaluation module and the execution module, and updating the weights of the evaluation module neural network and the execution module neural network; saving The control strategy at the current moment, and calculate the state of the controlled object at the next moment; repeat the above steps until the end of the control process, and output the control strategy at each moment. The system includes a parameter initialization module, a data collection and calculation module, an evaluation module, an execution module, an output module and the like. The invention realizes the power optimization control of the large-scale energy storage power station and the new energy combined power generation system, and improves the operating economy and coordination control ability of the battery energy storage system.

Description

technical field [0001] The invention relates to the fields of smart grid, new energy power generation, energy Internet, electric energy storage, and automatic control, and in particular to a power control method and system for a 100-megawatt battery energy storage system based on adaptive dynamic programming. Background technique [0002] With the continuous increase of wind power grid-connected scale, the volatility and randomness of large-scale wind power grid connection will have adverse effects on the safety, stability and power quality of power grid operation. Therefore, controlling the fluctuation rate of wind power output is of great significance to the economy and safety of power grid operation [0003] According to different storage forms, energy storage can be divided into physical energy storage, electrochemical energy storage and electromagnetic energy storage. At present, electrochemical energy storage technology has attracted much attention. Equipped with a b...

AI Technical Summary

Problems solved by technology

[0006] When smoothing large-scale new energy generation output fluctuations in large-scale battery energy storage power stations, the traditional first-order low-pass filtering or output filtering method with variable time constant (T) is used, which sometimes leads to control sensitivity due to the time lag of the method itself. bad

The energy storage output target value output by the general moving average filtering algorithm is also largely limited by the input of new energy generation power such as wind power and photovoltaic power generation. These traditional methods encounter sudden changes in the output of new energy power generation. The performance is degraded and affects the subsequent filtering effect

[0007] On the other hand, when improving the output control of energy storage power stations that are friendly to new energy power generation, the traditional control method needs to be further improved in the aspect of adaptive control of the overall output of energy storage power stations based on self-learning intelligent optimization control

Images