Online estimation method and system for primary frequency modulation capability of deep peak regulation unit based on LSTM (Long Short Term Memory)

Abstract

The invention discloses an LSTM-based deep peak regulation unit primary frequency modulation capability online estimation method and system, and the method comprises the steps: carrying out the modeling of a boiler heat storage system, a reheating system, a steam turbine speed regulation system and a steam turbine system which affect the primary frequency modulation function of a thermal power unit through an LSTM neural network; the four sub-networks are combined to generate a complete deep peak regulation thermal power generating unit primary frequency modulation load prediction model, off-line training is carried out on the model by utilizing unit historical data, and unit primary frequency modulation related data collected in real time are input into the model for on-line prediction and parameter updating. The method is suitable for the deep peak regulation working condition, the primary frequency modulation load prediction accuracy of the thermal power generating unit is high, and the primary frequency modulation capability of the deep peak regulation thermal power generating unit can be fully exerted.

Description

technical field [0001] The invention belongs to the technical field of primary frequency regulation of thermal power units, and in particular relates to an LSTM-based online estimation method and system for primary frequency regulation capability of deep peak-shaving units. Background technique [0002] With the rapid development of new energy power generation in my country, the proportion of traditional coal-fired units in the power grid is getting smaller and smaller. Clean energy power generation has a series of advantages that traditional thermal power generation does not have, but the fluctuation and intermittency of clean energy power generation output will also lead to the instability of the grid frequency, which puts forward new requirements for the peak regulation and frequency regulation capabilities of the grid . For quite a long time in the future, thermal power units will undertake the main tasks of peak regulation and frequency regulation of the power grid, an...

AI Technical Summary

Problems solved by technology

[0003] The current primary frequency modulation load forecasting method for thermal power units is mainly realized by building the mechanism modeling of the thermal power unit coordination control system and digital electro-hydraulic control system, but the thermal power unit itself is highly complex, and the primary frequency modulation process mainly involves equipment including steam turbines, Heater, digital electro-hydraulic system, etc., the change of the main steam parameters of the unit and the flow characteristics of the steam turbine valve also have an important impact on the primary frequency regulation capability, and the deep peak-shaving operation also makes the operating characteristics of the unit change greatly, which can be predicted through mechanism modeling It is difficult to fully describe the complex characteristics of the primary frequency regulation of deep peak-shaving thermal power units, and the massive historical data of unit operation has not been fully utilized, and the prediction accuracy is poor.

Images