Short term PV power generation prediction based on wavelet transform and LSTM

Accurate short-term photovoltaic (PV) power generation prediction is helpful for the allocation and management of power grid resources, and is of great significance for the stable operation and economic benefits of the power system. The historical data of PV power generation systems has characteristics such as volatility, randomness, time series, and certain periodicity. Traditional prediction methods cannot effectively mine and utilize the deep-seated features of the data, so they can no longer meet the current demand for high-precision prediction. This article proposes a WT-LSTM PV short-term power generation prediction method. Firstly, the historical time series data of the PV electric field is decomposed into high-frequency and low-frequency components through wavelet transform to improve the feature expression ability of the data. Then, a Long Short Term Memory (LSTM) network is used to predict each component, addressing the negative impact of data volatility and randomness on the prediction results caused by a single LSTM prediction algorithm. Finally, the final PV power generation prediction result is reconstructed by inverse wavelet transform.