Abstract
Accurate prediction of photovoltaic(PV) generation plays a vital role in power dispatching and is one of the effective ways to ensure the safe operation of power grid. In response to this issue, this paper improves the Rhino beetle optimization algorithm (LSDBO) using Logistic chaos mapping and sine function strategies an optimizes the PCL-MHA model (running CNN-MHA and LSTM-MHA models in parallel, PCL; Multi-Head-Attention, MHA) to enhance predictive accuracy. Various experiments were conducted using historical data from the Alice Springs PV system in Australia. PV component technologies comprise monocrystalline silicon and polycrystalline silicon, with array fixed on the ground. Through experiments, the proposed model in this paper achieved the best results in 16 metrics under different weather conditions, with average values of 98.43 % for R2, 2.69 % for MSE, 7.8 % for MAE, and 15.09 % for RMSE. Compared to other models, an average improvement of 2.41 %, 6.6 %, 7.77 %, and 11.21 % in these metrics.