Short-term photovoltaic power forecasting under complex weather conditions using optimized signal decomposition and attention-based learning

Abstract

Photovoltaic (PV) power sequences exhibit significant intermittency and strong non-stationarity under complex weather conditions, particularly during rapid cloud movements, posing significant challenges for short-term forecasting. To address this, this study proposes a hybrid deep learning forecasting model. First, the sparrow search algorithm is used to optimize key parameters of variational mode decomposition, enabling adaptive decomposition of PV power sequences into frequency-distinct sub-modes. Subsequently, a hybrid architecture combining a TCN-ECA module and a lightweight Transformer is developed to jointly capture local high-frequency fluctuations and long-term temporal dependencies. To validate the effectiveness of the proposed model, experiments are conducted on the DKASC Site 1 A. The results demonstrate that the proposed method reduces RMSE and MAE by 38.8% and 36.9%, respectively, compared to suboptimal models on an annual basis. It maintains high prediction accuracy even under cloudy conditions and during spring periods with strong meteorological fluctuations. An additional experiment was conducted on the independent DKASC Site 8 PV array to assess cross-array robustness. Furthermore, the relationship between meteorological feature fluctuations and prediction errors was analyzed to elucidate the mechanisms underlying forecasting errors under complex weather conditions. Results indicate that short-term non-stationary fluctuations in irradiance are the key factor amplifying prediction errors under complex weather conditions such as cloudiness.