Enhancing probabilistic photovoltaic power forecasting with parallel feature interaction and bayesian correction

Photovoltaic power forecasting holds significant importance for solar energy grid integration and real-time dispatching in power systems. However, existing models struggle to extract sufficiently effective features and photovoltaic power is highly dependent on weather conditions, posing two major challenges in forecasting: the underutilization of features and the difficulty of forecasting under weather uncertainty. To address these challenges, this study proposes a parallel interactive deep evidential regression with Bayesian uncertainty correction model to enhance the accuracy of photovoltaic power forecasts. The proposed model incorporates a parallel feature interaction module that employs a bidirectional flow feature extraction, followed by an attention free mechanism, addressing feature underutilization in photovoltaic power forecasting. Additionally, the deep evidential regression module is introduced to capture the heavy-tailed characteristics of photovoltaic power by using the Student's t-distribution, enabling the estimation of both epistemic and aleatoric uncertainties. Since high weather uncertainty leads to high aleatoric uncertainty. Therefore, to mitigate weather uncertainty, a Bayesian weather uncertainty correction module is designed to adjust results exceeding a certain aleatoric uncertainty threshold with outputs from a Bayesian linear regression model trained on weather-excluded variables. The effectiveness of the proposed model is demonstrated through experiments conducted in Australia across four seasons, encompassing both deterministic forecasts and probabilistic forecasts. The performance of models is validated through comparisons with nine other models and the Diebold-Mariano test, confirming its efficacy in both deterministic and probabilistic photovoltaic power forecasting.