The energy generated by a solar photovoltaic (PV) system depends on uncontrollable factors, including weather conditions and solar irradiation, which leads to uncertainty in the power output. Forecast PV power generation is vital to improve grid stability and balance the energy supply and demand. This study aims to predict hourly day-ahead PV power generation by applying Temporal Fusion Transformer (TFT), a new attention-based architecture that incorporates an interpretable explanation of temporal dynamics and high-performance forecasting over multiple horizons. The proposed forecasting model has been trained and tested using data from six different facilities located in Germany and Australia. The results have been compared with other algorithms like Auto Regressive Integrated Moving Average (ARIMA), Long Short-Term Memory (LSTM), Multi-Layer Perceptron (MLP), and Extreme Gradient Boosting (XGBoost), using statistical error indicators. The use of TFT has been shown to be more accurate than the rest of the algorithms to forecast PV generation in the aforementioned facilities.
Collective self-consumption (CSC) systems offer a great opportunity to increase the viability of photovoltaic installations by reducing costs and increasing profitability for consumers. In addition, CSC systems increase self-sufficiency (SS) and self-consumption (SC). These systems require a proper energy allocation strategy (EAS) to define the energy distribution within the CSC. However, most EASs do not analyze the individual impact of the rules and mechanisms adopted. Therefore, six different EASs are proposed and evaluated in terms of both collective and individual cost, SC, and SS. The results show that the EASs based on minimizing collective costs are the most beneficial for the community, although they imply an unfair distribution of energy among users. On the other hand, the other EASs proposed stand out for reaching an equilibrium in terms of cost, SS, and SC, although the collective profitability is lower. The best results are achieved considering dynamic coefficients, which are preferred over static ones.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.