Sustainable Energy Planning and Management Using Metaheuristic Algorithms and Computational Modeling

1. Solar Power Forecasting

Computational modeling can be used to predict the amount of solar power that will be generated by a photovoltaic (PV) system. This can help grid operators to manage the grid and balance the energy supply and demand. Computational modeling methods for solar power forecasting can include machine learning algorithms, such as neural networks or support vector regression, and physical models, such as radiative transfer models or clear sky models. These methods use historical solar irradiance data and weather forecasting data to predict the output of a PV system. Yu et al. (2023) proposed a hybrid forecasting system that integrates pattern recognition algorithms, data decomposition strategy, and multi-objective optimization algorithm. The proposed system achieved the best performance in all aspects of the four forecast scenarios and also performed well in the multistep advance forecast. Cheng et al. (2022) evaluated the performance of opaque deep-learning solar power forecast models towards power-grid applications. The study concluded that some simple evaluation procedures can aid a better understanding of the factors that influence the performances of opaque models, and these procedures can help in the design methods for model modifications. Lindberg et al. (2023) investigated the effect of aggregation on forecast accuracy and value at a co-located wind and photovoltaic (PV) park in Sweden using roughly three years of data. The results showed that aggregation improves forecast accuracy in terms of continuous ranked probability score, interval score, and quantile score when compared to wind or PV power forecasts alone. The optimal aggregation ratio is found to be 50%-60% wind power and the remainder PV power.