<![CDATA[Developing and modeling strategies for sustainable renewable energy always involve complex optimization problems including design, planning, and control, which are often computationally intractable for conventional optimization methods. Advances in artificial intelligence technology have provided many optimization methods to handle these complex problems effectively and inspired by their promising performance and becoming increasingly popular nowadays for future energy. In this paper, we summarize recent advances in optimization methods inspired by advances in artificial neural network technology, evolutionary algorithms, and hybridization applied to the field of sustainable energy development. Modeling for the prediction of operational solar radiation is very important for decision-making, resource variability, and energy demand. This paper presents an ANN-based method to generate DNI forecast operations using weather and aerosol forecasts of each data. The ANN model is designed to predict weather and aerosol variables at a certain time as input, while the other models use the DNI forecast improvement period before the instant forecast. The developed model uses observations of the North Sumatra location and the results of DNI forecasting are obtained every 10 minutes on the first day with DNI forecasting compared to the initial forecast that comes down based on modeling with R2, MAE, and RMSE and provides a good fit to the experimental data. Energy modeling strategy is one of the basic concepts in maintaining security, comfort, and privacy by creating a green and emission-free environment. The concept of development and modeling strategy of new renewable energy for the future is increasingly attracting attention to be studied and observed more deeply to prepare for sustainable future energy.]]>
Copyrights © 2024
