Evaluation of the effectiveness of decision-making algorithms in the management of renewable energy sources: A case study of Ukraine

Abstract

The integration of renewable energy sources in Ukraine requires advanced decision-making algorithms to address various challenges, including energy forecasting, resource optimization, and grid stability. The existing algorithms exhibit limitations in accuracy and efficiency, necessitating the development of innovative approaches to enhance performance in this regard. This work evaluated the performance of existing algorithms and developed two new algorithms: the enhanced forecasting algorithm (EFA) and the dynamic resource optimization algorithm (DROA). Data from a hybrid energy system comprising solar, wind, and battery storage was used for analysis. The algorithms were assessed based on forecasting accuracy, economic efficiency, and system stability. Moreover, key metrics like mean absolute percentage error (MAPE) and operational cost reductions were used for the evaluation in the current work. According to the analysis results, the EFA achieved a 54% improvement in forecasting accuracy and reduced MAPE to 5.8%. The DROA enhanced resource optimization, resulting in a 56% reduction in energy losses and an 18% decrease in operational costs. System stability was improved, and grid frequency fluctuations were reduced by 67%. These results demonstrated the superiority of these new algorithms over existing methods. This work highlighted advanced algorithms' critical role in optimizing Ukraine's renewable energy systems. The EFA and DROA demonstrated significant potential for operational and economic benefits. This is possible with improved energy forecasting, reduced losses, and enhanced grid stability. Future research endeavors should focus more on applications and explore additional performance metrics to optimize energy systems in this regard.