Multi-Objective Optimization In Environmental Decision-Making: A Hybrid AI Approach

Abstract

This paper investigates the application of a hybrid artificial intelligence (AI) approach for multi-objective optimization in environmental decision-making. The study comprises four key components: data collection, modeling and simulation, performance evaluation, and comparative analysis. Hypothetical data for hourly variations of insolation and wind speed at Hambantota was utilized for demonstration purposes. Python programming language and libraries such as NumPy and Matplotlib were employed for modeling and visualization. Performance evaluation involved calculating metrics such as the Hypervolume Indicator, Generational Distance, and Inverted Generational Distance to assess the convergence and diversity of solutions obtained through multi-objective optimization. Comparative analysis was conducted to compare the performance of the hybrid AI approach with traditional optimization methods and other AI-based techniques. The results highlight the effectiveness and efficiency of the hybrid AI approach in optimizing multiple conflicting objectives. The findings contribute to the understanding of AI-based approaches in environmental decision-making and provide insights for future research and practical applications.