Optimization of solar farm design for energy efficiency in university campuses using machine learning: A case study
Ehsanolah Assareh, Nima Izadyar, Elmira Jamei, Mohammad amin Monzavian, Saurabh Agarwal, Wooguil Pak
Abstract
The increasing energy demand in multifunctional buildings, like university buildings, hinders sustainability and cost efficiency. This study addresses this issue by designing and optimizing a multi-generation solar farm using Machine Learning to enhance system performance and reduce costs. By framing Response Surface Methodology (RSM) as an interpretable supervised machine learning technique, this study combines it with the Building Energy Optimization Tool (BEopt) and Engineering Equation Solver (EES) for data modeling and optimization. The integration leverages RSM's computational efficiency to optimize exergy efficiency and cost. The novelty lies in enhancing renewable energy integration in large-scale educational facilities, an underexplored domain, using Machine Learning-driven Multi-Objective Optimization. A university building in a cooling-dominant extreme climate was selected, with annual energy demands of 18.24 Gigawatt hours (GWh) for electricity, 6.57 GWh for heating, and 7.52 GWh for cooling. A multi-generation solar farm is proposed and optimized to meet this demand and provide surplus energy, which can be stored, utilized for additional applications, or exported to the grid. The optimized solar farm generates 22.8 GWh of electricity, 17.9 GWh of heating, and 12.9 GWh of cooling, achieving an exergy efficiency of 25.69 % with an operational cost of $10.15 per hour, and a CO 2 emissions reduction of 7395 metric tons per year. This study provides a scalable and modular framework for optimizing energy management in high-demand environments, contributing to sustainability goals and energy-efficient buildings. Future studies may explore dynamic climate variations, real-time demand forecasting, and hybrid renewable energy sources to improve system resilience, adaptability, and sustainability. • Machine learning optimizes solar systems to improve energy efficiency in campuses. • Response Surface Methodology enhances efficiency and reduces operational costs. • Optimized solar farm generates surplus energy for cooling, heating, and power. • Achieved 25.69 % exergy efficiency with an operational cost of $10.15/hour. • Scalable Machine-Learning solutions advance sustainability in university buildings.