Abstract
Utilizing the capabilities of artificial intelligence can lead to the development of energy systems and power supply chain that are more efficient, sustainable, and resilient. The integration of machine learning techniques within these systems provides substantial benefits and is essential for enhancing overall performance. As the global community confronts challenges like climate change and rising energy demands, machine learning will play an increasingly vital role in defining the future of energy systems. This research examines how effective regression-based machine learning techniques are for analyzing and optimizing the performance of a geothermal combined heat and power system. It focuses on creating both linear and quadratic models to assess electricity generation, heat production, and the efficiency of the entire system. The evaluation of these models is performed through residual analysis and R-squared statistics. Results indicate that quadratic models surpass linear ones, with linear model achieving an R-squared value of 88.56 % for power generation, while the quadratic model reaches an impressive R-squared level of 99.88 %. Furthermore, the study demonstrates that quadratic machine learning models hold significant promise for optimizing system performance, shown by desirability metrics exceeding 0.99. This research highlights the importance of regression-based machine learning methods in analyzing and improving geothermal combined heat and power systems.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call