A comprehensive review of data analytics and storage methods in geothermal energy operations

Abstract

Geothermal energy storage (GES) systems are thoroughly examined in this research, with a focus on methods like borehole thermal energy storage (BTES), underground thermal energy storage (UTES), and aquifer thermal energy storage (ATES). It highlights the importance of thermal energy storage (TES) systems in addressing global energy challenges. The feasibility of UTES for large-scale energy storage and its integration with geothermal power plants is investigated. The ATES, with the advantage of large storage capacity and low operating costs has could be employed in regions with suitable aquifers. The adaptability of BTES to different ground conditions and its small land footprint made it a spotlight for the researchers. The study emphasizes the role of TES technologies in meeting the growing demand for renewable energy, reducing the impact of climate change, and providing efficient energy solutions for heating, ventilating, and air conditioning. HVAC systems. Also, the application of geothermal power plants and TES systems in decreasing the dependence on nonrenewable energy sources and increasing energy efficiency increase investigated. The development of reliable and affordable sensors, together with improvements in processing power, has made data-intensive algorithms and real-time operational decision-making applications in the field of geothermal energy. The study also delves into the potential of machine learning to optimize geothermal design, monitor performance, improve performance, find errors, and more. It was shown that artificial neural networks were the most common kind of trained model, while several other models were often used as benchmarks for performance. Picture selection, systematic time series feature engineering and model evaluation were all areas that showed a lot of promise in the systematic review for future research and practical applications.