Machine learning-based multi-criteria decision-making optimization of a geothermal integrated system

Arslan A. E., ARSLAN O.

Geothermics, cilt.133, 2025 (SCI-Expanded) identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 133
  • Basım Tarihi: 2025
  • Doi Numarası: 10.1016/j.geothermics.2025.103472
  • Dergi Adı: Geothermics
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, PASCAL, Aerospace Database, Aquatic Science & Fisheries Abstracts (ASFA), CAB Abstracts, Communication Abstracts, Compendex, Environment Index, Greenfile, INSPEC, Metadex, Civil Engineering Abstracts
  • Anahtar Kelimeler: Geothermal energy, Integrated system, Machine learning, Multi-criteria decision-making
  • Bilecik Şeyh Edebali Üniversitesi Adresli: Evet

Özet

This study investigates the optimal use of an integrated geothermal energy system. The integrated system includes power generation, residential, and greenhouse heating. The power generation is based on the ORC system using medium-temperature geothermal resources. Residential heating is based on the district system, which uses the waste from the power cycle system. The greenhouse heating is also based on the district system using the waste of residential heating before the reinjection of the geothermal fluid. In this aim, 144 main designs were formed using the demands and meteorological data of the selected geothermal field. The formed designs were analyzed through thermodynamic and economic calculations. Later, artificial neural network (ANN) models were conducted to obtain more design units of 7337 to determine the optimal design. The optimal design was evaluated using the efficiency analysis technique with output satisficing (EATWOS) analysis. The design points were weighted through the entropy method, whereas the outputs of the system were weighted through the analytical hierarchic process (AHP), including expert views. As result, the most efficient case is obtained for ΔT1=45.5 °C, ΔT2=28 °C, ΔT3=20 °C. where Tb=133.5 °C, Tb=88 °C, Tc=60 °C, and Td=40 °C. The RN, GA, ẆORC, η, ε, and NPV are obtained as 14889, 294735 m2, 13332 kW, 19.39%, 49.61%, and 21.59 million US$.