Urban Economics and Planning

Urban Economics and Planning

Evaluation Of the Optimal Location for A Solar Power Plant in Fars Province Using Multi-Criteria Decision-Making Methods and A Machine Learning Approach

Document Type : Original Article

Authors
Vahidreza Atabati 1
Mahdi Arabi 2
1 M.Sc. in Geospatial Information System (GIS), Department of Geomatics Engineering, Faculty of Civil Engineering, Shahid Rajaee Teacher Training University, Tehran, Iran
2 Associate Professor, Department of Geomatics Engineering, Faculty of Civil Engineering, Shahid Rajaee Teacher Training University, Tehran, Iran
10.22034/uep.2025.539739.1685
Abstract
Introduction 
Energy plays a critical role in sustainable development and improving human quality of life. As global energy demand rises, especially in developing countries, there is a significant need to shift towards renewable energy sources. Among these, solar energy, particularly photovoltaic (PV) technology, stands out for its environmental sustainability, minimal carbon footprint, and considerable potential to mitigate climate change. Iran, located in a region with high solar radiation potential, is well-positioned to harness solar energy. With an annual average of 1800 kWh/m² of solar radiation and over 280 to 300 sunny days per year, Iran presents an ideal opportunity to develop solar power plants. However, despite this significant potential, the country has not fully capitalized on solar energy due to challenges in selecting optimal locations for these plants.
The effectiveness of solar power projects depends heavily on selecting the most suitable sites for power plants. Optimal site selection maximizes energy production efficiency and minimizes environmental impact and economic costs. Poor site selection can lead to reduced plant efficiency, wasted financial resources, and increased environmental degradation. Therefore, the first step in solar power development is identifying regions with high solar radiation potential and other critical factors such as access to the electricity grid, water resources, and infrastructure. Multi-Criteria Decision-Making (MCDM) methods have proven to be practical tools for evaluating various factors involved in site selection. Furthermore, Geographic Information Systems (GIS) have become invaluable in spatial data analysis, allowing for accurate site assessments and decision-making. More recently, machine learning techniques have emerged as a promising approach to optimizing solar power plant site selection.
Materials and Methods
The study applies a combination of MCDM, GIS, and machine learning techniques for optimal solar power plant site selection in Fars Province, Iran. Initially, nine key criteria were identified, including solar radiation, temperature, slope, and proximity to infrastructure. GIS was employed to generate spatial data layers for these criteria. Two MCDM methods, the Best-Worst Method (BWM) and SWARA, were used to assign weights to the criteria. At the same time, the Dempster-Shafer Information Fusion Theory was utilized to enhance the reliability of the weights by combining the results of both methods. The land suitability map for solar power plant placement was generated using the Marcos method.
Subsequently, machine learning, specifically Support Vector Regression (SVR), was applied to predict the most suitable areas for solar power plants. The SVR model’s hyperparameters were optimized using the Grey Wolf Optimizer (GWO), an evolutionary algorithm. The SVR model was trained using reference data from the Marcos method’s suitability map. This combined approach created a highly reliable land suitability map for solar power plant installation, offering valuable insights into the potential for renewable energy development in Fars Province.
Findings
The results demonstrated that 14% and 34% of the region in Fars Province were highly suitable for solar power plant installation according to the Marcos method and machine learning approach, respectively. In total, 48% of the area was identified as highly suitable or very suitable for solar power generation. Specific areas in the province’s northern, northeastern, and central parts, including cities such as Abadeh, Sarchahan, Pasargad, and Bavanat, were recommended as priority locations for solar power development.
The analysis further revealed that the machine learning-based approach provided more accurate predictions than the Marcos method alone. The machine learning model optimized using GWO achieved high prediction accuracy, with an R² value of 0.9975 for the training data and 0.9923 for the testing data. The machine learning approach classified 48% of the region as highly suitable for solar power plants, substantially improving over the 39% identified by the Marcos method.
This study’s combination of MCDM methods, GIS, and machine learning techniques offers a robust solar power plant site selection framework. The integration of MCDM with GIS provides a comprehensive approach for evaluating multiple factors, while the addition of machine learning further enhances the accuracy and efficiency of site selection. The results suggest that machine learning can significantly improve the reliability of predictions, especially when dealing with complex spatial and environmental data.
The findings of this research are consistent with previous studies on solar power plant site selection, highlighting the importance of incorporating multiple factors such as solar radiation, proximity to infrastructure, and environmental conditions. Machine learning also underscores the growing potential of artificial intelligence in optimizing decision-making processes for renewable energy projects.
Conclusion
Considering the necessity of renewable energy expansion, optimal site selection for solar power plants plays a critical role. In this study, nine climatic, topographic, and infrastructural criteria—including photovoltaic potential, direct normal irradiance, temperature, precipitation, slope, distance from roads, distance from faults, elevation, and distance from urban centers—were selected based on previous research and analyzed using a multi-criteria decision-making approach with BWM and SWARA weighting methods. Results indicated that the most influential criteria were photovoltaic potential and direct normal irradiance. To enhance accuracy, weights were integrated using Dempster–Shafer theory, and a land suitability map was generated through the MARCOS method. Subsequently, an SVR model was optimized via the Grey Wolf Optimizer to predict suitability, showing that about 48% of Fars Province possesses high or very high suitability for solar plant development. Finally, top priorities were identified by Abadeh, Sarchehan, Pasargad, Bavanat, and Khorrambid counties. The findings provide valuable insights for policymakers and investors in promoting sustainable solar energy development. This study demonstrates the effectiveness of combining MCDM, GIS, and machine learning for optimizing the site selection process for solar power plants. By employing a hybrid decision-making framework, the research contributes to advancing solar energy development in Iran and similar regions with high solar radiation potential. The study results provide valuable insights for energy planners, policymakers, and investors in selecting the most suitable locations for solar power infrastructure. This approach optimizes energy production, promotes environmental sustainability, and contributes to the global shift towards renewable energy sources.
Keywords
Multi-criteria decision making
support vector regression
spatial information system
solar power plant location
machine learning

Subjects

Agyekum, E. B., Amjad, F., Shah, L., & Velkin, V. I. (2021). Optimizing photovoltaic power plant site selection using analytical hierarchy process and density-based clustering – Policy implications for transmission network expansion, Ghana. Sustainable Energy Technologies and Assessments, 47, 101521. https://doi.org/https://doi.org/10.1016/j.seta.2021.101521 
Agyekum, E. B., Kumar, N. M., Mehmood, U., Panjwani, M. K., Haes Alhelou, H., Adebayo, T. S., & Al-Hinai, A. (2021). Decarbonize Russia — A Best–Worst Method approach for assessing the renewable energy potentials, opportunities and challenges. Energy Reports, 7, 4498-4515. https://doi.org/https://doi.org/10.1016/j.egyr.2021.07.039 
Ahadi, P., Fakhrabadi, F., Pourshaghaghy, A., & Kowsary, F. (2023). Optimal site selection for a solar power plant in Iran via the Analytic Hierarchy Process (AHP). Renewable Energy, 215, 118944. https://doi.org/https://doi.org/10.1016/j.renene.2023.118944 
Amjad, F., Agyekum, E. B., & Wassan, N. (2024). Identification of appropriate sites for solar-based green hydrogen production using a combination of density-based clustering, Best-Worst Method, and Spatial GIS. International Journal of Hydrogen Energy, 68, 1281-1296. https://doi.org/https://doi.org/10.1016/j.ijhydene.2024.04.310 
Asakereh, A., Soleymani, M., & Sheikhdavoodi, M. J. (2017). A GIS-based Fuzzy-AHP method for the evaluation of solar farms locations: Case study in Khuzestan province, Iran. Solar Energy, 155, 342-353. https://doi.org/https://doi.org/10.1016/j.solener.2017.05.075 
Ayough, A., Boshruei, S., & Khorshidvand, B. (2022). A new interactive method based on multi-criteria preference degree functions for solar power plant site selection. Renewable Energy, 195, 1165-1173. https://doi.org/https://doi.org/10.1016/j.renene.2022.06.087 
Azizkhani, M., Vakili, A., Noorollahi, Y., & Naseri, F. (2017). Potential survey of photovoltaic power plants using Analytical Hierarchy Process (AHP) method in Iran. Renewable and Sustainable Energy Reviews, 75, 1198-1206. https://doi.org/https://doi.org/10.1016/j.rser.2016.11.103 
Celik, E., & Gul, M. (2021). Hazard identification, risk assessment and control for dam construction safety using an integrated BWM and MARCOS approach under interval type-2 fuzzy sets environment. Automation in Construction, 127, 103699. https://doi.org/https://doi.org/10.1016/j.autcon.2021.103699 
Cozzi , M., & Goodson , T. (2021). Global energy review International Energy Agency. https://doi.org/10.1016/B978-0-323-93940-9.00257-7 
Dweiri, F., Khan, S. A., & Almulla, A. (2018). A multi-criteria decision support system to rank sustainable desalination plant location criteria. Desalination, 444, 26-34. https://doi.org/https://doi.org/10.1016/j.desal.2018.07.007 
Ervural, B., & Öztaş, Ö. (2025). Integrating GIS and Fuzzy BWM for Solar PV Power Plant Site Selection: A Case Study of Konya, Turkey [CBS ve Bulanık BWM Kullanarak Güneş Enerjisi Santrali Yer Seçimi için Yeni Bir Çerçeve]. Celal Bayar University Journal of Science, 21(1), 75-89. https://doi.org/10.18466/cbayarfbe.1589809
Fard, M. B., Moradian, P., Emarati, M., Ebadi, M., Chofreh, A. G., & Klemeŝ, J. J. (2022). Ground-mounted photovoltaic power station site selection and economic analysis based on a hybrid fuzzy best-worst method and geographic information system: A case study Guilan province. Renewable and Sustainable Energy Reviews, 169, 112923. https://doi.org/10.1016/j.rser.2022.112923 
Fattahi, H., & Babanouri, N. (2017). Applying Optimized Support Vector Regression Models for Prediction of Tunnel Boring Machine Performance. Geotechnical and Geological Engineering, 35(5), 2205-2217. https://doi.org/10.1007/s10706-017-0238-4 
Gorjian, S., & Ghobadian, B. (2015). Solar Thermal Power Plants: Progress and Prospects in Iran. Energy Procedia, 75, 533-539. https://doi.org/https://doi.org/10.1016/j.egypro.2015.07.447 
Haselip, J., Narkeviciute, R., Mackenzie, G., & Batidzirai, B. (2015). Energy systems integration for a decarbonising world. In (pp. 84-92). DTU International Energy Report. https://orbit.dtu.dk/en/publications/energy-systems-integration-for-a-decarbonising-world
Hassan, I., Alhamrouni, I., & Azhan, N. H. (2023). A CRITIC–TOPSIS Multi-Criteria Decision-Making Approach for Optimum Site Selection for Solar PV Farm. Energies, 16(10). https://www.mdpi.com/1996-1073/16/10/4245
Heidary Dahooie, J., Husseinzadeh Kashan, A., Shoaei Naeini, Z., Vanaki, A. S., Zavadskas, E. K., & Turskis, Z. (2022). A Hybrid Multi-Criteria-Decision-Making Aggregation Method and Geographic Information System for Selecting Optimal Solar Power Plants in Iran. Energies, 15(8). https://www.mdpi.com/1996-1073/15/8/2801
Hooshangi, N., Gharakhanlou, N. M., & Razin, S. R. G. (2023). Evaluation of potential sites in Iran to localize solar farms using a GIS-based Fermatean Fuzzy TOPSIS. Journal of Cleaner Production, 384, 135481. https://doi.org/10.1016/j.jclepro.2022.135481
Imam, A. A., Abusorrah, A., & Marzband, M. (2024). Potentials and opportunities of solar PV and wind energy sources in Saudi Arabia: Land suitability, techno-socio-economic feasibility, and future variability. Results in Engineering, 21, 101785. https://doi.org/https://doi.org/10.1016/j.rineng.2024.101785 
Iordache, M., Pamucar, D., Deveci, M., Chisalita, D., Wu, Q., & Iordache, I. (2022). Prioritizing the alternatives of the natural gas grid conversion to hydrogen using a hybrid interval rough based Dombi MARCOS model. International Journal of Hydrogen Energy, 47(19), 10665-10688. https://doi.org/https://doi.org/10.1016/j.ijhydene.2022.01.130 
Islam, M. R., Aziz, M. T., Alauddin, M., Kader, Z., & Islam, M. R. (2024). Site suitability assessment for solar power plants in Bangladesh: A GIS-based analytical hierarchy process (AHP) and multi-criteria decision analysis (MCDA) approach. Renewable Energy, 220, 119595. https://doi.org/https://doi.org/10.1016/j.renene.2023.119595 
Jerome, J. B. (2000). Dempster-Shafer theory and Bayesian reasoning in multisensor data fusion. Proc.SPIE. https://doi.org/10.1117/12.381638 
Jung, J., Han, S., & Kim, B. (2019). Digital numerical map-oriented estimation of solar energy potential for site selection of photovoltaic solar panels on national highway slopes. Applied Energy, 242, 57-68. https://doi.org/10.1016/j.apenergy.2019.03.101 
Kaltsounidis, A., & Karali, I. (2020). Dempster-Shafer Theory: Ηow Constraint Programming Can Help. Information Processing and Management of Uncertainty in Knowledge-Based Systems, Cham. https://link.springer.com/chapter/10.1007/978-3-030-50143-3_27
Karimipour, H., & Alesheikh, A. A. (2021). Location of Solar Power Plants by Combining the Best-worst Methods, Danp, Copras and TOPSIS Case Study of Fars Province. Journal of Geomatics Science and Technology , 10(3), 183-199. http://jgst.issgeac.ir/article-1-987-fa.html
Keršuliene, V., Zavadskas, E. K., & Turskis, Z. (2010). Selection of rational dispute resolution method by applying new step‐wise weight assessment ratio analysis (Swara). Journal of Business Economics and Management, 11(2), 243-258. https://doi.org/10.3846/jbem.2010.12 
Khajavi Pour, A., Shahraki, M. R., & Hosseinzadeh Saljooghi, F. (2021). Solar PV Power Plant Site Selection Using GIS-FFDEA Based Approach with Application in Iran. Journal of Renewable Energy and Environment, 8(1), 28-43. https://doi.org/10.30501/jree.2020.230490.1110 
Kumar, R., & Singal, S. K. (2015). Selection of Best Operating Site of SHP Plant based on Performance. Procedia - Social and Behavioral Sciences, 189, 110-116. https://doi.org/https://doi.org/10.1016/j.sbspro.2015.03.205
Li, X.-Y., Dong, X.-Y., Chen, S., & Ye, Y.-M. (2024). The promising future of developing large-scale PV solar farms in China: A three-stage framework for site selection. Renewable Energy, 220, 119638. https://doi.org/10.1016/j.renene.2023.119638 
Lin, G., Liang, J., & Qian, Y. (2015). An information fusion approach by combining multigranulation rough sets and evidence theory. Information Sciences, 314, 184-199. https://doi.org/https://doi.org/10.1016/j.ins.2015.03.051 
Makhadmeh, S. N., Al-Betar, M. A., Doush, I. A., Awadallah, M. A., Kassaymeh, S., Mirjalili, S., & Zitar, R. A. (2024). Recent Advances in Grey Wolf Optimizer, its Versions and Applications: Review. IEEE Access, 12, 22991-23028. https://doi.org/10.1109/ACCESS.2023.3304889 
Mardani, A., Nilashi, M., Zakuan, N., Loganathan, N., Soheilirad, S., Saman, M. Z. M., & Ibrahim, O. (2017). A systematic review and meta-Analysis of SWARA and WASPAS methods: Theory and applications with recent fuzzy developments. Applied Soft Computing, 57, 265-292. https://doi.org/https://doi.org/10.1016/j.asoc.2017.03.045 
Mi, X., Tang, M., Liao, H., Shen, W., & Lev, B. (2019). The state-of-the-art survey on integrations and applications of the best worst method in decision making: Why, what, what for and what’s next? Omega, 87, 205-225. https://doi.org/https://doi.org/10.1016/j.omega.2019.01.009 
Mirhosseini, M., Sharifi, F., & Sedaghat, A. (2011). Assessing the wind energy potential locations in province of Semnan in Iran. Renewable and Sustainable Energy Reviews, 15(1), 449-459. https://doi.org/https://doi.org/10.1016/j.rser.2010.09.029
Mirjalili, S., Mirjalili, S. M., & Lewis, A. (2014). Grey wolf optimizer. Advances in engineering software, 69, 46-61. https://doi.org/10.1016/j.advengsoft.2013.12.007
Moonchai, S., & Chutsagulprom, N. (2020). Short-term forecasting of renewable energy consumption: Augmentation of a modified grey model with a Kalman filter. Applied Soft Computing, 87, 105994. https://doi.org/https://doi.org/10.1016/j.asoc.2019.105994 
Najafi, G., Ghobadian, B., Mamat, R., Yusaf, T., & Azmi, W. H. (2015). Solar energy in Iran: Current state and outlook. Renewable and Sustainable Energy Reviews, 49, 931-942. https://doi.org/https://doi.org/10.1016/j.rser.2015.04.056 
Negi, G., Kumar, A., Pant, S., & Ram, M. (2021). GWO: a review and applications. International Journal of System Assurance Engineering and Management, 12(1), 1-8. https://doi.org/10.1007/s13198-020-00995-8 
Neisani Samani, N., & Tahouni, A. (2019). The Evaluation of suitable Sites for Solar Farms by Multi Criteria Decision Making in GIS (Case Study: East Azarbaijan Province). Human Geography Research, 51(3), 747-764. https://doi.org/10.22059/jhgr.2019.279885.1007909 
Noorollahi, E., Fadai, D., Akbarpour Shirazi, M., & Ghodsipour, S. H. (2016). Land suitability analysis for solar farms exploitation using GIS and fuzzy analytic hierarchy process (FAHP)—a case study of Iran. Energies, 9(8), 643. https://www.mdpi.com/1996-1073/9/8/643
Olindo, I., Klaus, J., Arno, S., Rene, V.S. and Miro, Z. (2016). Solar Energy: The physics and engineering of photovoltaic conversion, technologies and systems (1st edition ed.). UIT Cambridge Ltd. https://www.amazon.com/Solar-Energy-Engineering-Photovoltaic-Technologies/dp/1906860327 
Owusu, P. A., & Asumadu-Sarkodie, S. (2016). A review of renewable energy sources, sustainability issues and climate change mitigation. Cogent Engineering, 3(1), 1167990. https://doi.org/10.1080/23311916.2016.1167990 
Qasimi, A. B., Toomanian, A., Nasri, F., & Samany, N. N. (2023). Genetic algorithms-based optimal site selection of solar PV in the north of Afghanistan. International Journal of Sustainable Energy, 42(1), 929-953. https://doi.org/10.1080/14786451.2023.2246081 
Rana, M. M. S. P., & Moniruzzaman, M. (2024). Demarcation of suitable site for solar photovoltaic power plant installation in Bangladesh using geospatial techniques. Next Energy, 3, 100109. https://doi.org/https://doi.org/10.1016/j.nxener.2024.100109 
Rane, N. L., Günen, M. A., Mallick, S. K., Rane, J., Pande, C. B., Giduturi, M., Bhutto, J. K., Yadav, K. K., Tolche, A. D., & Alreshidi, M. A. (2024). GIS-based multi-influencing factor (MIF) application for optimal site selection of solar photovoltaic power plant in Nashik, India. Environmental Sciences Europe, 36(1), 5. https://doi.org/10.1186/s12302-023-00832-2 
Razavi-Termeh, S. V., Khosravi, K., Sadeghi-Niaraki, A., Choi, S.-M., & Singh, V. P. (2020). Improving groundwater potential mapping using metaheuristic approaches. Hydrological Sciences Journal, 65(16), 2729-2749. https://doi.org/10.1080/02626667.2020.1828589 
Rezaie, F., Panahi, M., Bateni, S. M., Jun, C., Neale, C. M. U., & Lee, S. (2022). Novel hybrid models by coupling support vector regression (SVR) with meta-heuristic algorithms (WOA and GWO) for flood susceptibility mapping. Natural Hazards, 114(2), 1247-1283. https://doi.org/10.1007/s11069-022-05424-6 
Rezaei, J. (2015). Best-worst multi-criteria decision-making method. Omega, 53, 49-57. https://doi.org/https://doi.org/10.1016/j.omega.2014.11.009 
Rylatt, R. M., Gadsden, S., & Lomas, K. (2001). GIS-based decision support for solar energy planning in urban environments. Computers, Environment and Urban Systems, 25, 579-603. https://doi.org/10.1016/S0198-9715(00)00032-6 
Şahin, G., Koç, A., & van Sark, W. (2024). Multi-criteria decision making for solar power-Wind power plant site selection using a GIS-intuitionistic fuzzy-based approach with an application in the Netherlands. Energy Strategy Reviews, 51, 101307. https://doi.org/10.1016/j.esr.2024.101307 
Shorabeh, S. N., Firozjaei, M. K., Nematollahi, O., Firozjaei, H. K., & Jelokhani-Niaraki, M. (2019). A risk-based multi-criteria spatial decision analysis for solar power plant site selection in different climates: A case study in Iran. Renewable Energy, 143, 958-973. https://doi.org/https://doi.org/10.1016/j.renene.2019.05.063 
Shorabeh, S. N., Samany, N. N., Minaei, F., Firozjaei, H. K., Homaee, M., & Boloorani, A. D. (2022). A decision model based on decision tree and particle swarm optimization algorithms to identify optimal locations for solar power plants construction in Iran. Renewable Energy, 187, 56-67. https://doi.org/https://doi.org/10.1016/j.renene.2022.01.011 
Smola, A. J., & Schölkopf, B. (2004). A tutorial on support vector regression. Statistics and Computing, 14(3), 199-222. https://doi.org/10.1023/B:STCO.0000035301.49549.88 
Stević, Ž., Pamučar, D., Puška, A., & Chatterjee, P. (2020). Sustainable supplier selection in healthcare industries using a new MCDM method: Measurement of alternatives and ranking according to COmpromise solution (MARCOS). Computers & Industrial Engineering, 140, 106231. https://doi.org/https://doi.org/10.1016/j.cie.2019.106231 
Tehreem, F., Shahzad, U., & Cui, L. (2020). Renewable and nonrenewable energy consumption, trade and CO 2 emissions in high emitter countries: does the income level matter? Journal of Environmental Planning and Management, 64. https://doi.org/10.1080/09640568.2020.1816532 
Vapnik, V. N. (2000). The nature of statistical learning theory. Springer New York, NY. https://link.springer.com/book/10.1007/978-1-4757-3264-1
Wang, C.-N., Dang, T.-T., & Bayer, J. (2021). A two-stage multiple criteria decision making for site selection of solar photovoltaic (PV) power plant: A case study in Taiwan. IEEE Access, 9, 75509-75525. https://doi.org/10.1109/ACCESS.2021.3081995 
Zavadskas, E. K., Čereška, A., Matijošius, J., Rimkus, A., & Bausys, R. (2019). Internal Combustion Engine Analysis of Energy Ecological Parameters by Neutrosophic MULTIMOORA and SWARA Methods. Energies, 12(8). https://www.mdpi.com/1996-1073/12/8/1415
Zhang, S., & Li, X. (2021). Future projections of offshore wind energy resources in China using CMIP6 simulations and a deep learning-based downscaling method. Energy, 217, 119321. https://doi.org/https://doi.org/10.1016/j.energy.2020.119321 
Urban Economics and Planning
Volume 6, Issue 4
Winter 2026
Pages 88-109

  • Receive Date 07 August 2025
  • Revise Date 04 September 2025
  • Accept Date 06 September 2025