Due to the depletion of fossil fuels and environmental concerns, renewable energy has become increasingly popular. Even so, the economic competitiveness and cost of energy in renewable systems remain a challenge. Optimization of renewable energy systems from an economic standpoint is important not only from the point of view of researchers but also industry owners, stakeholders, and governments. Solar collectors are one of the most optimized and developed renewable energy systems. However, due to the high degree of nonlinearity and many unknowns associated with these systems, optimizing them is an extremely time-consuming and expensive process. This study presents an economically optimal design platform for solar power plants with a fast response time using machine learning techniques. Compared with traditional mathematical optimization, the speed of economic optimization with the help of the machine learning method increased by up to 1100 times. A total of seven continuous variables and three discrete variables were selected for optimization of the parabolic trough solar collector. The objective functions were to optimize the exergy efficiency and the heat cost. As part of the environmental assessment, the cost of carbon dioxide emission was calculated based on the system's exergy and energy efficiencies. According to the sensitivity analysis, the mass flow of working fluid and the initial temperature of the fluid play the most significant roles. A simulated solar collector in Calgary was optimized in order to evaluate the applicability of the proposed platform.
Citation: Ali Omidkar, Razieh Es'haghian, Hua Song. Developing a machine learning model for fast economic optimization of solar power plants using the hybrid method of firefly and genetic algorithms, case study: optimizing solar thermal collector in Calgary, Alberta[J]. Green Finance, 2024, 6(4): 698-727. doi: 10.3934/GF.2024027
Due to the depletion of fossil fuels and environmental concerns, renewable energy has become increasingly popular. Even so, the economic competitiveness and cost of energy in renewable systems remain a challenge. Optimization of renewable energy systems from an economic standpoint is important not only from the point of view of researchers but also industry owners, stakeholders, and governments. Solar collectors are one of the most optimized and developed renewable energy systems. However, due to the high degree of nonlinearity and many unknowns associated with these systems, optimizing them is an extremely time-consuming and expensive process. This study presents an economically optimal design platform for solar power plants with a fast response time using machine learning techniques. Compared with traditional mathematical optimization, the speed of economic optimization with the help of the machine learning method increased by up to 1100 times. A total of seven continuous variables and three discrete variables were selected for optimization of the parabolic trough solar collector. The objective functions were to optimize the exergy efficiency and the heat cost. As part of the environmental assessment, the cost of carbon dioxide emission was calculated based on the system's exergy and energy efficiencies. According to the sensitivity analysis, the mass flow of working fluid and the initial temperature of the fluid play the most significant roles. A simulated solar collector in Calgary was optimized in order to evaluate the applicability of the proposed platform.
[1] | Alawi OA, Kamar HM, Abdelrazek AH, et al. (2024) Design optimization of solar collectors with hybrid nanofluids: An integrated ansys and machine learning study. Sol Energ Mat Sol C 271: 112822. https://doi.org/https://doi.org/10.1016/j.solmat.2024.112822 doi: 10.1016/j.solmat.2024.112822 |
[2] | Alawi OA, Kamar HM, Salih SQ, et al. (2024) Development of optimized machine learning models for predicting flat plate solar collectors thermal efficiency associated with Al2O3-water nanofluids. Eng Appl Artif Intel 133: 108158. https://doi.org/https://doi.org/10.1016/j.engappai.2024.108158 doi: 10.1016/j.engappai.2024.108158 |
[3] | Ali B (2018) Forecasting model for water-energy nexus in Alberta, Canada. Water-Energy Nexus 1: 104–115. https://doi.org/10.1016/j.wen.2018.08.002 doi: 10.1016/j.wen.2018.08.002 |
[4] | Ashouri M, Khoshkar Vandani AM, Mehrpooya M, et al. (2015) Techno-economic assessment of a Kalina cycle driven by a parabolic Trough solar collector. Energ Convers Manage 105: 1328–1339. https://doi.org/https://doi.org/10.1016/j.enconman.2015.09.015 doi: 10.1016/j.enconman.2015.09.015 |
[5] | Azad Gilani H, Hoseinzadeh S (2021) Techno-economic study of compound parabolic collector in solar water heating system in the northern hemisphere. Appl Therm Eng 190: 116756. https://doi.org/https://doi.org/10.1016/j.applthermaleng.2021.116756 doi: 10.1016/j.applthermaleng.2021.116756 |
[6] | Badescu V (2018) How much work can be extracted from diluted solar radiation? Sol Energy 170: 1095-1100. https://doi.org/10.1016/j.solener.2018.05.094 doi: 10.1016/j.solener.2018.05.094 |
[7] | Barrington-Leigh C, Ouliaris M (2017) The renewable energy landscape in Canada: a spatial analysis. Renew Sust Energ Rev 75: 809–819. |
[8] | Bellos E, Tzivanidis C (2017) A detailed exergetic analysis of parabolic trough collectors. Energ Convers Manage 149: 275–292. |
[9] | Bergman TL (2011) Fundamentals of heat and mass transfer. John Wiley & Sons. |
[10] | Brenner A, Kahn J, Hirsch T, et al. (2023) Soiling determination for parabolic trough collectors based on operational data analysis and machine learning. Sol Energy 259: 257–276. https://doi.org/https://doi.org/10.1016/j.solener.2023.05.008 doi: 10.1016/j.solener.2023.05.008 |
[11] | Cuce PM, Cuce E (2023) Performance analysis of fresnel lens driven hot water/steam generator for domestic and industrial use: A CFD research. Hittite J Sci Eng 10: 1–9. https://doi.org/10.17350/HJSE19030000285 doi: 10.17350/HJSE19030000285 |
[12] | Cuce PM, Cuce E, Guclu T, et al. (2021) Energy saving aspects of green facades: Current applications and challenges. Green Build Constr Econ 2021: 18–28. https://doi.org/10.37256/gbce.2220211007 doi: 10.37256/gbce.2220211007 |
[13] | Cuce PM, Guclu T, Cuce E (2024) Design, modelling, environmental, economic and performance analysis of parabolic trough solar collector (PTC) based cogeneration systems assisted by thermoelectric generators (TEGs). Sustain Energy Techn 64: 103745. https://doi.org/https://doi.org/10.1016/j.seta.2024.103745 doi: 10.1016/j.seta.2024.103745 |
[14] | Deniz E, Çınar S (2016) Energy, exergy, economic and environmental (4E) analysis of a solar desalination system with humidification-dehumidification. Energ Convers Manage 126: 12–19. https://doi.org/10.1016/j.enconman.2016.07.064 doi: 10.1016/j.enconman.2016.07.064 |
[15] | Desai NB, Pranov H, Haglind F (2021) Techno-economic analysis of a foil-based solar collector driven electricity and fresh water generation system. Renew Energy 165: 642–656. https://doi.org/https://doi.org/10.1016/j.renene.2020.11.043 doi: 10.1016/j.renene.2020.11.043 |
[16] | Duffie JA, Beckman WA, Blair N (2020) Solar engineering of thermal processes, photovoltaics and wind. John Wiley & Sons. |
[17] | El-Shorbagy MA, El-Refaey AM (2022) A hybrid genetic–firefly algorithm for engineering design problems. J Comput Des Eng 9: 706–730. https://doi.org/10.1093/jcde/qwac013 doi: 10.1093/jcde/qwac013 |
[18] | Elfeky KE, Wang Q (2023) Techno-environ-economic assessment of photovoltaic and CSP with storage systems in China and Egypt under various climatic conditions. Renew Energy 215: 118930. https://doi.org/https://doi.org/10.1016/j.renene.2023.118930 doi: 10.1016/j.renene.2023.118930 |
[19] | Elsheikh A, Zayed M, Aboghazala A, et al. (2024) Innovative solar distillation system with prismatic absorber basin: Experimental analysis and LSTM machine learning modeling coupled with great wall construction algorithm. Process Saf Environ Prot 186: 1120–1133. https://doi.org/https://doi.org/10.1016/j.psep.2024.04.063 doi: 10.1016/j.psep.2024.04.063 |
[20] | Faizal M, Saidur R, Mekhilef S, et al. (2015) Energy, economic, and environmental analysis of a flat-plate solar collector operated with SiO2 nanofluid. Clean Technol Envir 17: 1457–1473. https://doi.org/10.1007/s10098-014-0870-0 doi: 10.1007/s10098-014-0870-0 |
[21] | Fister I, Fister Jr I, Yang XS, et al. (2013) A comprehensive review of firefly algorithms. Swarm Evol Comput 13: 34–46. https://doi.org/10.1016/j.swevo.2013.06.001 doi: 10.1016/j.swevo.2013.06.001 |
[22] | Forristall R (2003) Heat transfer analysis and modeling of a parabolic trough solar receiver implemented in engineering equation solver. |
[23] | Frangopoulos CA (1987) Thermo-economic functional analysis and optimization. Energy 12: 563–571. |
[24] | García-García JC, Ponce-Rocha JD, Marmolejo-Correa D, et al. (2019) Exergy analysis for energy integration in a bioethanol production process to determine heat exchanger networks feasibility. In A. A. Kiss, E. Zondervan, R. Lakerveld, & L. Özkan (Eds.), Computer Aided Chemical Engineering, 46: 475–480. Elsevier. https://doi.org/https://doi.org/10.1016/B978-0-12-818634-3.50080-1 |
[25] | Gnielinski V (1976) New equations for heat and mass transfer in turbulent pipe and channel flow. Int J Chem Eng 16: 359–367. |
[26] | Haykin S (1998) Neural networks: a comprehensive foundation. Prentice Hall PTR. |
[27] | Jehring L (1992) Bejan, A., Advanced Engineering Thermodynamics. New York etc., John Wiley & Sons 1988. XXIII, 758. ISBN 0‐471‐83043‐7, Wiley Online Library. |
[28] | Johari NF, Zain AM, Noorfa MH, et al. (2013) Firefly algorithm for optimization problem. Appl Mech Mater 421: 512–517. |
[29] | Kalogirou SA (2004) Solar thermal collectors and applications. Prog Energ Combust Sci 30: 231–295. https://doi.org/10.1016/j.pecs.2004.02.001 doi: 10.1016/j.pecs.2004.02.001 |
[30] | Kottala RK, Balasubramanian KR, Jinshah BS, et al. (2023) Experimental investigation and machine learning modelling of phase change material-based receiver tube for natural circulated solar parabolic trough system under various weather conditions. J Therm Anal Calorim 148: 7101–7124. https://doi.org/10.1007/s10973-023-12219-9 doi: 10.1007/s10973-023-12219-9 |
[31] | Landsberg P, Mallinson J (1976) Thermodynamic constraints, effective temperatures and solar cells. International Conference on Solar Electricity. |
[32] | Mazen F, AbulSeoud RA, Gody AM (2016) Genetic algorithm and firefly algorithm in a hybrid approach for breast cancer diagnosis. Int J Comput Trends Tech 32: 62–68. |
[33] | Mehdipour R, Baniamerian Z, Golzardi S, et al. (2020) Geometry modification of solar collector to improve performance of solar chimneys. Renew Energy 162: 160–170. https://doi.org/https://doi.org/10.1016/j.renene.2020.07.151 doi: 10.1016/j.renene.2020.07.151 |
[34] | Mustafa J, Alqaed S, Sharifpur M (2022) Numerical study on performance of double-fluid parabolic trough solar collector occupied with hybrid non-Newtonian nanofluids: Investigation of effects of helical absorber tube using deep learning. Eng Anal Bound Elem 140: 562–580. https://doi.org/https://doi.org/10.1016/j.enganabound.2022.04.033 doi: 10.1016/j.enganabound.2022.04.033 |
[35] | Nguyen HM, Omidkar A, Li W, et al. (2023) Non-thermal plasma assisted catalytic nitrogen fixation with methane at ambient conditions. Chem Eng J 471: 144748. https://doi.org/https://doi.org/10.1016/j.cej.2023.144748 doi: 10.1016/j.cej.2023.144748 |
[36] | Omidkar A, Alagumalai A, Li Z, et al. (2024) Machine learning assisted techno-economic and life cycle assessment of organic solid waste upgrading under natural gas. Appl Energy 355: 122321. https://doi.org/https://doi.org/10.1016/j.apenergy.2023.122321 doi: 10.1016/j.apenergy.2023.122321 |
[37] | Omidkar A, Haddadian K, Es'haghian R, et al. (2024) Novel energy efficient in-situ bitumen upgrading technology to facilitate pipeline transportation using natural gas: Sustainability evaluation using a new hybrid approach based on fuzzy multi-criteria decision-making tool and techno-economic and life cycle assessment. Energy 297: 131280. https://doi.org/https://doi.org/10.1016/j.energy.2024.131280 doi: 10.1016/j.energy.2024.131280 |
[38] | Omidkar A, Xu H, Li Z, et al. (2023) Techno-economic and life cycle assessment of renewable diesel production via methane-assisted catalytic waste cooking oil upgrading. J Clean Prod 414: 137512. https://doi.org/https://doi.org/10.1016/j.jclepro.2023.137512 doi: 10.1016/j.jclepro.2023.137512 |
[39] | Pal RK, K RK (2021) Investigations of thermo-hydrodynamics, structural stability, and thermal energy storage for direct steam generation in parabolic trough solar collector: A comprehensive review. J Clean Product 311: 127550. https://doi.org/https://doi.org/10.1016/j.jclepro.2021.127550 doi: 10.1016/j.jclepro.2021.127550 |
[40] | Patel S, Parkins JR (2023) Assessing motivations and barriers to renewable energy development: Insights from a survey of municipal decision-makers in Alberta, Canada. Energy Rep 9: 5788–5798. |
[41] | Pourasl HH, Barenji RV, Khojastehnezhad VM (2023) Solar energy status in the world: A comprehensive review. Energy Rep 10: 3474–3493. https://doi.org/https://doi.org/10.1016/j.egyr.2023.10.022 doi: 10.1016/j.egyr.2023.10.022 |
[42] | Ruiz-Moreno S, Sanchez AJ, Gallego AJ, et al. (2022) A deep learning-based strategy for fault detection and isolation in parabolic-trough collectors. Renew Energy 186: 691–703. https://doi.org/https://doi.org/10.1016/j.renene.2022.01.029 doi: 10.1016/j.renene.2022.01.029 |
[43] | Salari A, Shakibi H, Soltani S, et al. (2024) Optimization assessment and performance analysis of an ingenious hybrid parabolic trough collector: A machine learning approach. Appl Energy 353: 122062. https://doi.org/https://doi.org/10.1016/j.apenergy.2023.122062 doi: 10.1016/j.apenergy.2023.122062 |
[44] | Shafieian A, Parastvand H, Khiadani M (2020) Comparative and performative investigation of various data-based and conventional theoretical methods for modelling heat pipe solar collectors. Sol Energy 198: 212–223. https://doi.org/https://doi.org/10.1016/j.solener.2020.01.056 doi: 10.1016/j.solener.2020.01.056 |
[45] | Shboul B, Zayed ME, Al-Tawalbeh N, et al. (2024) Dynamic numerical modeling and performance optimization of solar and wind assisted combined heat and power system coupled with battery storage and sophisticated control framework. Results Eng 22: 102198. https://doi.org/https://doi.org/10.1016/j.rineng.2024.102198 doi: 10.1016/j.rineng.2024.102198 |
[46] | Shboul B, Zayed ME, Tariq R, et al. (2024) New hybrid photovoltaic-fuel cell system for green hydrogen and power production: Performance optimization assisted with Gaussian process regression method. Int J Hydrogen Energ 59: 1214–1229. https://doi.org/https://doi.org/10.1016/j.ijhydene.2024.02.087 doi: 10.1016/j.ijhydene.2024.02.087 |
[47] | Sultan AJ, Hughes KJ, Ingham DB, et al. (2020) Techno-economic competitiveness of 50 MW concentrating solar power plants for electricity generation under Kuwait climatic conditions. Renew Sust Energ Rev 134: 110342. https://doi.org/10.1016/j.rser.2020.110342 doi: 10.1016/j.rser.2020.110342 |
[48] | Tabarhoseini SM, Sheikholeslami M, Said Z (2022) Recent advances on the evacuated tube solar collector scrutinizing latest innovations in thermal performance improvement involving economic and environmental analysis. Sol Energ Mat Sol C 241: 111733. https://doi.org/https://doi.org/10.1016/j.solmat.2022.111733 doi: 10.1016/j.solmat.2022.111733 |
[49] | Vakili M, Salehi SA (2023) A review of recent developments in the application of machine learning in solar thermal collector modelling. Environ Sci Pollut Res 30: 2406–2439. https://doi.org/10.1007/s11356-022-24044-y doi: 10.1007/s11356-022-24044-y |
[50] | Vapnik VN (1999) An overview of statistical learning theory. Ieee T Neural Networ 10: 988–999. |
[51] | Wahid F, Alsaedi AKZ, Ghazali R (2019) Using improved firefly algorithm based on genetic algorithm crossover operator for solving optimization problems. J Intell Fuzzy Syst 36: 1547–1562. https://doi.org/10.3233/JIFS-181936 doi: 10.3233/JIFS-181936 |
[52] | Wahid F, Ghazali R, Ismail LH (2019) Improved firefly algorithm based on genetic algorithm operators for energy efficiency in smart buildings. Arab J Sci Eng 44: 4027–4047. https://doi.org/10.1007/s13369-019-03759-0 doi: 10.1007/s13369-019-03759-0 |
[53] | Wang Y, Kandeal AW, Swidan A, et al. (2021) Prediction of tubular solar still performance by machine learning integrated with Bayesian optimization algorithm. Appl Therm Eng 184: 116233. https://doi.org/https://doi.org/10.1016/j.applthermaleng.2020.116233 doi: 10.1016/j.applthermaleng.2020.116233 |
[54] | Wu S, Wang C, Tang R (2022) Optical efficiency and performance optimization of a two-stage secondary reflection hyperbolic solar concentrator using machine learning. Renew Energy 188: 437–449. https://doi.org/https://doi.org/10.1016/j.renene.2022.01.117 doi: 10.1016/j.renene.2022.01.117 |
[55] | Yang XS (2010) Firefly algorithm, stochastic test functions and design optimisation. Int J Bio-Inspir Com 2: 78–84. https://doi.org/10.1504/IJBIC.2010.032124 doi: 10.1504/IJBIC.2010.032124 |
[56] | Zayed ME, Aboelmaaref MM, Chazy M (2023a) Design of solar air conditioning system integrated with photovoltaic panels and thermoelectric coolers: Experimental analysis and machine learning modeling by random vector functional link coupled with white whale optimization. Therm Sci Eng Prog 44: 102051. https://doi.org/https://doi.org/10.1016/j.tsep.2023.102051 doi: 10.1016/j.tsep.2023.102051 |
[57] | Zayed ME, Kabeel AE, Shboul B, et al. (2023b) Performance augmentation and machine learning-based modeling of wavy corrugated solar air collector embedded with thermal energy storage: Support vector machine combined with Monte Carlo simulation. J Energy Storage 74: 109533. https://doi.org/https://doi.org/10.1016/j.est.2023.109533 doi: 10.1016/j.est.2023.109533 |
[58] | Zayed ME, Zhao J, Li W, et al. (2021) Predicting the performance of solar dish Stirling power plant using a hybrid random vector functional link/chimp optimization model. Solar Energy 222: 1–17. https://doi.org/https://doi.org/10.1016/j.solener.2021.03.087 doi: 10.1016/j.solener.2021.03.087 |