Artificial Intelligence and Computational Optimization in Solar Energy Systems: A Survey of Single and Multi-Objective Methods
DOI:
https://doi.org/10.63282/3050-9246.IJETCSIT-V6I3P102Keywords:
Solar energy, Optimization techniques, Single-objective optimization, Multi-objective optimization, Photovoltaic systems, Artificial intelligenceAbstract
To increase the sustainability, affordability, and efficiency of renewable energy sources, solar energy systems must be optimized. As solar energy continues to gain prominence in international energy regulations, the need for sophisticated optimization approaches has become evident. This paper provides a comprehensive evaluation of single-objective and multi-objective optimization techniques utilized in solar energy systems. This evaluation aims to shed light on the critical role optimization plays in achieving optimal system performance and operational effectiveness by carefully analyzing the approaches, advantages, and challenges of each technique.In order to demonstrate how optimization strategies operate for a variety of solar technologies, including hybrid solar systems, photovoltaic (PV) systems, and solar thermal systems, the study compiles recent research and case studies. In contrast to single-objective optimization methods, which focus on optimizing a single criterion, such as energy output or cost, the study also looks at the drawbacks and trade-offs of multi-objective optimization techniques, which consider multiple, often incompatible goals at once, such as maximizing energy output while minimizing cost and environmental impact.
The survey explores the evolving subject of solar energy system optimization in further detail, including recent advancements such as the use of artificial intelligence (AI), machine learning, and digital twin technologies. These advancements have the potential to significantly improve the adaptability and efficiency of optimization processes in real-time applications. The paper ends by listing a number of important challenges, including the requirement for more comprehensive models that take into account computational complexity in addition to social, environmental, and economic factors.
The findings of the review are meant to act as a guide for future research and development in the area of solar energy optimization, establishing the framework for the development of more cost-effective, efficient, and sustainable solar energy systems.Keywords: artificial intelligence, photovoltaic systems, solar energy, optimization methods, single-objective optimization, and multi-objective optimization.
Downloads
References
[1] Fettah, B., & Pasaoglu, G. (2024). Optimization techniques for renewable energy systems: A comprehensive review. Renewable and Sustainable Energy Reviews, 140, 110715.
[2] Hossain, M. S., & Ali, M. (2021). Optimization Techniques for Solar Power Systems: A Review of Current Trends. Renewable Energy Reviews, 134, 256–274.
[3] Launay, C., & Gosselin, F. (2019). Optimization of solar thermal power systems using improved particle swarm optimization. Energy Procedia, 157, 568–575.
[4] Vargas, R., & Alvarez, D. (2017). Optimization of photovoltaic systems in urban environments. Solar Energy, 151, 50-60.
[5] Zhao, H., & Liu, Y. (2020). A Review of Multi-Objective Optimization Methods in Solar Power System Design. Journal of Solar Energy Engineering, 142(5), 051006.
[6] Niu, Z., & Zhao, Z. (2019). Cost minimization strategies for concentrated solar power systems. Renewable Energy, 132, 987-998.
[7] Mohammadi, K., & Shayanfar, H. A. (2022). Hybrid Approaches to Optimization in Solar Energy Systems. Renewable and Sustainable Energy Reviews, 153, 111772.
[8] Cao, X., et al. (2024). Genetic algorithms for optimizing solar thermal energy systems. Energy Reports, 10, 140–150.
[9] Ming, L., & Xie, X. (2023). Multi-objective optimization for hybrid renewable energy systems. Energy Reports, 9, 210-220.
[10] Vaish, P., & Patel, P. (2023). Multi-objective optimization for operational planning in renewable-powered microgrids. Energy, 263, 124739.
[11] Ferreira, F., & Silva, P. (2020). Integrating forecasting in renewable energy systems for improved optimization. Renewable Energy, 143, 234-246.
[12] Khan, M. J., & Iqbal, M. T. (2020). Computational Methods in Solar Energy System Optimization. Solar Energy, 202, 150–168.
[13] Chakraborty, P., & Saha, S. K. (2021). Multi-Objective Optimization in Solar Thermal Systems: Techniques and Applications. Energy Conversion and Management, 227, 113591.
[14] Mollah, M. B., & Tushar, S. (2021). Optimization of Solar Photovoltaic and Hybrid Systems using Genetic Algorithms and Particle Swarm Optimization. Renewable Energy, 163, 159–175.
[15] Deb, K., Pratap, A., Agarwal, S., & Meyarivan, T. (2002). A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation, 6(2), 182–197.
[16] Talbi, E.-G. (2009). Metaheuristics: From design to implementation. John Wiley & Sons.
[17] Marler, R. T., & Arora, J. S. (2004). Survey of multi-objective optimization methods for engineering. Structural and Multidisciplinary Optimization, 26(6), 369–395.
[18] Zhang, X., & Wang, L. (2022). Recent advances and research gaps in the optimization of solar photovoltaic systems. Renewable and Sustainable Energy Reviews, 153, 111773.
[19] Hassan, M. A., & Elhassan, E. A. (2023). Challenges and future directions in the integration of AI-based optimization for renewable energy systems. Energy Reports, 9, 1450–1465.
[20] Kumar, A., & Singh, R. (2021). A systematic review on optimization techniques in solar energy systems. Renewable Energy Reviews, 150, 111458.
[21] Smith, J., & Lee, H. (2020). Selection criteria and methodologies in energy optimization literature surveys. Journal of Cleaner Production, 270, 122414.
[22] Boyd, S., & Vandenberghe, L. (2004). Convex Optimization. Cambridge University Press.
[23] Bejan, A. (2016). Advanced Engineering Thermodynamics
[24] Wang, J., & Shahidehpour, M. (2017). Optimization Techniques for Renewable Energy Systems: A Review. Renewable and Sustainable Energy Reviews, 77, 211-224. https://doi.org/10.1016/j.rser.2017.03.045
