Abstract
The growing demand for renewable energy has led to increased adoption of photovoltaic (PV) systems. However, their efficiency and reliability are significantly affected by partial shading conditions (PSCs), which cause power losses and fault occurrences. Traditional fault detection methods often fail to provide accurate and timely identification of shading-induced issues. To address this challenge, metaheuristic techniques have emerged as effective solutions due to their optimization capabilities in complex, nonlinear environments. This review explores various metaheuristic-based fault detection methods for PV systems under PSCs, analysing their effectiveness, advantages, and limitations. Key algorithms such as Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Differential Evolution (DE), Ant Colony Optimization (ACO), and Artificial Bee Colony (ABC) are discussed, emphasizing their roles in improving fault detection accuracy. Additionally, hybrid approaches integrating machine learning and metaheuristic algorithms are reviewed to assess their potential in enhancing fault diagnosis. The study aims to provide insights into the most efficient metaheuristic techniques for fault detection, emphasizing their application in real-time PV system monitoring. Future research directions and challenges in implementing these techniques are also outlined to facilitate further advancements in PV fault detection methodologies.
References
- Pillai, D. S., & Rajasekar, N. (2018). Metaheuristic algorithms for PV parameter identification: A comprehensive review with an application to threshold setting for fault detection in PV systems. Renewable and Sustainable Energy Reviews, 82, 3503-3525.
- Manjunath, T. G., & Kusagur, A. (2018). Analysis of different metaheuristics method in intelligent fault detection of multilevel inverter with photovoltaic power generation source. International Journal of Power Electronics and Drive Systems, 9(3), 1214-1222.
- Pandian, P. S., Denosha, T. G., Kumar, R. S., & Sivaiah, B. V. (2024). Real-time fault detection in solar PV systems using hybrid ANN–SVM machine learning algorithm. International Journal of Intelligent Systems and Applications in Engineering, 12(22s), 1367–1374.
- Li, K., Zhang, J., He, Y., Xie, Y., Liu, J., & Chen, Q. (2019). A fault diagnosis method of PV arrays based on improved deep belief network. IEEE Access, 7, 156167-156178.
- Wang, Junjie, Dedong Gao, Shaokang Zhu, Shan Wang, and Haixiong Liu. "Fault diagnosis method of photovoltaic array based on support vector machine." Energy sources, part a: recovery, utilization, and environmental effects 45, no. 2 (2023): 5380-5395.
- Ali, Mohamed Hassan, Abdelhamid Rabhi, Ahmed El Hajjaji, and Giuseppe M. Tina. "Real time fault detection in photovoltaic systems." Energy Procedia 111 (2017): 914-923.
- Aghaei, Mohammadreza, M. Kolahi, Amir Nedaei, N. S. Venkatesh, Sayyed Majid Esmailifar, A. M. Moradi Sizkouhi, A. Aghamohammadi et al. "Autonomous Intelligent Monitoring of Photovoltaic Systems: An In‐Depth Multidisciplinary Review." Progress in Photovoltaics: Research and Applications 33, no. 3 (2025): 381-409.
- Liu, D., & Sun, K. (2019). Random forest solar power forecast based on classification optimization. Energy, 187, 1.
- Afifi, S., Hosseini, H. G., & Sinha, R. (2018). A system on chip for melanoma detection using FPGA-based SVM classifier. Microprocessors and Microsystems.
- Ba, Abdellahi, Chighali Ould Ehssein, Mouhamed El Mamy Ould Mouhamed Mahmoud, Ouafae Hamdoun, and Aroudam Elhassen. "Comparative study of different DC/DC power converter for optimal PV system using MPPT (P&O) method." Applied Solar Energy 54 (2018): 235-245.
- Kheirrouz, Mahdi, Francesco Melino, and Maria Alessandra Ancona. "Fault detection and diagnosis methods for green hydrogen production: A review." International Journal of Hydrogen Energy 47, no. 65 (2022): 27747-27774.