article · Energy Exploration & Exploitation
Photovoltaic power plants in desert environments experience continuous efficiency losses because dust accumulation reduces the solar radiation reaching panel surfaces. Distinguishing genuine operational faults from natural weather variations requires accurate prediction of normal system behaviour. A data-driven framework was tested at the Aoulef photovoltaic plant in southern Algeria, using artificial neural networks and adaptive neuro-fuzzy inference systems to predict healthy power output from measured solar irradiance and ambient temperature. Operational faults were detected using residuals between measured and predicted power. Both models achieved coefficients of determination near 0.99, but the neural network delivered lower error rates, with a root mean square error of 0.009 and a mean absolute error of 0.004. This sensitivity allowed dust accumulation to be detected automatically without interrupting plant operations, demonstrating an accurate, low-computation monitoring method.
Dust accumulation severely degrades solar panel performance in desert installations, where harsh conditions make maintenance challenging. Traditional troubleshooting often requires shutting down equipment or struggling to separate environmental effects from true mechanical faults. By predicting healthy baseline output from basic weather data, operators can identify performance issues automatically and maintain continuous energy generation without costly interruptions.
The method could be used by solar plant operators, maintenance contractors, and condition-monitoring software vendors operating in arid climates. The framework represents an applied and tested solution validated on real operating data from the Aoulef plant. Because it relies on standard temperature and irradiance measurements and has low computational requirements, it is suited for integration into commercial supervisory control and data acquisition systems to guide cleaning schedules.
AI-generated from the published abstract. Always read the original work before citing.
Photovoltaic (PV) power plants operating in desert environments experience continuous efficiency losses because dust accumulation gradually reduces solar radiation reaching the module surface, leading to lower energy production even under favourable weather conditions. Accurate prediction of normal operating behaviour therefore provides a reference for distinguishing genuine faults from natural fluctuations in plant performance. This study proposes a data-driven framework for PV power prediction and residual-based fault diagnosis at the Aoulef PV power plant in southern Algeria. Artificial neural networks (ANN) and adaptive neuro-fuzzy inference systems (ANFIS) were developed from measured solar irradiance and ambient temperature to estimate the healthy-state PV power output. Model performance was assessed through regression analysis and statistical error indices, whereas fault detection relied on residuals computed from the difference between measured and predicted power. Both models achieved excellent prediction accuracy, with coefficients of determination approaching 0.99. The ANN produced lower prediction errors than the ANFIS, with a root mean square error of 0.009 and an mean absolute error of 0.004, which improved the sensitivity of the residual-based diagnosis. Dust accumulation, identified as fault F13, generated clear residual deviations that enabled automatic fault detection without interrupting plant operation. The findings indicate that the ANN framework combines high predictive accuracy with low computational demand, offering a practical and reliable solution for intelligent monitoring and maintenance of PV systems operating under harsh desert conditions.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1177/01445987261480391
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
