The performance of photovoltaic systems is highly dependent on environmental conditions, with soiling due to dust accumulation often being referred to as a predominant energy degradation factor, especially in dry and semi-arid environments. This paper introduces an AI-based robotic cleaning system that can independently forecast and schedule cleaning sessions from real-time sensor and environmental data. Methods: The system integrates sources of data like embedded sensors, weather stations, and DustIQ data to create an integrated dataset for predictive modeling. Machine learning models were employed to forecast soiling loss based on significant atmospheric parameters such as relative humidity, air pressure, ambient temperature, and wind speed. Dimensionality reduction through the principal component analysis and correlation-based feature selection enhanced the model performance as well as the interpretability. A comparative study of four conventional machine learning models, including logistic regression, k-nearest neighbors, decision tree, and support vector machine, was conducted to determine the most appropriate approach to classifying cleaning needs. Results: Performance, based on accuracy, precision, recall, and F1-score, demonstrated that logistic regression and SVM provided optimal classification performance with accuracy levels over 92%, and F1-scores over 0.90, demonstrating outstanding balance between recall and precision. The KNN and decision tree models, while slightly poorer in terms of accuracy (around 85–88%), had computational efficiency benefits, making them suitable for utilization in resource-constrained applications. Conclusions: The proposed system employs a dry-cleaning mechanism that requires no water, making it highly suitable for arid regions. It reduces unnecessary cleaning operations by approximately 30%, leading to decreased mechanical wear and lower maintenance costs. Additionally, by minimizing delays in necessary cleaning, the system can improve annual energy yield by 3–5% under high-soiling conditions. Overall, the intelligent cleaning schedule minimizes manual intervention, enhances sustainability, reduces operating costs, and improves system performance in challenging environments.

This study investigates the impact of data augmentation on predictive maintenance machine learning models for robot solar panel cleaning. Data augmentation techniques like synthetic data generation, time-series transformation (shifting, interpolation, and resampling), and extreme condition simulation were used to enhance data diversity and model generalization. Machine learning algorithms, including logistic regression, support vector machines, deep learning, and ensemble learning, were compared to identify their sensitivity to these techniques. Our experimental findings show that ensemble models (stacking and boosting) show the maximum improvement in predictive accuracy with the added benefit of higher diversity and strength in features. Deep learning models show moderate gains primarily in feature extraction, and simple models such as logistic regression show little impact, indicating the model-dependent effectiveness of data augmentation. Despite better generalization, ensemble methods are at the expense of increased computational cost, indicating a trade-off between accuracy and efficiency. The study employs widely used machine learning frameworks and libraries for data preprocessing, augmentation, model training, and evaluation, ensuring robust and scalable implementation.

This paper assesses the features/characteristics of a photovoltaic system’s data, investigates the relationship between the soiling and solar panel performance, and leverages real-world data obtained from a solar site in Shams Solar Facility located at the German University of Technology in Oman. Through an experimental approach, different parameters were scrutinized to unravel the dynamics at play. Due to the lack of studies on how to assess the features of a PV System’s data, and in order to model the PV System’s data, extensive analyses were conducted based on a big dataset containing 36,851 observations of each parameter (environmental factors) of the study. In addition, diverse environmental factors, operational conditions, and the collected data were analyzed by various mathematical/statistical measures, and inferential statistical measures were applied to obtain accurate and significant results that explain the level of each parameter (environmental factors), and are developed to examine the features/characteristics and performance of PV Systems and reveal the influence of soiling accumulation on the energy output. The research findings do not only deepen the understanding of the features of PV Systems data and the impact of soiling on solar panels, but also underscore the significance of considering geographical and climatic variations. This research contributes significantly to advancing knowledge within the realm of solar energy systems and provides actionable insights for optimizing the performance and reliability of PV installations in real-world settings. The discussion, conclusions, limitations, and future directions have been discussed.

Solar photovoltaic technology has become a cornerstone of the renewable energy sector over the last 20 years, yet its efficiency remains sensitive to environmental and operational conditions. This study rigorously analyzes how irradiance, temperature, humidity, wind speed, and soiling affect key electrical outputs—Direct current, power, and voltage—of solar panels using advanced robust regression methods: Ridge Regression, Least Absolute Deviation, and M-Estimation. Our results demonstrate that irradiance is the dominant driver of performance, with Ridge Regression coefficients reaching up to 1193 for power. The M-estimation model achieved high predictive accuracy, with R² Scores of 0.989 for current (Mean Squared Error = 0.0399) and 0.991 for power (Mean Squared Error ≈ 10,445), indicating strong model reliability. voltage prediction was more challenging but still robust (R² = 0.836, Mean Squared Error = 49.63). Negative impacts from ambient temperature and humidity were consistently observed across models, while wind speed exhibited a beneficial effect by enhancing cooling and thus improving current and power outputs. Soiling was also identified as a critical factor, significantly reducing power and voltage generation. These findings provide quantifiable evidence of how environmental variables shape solar photovoltaic performance and underscore the importance of environmental monitoring and maintenance strategies to optimize energy yield in operational solar power systems.

This paper focuses on the modeling of the performance of photovoltaic systems based on advanced techniques. This research leverages real-world data from the Shams Solar Facility at the German University of Technology in Oman to explore the application of Linear, Lasso, Ridge, and Elastic Net Regressions to predict and optimize the performance of photovoltaic systems. A comprehensive dataset of 36,851 observations of environmental and operational conditions forms the basis of the analysis. The research identifies the strengths and limitations of these modeling techniques for an accurate forecast of energy output under various scenarios. The comparative analysis highlights the precision and reliability of each regression method and offers actionable insights into their practical implementation. The findings highlight the importance of more sophisticated modeling approaches in increasing the knowledge of photovoltaic system dynamics and optimizing their performance. This research facilitates the advancement in solar energy systems and provides critical recommendations for the improvement in efficiency and reliability of photovoltaic installations under different geographic and climatic settings.