Search

Anomaly detection is indispensable for ensuring the reliable operation of grid-connected photovoltaic (PV) systems. This study introduces a semi-supervised deep learning approach for fault detection in such systems. The method leverages a variational autoencoder (VAE) to extract features and identify anomalies. By training the VAE on normal operation data, a compact latent space representation is created. Abnormal observations, indicating faults, exhibit distinct feature vectors in this latent space. Multiple anomaly detection algorithms, including Isolation Forest, Epileptic Envelope, Local Outlier Factor, and One-Class SVM, are employed to discern normal and abnormal observations. This semi-supervised approach only requires fault-free data for training, without labeled faults, making it attractive in practice. A publicly available dataset, the Grid-connected PV System Faults (GPVS-Faults) dataset, which includes data from a PV plant operating in both maximum power point tracking (MPPT) and intermediate power point tracking (IPPT) switching modes, is used for evaluation. The proposed approach is assessed across various fault scenarios, such as partial shading, inverter faults, and MPPT/IPPT controller faults in boost converters. The outcomes underscore the effectiveness of VAE-based techniques in accurately identifying these faults, with accuracy rates reaching up to 92.90% for MPPT mode and 92.99% for IPPT mode, thus contributing to the robustness of fault detection in grid-connected PV systems. • Anomaly detection is crucial for reliable grid-connected PV systems. • Developed semi-supervised anomaly detection for reliable operation of PV systems. • Introduced Variational Autoencoder (VAE) for feature extraction and anomaly detection. • Effectiveness of VAE-based methods in detecting faults under MPPT and IPPT modes, achieving high AUC and F1-scores. • A publicly available dataset, GPVS-Faults, validate the VAE-based anomaly detectors. [ABSTRACT FROM AUTHOR]

Highlights • Developed a clustering-based approach for anomaly detection in photovoltaic systems. • Real data from a photovoltaic system is used to evaluate the performances of the developed approach. • The results show the superior performance of the proposed approach over other five binary clustering schemes. Abstract One of the greatest challenges in a photovoltaic solar power generation is to keep the designed photovoltaic systems working with the desired operating efficiency. Towards this goal, fault detection in photovoltaic plants is essential to guarantee their reliability, safety, and to maximize operating profitability and avoid expensive maintenance. In this context, a model-based anomaly detection approach is proposed for monitoring the DC side of photovoltaic systems and temporary shading. First, a model based on the one-diode model is constructed to mimic the characteristics of the monitored photovoltaic array. Then, a one-class Support Vector Machine (1SVM) procedure is applied to residuals from the simulation model for fault detection. The choice of 1SVM approach to quantify the dissimilarity between normal and abnormal features is motivated by its good capability to handle nonlinear features and do not make assumptions on the underlying data distribution. Experimental results over real data from a 9.54 kWp grid-connected plant in Algiers, show the superior detection efficiency of the proposed approach compared with other binary clustering schemes (i.e., K-means, Birch, mean-shift, expectation–maximization, and agglomerative clustering). [ABSTRACT FROM AUTHOR]

• Unsupervised deep learning strategy developed to monitor influent characteristics (ICs) in WWTP. • This system combines the advantages of a RNN-RBM model and clustering algorithms. • Seven-years historical data involved to verify the deep learning-based strategy approach. • Saudi Arabian coastal municipal WWTP investigated to serve the case study. • Results show that the proposed method has good ability in monitoring ICs of WWTPs. Wastewater treatment plants (WWTPs) are sustainable solutions to water scarcity. As initial conditions offered to WWTPs, influent conditions (ICs) affect treatment units states, ongoing processes mechanisms, and product qualities. Anomalies in ICs, often raised by abnormal events, need to be monitored and detected promptly to improve system resilience and provide smart environments. This paper proposed and verified data-driven anomaly detection approaches based on deep learning methods and clustering algorithms. Combining both the ability to capture temporal auto-correlation features among multivariate time series from recurrent neural networks (RNNs), and the function to delineate complex distributions from restricted Boltzmann machines (RBM), RNN-RBM models were employed and connected with various classifiers for anomaly detection. The effectiveness of RNN based, RBM based, RNN-RBM based, or standalone individual detectors, including expectation maximization clustering, K-means clustering, mean-shift clustering, one-class support vector machine (OCSVM), spectral clustering, and agglomerative clustering algorithms were evaluated by importing seven years ICs data from a coastal municipal WWTP where more than 150 abnormal events occurred. Results demonstrated that RNN-RBM-based OCSVM approach outperformed all other scenarios with an area under the curve value up to 0.98, which validated the superiority in feature extraction by RNN-RBM, and the robustness in multivariate nonlinear kernels by OCSVM. The model was flexible for not requiring assumptions on data distribution, and could be shared and transferred among environmental data scientists. [ABSTRACT FROM AUTHOR]