Dropout and Pruned Neural Networks for Fault Classification in Photovoltaic Arrays

Rao, Sunil; Muniraju, Gowtham; Tepedelenlioğlu, Cihan; Srinivasan, Devarajan; TamizhMani, GovindaSamy; Spanias, Andreas

doi:10.1109/access.2021.3108684

Cited by 27 publications

(8 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our method adopts a novel strategy that leverages learned patterns of irradiances to guide switching. Our method offers high inference time speeds as evaluating such a DNN with test-time feature vectors is significantly faster [40]. Other existing approaches [3], [25] rely on the use of externally connected unshaded additional panels or sophisticated panel interconnection schemes to perform reconfiguration and mitigate shading.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Optimizing Solar Power Using Array Topology Reconfiguration With Regularized Deep Neural Networks

et al. 2023

Self Cite

View full text Add to dashboard Cite

Reconfiguring photovoltaic (PV) array connections among different topologies such as seriesparallel, bridge-link, honeycomb, or total-cross-tied is a popular strategy to mitigate impediments in power production caused by partial shading. Conventional approaches rely on either by-passing or replacing shaded modules with auxiliary panels through complex control mechanisms, optimization strategies, or simulator driven approaches to obtain the best topology. However, these solutions are not scalable and incur significant installation costs and computational overhead, motivating the need to develop 'smart' methods for topology reconfiguration. To this end, we propose a regularized neural network based algorithm that leverages panel-level sensor data to reconfigure the array to the topology that maximizes power output under arbitrary shading conditions. Based on our simulations that include wiring losses in different configurations, we observe power improvement of up to 11% through reconfiguration. The proposed algorithm can be easily integrated in any cyber-physical PV system with reconfiguration capabilities and is scalable.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Neural networks have produced state-of-the-art performance in a variety of applications including PV array fault detection [40], [41], [42]. In this work, we design a six-layered, feed-forward DNN with dropout [14], and batchnorm [15] to perform topology reconfiguration.…”

Section: Design Of the Regularized Neural Networkmentioning

confidence: 99%

Optimizing Solar Power Using Array Topology Reconfiguration With Regularized Deep Neural Networks

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…It was established that the most appropriate supervised machine learning technique would be Neural Networks, which were used in works such as [36] and other cases with Deep Neural Networks [37]. In the present study, an average prediction of 90.12% was found in an execution time of 0.02 seconds; it was also the one that best suited the type of prediction that was executed in this investigation since neural networks create their interpretation of their information inside and are more robust to fault tolerance and flexible when the input data may present changes that are not so significant.…”

Section: Discussionmentioning

confidence: 99%

Supervised Machine Learning Techniques for the Prediction of the State of Charge of Batteries in Photovoltaic Systems in the Mining Sector

Pinto¹,

Tejada²,

Lopez-Casaperalta³

et al. 2022

IEEE Access

View full text Add to dashboard Cite

One of the critical aspects in the mining sector is energy, being of great importance for the operation since if it were to stop, one of the consequences would be the loss of large amounts of money. The research objective is to predict the State of Charge of Batteries of equipment powered by photovoltaic solar panels in the mining sector based on automatic supervised learning techniques. A monitoring system records each energy variable programmed in the photovoltaic system, for which an analysis of the data extracted from the monitoring system was carried out. The data were evaluated using automatic supervised learning techniques using the RapidMiner tool, whose prediction average was 90.12%. The technique of automatic supervised learning of artificial neural networks was chosen to predict the state of charge of batteries for photovoltaic systems. A software tool was built with the neural network. The analysis and discussion of the results of the training of the model were carried out, the contribution of this research being to determine the prediction of the state of charge of batteries in photovoltaic systems in the mining sector using techniques of supervised machine learning which was the neural network. Finally, with the model correctly trained, validation was carried out that allowed comparing the predictive data with the data in realtime, obtaining a good relationship and satisfactory results.

show abstract

“…2. Reducing Maintenance Costs and Downtime: Using automated fault detection systems can effectively reduce potential problems, reducing the need for manual inspections, limiting system downtime, and lowering maintenance costs at the same time [12].…”

Section: Improving Solar Panel Efficiency and Reliabilitymentioning

confidence: 99%

Comparative Analysis of Machine Learning Techniques for Fault Detection in Solar Panel Systems

Abdelsattar Mohamed Saeed,

Rasslan,

Emad-Eldeen

2024

SVU-International Journal of Engineering Sciences and Applicati

View full text Add to dashboard Cite

The utilization of Machine Learning (ML) classifiers offers a viable approach to improving diagnostic accuracy and system dependability in the pursuit of optimizing problem detection in solar panel systems. This work aims to conduct a thorough assessment of different Machine Learning (ML) classifiers in order to determine the most efficient models for detecting faults in solar panel systems. We rigorously tested and analyzed the classifiers AdaBoost, GaussianNB, Logistic Regression, Support Vector Classifier (SVC), Multi-Layer Perceptron (MLP), Decision Tree (DT), K-Nearest Neighbors (KNN), Random Forest (RF), and Extra Trees (ET). We evaluated the classifiers using their F1 scores, a crucial metric for measuring model performance in imbalanced class scenarios commonly encountered in fault detection tasks. The results show that the Decision Tree (DT), KNN, Random Forest (RF), and Extra Trees (ET) classifiers worked better than expected. All of them got perfect F1 scores of 1.000, which shows how well they can find bugs. On the other hand, AdaBoost demonstrated a lower F1 score of 0.591, suggesting possible constraints in its use for detecting faults in solar panel systems. This study advances fault detection in solar panels, enhancing system reliability and reducing maintenance costs. It also guides the development of sophisticated diagnostic tools, boosting solar technology adoption.

show abstract

Dropout and Pruned Neural Networks for Fault Classification in Photovoltaic Arrays

Cited by 27 publications

References 19 publications

Optimizing Solar Power Using Array Topology Reconfiguration With Regularized Deep Neural Networks

Optimizing Solar Power Using Array Topology Reconfiguration With Regularized Deep Neural Networks

Supervised Machine Learning Techniques for the Prediction of the State of Charge of Batteries in Photovoltaic Systems in the Mining Sector

Comparative Analysis of Machine Learning Techniques for Fault Detection in Solar Panel Systems

Contact Info

Product

Resources

About