Interval-Valued Reduced Ensemble Learning Based Fault Detection and Diagnosis Techniques for Uncertain Grid-Connected PV Systems
Open Access
- 13 April 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 47673-47686
Abstract
One of the most promising renewable energy technologies is photovoltaics (PV). Fault detection and diagnosis (FDD) becomes more and more important in order to guarantee high reliability in PV systems. FDD of PV systems using machine learning technique aims to develop effective models that can provide a better rate of accuracy. Recently, numerous machine learning based ensemble models have been applied in FDD using different combination techniques. Ensemble method is a tool that merges several base models in order to produce one optimal predictive model. In this study, we propose six effective Ensemble Leaning (EL)-based FDD paradigms for uncertain Grid-Connected PV systems. First, EL-based interval centers and ranges and interval upper and lower bounds techniques are proposed to deal with PV system uncertainties (current/voltage variability, noise, measurement errors, $\ldots$ ). Next, in order to more improve the diagnosis abilities, two interval kernel PCA (IKPCA)-based EL classifiers are developed. The IKPCA-EL techniques are addressed so that the features extraction and selection phases are performed using the IKPCA models and the sensitive and significant interval-valued characteristics are transmitted to the EL model for classification purposes. Finally, the number of observations in the training data set is reduced using Hierarchical K-means techniques in order to overcome the problem of computation time and storage cost. Therefore, two interval reduced KPCA-EL techniques are proposed. The study demonstrated the feasibility and efficiency of the proposed techniques for fault diagnosis of Grid-Connected PV systems.Keywords
Funding Information
- Qatar National Library
- Qatar National Research Fund (QNRF) Research Grant
This publication has 54 references indexed in Scilit:
- Line–Line Fault Analysis and Protection Challenges in Solar Photovoltaic ArraysIEEE Transactions on Industrial Electronics, 2012
- Algorithms for hierarchical clustering: an overviewWIREs Data Mining and Knowledge Discovery, 2011
- A robust method for linear regression of symbolic interval dataPattern Recognition Letters, 2010
- A Novel Fault Diagnosis Method Based-on Modified Neural Networks for Photovoltaic Systems2010
- Support Vector Machines (SVM) as a Technique for Solvency AnalysisSSRN Electronic Journal, 2008
- Dependencies and Variation Components of Symbolic Interval-Valued Data2007
- Simple Direct Power Control of Three-Phase PWM Rectifier Using Space-Vector Modulation (DPC-SVM)IEEE Transactions on Industrial Electronics, 2004
- KNN Model-Based Approach in Classification2003
- Bagging, Boosting and the Random Subspace Method for Linear ClassifiersPattern Analysis and Applications, 2002
- Support-vector networksMachine Learning, 1995