Shahid Tufail
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Shahid Tufail has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Arif I. Sarwat
Department of Electrical and Computer Engineering, Florida International University, Miami, FL, USA
8 shared publications - Mohd Tariq
Aligarh Muslim University
5 shared publications Arif Sarwat
2 shared publicationsHugo Riggs
2 shared publications- Hugo Riggs
Department of Electrical and Computer Engineering, Florida International University, Miami, FL 33174, USA
2 shared publications - Imtiaz Parvez
Department of Electrical and Computer Engineering, Florida International University, Miami, FL 33174, USA
2 shared publications
Latest Publications
- 10 November 2026
- Published by Elsevier in Electric Power Systems Research
- Vol. 265
The contribution of graph neural network architecture and grid topology to false data injection detection in distribution systems
- 10 November 2026
- Published by Elsevier in Electric Power Systems Research
- Vol. 265
The contribution of graph neural network architecture and grid topology to false data injection detection in distribution systems
- Open Access
- 30 October 2026
- Published by Elsevier in SSRN Electronic Journal
A Data-Driven Deep Learning Model for Weather Impacted Reliability Prediction of Photovoltaic Solar Inverter
Outdoor photovoltaic (PV) inverters are subject to spatio-temporal degradation driven by environmental conditions, which can significantly impact their operational reliability and service life. The disclosed method introduces a novel, data-driven framework for estimating inverter reliability using machine learning (ML) techniques, with application to a 1.4 MW PV power plant. The invention applies a top-down supervised learning approach that integrates diverse environmental and operational data inputs, including irradiance, humidity, temperature, weather patterns, and time of day. The dataset comprises extensive alert logs from 17 functionally identical PV inverters, detailing alert types, propagation behaviors, and frequency. Analysis of these datasets reveals statistically significant correlations between environmental variables and inverter operational anomalies and output levels. A two-stage ML architecture is proposed: 1) First-stage model (classification followed by regression): Implemented using an Artificial Neural Network (ANN), applied to an averaged dataset aggregating alert and ambient environmental data ("Alert-Ambient" dataset). 2) Second-stage model (clustering followed by regression): Incorporates K-means clustering with Principal Component Analysis (PCA) for dimensionality reduction, followed by regression via Random Forest (RF) and K-Nearest Neighbors (KNN) algorithms. This approach is applied to non-aggregated, individual inverter datasets. Comparative performance evaluation shows that the clusteringregression method achieves significantly greater predictive accuracy, exceeding 80%, and obtains a mean squared error (MSE) as low as 0.002, outperforming the ANN-based model (MSE 0.0195 on the averaged dataset).
- 30 October 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessA Data-Driven Deep Learning Model for Weather Impacted Reliability Prediction of Photovoltaic Solar Inverter
Outdoor photovoltaic (PV) inverters are subject to spatio-temporal degradation driven by environmental conditions, which can significantly impact their operational reliability and service life. The disclosed method introduces a novel, data-driven framework for estimating inverter reliability using machine learning (ML) techniques, with application to a 1.4 MW PV power plant. The invention applies a top-down supervised learning approach that integrates diverse environmental and operational data inputs, including irradiance, humidity, temperature, weather patterns, and time of day. The dataset comprises extensive alert logs from 17 functionally identical PV inverters, detailing alert types, propagation behaviors, and frequency. Analysis of these datasets reveals statistically significant correlations between environmental variables and inverter operational anomalies and output levels. A two-stage ML architecture is proposed: 1) First-stage model (classification followed by regression): Implemented using an Artificial Neural Network (ANN), applied to an averaged dataset aggregating alert and ambient environmental data ("Alert-Ambient" dataset). 2) Second-stage model (clustering followed by regression): Incorporates K-means clustering with Principal Component Analysis (PCA) for dimensionality reduction, followed by regression via Random Forest (RF) and K-Nearest Neighbors (KNN) algorithms. This approach is applied to non-aggregated, individual inverter datasets. Comparative performance evaluation shows that the clusteringregression method achieves significantly greater predictive accuracy, exceeding 80%, and obtains a mean squared error (MSE) as low as 0.002, outperforming the ANN-based model (MSE 0.0195 on the averaged dataset).
- 6 September 2026
- Published by Elsevier in Electric Power Systems Research
- Vol. 265
Image-based fault diagnosis for reliable operation of photovoltaic generation plants using a modified ConvNeXt model
- 6 September 2026
- Published by Elsevier in Electric Power Systems Research
- Vol. 265
Image-based fault diagnosis for reliable operation of photovoltaic generation plants using a modified ConvNeXt model
- Open Access
- 30 July 2026
- Published by Elsevier in Solar Compass
- Vol. 19
Explainable AI in solar PV forecasting: A systematic review of models, explainers, and physical drivers
- 30 July 2026
- Published by Elsevier in Solar Compass
- Vol. 19
Open AccessExplainable AI in solar PV forecasting: A systematic review of models, explainers, and physical drivers
- Open Access
- 17 February 2026
- Published by Elsevier in Energy Conversion and Management: X
- Vol. 30
Techno-economic and environmental assessment of photovoltaic–battery microgrids across diverse U.S. states
- 17 February 2026
- Published by Elsevier in Energy Conversion and Management: X
- Vol. 30
Open AccessTechno-economic and environmental assessment of photovoltaic–battery microgrids across diverse U.S. states
- Open Access
- 21 July 2025
- Published by MDPI AG in Electronics
- Vol. 14 (14) , 2916
A Comparative Study of Dimensionality Reduction Methods for Accurate and Efficient Inverter Fault Detection in Grid-Connected Solar Photovoltaic Systems
The continuous, effective operation of grid-connected photovoltaic (GCPV) systems depends on dependable inverter failure detection. Early, precise fault diagnosis improves general system dependability, lowers maintenance costs, and saves downtime. Although computing efficiency remains a difficulty, particularly in resource-limited contexts, machine learning-based fault detection presents interesting prospects in accuracy and responsiveness. By streamlining data complexity and allowing faster and more effective fault diagnosis, dimensionality reduction methods play vital role. Using dimensionality reduction and ML techniques, this work explores inverter fault detection in GCPV systems. Photovoltaic inverter operational data was normalized and preprocessed. In the next step, dimensionality reduction using Principal Component Analysis (PCA) and autoencoder-based feature extraction were explored. For ML training four classifiers which include Random Forest (RF), logistic regression (LR), decision tree (DT), and K-Nearest Neighbors (KNN) were used. Trained on the whole standardized dataset, the RF model routinely produced the greatest accuracy of 99.87%, so efficiently capturing complicated feature interactions but requiring large processing resources and time of 36.47sec. LR model showed reduction in accuracy, but very fast training time compared to other models. Further, PCA greatly lowered computing demands, especially improving inference speed for LR and KNN. High accuracy of 99.23% across all models was maintained by autoencoder-derived features.
- 21 July 2025
- Published by MDPI AG in Electronics
- Vol. 14 (14) , 2916
Open AccessA Comparative Study of Dimensionality Reduction Methods for Accurate and Efficient Inverter Fault Detection in Grid-Connected Solar Photovoltaic Systems
The continuous, effective operation of grid-connected photovoltaic (GCPV) systems depends on dependable inverter failure detection. Early, precise fault diagnosis improves general system dependability, lowers maintenance costs, and saves downtime. Although computing efficiency remains a difficulty, particularly in resource-limited contexts, machine learning-based fault detection presents interesting prospects in accuracy and responsiveness. By streamlining data complexity and allowing faster and more effective fault diagnosis, dimensionality reduction methods play vital role. Using dimensionality reduction and ML techniques, this work explores inverter fault detection in GCPV systems. Photovoltaic inverter operational data was normalized and preprocessed. In the next step, dimensionality reduction using Principal Component Analysis (PCA) and autoencoder-based feature extraction were explored. For ML training four classifiers which include Random Forest (RF), logistic regression (LR), decision tree (DT), and K-Nearest Neighbors (KNN) were used. Trained on the whole standardized dataset, the RF model routinely produced the greatest accuracy of 99.87%, so efficiently capturing complicated feature interactions but requiring large processing resources and time of 36.47sec. LR model showed reduction in accuracy, but very fast training time compared to other models. Further, PCA greatly lowered computing demands, especially improving inference speed for LR and KNN. High accuracy of 99.23% across all models was maintained by autoencoder-derived features.
- Open Access
- 19 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 33783-33798
A Hybrid Machine Learning-Based Framework for Data Injection Attack Detection in Smart Grids Using PCA and Stacked Autoencoders
Cyberattacks, especially data injection attacks, are becoming more common as smart grids are increasingly interconnected. In addition, accurate and unbiased high-quality data is required for model training. Most of the data we collect from the real world is sparse, incomplete, inconsistent, and skewed. To address these issues, we have proposed a framework to detect such attacks in this study. Using a stacked autoencoder architecture, synthetic instances of minority class data were generated to enhance the generalizability of the model and address diverse attack scenarios. Various machine learning algorithms were evaluated, and the Random Forest model consistently achieved superior accuracy, ranging from 99.32% to 95.89%. In particular, traditional algorithms such as Logistic Regression exhibited sensitivity to dimensionality reductions, experiencing a 16.96% accuracy drop when the principal components were reduced from all to 10. In contrast, RF demonstrated resilience, with only a 1.67% mean accuracy drop under similar conditions. Both RF and XGBoost emerged as standout models, showcasing high accuracy and robust performance even with dimensionality reduction via principal component analysis (PCA). However, reducing PCA components from 10 to 5 led to performance decreases in all models, with the Support Vector Machine Classifier showing the highest accuracy drop of 14.21%. This study underscores the importance of understanding algorithmic behavior and data features to strengthen cybersecurity in smart grids and emphasizes the critical need for careful feature selection and tuning, particularly for models sensitive to dimensionality reduction.
- 19 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 33783-33798
Open AccessA Hybrid Machine Learning-Based Framework for Data Injection Attack Detection in Smart Grids Using PCA and Stacked Autoencoders
Cyberattacks, especially data injection attacks, are becoming more common as smart grids are increasingly interconnected. In addition, accurate and unbiased high-quality data is required for model training. Most of the data we collect from the real world is sparse, incomplete, inconsistent, and skewed. To address these issues, we have proposed a framework to detect such attacks in this study. Using a stacked autoencoder architecture, synthetic instances of minority class data were generated to enhance the generalizability of the model and address diverse attack scenarios. Various machine learning algorithms were evaluated, and the Random Forest model consistently achieved superior accuracy, ranging from 99.32% to 95.89%. In particular, traditional algorithms such as Logistic Regression exhibited sensitivity to dimensionality reductions, experiencing a 16.96% accuracy drop when the principal components were reduced from all to 10. In contrast, RF demonstrated resilience, with only a 1.67% mean accuracy drop under similar conditions. Both RF and XGBoost emerged as standout models, showcasing high accuracy and robust performance even with dimensionality reduction via principal component analysis (PCA). However, reducing PCA components from 10 to 5 led to performance decreases in all models, with the Support Vector Machine Classifier showing the highest accuracy drop of 14.21%. This study underscores the importance of understanding algorithmic behavior and data features to strengthen cybersecurity in smart grids and emphasizes the critical need for careful feature selection and tuning, particularly for models sensitive to dimensionality reduction.
- 26 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industry Applications
- Vol. PP (00939994) , 1-15
Machine Learning-Driven Reliability Estimation of PV Inverters Considering Alert-Ambient Variability
Weather-induced spatio-temporal degradation limits outdoor PV inverter lifetime and reliability, necessitating advanced data analysis. This study employs a top-down, data-driven approach utilizing multiple machine learning (ML) algorithms to estimate inverter reliability in a 1.4 MW PV power plant, considering factors such as irradiance, humidity, temperature, time of day, and weather conditions. An extensive alert dataset from 17 identical inverters, including alert types, propagation, and frequency, reveals significant correlations with environmental factors and inverter output power, enabling the construction of a performance reliability model. Dual-stage supervised-ML models are evaluated for accuracy, with the ‘classification-regression’ model by an artificial neural network (ANN) tested on the averaged “Alert-Ambient” dataset, which is outperformed by ‘clustering-regression’ models using random forest (RF) and K-Nearest Neighbors (KNN) on individual inverter datasets. K-means clustering applies principal component analysis to reduce dimensions, achieving improved accuracy beyond the $80\%$ achieved by ANN on the averaged dataset. Second-stage regression estimates inverter reliability with a mean square error of 0.0195 on the averaged dataset and as low as 0.002 on individual inverter datasets using RF. These findings highlight the method's suitability for estimating PV inverter output reliability under ambient conditions, essential for digital twin development and related applications.
- 26 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industry Applications
- Vol. PP (00939994) , 1-15
Machine Learning-Driven Reliability Estimation of PV Inverters Considering Alert-Ambient Variability
Weather-induced spatio-temporal degradation limits outdoor PV inverter lifetime and reliability, necessitating advanced data analysis. This study employs a top-down, data-driven approach utilizing multiple machine learning (ML) algorithms to estimate inverter reliability in a 1.4 MW PV power plant, considering factors such as irradiance, humidity, temperature, time of day, and weather conditions. An extensive alert dataset from 17 identical inverters, including alert types, propagation, and frequency, reveals significant correlations with environmental factors and inverter output power, enabling the construction of a performance reliability model. Dual-stage supervised-ML models are evaluated for accuracy, with the ‘classification-regression’ model by an artificial neural network (ANN) tested on the averaged “Alert-Ambient” dataset, which is outperformed by ‘clustering-regression’ models using random forest (RF) and K-Nearest Neighbors (KNN) on individual inverter datasets. K-means clustering applies principal component analysis to reduce dimensions, achieving improved accuracy beyond the $80\%$ achieved by ANN on the averaged dataset. Second-stage regression estimates inverter reliability with a mean square error of 0.0195 on the averaged dataset and as low as 0.002 on individual inverter datasets using RF. These findings highlight the method's suitability for estimating PV inverter output reliability under ambient conditions, essential for digital twin development and related applications.
- 14 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Reliability
- Vol. 73 (3) , 1418-1432
Photovoltaic Inverter Failure Mechanism Estimation Using Unsupervised Machine Learning and Reliability Assessment
This article introduces a data-driven approach to assessing failure mechanisms and reliability degradation in outdoor photovoltaic (PV) string inverters. The manufacturer's stated PV inverter lifetime can vary due to the impact of operating site conditions. To address limitations in degradation estimation through accelerated testing, condition monitoring, or degradation modeling, we propose a machine learning (ML) oriented approach. Utilizing data from a 1.4 MW PV power plant operational since 2016, with 46 string PV inverters tied to the grid, we employ the unsupervised one-class support vector machine ML technique to analyze inverter and sensor data, capable of classifying humidity cycling and temperature fluctuations as dominant failure mechanisms. Utilizing the anomaly alert relationship and alert details specific to the inverter, the level of PV inverter output is considered as its availability or available reliability. Subsequently, a continuous Markov model is applied to six-month alert data, revealing an average stated reliability of 20% after 20 years of continuous operation. These results support recommendations for time-bound preventive measures to enhance PV inverter reliability under diverse outdoor conditions. The approach provides a nondestructive, top–down, and generalized method for analyzing any commercial PV inverter exposed to outdoor conditions, contingent on the availability of relevant data.
- 14 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Reliability
- Vol. 73 (3) , 1418-1432
Photovoltaic Inverter Failure Mechanism Estimation Using Unsupervised Machine Learning and Reliability Assessment
This article introduces a data-driven approach to assessing failure mechanisms and reliability degradation in outdoor photovoltaic (PV) string inverters. The manufacturer's stated PV inverter lifetime can vary due to the impact of operating site conditions. To address limitations in degradation estimation through accelerated testing, condition monitoring, or degradation modeling, we propose a machine learning (ML) oriented approach. Utilizing data from a 1.4 MW PV power plant operational since 2016, with 46 string PV inverters tied to the grid, we employ the unsupervised one-class support vector machine ML technique to analyze inverter and sensor data, capable of classifying humidity cycling and temperature fluctuations as dominant failure mechanisms. Utilizing the anomaly alert relationship and alert details specific to the inverter, the level of PV inverter output is considered as its availability or available reliability. Subsequently, a continuous Markov model is applied to six-month alert data, revealing an average stated reliability of 20% after 20 years of continuous operation. These results support recommendations for time-bound preventive measures to enhance PV inverter reliability under diverse outdoor conditions. The approach provides a nondestructive, top–down, and generalized method for analyzing any commercial PV inverter exposed to outdoor conditions, contingent on the availability of relevant data.