Manish Kumar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Manish Kumar has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
Arun Kumar
Department of Hydro and Renewable Energy Indian Institute of Technology Roorkee Roorkee Uttarakhand 247667 India
7 shared publicationsRajesh Gupta
4 shared publications- Rajesh Gupta
Indian Institute of Technology Bombay
4 shared publications Chandan Kumar
Department of Computer Science and Engineering, Career Point University, Hamirpur, India
2 shared publicationsDheeraj Sharma
Department of Computer Science and Engineering, Career Point University, Hamirpur, India
2 shared publications- Gaute Otnes
Institute for Energy Technology, Kjeller, Norway
2 shared publications
Latest Publications
- Open Access
- 26 September 2026
- Published by Springer Nature in Sustainable Energy Research
- Vol. 13 (1) , 41
A review of deep learning transformer variants used in solar PV forecasting
Solar power has become one of the most important renewable energy sources as it is sustainable, its prices are reducing, and it could contribute to the transition to clean energy across the world. Nevertheless, the inherently intermittent nature of solar PV output due to the rapidly fluctuating weather conditions demands a very serious need to have accurate forecasting systems. The current reviews are primarily over traditional deep learning or statistical models, creating a knowledge gap on how transformer-based architectures intend to separate long-term dependencies and nonlinear behaviours of solar PV forecasting. Consequently, the objective of this review is to fill this gap by giving a detailed analysis of the variants of transformers that would be utilized when predicting PV power. A large variety of transformer models, among which are Simple Transformer, Informer, Temporal Fusion Transformer (TFT), Patch-Transformers, TSformer, and Hybrid Transformer models, among other recent models, are systematically analysed in this paper. Their architectural innovations, approach enhancement, benefits, and drawbacks in the forecasting of solar energy are described in the review. The strategy adopted also involves comparative appraisal, architecture-based classification, and analysis based on published benchmark investigations in terms of performance metrics. The result of this review demonstrates that transformer-based models are better than classic AI algorithms to capture long-range temporal patterns, process heterogeneous inputs, and achieve better forecasting results. The findings of the literature show further that strong increases in robustness, interpretability, and predictability of multiple horizons are achieved. Altogether, this review provides a unified picture of the modern transformer-based developments and defines the future research that ought to facilitate the improvement of scalability, uncertainty quantification, and the deployment of PV forecasting systems in the real world.
- 26 September 2026
- Published by Springer Nature in Sustainable Energy Research
- Vol. 13 (1) , 41
Open AccessA review of deep learning transformer variants used in solar PV forecasting
Solar power has become one of the most important renewable energy sources as it is sustainable, its prices are reducing, and it could contribute to the transition to clean energy across the world. Nevertheless, the inherently intermittent nature of solar PV output due to the rapidly fluctuating weather conditions demands a very serious need to have accurate forecasting systems. The current reviews are primarily over traditional deep learning or statistical models, creating a knowledge gap on how transformer-based architectures intend to separate long-term dependencies and nonlinear behaviours of solar PV forecasting. Consequently, the objective of this review is to fill this gap by giving a detailed analysis of the variants of transformers that would be utilized when predicting PV power. A large variety of transformer models, among which are Simple Transformer, Informer, Temporal Fusion Transformer (TFT), Patch-Transformers, TSformer, and Hybrid Transformer models, among other recent models, are systematically analysed in this paper. Their architectural innovations, approach enhancement, benefits, and drawbacks in the forecasting of solar energy are described in the review. The strategy adopted also involves comparative appraisal, architecture-based classification, and analysis based on published benchmark investigations in terms of performance metrics. The result of this review demonstrates that transformer-based models are better than classic AI algorithms to capture long-range temporal patterns, process heterogeneous inputs, and achieve better forecasting results. The findings of the literature show further that strong increases in robustness, interpretability, and predictability of multiple horizons are achieved. Altogether, this review provides a unified picture of the modern transformer-based developments and defines the future research that ought to facilitate the improvement of scalability, uncertainty quantification, and the deployment of PV forecasting systems in the real world.
- Open Access
- 20 July 2026
- Published by Springer Nature in Journal of Electrical Systems and Information Technology
- Vol. 13 (1) , 74
A review of machine learning and deep learning models, features, and applications for solar PV forecasting
- 20 July 2026
- Published by Springer Nature in Journal of Electrical Systems and Information Technology
- Vol. 13 (1) , 74
Open AccessA review of machine learning and deep learning models, features, and applications for solar PV forecasting
- 10 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
A Review of Agro Photovoltaic Systems Leveraging AI for Sustainable Food and Energy Production
Agro Photovoltaic (Agro PV) systems offer a transformative solution to the dual challenges of sustainable food and energy production by co-locating photovoltaic panels with crop cultivation. The integration of Artificial Intelligence (AI) into these systems enhances their efficiency through intelligent resource management, predictive analytics, and realtime control. This review synthesizes recent advancements in Agro Photovoltaics, focusing on AI-enabled monitoring, precision agriculture, and energy optimization. We will discuss key technological developments, agricultural benefits, and environmental impacts, and identify prevailing challenges and future research directions. The synergistic combination of AI and Agro PV not only supports multiple UN Sustainable Development Goals but also contributes to climate resilience and rural development. This paper provides a foundation for stakeholders to harness AI-driven Agro Photovoltaics for a sustainable future.
- 10 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
A Review of Agro Photovoltaic Systems Leveraging AI for Sustainable Food and Energy Production
Agro Photovoltaic (Agro PV) systems offer a transformative solution to the dual challenges of sustainable food and energy production by co-locating photovoltaic panels with crop cultivation. The integration of Artificial Intelligence (AI) into these systems enhances their efficiency through intelligent resource management, predictive analytics, and realtime control. This review synthesizes recent advancements in Agro Photovoltaics, focusing on AI-enabled monitoring, precision agriculture, and energy optimization. We will discuss key technological developments, agricultural benefits, and environmental impacts, and identify prevailing challenges and future research directions. The synergistic combination of AI and Agro PV not only supports multiple UN Sustainable Development Goals but also contributes to climate resilience and rural development. This paper provides a foundation for stakeholders to harness AI-driven Agro Photovoltaics for a sustainable future.
- Top Cited PapersOpen Access
- 2 April 2025
- Published by Elsevier in Solar Energy
- Vol. 293
Modelling wave-induced losses for floating photovoltaics: Impact of design parameters and environmental conditions
- 2 April 2025
- Published by Elsevier in Solar Energy
- Vol. 293
Top Cited PapersOpen AccessModelling wave-induced losses for floating photovoltaics: Impact of design parameters and environmental conditions
- Open Access
- 7 January 2024
- Published by Elsevier in Solar Energy Advances
- Vol. 4
Categorizing Indian states based on operating condition of photovoltaic system
- 7 January 2024
- Published by Elsevier in Solar Energy Advances
- Vol. 4
Open AccessCategorizing Indian states based on operating condition of photovoltaic system
- 3 November 2022
- Published by Taylor & Francis
- p. 247-268
Secure Permission-based Medical Blockchain Framework for the Exchange of Electronic Health Records
The Blockchain revolution began in the form of Bitcoin cryptocurrency. This decentralized technology has been adopted and developed worldwide in many fields, including e-Governance, e-commerce, e-health care, and wealth management, in recent years. Nowadays, blockchain technology appears to be a ground-breaking tool for solving real-world challenges in managing electronic health records. In this work, an attempt was made to explore the potential of blockchain to boost electronic health records management using a permissioned blockchain platform called Hyperledger fabric. As blockchain is a distributed system, electronic health records need to be shared among different computers. Hence, to ensure privacy to the medical documents, encryption of data is required before transferring it to the blockchain technology. In the proposed system, a novel cryptosystem using chaos theory is designed to encrypt electronic health records. Analysis of performance and security proves that the proposed system is well protected against cryptanalytic attacks.
- 3 November 2022
- Published by Taylor & Francis
- p. 247-268
Secure Permission-based Medical Blockchain Framework for the Exchange of Electronic Health Records
The Blockchain revolution began in the form of Bitcoin cryptocurrency. This decentralized technology has been adopted and developed worldwide in many fields, including e-Governance, e-commerce, e-health care, and wealth management, in recent years. Nowadays, blockchain technology appears to be a ground-breaking tool for solving real-world challenges in managing electronic health records. In this work, an attempt was made to explore the potential of blockchain to boost electronic health records management using a permissioned blockchain platform called Hyperledger fabric. As blockchain is a distributed system, electronic health records need to be shared among different computers. Hence, to ensure privacy to the medical documents, encryption of data is required before transferring it to the blockchain technology. In the proposed system, a novel cryptosystem using chaos theory is designed to encrypt electronic health records. Analysis of performance and security proves that the proposed system is well protected against cryptanalytic attacks.
- Open Access
- 28 September 2022
- Published by Elsevier in Results in Engineering
- Vol. 16
Comparative degradation analysis of accelerated-aged and field-aged crystalline silicon photovoltaic modules under Indian subtropical climatic conditions
- 28 September 2022
- Published by Elsevier in Results in Engineering
- Vol. 16
Open AccessComparative degradation analysis of accelerated-aged and field-aged crystalline silicon photovoltaic modules under Indian subtropical climatic conditions
- Open Access
- 17 May 2022
- Published by Elsevier in Solar Energy
- Vol. 239, 242-251
The performance and amphibious operation potential of a new floating photovoltaic technology
- 17 May 2022
- Published by Elsevier in Solar Energy
- Vol. 239, 242-251
Open AccessThe performance and amphibious operation potential of a new floating photovoltaic technology
- 13 May 2022
- Published by Wiley in Progress in Photovoltaics: Research and Applications
- Vol. 30 (11) , 1312-1324
Investigation of dominant degradation mode in field‐aged photovoltaic modules using novel differential current‐voltage analysis approach
Photovoltaic (PV) modules are susceptible to various types of defects and degradations (D&Ds) under field‐operating conditions, which affect their performance and reliability. These D&Ds have non‐uniform distribution in the PV modules, which makes it difficult to distinguish amongst multiple D&Ds using a single characterization technique. In the present work, a simple non‐destructive characterization approach called differential current‐voltage (DIV) analysis using current‐voltage (I‐V) measurements have been developed for investigation of the dominant degradation mode in the cells of modules, wherein consecutive cells have been partially shaded while measuring the I‐V curve of the modules. For this purpose, a batch of crystalline silicon PV modules operating under hot and humid climatic conditions for 20 years has been investigated. A correlation has been established between the trend of percentage change in modules' electrical parameters during DIV measurements and the dominant degradation mode present in the cell under investigation. The trend of change in short circuit current and voltage at maximum power point has been identified as key electrical parameters to identify the dominant degradation mode in the cell. To analyse the trends of DIV analysis, the effect of prominent degradation modes on the module parameters has been investigated using electrical simulations. The investigated PV modules have been cross‐characterized through microscopic inspection and electroluminescence imaging to identify various D&Ds present in the investigated modules. The results of cross‐characterization substantiate the findings of DIV analysis. The presented DIV approach can be used for the analysis of non‐uniform degradation in the PV plants under field‐operating conditions.
- 13 May 2022
- Published by Wiley in Progress in Photovoltaics: Research and Applications
- Vol. 30 (11) , 1312-1324
Investigation of dominant degradation mode in field‐aged photovoltaic modules using novel differential current‐voltage analysis approach
Photovoltaic (PV) modules are susceptible to various types of defects and degradations (D&Ds) under field‐operating conditions, which affect their performance and reliability. These D&Ds have non‐uniform distribution in the PV modules, which makes it difficult to distinguish amongst multiple D&Ds using a single characterization technique. In the present work, a simple non‐destructive characterization approach called differential current‐voltage (DIV) analysis using current‐voltage (I‐V) measurements have been developed for investigation of the dominant degradation mode in the cells of modules, wherein consecutive cells have been partially shaded while measuring the I‐V curve of the modules. For this purpose, a batch of crystalline silicon PV modules operating under hot and humid climatic conditions for 20 years has been investigated. A correlation has been established between the trend of percentage change in modules' electrical parameters during DIV measurements and the dominant degradation mode present in the cell under investigation. The trend of change in short circuit current and voltage at maximum power point has been identified as key electrical parameters to identify the dominant degradation mode in the cell. To analyse the trends of DIV analysis, the effect of prominent degradation modes on the module parameters has been investigated using electrical simulations. The investigated PV modules have been cross‐characterized through microscopic inspection and electroluminescence imaging to identify various D&Ds present in the investigated modules. The results of cross‐characterization substantiate the findings of DIV analysis. The presented DIV approach can be used for the analysis of non‐uniform degradation in the PV plants under field‐operating conditions.
- Top Cited Papers
- 1 December 2021
- Published by Elsevier in Solar Energy Materials and Solar Cells
- Vol. 233
Challenges and opportunities towards the development of floating photovoltaic systems
- 1 December 2021
- Published by Elsevier in Solar Energy Materials and Solar Cells
- Vol. 233
Top Cited PapersChallenges and opportunities towards the development of floating photovoltaic systems