Data-driven green energy extraction: Machine learning-based MPPT control with efficient fault detection method for the hybrid PV-TEG system

Khan, Kamran; Rashid, Saad; Mansoor, Majad; Khan, Ammar Ahmed; Rakhshandeh, Hasan; Zafar, Muhammad Usman; Akhtar, Naureen

doi:10.1016/j.egyr.2023.02.047

Cited by 26 publications

(12 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Proposing new GMPPT approaches using Data-driven energy extraction based on trained deep learning and machine learning models [55][56].…”

Section: Future Directions and Challengesmentioning

confidence: 99%

MPPT techniques for PV systems: A systematic review in current trends and recent advances in AI

Boubaker

2023

Preprint

View full text Add to dashboard Cite

Over the past decades, solar photovoltaic (PV) energy has been the most valuable green energy. It is renowned for its sustainability, environmentally friendly nature, and minimal maintenance costs. Several methods aiming to extract the highest photovoltaic energy are found in the vast literature. The aim of this systematic review is to focus on current trends and the most recent advances in the field. A “Scopus” bibliographic survey is conducted around survey and research articles published over the past three years (2019–2022) according to the PRISMA selection methodology. Over the selected works, different taxonomies of maximum power point tracking (MPPT) approaches are found. The list of associated performance criteria is also established, current trends, future directions and challenges in the field are well identified. This survey paper could be a useful reference for researchers and companies concerned by the sustainable development goals (GSD) for clean energy production and climate change.

show abstract

“…Proposing new GMPPT approaches using Data-driven energy extraction based on trained deep learning and machine learning models [55][56].…”

Section: Future Directions and Challengesmentioning

confidence: 99%

MPPT techniques for PV systems: A systematic review in current trends and recent advances in AI

Boubaker

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…This technique utilizes dynamic irradiation and temperature as inputs, storing them as datasets. As is the case in Machine learning (Memaya et al, 2019 andkhan et al, 2023). Deep Reinforcement Learning based MPPT (Phan et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

A Comparative Study of PSO, GWO, and HOA Algorithms for Maximum Power Point Tracking in Partially Shaded Photovoltaic Systems

Berttahar,

Abdeddaim,

Betka

et al. 2024

Power Electronics and Drives

View full text Add to dashboard Cite

Solar energy harnessed through photovoltaic technology plays a crucial role in generating electrical energy. Maximising the power output of solar modules requires optimal solar radiation. However, challenges arise due to obstacles such as stationary objects, buildings, and sand-laden winds, resulting in multiple points of maximum power on the P–V curve. This problem requires the use of maximum power point tracking algorithms, especially in unstable climatic conditions and partial shading scenarios. In this study, we propose a comparative analysis of three MPPT methods: particle swarm optimisation (PSO), grey wolf optimisation (GWO) and Horse Herd Optimization Algorithm (HOA) under dynamic partial shading conditions. We evaluate the accuracy of these methods using Matlab / Simulink simulations. The results show that all three methods solve partial shading problems effectively and with high precision. Furthermore, the Horse Herd Optimization approach has superior tracking accuracy and faster convergence compared with the other proposed methods.

show abstract

“…Ref. [21] proposes a machine learning-based approach with efficient fault detection methods to achieve fast real-time global maximum power point tracking for addressing the low efficiency of PV and thermoelectric generation devices in hybrid PVTEG systems. This demonstrates the potential of machine learning and efficient fault detection methods to significantly enhance system performance.…”

Section: Introductionmentioning

confidence: 99%

Anomaly Identification for Photovoltaic Power Stations Using a Dual Classification System and Gramian Angular Field Visualization

Wang,

Cui,

Gong

et al. 2024

Processes

View full text Add to dashboard Cite

With the increasing scale of photovoltaic (PV) power stations, timely anomaly detection through analyzing the PV output power curve is crucial. However, overlooking the impact of external factors on the expected power output would lead to inaccurate identification of PV station anomalies. This study focuses on the discrepancy between measured and expected PV power generation values, using a dual classification system. The system leverages two-dimensional Gramian angular field (GAF) data and curve features extracted from one-dimensional time series, along with attention weights from a CNN network. This approach effectively classifies anomalies, including normal operation, aging pollution, and arc faults, achieving an overall classification accuracy of 95.83%.

show abstract

Data-driven green energy extraction: Machine learning-based MPPT control with efficient fault detection method for the hybrid PV-TEG system

Cited by 26 publications

References 44 publications

MPPT techniques for PV systems: A systematic review in current trends and recent advances in AI

MPPT techniques for PV systems: A systematic review in current trends and recent advances in AI

A Comparative Study of PSO, GWO, and HOA Algorithms for Maximum Power Point Tracking in Partially Shaded Photovoltaic Systems

Anomaly Identification for Photovoltaic Power Stations Using a Dual Classification System and Gramian Angular Field Visualization

Contact Info

Product

Resources

About