Machine learning based maximum power point tracking in solar energy conversion systems

Memaya, Mounil; Moorthy, C. Balakrishna; Tahiliani, Sahitya; Sreeni, Siddarth

doi:10.12720/sgce.8.6.662-669

Cited by 12 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…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

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

show abstract

“…So, the deep learning neural networks (DLNN) are introduced in the article 12 to recognize the partial shading conditions of the sunlight systems. The DLNNs have the possibility of solving any nonlinear issue without any complexity.…”

Section: Introductionmentioning

confidence: 99%

A novel design and analysis of hybrid fuzzy logic MPPT controller for solar PV system under partial shading conditions

Kumar,

Balakrishna

2024

Sci Rep

View full text Add to dashboard Cite

Renewable energy resources are more useful when associated with the thermal power generation network because of their high accessibility in the environment, good system response, easy manufacturing, plus high scalable. So, the present research is going on solar power to reduce consumer grid dependency. The running of the PV network is quite easier, plus less human sources are involved. However, the solar modules’ power generation is nonlinear fashion. So, the collection of peak power from the sunlight-dependent systems is a highly challenging task. In this article, a Modified Differential Step Grey Wolf Optimization with Adaptive Fuzzy Logic Controller (MDSGWO with FLC) is developed for collecting the maximum power from renewable energy resources under diverse Partial Shading Conditions (PSCs). The introduced method comprehensive analysis has been done along with the other recently existing MPPT methods in terms of convergence speed, MPP tracking accuracy, operating efficiency of the introduced method, functioning duty value of the DC–DC boost power converter, dependence of MPPT on sunlight system, total number of sensing devices are needed, plus peak power extraction from the proposed system. Here, the sunlight power generation cost is more to limit this issue, a power converter is selected in the second objective to develop the voltage source capability of the PV network. The overall PV-interfaced power converter network is examined by utilizing the MATLAB environment.

show abstract

Watertightness Design and Experimental Evaluation of a Solar Panel Structure for Building Integrated Photovoltaics (BIPV) Roofs

Chen,

Shi

2024

Lecture Notes in Civil Engineering

View full text Add to dashboard Cite

Machine learning based maximum power point tracking in solar energy conversion systems

Cited by 12 publications

References 6 publications

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

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

A novel design and analysis of hybrid fuzzy logic MPPT controller for solar PV system under partial shading conditions

Watertightness Design and Experimental Evaluation of a Solar Panel Structure for Building Integrated Photovoltaics (BIPV) Roofs

Contact Info

Product

Resources

About