A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
AI based Optimization of Global Maximum Power Point Tracking for Photovoltaic Systems during Partial Shading Conditions
This paper aims to investigate the suitability of Artificial Intelligence (AI) based algorithms for optimizing the Global Maximum Power Point Tracking (GMPPT) performance in Photovoltaic (PV) systems during partial shading conditions (PSC). The performance of AI based techniques such as Genetic Algorithm (GA), Fuzzy Logic Control (FLC), Partial swarm optimization (PSO), Artificial Neural Network (ANN) and Adaptive Neuro Fuzzy Inference Systems (ANFIS) will be examined in this paper. A range of PV system configurations, such as 3 panel, 4 panel and 6 panel PV strings and various DC-DC converter topologies, including buck and boost converters, are utilized to test the scalability and variability of the designs. For evaluating the effectiveness of GMMP tracking during PSC a PV system is modelled and simulated using MATLAB SIMULINK. Fuzzy Logic Control and Artificial Neural Network, Adaptive Neuro Fuzzy Inference Systems (ANFIS) based MPPT are implemented using Fuzzy Toolbox, Neural Network Toolbox and ANFIS toolbox in MATLAB. The outcome of the study shows that the GA algorithm exhibits instability and oscillations during partial shading conditions (PSC), failing to track the Global MPP (GMPP) under PSC reliably. The FLC algorithm struggles to track the GMPP during PSC accurately. On the other side, PSO demonstrates a good tracking performance, achieving a GMPP tracking efficiency of 90.23% on average, though it does not track under certain PSCs the average MPPT tracking efficiency of ANN is 77.71% for the six cases. However, ANN is unable to track GMPP and is unstable during PSC. Out of six partial shading tests conducted, ANFIS MPPT was able to track the GMPP in three specific PSC scenarios.
AI based Optimization of Global Maximum Power Point Tracking for Photovoltaic Systems during Partial Shading Conditions
This paper aims to investigate the suitability of Artificial Intelligence (AI) based algorithms for optimizing the Global Maximum Power Point Tracking (GMPPT) performance in Photovoltaic (PV) systems during partial shading conditions (PSC). The performance of AI based techniques such as Genetic Algorithm (GA), Fuzzy Logic Control (FLC), Partial swarm optimization (PSO), Artificial Neural Network (ANN) and Adaptive Neuro Fuzzy Inference Systems (ANFIS) will be examined in this paper. A range of PV system configurations, such as 3 panel, 4 panel and 6 panel PV strings and various DC-DC converter topologies, including buck and boost converters, are utilized to test the scalability and variability of the designs. For evaluating the effectiveness of GMMP tracking during PSC a PV system is modelled and simulated using MATLAB SIMULINK. Fuzzy Logic Control and Artificial Neural Network, Adaptive Neuro Fuzzy Inference Systems (ANFIS) based MPPT are implemented using Fuzzy Toolbox, Neural Network Toolbox and ANFIS toolbox in MATLAB. The outcome of the study shows that the GA algorithm exhibits instability and oscillations during partial shading conditions (PSC), failing to track the Global MPP (GMPP) under PSC reliably. The FLC algorithm struggles to track the GMPP during PSC accurately. On the other side, PSO demonstrates a good tracking performance, achieving a GMPP tracking efficiency of 90.23% on average, though it does not track under certain PSCs the average MPPT tracking efficiency of ANN is 77.71% for the six cases. However, ANN is unable to track GMPP and is unstable during PSC. Out of six partial shading tests conducted, ANFIS MPPT was able to track the GMPP in three specific PSC scenarios.
AI based Optimization of Global Maximum Power Point Tracking for Photovoltaic Systems during Partial Shading Conditions
Viswambaran, Vidhya (author) / Bati, Akram (author) / Pillai, Swaroop (author) / Elizabeth Michael, Neethu (author)
2024-06-03
1155497 byte
Conference paper
Electronic Resource
English
| British Library Online Contents | 2017
| British Library Online Contents | 2017