Research Article

A MAXIMUM POWER POINT TRACKING ALGORITHM BASED ON ARTIFICAL NEURAL NETWORK AND PARTICLE SWARM OPTIMIZATION IN PARTAL SHADING

Volume: 26 Number: 4 December 3, 2023
EN TR

A MAXIMUM POWER POINT TRACKING ALGORITHM BASED ON ARTIFICAL NEURAL NETWORK AND PARTICLE SWARM OPTIMIZATION IN PARTAL SHADING

Abstract

In photovoltaic (PV) systems, partial shading occurs under real conditions when maximum power point tracking (MPPT) is performed. In this paper, a PV system consisting of PV panels and a boost converter is created in MATLAB/Simulink to investigate the partial shadowing conditions. Conventional and artificial intelligence-based MGNT algorithms are applied to this system. In order to track the maximum power point (MPP), the traditional method of the Perturb and Observe algorithm and Artificial Neural Networks (ANN) technique are used. In addition to the classical ANN technique, a hybrid technique was created with Particle Swarm Optimization (PSO). First, the partial shading situation was simulated with different scenarios. To support the accuracy of the algorithms, real-time irradiance data for two days, both sunny and cloudy, were collected and analyzed in MATLAB/Simulink on the PV system. As a result of the analysis, it was observed that the PSO-based ANN technique tracks MPP more efficiently than other algorithms. This study contributes to the studies on MGNT in the case of partial shading and demonstrates the use of artificial intelligence algorithms for PV systems, which is a different field.

Keywords

References

  1. Ahmed, Sajib, Saad Mekhilef, Marizan Mubin, Kok Soon Tey, and Mostefa Kermadi. 2023. “An Enhanced Scanning Technique for Flexible Power Point Tracking under Partial Shading Condition.” Solar Energy 262(January):111817. doi: 10.1016/j.solener.2023.111817.
  2. Al-Majidi, Sadeq D., Maysam F. Abbod, and Hamed S. Al-Raweshidy. 2020. “A Particle Swarm Optimisation-Trained Feedforward Neural Network for Predicting the Maximum Power Point of a Photovoltaic Array.” Engineering Applications of Artificial Intelligence 92(September 2019):103688. doi: 10.1016/j.engappai.2020.103688.
  3. Bollipo, Ratnakar Babu, Suresh Mikkili, and Praveen Kumar Bonthagorla. 2020. “Hybrid, Optimization, Intelligent and Classical PV MPPT Techniques: Review.” CSEE Journal of Power and Energy Systems 7(1):9–33. doi: 10.17775/CSEEJPES.2019.02720.
  4. Bouselham, L., B. Hajji, and H. Hajji. 2015. “Comparative Study of Different MPPT Methods for Photovoltaic System.” Pp. 1–5 in 2015 3rd International Renewable and Sustainable Energy Conference (IRSEC). IEEE.
  5. Divyasharon, R., R. Narmatha Banu, and D. Devaraj. 2019. “Artificial Neural Network Based MPPT with CUK Converter Topology for PV Systems Under Varying Climatic Conditions.” Pp. 1–6 in 2019 IEEE International Conference on Intelligent Techniques in Control, Optimization and Signal Processing (INCOS). IEEE.
  6. Elbarbary, Zakaria Mohamed Salem, and Mohamed Abdullrahman Alranini. 2021. “Review of Maximum Power Point Tracking Algorithms of PV System.” Frontiers in Engineering and Built Environment 1(1):68–80. doi: 10.1108/FEBE-03-2021-0019.
  7. Farah, Lotfi, Amir Hussain, Abdelfateh Kerrouche, Cosimo Ieracitano, Jamil Ahmad, and Mufti Mahmud. 2020. “A Highly-Efficient Fuzzy-Based Controller with High Reduction Inputs and Membership Functions for a Grid-Connected Photovoltaic System.” IEEE Access 8:163225–37. doi: 10.1109/ACCESS.2020.3016981.
  8. Fathi, Milad, and Jafar Amiri Parian. 2021. “Intelligent MPPT for Photovoltaic Panels Using a Novel Fuzzy Logic and Artificial Neural Networks Based on Evolutionary Algorithms.” Energy Reports 7:1338–48. doi: 10.1016/j.egyr.2021.02.051.

Details

Primary Language

Turkish

Subjects

Photovoltaic Power Systems , Electrical Engineering (Other)

Journal Section

Research Article

Publication Date

December 3, 2023

Submission Date

June 22, 2023

Acceptance Date

October 23, 2023

Published in Issue

Year 1970 Volume: 26 Number: 4

APA
Baldan, E., & Erişti, H. (2023). PARÇALI GÖLGELENME DURUMUNDA YAPAY SİNİR AĞLARI VE PARÇACIK SÜRÜ OPTİMİZASYONU TABANLI BİR MAKSİMUM GÜÇ NOKTASI TAKİBİ ALGORİTMASI. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 26(4), 895-908. https://doi.org/10.17780/ksujes.1318480