Publication Date

2024

Document Type

Dissertation/Thesis

First Advisor

Shamim, Tariq

Degree Name

M.S. (Master of Science)

Legacy Department

Department of Mechanical Engineering

Abstract

The efficiency levels to convert from sunlight to electricity are in the range up to 22% commercially, based on the technology used. Due to comparatively low efficiency of photovoltaic systems, it is imperative to extract maximum power from the PV module array. Thus, in solar PV system, tracking the module’s MPP (maximum power point) is crucial and at the same time challenging as well due to varying climatic conditions. This research focuses on the modeling and performance evaluation of traditional Maximum Power Point Tracking (MPPT) techniques and AI-Based MPPT algorithms in photovoltaic systems. It addresses the issue of dynamic adjustment of the electrical operating point depending on various environmental conditions to maintain peak power output. The study utilizes a simulated PV cell and identifies suitable algorithms, comparing Perturb & Observe MPPT techniques to a machine learning based Neural Network algorithm which finds the most effective electrical point for the PV model in question. The study searched into various performance aspects such as power output, accuracy, stability, efficiency, and convergence time under different seasonal variations, including investigation of mathematical functions using both sinusoidal and step-change irradiance inputs. The ANN-based MPPT system consistently demonstrated superior performance across all parameters when compared to traditional P&O methods. It exhibited faster convergence to the maximum power point (MPP), reduced oscillations, and higher power output, especially in scenarios where environmental conditions changed rapidly. The study also discussed the process of integrating AI techniques into MPPT. The goal of the study is to conclude the suitable PV system analyzing the results and performance comparison between the two systems.

Extent

86 pages

Language

en

Publisher

Northern Illinois University

Rights Statement

In Copyright

Rights Statement 2

NIU theses are protected by copyright. They may be viewed from Huskie Commons for any purpose, but reproduction or distribution in any format is prohibited without the written permission of the authors.

Media Type

Text

Share

COinS