Work

Comparative Evaluation of PV Systems Efficiency Using Machine Learning Models

Year: 2026

Type: conference-paper

Abstract: Various elements, such as solar irradiation, angle of incidence, ambient temperature, wind speed and direction, shading effects, panel degradation, and other environmental and operational parameters, may substantially affect the efficiency of photovoltaic (PV) systems. This paper examines critical factors influencing PV performance, including cooling solutions, temperature coefficient evaluation, geographical effects, and sophisticated materials, emphasizing the effects of solar irradiation and ambient temperature. The potential of artificial intelligence (AI) in forecasting PV system efficiency is examined. Four Machine Learning (ML) models are used; the Neural Network outperforms others in performance, while the Fine Tree model offers superior training time. Feature importance analysis indicates that prioritizing solar irradiance enhances PV prediction accuracy, while excluding low-impact variables, such as wind direction, enables simpler, cost-effective, and reliable real-world PV prediction systems.

Source: IEEE Jordan Conference on Applied Electrical Engineering and Computing Technologies

DOI: 10.1109/aeect69724.2026.11657888

Authors: Nour Husain, Mohammed Jouda, Mohammed Salem, Mohammed Wadi

Institution: İstanbul Sabahattin Zaim Üniversitesi

Language: English

Topic: Photovoltaic System Optimization Techniques

Subfield: Renewable Energy, Sustainability and the Environment

Field: Energy

Domain: Physical Sciences

SDGs: Affordable and clean energy, Industry, innovation and infrastructure, Climate action

Open Access status: hybrid

OpenAlex ID: W7204179208

FWCI:

Cites: 24

Cited by:

Related to: 10