SOLAR PHOTOVOLTAIC PANEL DEGRADATION AND OUTPUT POWER PREDICTION USING ENVIRONMENTAL INPUTS

Abstract

Solar energy has emerged as a key renewable energy source due to the growing
demand for clean and sustainable power. Solar photovoltaic (PV) panels convert
sunlight into electricity; however, their performance gradually declines over time
because of degradation and varying environmental conditions. Factors such as solar
radiation, temperature, humidity, wind speed, and air pressure significantly influence
the efficiency and output power of PV systems. Accurate prediction of PV panel
output and understanding degradation patterns are therefore essential for optimizing
performance, planning maintenance, and improving energy management.
This project, titled “Solar Photovoltaic Panel Degradation and Output Power
Prediction Using Environmental Inputs,” focuses on analyzing the impact of
environmental parameters on PV panel performance and predicting power output
using machine learning techniques. The dataset used includes features such as solar
radiation, air temperature, wind speed, sunshine duration, air pressure, relative
humidity, and corresponding power generation values.
Data preprocessing and feature selection are performed to ensure data quality and
identify the most influential factors affecting power output. Machine learning models
are trained to learn the relationship between environmental conditions and PV system
performance. The trained model can predict output power based on given
environmental inputs, enabling early detection of performance degradation and
inefficiencies.
The proposed system enhances the monitoring and maintenance of solar PV systems
by providing accurate predictions and insights.