Investigating PV Power Loss Correlations with Environmental Factors: A Case Study from Delhi

Photovoltaic (PV) systems exhibit a high degree of environmental sensitivity, which can result in power losses and reduced system efficiency. To analyze power loss in PV systems, this paper presents an analytical method that uses the Random Forest algorithm while accounting for environmental factors like dust density, temperature, irradiance, humidity, and wind speed. To investigate these relationships, cross-sectional data were analyzed. The data came from rooftop PV plant situated at a University in Delhi, India, were collected between January 1, 2021, and December 31, 2021. Because of its ability to manage non-linear relationships between variables and enable a thorough understanding of complex interactions, the Random Forest model was chosen. It can be helpful in predicting power outages as well as identifying how specific environmental factors affected the operation of the system. Pair plots and scatter plots were used in data preprocessing and exploratory analysis to show that dust concentration is one of the main factors affecting power loss. Dust concentration is closely correlated with ambient temperature, highlighting the urgent need for strategies to mitigate these impacts to increase the efficiency of PV systems. The data reveals that power loss peaks around 2000 W, indicating a significant loss threshold. The results highlight the need for ongoing observation and flexible management to improve performance in a variety of environmental settings.