Long-term power prediction of photovoltaic panels based on meteorological parameters and support vector machine

Saurabh Gupta, Palanisamy Ramasamy, Pandi Maharajan Murugamani, Selvakumar Kuppusamy, Selvabharathi Devadoss, Barath Suresh, Vignesh Kumar


Solar energy is the most generally accessible energy in the entire globe. Proper solar panel maintenance is necessary to reduce reliance on imported energy. Continuous monitoring of the solar panel's power output is required. The deployment of internet of things (IoT) monitoring of solar panels for maintenance is the basis for the current research. A multi-variable long-term photovoltaic (PV) power production prediction approach based on support vector machine (SVM) is developed in this study with the aim of completely evaluating the influence of PV panels performance and actual operational state factors on the power generation efficiency. This study examines the use of SVM and climatic factors to forecast the long-term output of power from solar panels. A solar power facility in a semi-arid area provided the data utilized in this investigation. Temperature, humidity, wind speed, and sun radiation are some of the meteorological variables that were considered in the study. To anticipate the power generation of the panels, the SVM is trained using the climatic factors and the power generation data. The findings demonstrate that the SVM model consistently predicts the panels' long-term power generation with a high degree of accuracy.


Internet of things; Meteorological system; Photovoltaic system; Solar energy; Support vector machine

Full Text:


DOI: http://doi.org/10.11591/ijeecs.v33.i2.pp687-695


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

The Indonesian Journal of Electrical Engineering and Computer Science (IJEECS)
p-ISSN: 2502-4752, e-ISSN: 2502-4760
This journal is published by the Institute of Advanced Engineering and Science (IAES) in collaboration with Intelektual Pustaka Media Utama (IPMU).

shopify stats IJEECS visitor statistics