International Journal of Electrical and Electronics Research (IJEER) Open Access | Rapid and quality publishing Research Article | Volume 10, Issue 4 | Pages 779-783 | e-ISSN: 2347-470X 779 Website: www.ijeer.forexjournal.co.in Output Power Prediction of Solar Photovoltaic Panel ░ ABSTRACT- Solar power-based photovoltaic energy conversion could be considered one of the best sustainable sources of electric power generation. Thus, the prediction of the output power of the photovoltaic panel becomes necessary for its efficient utilization. The main aim of this paper is to predict the output power of solar photovoltaic panels using different machine learning algorithms based on the various input parameters such as ambient temperature, solar radiation, panel surface temperature, relative humidity and time of the day. Three different machine learning algorithms namely, multiple regression, support vector machine regression and gaussian regression were considered, for the prediction of output power, and compared on the basis of results obtained by different machine learning algorithms. The outcomes of this study showed that the multiple linear regression algorithm provides better performance with the result of mean absolute error, mean squared error, coefficient of determination and accuracy of 0.04505, 0.00431, 0.9981 and 0.99997 respectively, whereas the support vector machine regression had the worst prediction performance. Moreover, the predicted responses are in great understanding with the actual values indicating that the purposed machine learning algorithms are quite appropriate for predicting the output power of solar photovoltaic panels under different environmental conditions. Keywords: Solar photovoltaic, Output power, Machine learning, Support vector machine regression, Multiple linear regression, Gaussian regression. ░ 1. INTRODUCTION The generation of electrical power, usage and storage are the key parameters for the development of any country. Due to the tremendous changes in technology and industrial sectors the demand for electrical power also increases [1]. Electric power can be generated by the help of un-replenishable and replenishable energy sources. The major drawback of non- renewable(conventional) power generation is its environmental pollution and unsustainable nature. However, at the present, electrical power generation is highly dependent on the conventional technique and for this reason, there is a need to promote a sustainable and environment-friendly source of electrical power generation [2]. Renewable sources of power generation like solar, wind, biomass, geothermal, tidal etc., has the potential to provide an environment-friendly and sustainable source of electrical power generation. In all renewable sources, solar energy has sufficient potential to meet the demand of future power generation. Therefore, solar energy could be considered an alternative source of power generation. The solar energy which is coming from the sun can be converted into electrical energy by the practice of a photovoltaic (PV) panel that works on the principle of the photovoltaic effect [3]. In general, the PV panels are installed in an open environment where it experiences a change in their output power due to the change in the operating parameters [4]. The operating parameter namely atmospheric temperature, solar radiation, relative humidity, panel surface temperature and time of operation are responsible for the change in PV panel output power [5]. Any changes in these parameters affect the panel output power considerably. The yield value of the PV panel is strongly dependent on the solar radiation that falls on its surface. In PV panel operation, solar radiation is linearly related to the output power and current whereas the output voltage is logarithmically related to solar radiation [6]. Atmospheric temperature is the other operating parameter that affects PV panel output and any increase in its value puts a proportional impact on the panel temperature, as a result of this, panel yield value decreases [7]. In a study, a negative impact on the panel output was observed due to a rise in its surface temperature [8]. In [9] the rate of reduction of output power and fill factor, with reference to panel temperature, were recorded as 0.65%/K and 0.2%/K [9]. Another study showed a decrement of 9% due to the 20% increase in panel temperature [10]. Humidity, which is defined Output Power Prediction of Solar Photovoltaic Panel Using Machine Learning Approach Abhishek Kumar Tripathi 1 , Neeraj Kumar Sharma 2 , Jonnalagadda Pavan 3 and Sriramulu Bojjagania 4 1 Dept of Mining Engineering, Aditya Engineering College, Surampalem, AP, India, Email: abhishekkumar@aec.edu.in 2 Dept. of Computer Science and Engineering, SRM University-AP, Amaravati, AP, India, Email: neeraj16ks@gmail.com 3 Dept. of Electrical and Electronics Engineering, Aditya Engineering College, Surampalem, Andhra Pradesh, India, Email: pavan.jonnalagadda@aec.edu.in 4 Dept. of Computer Science and Engineering, SRM University-AP, Amaravati, AP, India, Email: sriramulubojjagani@gmail.com *Correspondence: Abhishek Kumar Tripathi; Email: abhishekkumar@aec.edu.in ARTICLE INFORMATION Author(s): Abhishek Kumar Tripathi, Neeraj Kumar Sharma, Jonnalagadda Pavan and Sriramulu Bojjagania; Received: 12/07/2022; Accepted: 03/10/2022; Published:18/10/2022; e-ISSN: 2347-470X; Paper Id: IJEER-RDECS3242; Citation: 10.37391/IJEER.100401 Webpage-link: https://ijeer.forexjournal.co.in/archive/volume-10/ijeer-100401.html Publisher’s Note: FOREX Publication stays neutral with regard to Jurisdictional claims in Published maps and institutional affiliations.