ORIGINAL ARTICLE Predicting power production from a photovoltaic panel through artificial neural networks using atmospheric indicators Ismail Kayri 1 • Muhsin Tunay Gencoglu 2 Received: 9 June 2017 / Accepted: 13 November 2017 Ó The Natural Computing Applications Forum 2017 Abstract In this study, an artificial neural network was modeled in order to predict the power generated by a monocrystalline silicon photovoltaic panel. This experi- mental study measured and recorded the voltage and cur- rent generated by the photovoltaic panel for a year, along with environmental variables such as solar irradiance, air temperature, wind speed, wind direction, relative humidity, and angle of the sun’s elevation. In the results of the comparisons between measured and estimated power, a perfect estimation was found to have been conducted in which the root mean square error did not exceed 1.4% and the coefficient of correlation (R) ranged from 99.637 to 99.998%. These results were obtained from the testing dataset. In this study, achieved artificial neural network models are able to perform estimations for any location using the atmospheric indicators. These models are con- sidered able to lead investors using extremely sensitive and robust estimations in order to learn solar energy’s potential in a location. Keywords Renewable energy sources Á Solar energy Á Photovoltaic systems Á Artificial neural networks 1 Introduction In today’s world, energy is an important indicator of eco- nomic growth and social development. However, unsuit- able management of energy production damages the environment in the short and long term. The main objective of countries must be to develop proper policies for energy production from renewable energy sources rather than fossil fuels [1–3]. One more reason is that according to projections from the World Energy Forum, in less than a century, fossil fuels such as oil, coal, and gas will be depleted [4]. Especially in developing countries like Tur- key, various programs are carried out in order to sustain their place in this market. Photovoltaic (PV) R&D activi- ties in Turkey are conducted mainly in universities and industrial organizations. These projects are mainly funded by the State Planning Organization (DPT) and the Scien- tific Research Council of Turkey (TUBITAK) [5, 6]. According to the 2014 Report from the International Energy Agency (IEA), the recent quick spread and reduced cost of photovoltaics has unexpectedly increased their share in energy production [7, 8], which has created major changes in IEA’s long-term assumptions and roadmaps. According to the report, average annual growth over the past 10 years was found to be 49%. Only in 2013, PV systems with a total capacity of 37 GW were installed in 30 different countries, an annual growth of 35%. IEA links this unexpected growth to new trends in energy policies, and a decrease in PV costs depends on the market supply. According to IEA’s 2010 roadmap, PV systems are expected to provide 11% of the world’s energy demand by 2050 [6]. According to its 2014 roadmap, this rate was revised to 16%. This has brought new excitement to PV studies. & Ismail Kayri ismail.kayri@batman.edu.tr 1 Department of Electric Education, Faculty of Technical Education, Batman University, Batman, Turkey 2 Department Electric and Electronic Engineering, Faculty of Engineering, Firat University, Elazig, Turkey 123 Neural Comput & Applic DOI 10.1007/s00521-017-3271-6