Uncorrected Author Proof Journal of Intelligent & Fuzzy Systems xx (20xx) x–xx DOI:10.3233/JIFS-201279 IOS Press 1 Photovoltaic power forecasting using wavelet Neuro-Fuzzy for active solar trackers 1 2 3 St´ efano Frizzo Stefenon a,b,∗ , Christopher Kasburg a , Roberto Zanetti Freire c , Fernanda Cristina Silva Ferreira a , Douglas Wildgrube Bertol b and Ademir Nied b 4 5 a Electrical Engineering, Center of Exact and Technological Sciences (CCET), University of Planalto Catarinense (UNIPLAC), Lages SC, Brazil 6 7 b Electrical Engineering Graduate Program (PPGEE), Department of Electrical Engineering, Santa Catarina State University (UDESC), Joinville SC, Brazil 8 9 c Industrial and Systems Engineering Graduate Program (PPGEPS), Polytechnique School (EP), Pontifical Catholic University of Parana (PUCPR), Curitiba PR, Brazil 10 11 Abstract. The generation of electric energy by photovoltaic (PV) panels depends on many parameters, one of them is the sun’s angle of incidence. By using solar active trackers, it is possible to maximize generation capacity through real-time positioning. However, if the engines that update the position of the panels use more energy than the difference in efficiency, the solar tracker system becomes ineffective. In this way, a time series forecasting method can be assumed to determine the generation capacity in a pre-established horizon prediction to evaluate if a position update would provide efficient results. Among a wide range of algorithms that can be used in forecasting, this work considered a Neuro-Fuzzy Inference System due to its combined advantages such as smoothness property from Fuzzy systems and adaptability property from neural networks structures. Focusing on time series forecasting, this article presents a model and evaluates the solar prediction capacity using the Wavelet Neuro-Fuzzy algorithm, where Wavelets were included in the model for feature extraction. In this sense, this paper aims to evaluate whether it is possible to obtain reasonable accuracy using a hybrid model for electric power generation forecasting considering solar trackers. The main contributions of this work are related to the efficiency improvement of PV panels. By assuming a hybrid computational model, it is possible to make a forecast and determine if the use of solar tracking is interesting during certain periods. Finally, the proposed model showed promising results when compared to traditional Nonlinear autoregressive model structures. 12 13 14 15 16 17 18 19 20 21 22 23 24 25 Keywords: Photovoltaic panels, Neuro-Fuzzy inference system, time series forecasting, wavelets, solar trackers 26 1. Introduction 27 There exist different types of solar trackers, from 28 sensor-based to sensorless systems. A sensor-based 29 solar tracker considers a closed-loop system where 30 photosensors are used for tracking the sun direc- 31 ∗ Corresponding author. St´ efano Frizzo Stefenon, E-mail: stefanostefenon@gmail.com. tion using a feedback control scheme [1]. Frequently, 32 light-dependent resistors (LDRs) are assumed to pro- 33 vide feedback signals to obtain the correct azimuth 34 angle showing the daily path of the sun. In appli- 35 cations involving photovoltaic (PV) panels, solar 36 trackers can maximize the amount of energy to be 37 captured by changing panels position. To obtain the 38 best performance, motors are used for position adjust- 39 ment, however, if the motors are not correctly sized 40 ISSN 1064-1246/20/$35.00 © 2020 – IOS Press and the authors. All rights reserved