Machine Learning Based Photovoltaics (PV) Power Prediction Using Different Environmental Parameters of Qatar

• Published in: Energies (Basel) Vol. 12; no. 14; p. 2782
• Main Authors: Khandakar, Amith, Chowdhury, Muhammad E H, Kazi, Monzure Khoda, Kamel Benhmed, Touati, Farid, Al-Hitmi, Mohammed, Antonio Jr S P Gonzales
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 19-07-2019
• Subjects: Algorithms; Alternative energy sources; Ambient temperature; Artificial intelligence; artificial neural network; Bias; Calibration; Climate change; Computer applications; Datasets; Economic forecasting; Electric power; Electricity distribution; Energy; Energy resources; Energy sources; Engineering schools; Environmental effects; environmental parameters; Error analysis; Fossil fuels; Gaussian process; Harsh environments; Irradiance; Laboratories; Learning algorithms; Learning theory; Machine learning; Model accuracy; multiple regression model; Multiple regression models; Neural networks; Optimization; Parameter sensitivity; Photovoltaics; Prediction models; PV power prediction; Regression analysis; Relative humidity; renewable energy; Root-mean-square errors; Sensors; Software; Solar energy; Systems stability; Weather; Wind speed; Work stations; United States > US; Qatar; Singapore
• ISSN: 1996-1073; 1996-1073
• DOI: 10.3390/en12142782

Photovoltaics (PV) output power is highly sensitive to many environmental parameters and the power produced by the PV systems is significantly affected by the harsh environments. The annual PV power density of around 2000 kWh/m2 in the Arabian Peninsula is an exploitable wealth of energy source. These countries plan to increase the contribution of power from renewable energy (RE) over the years. Due to its abundance, the focus of RE is on solar energy. Evaluation and analysis of PV performance in terms of predicting the output PV power with less error demands investigation of the effects of relevant environmental parameters on its performance. In this paper, the authors have studied the effects of the relevant environmental parameters, such as irradiance, relative humidity, ambient temperature, wind speed, PV surface temperature and accumulated dust on the output power of the PV panel. Calibration of several sensors for an in-house built PV system was described. Several multiple regression models and artificial neural network (ANN)-based prediction models were trained and tested to forecast the hourly power output of the PV system. The ANN models with all the features and features selected using correlation feature selection (CFS) and relief feature selection (ReliefF) techniques were found to successfully predict PV output power with Root Mean Square Error (RMSE) of 2.1436, 6.1555, and 5.5351, respectively. Two different bias calculation techniques were used to evaluate the instances of biased prediction, which can be utilized to reduce bias to improve accuracy. The ANN model outperforms other regression models, such as a linear regression model, M5P decision tree and gaussian process regression (GPR) model. This will have a noteworthy contribution in scaling the PV deployment in countries like Qatar and increase the share of PV power in the national power production.