Informatics Publishing Limited

B. Jency Paulin ¹, E. Praynlin ¹

Affiliations
1 Department of Electronics and Communication Engineering, V V College of Engineering, IN

Abstract

Solar Energy is an important renewable and unlimited source of energy. Solar photovoltaic power forecasting, is an estimation of the expected power production, that help the grid operators to better manage the electric balance between power demand and supply. Neural network is a computational model that can predict new outcomes from past trends. The artificial neural network is used for photovoltaic plant energy forecasting. The output power for solar photovoltaic cell is predicted on hourly basis. In historical dataset collection process, two dataset was collected and used for analysis. The dataset was provided with three independent attributes and one dependent attributes. The implementation of Artificial Neural Network structure is done by Multilayer Perceptron (MLP) and training procedure for neural network is done by error Back Propagation (BP). In order to train and test the neural network, the datasets are divided in the ratio 70:30. The accuracy of prediction can be done by using various error measurement criteria and the performance of neural network is to be noted.

Keywords

Energy Forecasting, Error Back Propagation (BP).

Full Text

     

S. Jefrin Packia Mispah ¹, E. Praynlin ¹

Affiliations
1 Department of Electronics and Communication Engineering, VV College of Engineering, IN

Abstract

Sunlight based vitality is a perfect and sustainable power source asset that has progressively turned out to be imperative due to the diminishing utilization of fossil fuel resources over the world. Forecasting output power in a Solar Photovoltaic panel is one of the major challenges under outdoor conditions. In this work, the problem is considered and two methodologies for the estimation of solar photovoltaic output power is analysed. As it is an outdoor power prediction, a historical dataset is collected by considering various parameters such as wind speed, weather, temperature, wind direction, air pressure, and rainfall. The prediction is timed under 5 minute’s basis. The linear regression model based on the Ordinary Least Square (OLS) method minimizes the sum of the squares error (SSE) and provides better results for forecasting. The error between the independent variables and the dependent variables is reduced by using linear regression model. On the other hand, artificial neural network is the method used for forecasting in the statistical approach. The implementation of ANN display is finished with Multilayer Perceptron (MLP) and the preparation technique for neural system is finished by Back Propagation calculation. After the prediction, the accuracy is measured by various error measurement criteria like Mean Absolute Percentage Error (MAPE), Mean Magnitude of Relative Error (MMRE) and Root Mean Square Error (RMSE) and at last MAPE is considered for analysis. The result shows that artificial neural network model brings out better prediction when compared to linear regression model for maximum power prediction.

Keywords

Photovoltaic Module, Solar Energy, Linear Regression, Ordinary Least Square (OLS), Sum of the Squares Error (SSE), Artificial Neural Network, Multilayer Perceptron, Error Back Propagation (EBP).

Full Text