Prediction of Solar Radiation Using Artificial Neural Network

TL;DR

This paper develops and compares two artificial neural network models to accurately predict hourly solar radiation using weather data, aiding various solar energy applications.

Contribution

It introduces two ANN-based models for solar radiation prediction utilizing weather datasets, demonstrating their effectiveness through statistical evaluation.

Findings

Models achieved low MAE and MSE, indicating accurate predictions.

ANN models effectively interpret weather patterns for solar radiation forecasting.

The approach enhances solar energy planning and management.

Abstract

Most solar applications and systems can be reliably used to generate electricity and power in many homes and offices. Recently, there is an increase in many solar required systems that can be found not only in electricity generation but other applications such as solar distillation, water heating, heating of buildings, meteorology and producing solar conversion energy. Prediction of solar radiation is very significant in order to accomplish the previously mentioned objectives. In this paper, the main target is to present an algorithm that can be used to predict an hourly activity of solar radiation. Using a dataset that consists of temperature of air, time, humidity, wind speed, atmospheric pressure, direction of wind and solar radiation data, an Artificial Neural Network (ANN) model is constructed to effectively forecast solar radiation using the available weather forecast data. Two models are created to efficiently create a system capable of interpreting patterns through supervised learning data and predict the correct amount of radiation present in the atmosphere. The results of the two statistical indicators: Mean Absolute Error (MAE) and Mean Squared Error (MSE) are performed and compared with observed and predicted data. These two models were able to generate efficient predictions with sufficient performance accuracy.