Home // ENERGY 2022, The Twelfth International Conference on Smart Grids, Green Communications and IT Energy-aware Technologies // View article

Photovoltaic Generation Forecasting – A Case Study

Authors:
Sinan Wannous
Isabel Praça
Rui Andrade
Sergio Ramos

Keywords: Energy Prediction; Energy Forecasting Tools; Prediction Models; Machine Learning

Abstract:
The increasing demand for renewable energy sources has empowered their integration into existing power networks. This initiated an interest in investigating the capabilities of these clean sources and how can then be efficiently utilized to support the balance of energy markets. In this regard, forecasting energy generation has become an essential research problem to improve the reliability of energy systems. It is of key importance to meet the energy demand, as well as to bridge the gap between energy consumption and production in energy markets. In this research, we present a case study to investigate the performance of ensemble learning models for forecasting the energy generation of photovoltaic (PV) modules. For this purpose, we utilize a dynamic energy forecasting tool to perform various experiments with different combinations of input data fields. Primarily, the performance of 3 ensemble learning models (Adaboost, Random Forest, and Gradient Boosting Regressor) has been investigated and then compared to the predictions of two previously undertaken neural network-based methods. The results indicated higher accuracy of the ensemble approaches in almost all experiments. Which was also better than the accuracy of the neural networks-based methods.

Pages: 36 to 41

Copyright: Copyright (c) IARIA, 2022

Publication date: May 22, 2022

Published in: conference

ISSN: 2308-412X

ISBN: 978-1-61208-967-6

Location: Venice, Italy

Dates: from May 22, 2022 to May 26, 2022