A novel approach based on integration of convolutional neural networks and echo state network for daily electricity demand prediction
Article
Article Title | A novel approach based on integration of convolutional neural networks and echo state network for daily electricity demand prediction |
---|---|
ERA Journal ID | 5115 |
Article Category | Article |
Authors | Ghimire, Sujan, Nguyen-Huy, Thong, AL-Musaylh, Mohanad S., Deo, Ravinesh, Casillas-Perez, David and Salcedo-sanz, Sancho |
Journal Title | Energy |
Journal Citation | 275, p. 127430 |
Number of Pages | 24 |
Year | 2023 |
Publisher | Elsevier |
Place of Publication | United Kingdom |
ISSN | 0360-5442 |
1873-6785 | |
Digital Object Identifier (DOI) | https://doi.org/10.1016/j.energy.2023.127430 |
Web Address (URL) | https://www.sciencedirect.com/science/article/pii/S0360544223008241 |
Abstract | Predicting electricity demand data is considered an essential task in decisions taking, and establishing new infrastructure in the power generation network. To deliver a high-quality electricity demand prediction, this paper proposes a hybrid combination technique, based on a deep learning model of Convolutional Neural Networks and Echo State Networks, named as CESN. Daily electricity demand data from four sites (Roderick, Rocklea, Hemmant and Carpendale), located in Southeast Queensland, Australia, have been used to develop the proposed hybrid prediction model. The study also analyzes five other machine learning-based models (support vector regression, multilayer perceptron, extreme gradient boosting, deep neural network, and Light Gradient Boosting) to compare and evaluate the outcomes of the proposed deep learning approach. The results obtained in the experimental study showed that the proposed hybrid deep learning model is able to obtain the highest performance compared to other existing models developed for daily electricity demand data forecasting. Based on the statistical approaches utilized in this study, the proposed hybrid approach presents the highest prediction accuracy among the compared models. The obtained results showed that the proposed hybrid deep learning algorithm is an excellent and accurate electricity demand forecasting method, which outperformed the state of the art algorithms that are currently used in this problem. |
Keywords | Electricity demand forecasting; Sustainable energy; Artificial intelligence; Deep learning; Echo state networks; Convolutional neural networks; Hybrid algorithms |
ANZSRC Field of Research 2020 | 400899. Electrical engineering not elsewhere classified |
460207. Modelling and simulation | |
Byline Affiliations | School of Mathematics, Physics and Computing |
Centre for Applied Climate Sciences (Research) | |
Southern Technical University, Iraq | |
Rey Juan Carlos University, Spain | |
University of Alcala, Spain |
https://research.usq.edu.au/item/xzx80/a-novel-approach-based-on-integration-of-convolutional-neural-networks-and-echo-state-network-for-daily-electricity-demand-prediction
Download files
88
total views49
total downloads4
views this month1
downloads this month