In this paper, Extreme Learning Machine (ELM) is shown to be a powerful tool for electricity consumption prediction, demonstrated by its competitive prediction accuracy and superior computational speed compared to Support Vector Machine (SVM). Moreover, ELM is utilized to investigate the potentials of using auxiliary information such as electricity-related factors and environmental factors to augment the prediction accuracy obtained by purely using the electricity consumption factors. Furthermore, we formulate a combinatorial optimization problem of seeking for an optimal subset of auxiliary factors and their corresponding optimal window sizes using the most suitable ELM structure, and propose a Discrete Dynamic Multi- Swarm Particle Swarm Optimization (DDMS-PSO) to address this problem. Experimental studies on a real-world building dataset demonstrate that electricity-related factors improve accuracy while environmental factors further boost the performance. By using DDMS-PSO, we find a subset of electricity-related and environmental factors, their respective window sizes, and the number of hidden neurons in ELM which lead to the best prediction accuracy.
@inproceedings{DBLP:conf/ijcnn/SongQS16,
author = {Hui Song and
A. Kai Qin and
Flora D. Salim},
bibsource = {dblp computer science bibliography, https://dblp.org},
biburl = {https://dblp.org/rec/conf/ijcnn/SongQS16.bib},
booktitle = {2016 International Joint Conference on Neural Networks, IJCNN 2016,
Vancouver, BC, Canada, July 24-29, 2016},
doi = {10.1109/IJCNN.2016.7727486},
pages = {2313--2320},
publisher = {IEEE},
timestamp = {Wed, 16 Oct 2019 14:14:55 +0200},
title = {Multivariate electricity consumption prediction with Extreme Learning
Machine},
url = {https://doi.org/10.1109/IJCNN.2016.7727486},
year = {2016}
}
© 2021 Flora Salim - CRUISE Research Group.