We propose a multi-resolution selective ensemble extreme learning machine (MRSE-ELM) method for time-series prediction with the application to the next-step and next-day electricity consumption prediction. Specifically, at the current time stamp, the preceding timeseries data is sampled at different time intervals (i.e. resolutions) to constitute the time windows used for the prediction. The value at each sampled point can be certain statistics calculated from its associated time interval. At each resolution, multiple extreme learning machines (ELMs) with different numbers of hidden neurons are first trained. Then, sequential forward selection and least square regression are used to select an optimal set of trained ELMs to constitute the final ensemble model. The experimental results demonstrate that the proposed MRSE-ELM outperforms the best single ELM model across all resolutions. Compared to three state-of-the-art prediction models, MRSE-ELM shows its superiority on the next-step and next-day electricity consumption prediction tasks.
@inproceedings{DBLP:conf/iconip/SongQS17,
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/iconip/SongQS17.bib},
booktitle = {Neural Information Processing - 24th International Conference, ICONIP
2017, Guangzhou, China, November 14-18, 2017, Proceedings, Part V},
doi = {10.1007/978-3-319-70139-4_61},
editor = {Derong Liu and
Shengli Xie and
Yuanqing Li and
Dongbin Zhao and
El-Sayed M. El-Alfy},
pages = {600--609},
publisher = {Springer},
series = {Lecture Notes in Computer Science},
timestamp = {Mon, 16 Sep 2019 01:00:00 +0200},
title = {Multi-resolution Selective Ensemble Extreme Learning Machine for Electricity
Consumption Prediction},
url = {https://doi.org/10.1007/978-3-319-70139-4_61},
volume = {10638},
year = {2017}
}
© 2021 Flora Salim - CRUISE Research Group.