Deakin University
Browse

File(s) under permanent embargo

Improving load forecasting based on deep learning and K-shape clustering

Version 2 2024-06-04, 06:14
Version 1 2017-11-17, 20:50
conference contribution
posted on 2024-06-04, 06:14 authored by F Fahiman, SM Erfani, Sutharshan RajasegararSutharshan Rajasegarar, M Palaniswami, C Leckie
One of the most crucial tasks for utility companies is load forecasting in order to plan future demand for generation capacity and infrastructure. Improving load forecasting accuracy over a short period is a challenging open problem due to the variety of factors that influence the load, and the volume of data that needs to be considered. This paper proposes a new approach for short term load forecasting using an effective new combination of clustering and deep learning methods, along with a new weighted aggregation mechanism. Our evaluation using smart meter data from a publicly available real-life dataset demonstrates the improved accuracy of our approach over existing methods.

History

Pagination

4134-4141

Location

Anchorage, Alaska

Start date

2017-05-14

End date

2017-05-19

ISBN-13

9781509061815

Language

eng

Publication classification

E Conference publication, E1.1 Full written paper - refereed

Copyright notice

2017, IEEE

Title of proceedings

IJCNN 2017 : Proceedings of the International Joint Conference on Neural Networks 2017

Event

Neural Networks. International Joint Conference (2017 : Anchorage, Alaska)

Publisher

IEEE

Place of publication

Piscataway, N.J.

Usage metrics

    Research Publications

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC