Short-term forecasting method for lighting energy consumption of large buildings based on time series analysis

Yanpeng Li and Guofeng Zhang

International Journal of Global Energy Issues, 2023, vol. 45, issue 3, 220-232

Abstract: In order to overcome the problems of high data noise, low prediction accuracy and long prediction time in the traditional short-term prediction method of lighting energy consumption of large buildings, a short-term prediction method of lighting energy consumption of large buildings based on time series analysis is proposed in this paper. The improved threshold function is used to denoise the data, and the fuzzy c-means clustering algorithm is used to cluster the denoised data. The time series analysis method is used to construct the self-excitation threshold autoregressive model. When the model parameters are optimal, the clustered data are input into the model to output the short-term prediction results of lighting energy consumption of large buildings. The experimental results show that compared with the traditional method, the average data noise of this method is 12.3 dB, the prediction accuracy remains above 94% and the average prediction time is only 57 ms.

Keywords: time series analysis; large buildings; lighting energy consumption; short-term forecast; fuzzy c-means clustering algorithm; self-excitation threshold autoregressive model; particle swarm optimisation algorithm. (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.inderscience.com/link.php?id=130673 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ids:ijgeni:v:45:y:2023:i:3:p:220-232

Access Statistics for this article

More articles in International Journal of Global Energy Issues from Inderscience Enterprises Ltd
Bibliographic data for series maintained by Sarah Parker ().