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

Authors: Yanpeng Li; Guofeng Zhang

Addresses: Department of Environmental Design, University of Science and Technology Liaoning, Liaoning, Anshan, China; Department of Architecture, University of Science and Technology Liaoning, Liaoning, Anshan, China ' Department of Environmental Design, University of Science and Technology Liaoning, Liaoning, Anshan, China; Department of Architecture, University of Science and Technology Liaoning, Liaoning, Anshan, China

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.

DOI: 10.1504/IJGEI.2023.130673

International Journal of Global Energy Issues, 2023 Vol.45 No.3, pp.220 - 232

Received: 16 Dec 2021
Accepted: 01 Jun 2022
Published online: 02 May 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article