Time Series Electricity Consumption Analysis using Non-negative Matrix Factorization

Akira Kusaba, Tetsuji Kuboyama, Takako Hashimoto

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

For developing a sustainable society, energy management systems are utilized in many organizations. Chiba University of Commerce (CUC) is one of the organizations that has completely switched to renewable energy-sourced electricity for the first time in Japan. In the campus, energy consumption due to air conditioning, lightning and so on at each room is monitored. These monitoring data are stored on a data server via smart meters. In order to promote awareness to reduce electricity consumption, we need to summarize a vast amount of data so that we can interpret the data easily, and find out where we can afford to save electricity consumption. In this paper, we employ non-negative matrix factorization (NMF) for summarizing time-series electricity consumption patterns to analyze the electricity consumption data over time. Through the data analysis, we show that the visualization of factor matrices by dimensionality reduction enables us easily to interpret the low level electricity consumption data, and it gives us some awareness on energy saving.

Original languageEnglish
Title of host publication2019 IEEE 10th International Conference on Awareness Science and Technology, iCAST 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728138213
DOIs
Publication statusPublished - Oct 2019
Event10th IEEE International Conference on Awareness Science and Technology, iCAST 2019 - Morioka, Japan
Duration: Oct 23 2019Oct 25 2019

Publication series

Name2019 IEEE 10th International Conference on Awareness Science and Technology, iCAST 2019 - Proceedings

Conference

Conference10th IEEE International Conference on Awareness Science and Technology, iCAST 2019
CountryJapan
CityMorioka
Period10/23/1910/25/19

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Information Systems
  • Artificial Intelligence
  • Computer Science Applications

Fingerprint Dive into the research topics of 'Time Series Electricity Consumption Analysis using Non-negative Matrix Factorization'. Together they form a unique fingerprint.

Cite this