Load Classification and Driven Factors Identification Based on Ensemble Clustering

Kaile Zhou () and Lulu Wen ()
Additional contact information
Kaile Zhou: Hefei University of Technology
Lulu Wen: Hefei University of Technology

Chapter Chapter 4 in Smart Energy Management, 2022, pp 81-99 from Springer

Abstract: Abstract A two-stage framework is presented for residential load classification and driven factors identification in this chapter. In the first stage, a combined method of k-means and spectral clustering (CKSC) is first used for load classification. In the second stage called driven factors identification, different residential load patterns in weekdays and weekends are first analyzed. Then driven factors behind each load pattern are investigated based on multi-nominal logistic regression. Experiment is carried out on the Irish open data, including both detailed smart meter measurements in a 30-min time interval and the survey data of 4,181 households. It shows that CKSC method obtains clustering results from the load profile data with high efficiency. Households with different load patterns are efficiently divided into several groups. The driven factors behind each pattern are found and discussed further. Knowledge discovered from load classification and driven factors identification can support better understanding of residential energy use and thus support the development of targeted energy service strategies.

Date: 2022
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

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:spr:sprchp:978-981-16-9360-1_4

Ordering information: This item can be ordered from
http://www.springer.com/9789811693601

DOI: 10.1007/978-981-16-9360-1_4

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().