The Korean Journal of Applied Statistics (응용통계연구)

The Korean Statistical Society (한국통계학회)
권호 표지
DOI QR코드

DOI QR Code

Clustering load patterns recorded from advanced metering infrastructure

AMI로부터 측정된 전력사용데이터에 대한 군집 분석

  • Ann, Hyojung (Department of Statistics, The Graduate School of Chung-Ang University) ;
  • Lim, Yaeji (Department of Statistics, The Graduate School of Chung-Ang University)
  • Received : 2021.07.12
  • Accepted : 2021.08.06
  • Published : 2021.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

We cluster the electricity consumption of households in A-apartment in Seoul, Korea using Hierarchical K-means clustering algorithm. The data is recorded from the advanced metering infrastructure (AMI), and we focus on the electricity consumption during evening weekdays in summer. Compare to the conventional clustering algorithms, Hierarchical K-means clustering algorithm is recently applied to the electricity usage data, and it can identify usage patterns while reducing dimension. We apply Hierarchical K-means algorithm to the AMI data, and compare the results based on the various clustering validity indexes. The results show that the electricity usage patterns are well-identified, and it is expected to be utilized as a major basis for future applications in various fields.

본 연구에서는 Hierarchical K-means 군집화 알고리즘을 이용해 서울의 A아파트 가구들의 전력 사용량 패턴을 군집화 하였다. 차원을 축소해주면서 패턴을 파악할 수 있는 Hierarchical K-means 군집화 알고리즘은 기존 K-means 군집화 알고리즘의 단점을 보완하여 최근 대용량 전력 사용량 데이터에 적용되고 있는 방법론이다. 본 연구에서는 여름 저녁 피크 시간대의 시간당 전력소비량 자료에 대해 군집화 알고리즘을 적용하였으며, 다양한 군집 개수와 level에 따라 얻어진 결과를 비교하였다. 결과를 통해 사용량에 따라 패턴이 군집화 됨을 확인하였으며, 군집화 유효성 지수들을 통해 이를 비교하였다.

Keywords

Acknowledgement

본 연구는 2021년도 정부의 재원으로 한국연구재단의 지원을 받았으며 (NRF-2021R1A2B5B01001790), 산업통상자원부(MOTIE)와 한국에너지기술평가원(KETEP)의 지원을 받아 수행한 연구 과제입니다 (No. 20199710100060).

References

  1. Chicco G, Napoli R, and Piglione F (2006). Comparisons among clustering techniques for electricity customer classification, IEEE Transactions on power systems, 21, 933-940.
  2. Desgraupes B (2017). Clustering Indices, University of Paris Ouest-Lab Modal'X, 1, 34.
  3. Jung D, Yoon Y, and Moon H (2017). Clustering of Energy Consumption Patterns from a Complex Commercial Building using K-means Algorithm, Autumn Conference, 175-176.
  4. Kim C and Park G (2015). Analyze Structural Changes and Factors of Change of Domestic Power Consumption Pattern, Korea Energy Economics Institute.
  5. Kim HM, Kim IG, Park KJ, and Yoo SH (2015). The effect of temperature on the electricity demand: An empirical investigation, Journal of Energy Engineering, 24, 167-173. https://doi.org/10.5855/ENERGY.2015.24.2.167
  6. Kwon S and Park M (2020). Time-series data clustering based on the correlation of periodogram, Journal of The Korean Data Analysis Society, 22, 1751-1766. https://doi.org/10.37727/jkdas.2020.22.5.1751
  7. Satre-Meloy A, Diakonova M, and Grunewald P (2020). Cluster analysis and prediction of residential peak demand profiles using occupant activity data, Applied Energy, 260, 114246. https://doi.org/10.1016/j.apenergy.2019.114246
  8. Xu TS, Chiang HD, Liu GY, and Tan CW (2015). Hierarchical K-means method for clustering large-scale advanced metering infrastructure data, IEEE Transactions on Power Delivery, 32, 609-616. https://doi.org/10.1109/TPWRD.2015.2479941
  9. Yoo N, Lee E, Chung BJ, and Kim DS (2019). Analysis of apartment power consumption and forecast of power consumption based on deep learning, Journal of IKEEE, 23, 1373-1380.