arrow
Return

An embedded deep-clustering-based load profiling framework

delete2022-03-01
delete30
PRE
AI
E
Eskandarnia, Elham *
A
Al-Ammal, Hesham M.
K
Ksantini, Riadh
DOI:10.1016/j.scs.2021.103618delete
deleteOriginal
deleteShare
deleteSave
Abstract

Abstract

En 中文
Load profiling is an essential step in several smart meter analytics tasks, such as forecasting and planning, that directly impact sustainable energy management. As most real-world smart meter data are unlabeled, the unsu-pervised learning clustering-driven load profiling approach aims to group related customers based on usage trends. However, due to the curse of dimensionality, conventional clustering algorithms perform poorly and often lead to inadequate load curves.The proposed load profiling framework's novelty is twofold. First, using an autoencoder the framework represents data as a hierarchy within the layers of the deep network, allowing for dimensionality reduction and highly nonlinear decision separation between clusters at the autoencoder bottleneck level. This is achieved by implementing autoencoder-based clustering that automatically converts smart meter data into more clustering-friendly representations that retain the original data characteristics. Second, the framework integrates dimen-sionality reduction and clustering into a single end-to-end unsupervised learning framework.The deep clustering framework is then tested on two real-world smart meter datasets, and the experimental results show that the proposed framework produces significantly better load profiles when compared to classical clustering algorithms as well as previous hybrid frameworks proposed in the literature. The paper concludes with a discussion of the results and a set of future directions for improving the load profiling task.
Keywords:
Smart grid
Deep clustering
Deep learning
Load profiling

Journal

Sustainable Cities and Society cover
Sustainable Cities and Society
IF:
12
Papers:
8.0K
Citations:
7.0W

Organization

U
university of bahrain
Scholars:
14
Papers: 13
Citations: 778
Cited Papers

Cited Papers

Ethnic identity positioning at work: Understanding professional career experiences
err2015-12-01
err0
PREAI
errCarolin Ossenkop; Claartje J. Vinkenburg; Paul G.W. Jansen; Halleh Ghorashi
errShare
errSave
errShare
errSave
Time-series clustering - A decade review
err2015-10-01
err1.2K
PREAI
errAghabozorgi, Saeed; Shirkhorshidi, Ali Seyed; Teh Ying Wah
errShare
errSave
Load Profiling and Its Application to Demand Response: A Review
err2015-04-01
err203
errOAAI
errWang, Yi; Chen, Qixin; Kang, Chongqing; Zhang, Mingming; Wang, Ke; Zhao, Yun
errShare
errSave
Deep clustering with a Dynamic Autoencoder: From reconstruction towards centroids construction
err2020-10-01
err55
errOAAI
errMrabah, Nairouz; Khan, Naimul Mefraz; Ksantini, Riadh; Lachiri, Zied
errShare
errSave
A Survey of Clustering With Deep Learning: From the Perspective of Network Architecture
err2018-01-01
err403
errOAAI
errMin, Erxue; Guo, Xifeng; Liu, Qiang; Zhang, Gen; Cui, Jianjing; Long, Jun
errShare
errSave
errShare
errSave
Evaluation of time series techniques to characterise domestic electricity demand
errENERGY
IF9.4
err2013-02-01
err82
PREAI
errMcLoughlin, Fintan; Duffy, Aidan; Conlon, Michael
errShare
errSave
researcher View more