A systematic review of data pre-processing methods and unsupervised mining methods used in profiling smart meter data

Abstract

<abstract> <p>The evolution of smart meters has led to the generation of high-resolution time-series data - a stream of data capable of unveiling valuable knowledge from consumption behaviours for different applications. The ability to extract hidden knowledge from such massive amounts of data requires that it be analysed intelligently. Hence, for a clear representation of the various consumption behaviours of consumers, a good number of data mining technologies are usually employed. This paper presents a systematic review of the various data mining techniques and methodologies employed while profiling energy data streams. The review identifies the strengths and shortcomings of existing data mining methods as applied in research, focusing more on data processing techniques and load clustering. Also discussed are data mining methods used to profile consumption data, their pros and cons. It was inferred during the research that the choice of data mining technique employed is highly dependent on the application it is intended for and the intrinsic nature of the dataset.</p> </abstract>

A reduced-dimension feature extraction method to represent retail store electricity profiles

“…Reviews of clustering methods applied over electrical data can be found in [11,12,10]. Most studies have used residential data-sets, but some work clustering electricity profiles of commercial and industrial customers has been completed.…”

“…A recent review of dimensional reduction techniques appears in [10]. Dimensional reduction has been attempted for electricity demand modelling and clustering [46], and for symbolic aggregate approximation with hierarchical clustering [49].…”

“…Inevitably there are differences between stores, with the key being understanding the variability and what is acceptable usage for any store. Grouping the stores based on common demand patterns reveals existing distinct behaviours in the store portfolio [10,11,12,13]. This informs which measures might be more effective or cost-efficient for each group, and identifies stores whose demand patterns do not match any of the discovered groups (anomalous behaviour).…”