Whole Time Series Data Streams Clustering: Dynamic Profiling of the Electricity Consumption
Data from smart grids are challenging to analyze due to their very large size, high dimensionality, skewness, sparsity, and number of seasonal fluctuations, including daily and weekly effects. With the data arriving in a sequential form the underlying distribution is subject to changes over the time...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-12-01
|
Series: | Entropy |
Subjects: | |
Online Access: | https://www.mdpi.com/1099-4300/22/12/1414 |
id |
doaj-95394ae0f5084726be915753b0ab6659 |
---|---|
record_format |
Article |
spelling |
doaj-95394ae0f5084726be915753b0ab66592020-12-16T00:03:35ZengMDPI AGEntropy1099-43002020-12-01221414141410.3390/e22121414Whole Time Series Data Streams Clustering: Dynamic Profiling of the Electricity ConsumptionKrzysztof Gajowniczek0Marcin Bator1Tomasz Ząbkowski2Department of Artificial Intelligence, Institute of Information Technology, Warsaw University of Life Sciences‑SGGW, 02-776 Warsaw, PolandDepartment of Artificial Intelligence, Institute of Information Technology, Warsaw University of Life Sciences‑SGGW, 02-776 Warsaw, PolandDepartment of Artificial Intelligence, Institute of Information Technology, Warsaw University of Life Sciences‑SGGW, 02-776 Warsaw, PolandData from smart grids are challenging to analyze due to their very large size, high dimensionality, skewness, sparsity, and number of seasonal fluctuations, including daily and weekly effects. With the data arriving in a sequential form the underlying distribution is subject to changes over the time intervals. Time series data streams have their own specifics in terms of the data processing and data analysis because, usually, it is not possible to process the whole data in memory as the large data volumes are generated fast so the processing and the analysis should be done incrementally using sliding windows. Despite the proposal of many clustering techniques applicable for grouping the observations of a single data stream, only a few of them are focused on splitting the whole data streams into the clusters. In this article we aim to explore individual characteristics of electricity usage and recommend the most suitable tariff to the customer so they can benefit from lower prices. This work investigates various algorithms (and their improvements) what allows us to formulate the clusters, in real time, based on smart meter data.https://www.mdpi.com/1099-4300/22/12/1414clusteringdata streammachine learningsmart meteringtime series |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Krzysztof Gajowniczek Marcin Bator Tomasz Ząbkowski |
spellingShingle |
Krzysztof Gajowniczek Marcin Bator Tomasz Ząbkowski Whole Time Series Data Streams Clustering: Dynamic Profiling of the Electricity Consumption Entropy clustering data stream machine learning smart metering time series |
author_facet |
Krzysztof Gajowniczek Marcin Bator Tomasz Ząbkowski |
author_sort |
Krzysztof Gajowniczek |
title |
Whole Time Series Data Streams Clustering: Dynamic Profiling of the Electricity Consumption |
title_short |
Whole Time Series Data Streams Clustering: Dynamic Profiling of the Electricity Consumption |
title_full |
Whole Time Series Data Streams Clustering: Dynamic Profiling of the Electricity Consumption |
title_fullStr |
Whole Time Series Data Streams Clustering: Dynamic Profiling of the Electricity Consumption |
title_full_unstemmed |
Whole Time Series Data Streams Clustering: Dynamic Profiling of the Electricity Consumption |
title_sort |
whole time series data streams clustering: dynamic profiling of the electricity consumption |
publisher |
MDPI AG |
series |
Entropy |
issn |
1099-4300 |
publishDate |
2020-12-01 |
description |
Data from smart grids are challenging to analyze due to their very large size, high dimensionality, skewness, sparsity, and number of seasonal fluctuations, including daily and weekly effects. With the data arriving in a sequential form the underlying distribution is subject to changes over the time intervals. Time series data streams have their own specifics in terms of the data processing and data analysis because, usually, it is not possible to process the whole data in memory as the large data volumes are generated fast so the processing and the analysis should be done incrementally using sliding windows. Despite the proposal of many clustering techniques applicable for grouping the observations of a single data stream, only a few of them are focused on splitting the whole data streams into the clusters. In this article we aim to explore individual characteristics of electricity usage and recommend the most suitable tariff to the customer so they can benefit from lower prices. This work investigates various algorithms (and their improvements) what allows us to formulate the clusters, in real time, based on smart meter data. |
topic |
clustering data stream machine learning smart metering time series |
url |
https://www.mdpi.com/1099-4300/22/12/1414 |
work_keys_str_mv |
AT krzysztofgajowniczek wholetimeseriesdatastreamsclusteringdynamicprofilingoftheelectricityconsumption AT marcinbator wholetimeseriesdatastreamsclusteringdynamicprofilingoftheelectricityconsumption AT tomaszzabkowski wholetimeseriesdatastreamsclusteringdynamicprofilingoftheelectricityconsumption |
_version_ |
1724381886279581696 |