Feature-Based Clustering for Electricity Use Time Series Data

Räsänen, Teemu; Kolehmainen, Mikko

doi:10.1007/978-3-642-04921-7_41

Cited by 75 publications

(54 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Academia proposes two approaches to cope with this issue. On the one hand, Räsänen and Kolehmainen (2009) extend the clustering objects by additional data points (e.g., standard deviation or skewness of the 15 minutes consumption). On the other hand, Ramos and Vale (2008) introduce a segmentation of the analysis days (weekday, season) which separates the raw data sets into more homogeneous subsets.…”

Section: Data Preparationmentioning

confidence: 99%

Cluster Analysis of Smart Metering Data

et al. 2012

View full text Add to dashboard Cite

Utilities and electricity retailers can benefit from the introduction of smart meter technology through process and service innovation. In order to offer customer specific services, smart meter mass data has to be analyzed. In the article we show how to integrate cluster analysis in a business Intelligence environment and apply cluster analysis to real smart meter data to identify detailed customer clusters.

show abstract

Section: Data Preparationmentioning

confidence: 99%

Cluster Analysis of Smart Metering Data

et al. 2012

View full text Add to dashboard Cite

show abstract

“…working directly with raw data: this approach can be very demanding in the cases vectors in V have high dimensionality or data is affected by autocorrelation or noise; working with features (such as average, standard deviation and skewness) extracted by the raw data and then clustering data in the space spanned by these features [23]. working with a model synthesizing the data, such as ARIMA [24] or Hidden Markov Model [25]; in this case and the clustering is then performed in the space spanned by the parameters of the selected model.…”

Section: Clustering Time Series Datamentioning

confidence: 99%

Identifying Typical Urban Water Demand Patterns for a Reliable Short-term Forecasting – The Icewater Project Approach

Candelieri

Archetti

2014

Procedia Engineering

View full text Add to dashboard Cite

This paper presents a computational framework performing, in two stages: urban water demand pattern characterization through time series clustering and reliable hourly water demand forecasting for the entire day based on Support Vector Machine (SVM) regression. An SVM regression model is trained for each cluster identified and for each hour of the day, taking the hourly water demand data acquired at the very first m hours of the day. The approach has been validated on a real case study that is the urban water demand of the Water Distribution Network (WDN) in Milan, managed by Metropolitana Milanese, one of the partner of the EU-FP7-ICT ICeWater project.

show abstract

“…Moss et al provided an overview of consumer segmentation in the electricity sector, especially for demand-side management [15]. Application-specific segmentations frameworks have been developed in [5,6,7,10,11,19,21], mainly for setting tariff or consumer classification, and predicting consumer characteristics [3].…”

Section: Related Workmentioning

confidence: 99%

“…Previous works have primarily targeted a specific problem (e.g. setting tariff [11,21], predicting consumer characteristics [3]) and do not consider this task in a holistic manner.…”

Section: Introductionmentioning

confidence: 99%

Consumer Segmentation and Knowledge Extraction from Smart Meter and Survey Data

Wijaya¹,

Ganu²,

Chakraborty³

et al. 2014

Proceedings of the 2014 SIAM International Conference on Data Mining

View full text Add to dashboard Cite

Many electricity suppliers around the world are deploying smart meters to gather fine-grained spatiotemporal consumption data and to effectively manage the collective demand of their consumer base. In this paper, we introduce a structured framework and a discriminative index that can be used to segment the consumption data along multiple contextual dimensions such as locations, communities, seasons, weather patterns, holidays, etc. The generated segments can enable various higher-level applications such as usagespecific tariff structures, theft detection, consumer-specific demand response programs, etc. Our framework is also able to track consumers' behavioral changes, evaluate different temporal aggregations, and identify main characteristics which define a cluster.

show abstract

Feature-Based Clustering for Electricity Use Time Series Data

Cited by 75 publications

References 11 publications

Cluster Analysis of Smart Metering Data

Cluster Analysis of Smart Metering Data

Identifying Typical Urban Water Demand Patterns for a Reliable Short-term Forecasting – The Icewater Project Approach

Consumer Segmentation and Knowledge Extraction from Smart Meter and Survey Data

Contact Info

Product

Resources

About