Feature Construction and Calibration for Clustering Daily Load Curves from Smart-Meter Data

Alotaibi, Reem; Jin, Nanlin; Wilcox, Tom; Flach, Peter A.

doi:10.1109/tii.2016.2528819

Cited by 117 publications

(53 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Normalizing the smart meter time series makes the data fit the interval [0-1]; in [31], normalization was applied to smart meter data. This process makes it possible to identify time series with equivalent consumption patterns instead of identical consumption volumes.…”

Section: K-meansmentioning

confidence: 99%

See 1 more Smart Citation

Electricity Consumption Clustering Using Smart Meter Data

2018

View full text Add to dashboard Cite

Electricity smart meter consumption data is enabling utilities to analyze consumption information at unprecedented granularity. Much focus has been directed towards consumption clustering for diversifying tariffs; through modern clustering methods, cluster analyses have been performed. However, the clusters developed exhibit a large variation with resulting shadow clusters, making it impossible to truly identify the individual clusters. Using clearly defined dwelling types, this paper will present methods to improve clustering by harvesting inherent structure from the smart meter data. This paper clusters domestic electricity consumption using smart meter data from the Danish city of Esbjerg. Methods from time series analysis and wavelets are applied to enable the K-Means clustering method to account for autocorrelation in data and thereby improve the clustering performance. The results show the importance of data knowledge and we identify sub-clusters of consumption within the dwelling types and enable K-Means to produce satisfactory clustering by accounting for a temporal component. Furthermore our study shows that careful preprocessing of the data to account for intrinsic structure enables better clustering performance by the K-Means method.

show abstract

Section: K-meansmentioning

confidence: 99%

“…The index is bound in the interval [−1, 1], where higher values are better; negative values indicate misclustering [31].…”

Section: Silhouette Indexmentioning

confidence: 99%

Electricity Consumption Clustering Using Smart Meter Data

2018

View full text Add to dashboard Cite

show abstract

“…Paper [11] presents the algorithm of k-means clustering for the IBM SPSS software and was used for load profiling for a gas station with measurements data acquired over a period of one year. Paper [1] presents cluster analysis using K-means++, and the calculation was performed using the Matlab software.…”

Section: B Cluster Analysismentioning

confidence: 99%

“…Several contributions to knowledge on energy load management and strategies for load profiling have recently been made. Al-Otaibi et al [1] provide details about the construction and calibration for clustering of daily load curves from smart metering by applying a new method of a conditional filtering on meter resolution in order to obtain new consumption pattern recognition. Koivisto et al perform an analysis with data from an AMR system.…”

Section: Introductionmentioning

confidence: 99%

A Novel Data Mining Procedure Generating a Typical Electrical Energy Daily Shape Based on Values From Smart Metering

Craiu¹,

Electrica²,

Pearsică³

et al. 2018

Review of the Air Force Academy

View full text Add to dashboard Cite

This paper presents a data mining procedure to generate a typical daily shape of energy consumption based on smart metering measurements. Such a typical daily shape describes an observed or estimated graphical representation of the variation of the electric load against time. This paper proposes two methods for the development of the novel data mining procedure: i) statistical analysis applied to a set of measured data; ii) cluster analysis using the machinelearning algorithm to determine a typical daily shape. The new procedure can be part of the Smart Metering and more precisely of the Automated Meter Reading (AMR). The results of the statistical analysis using the set of measured data show whether or not the average values are representative for the data set. The results of the cluster analysis extend the potential of forecasting a typical daily shape and of offering tools for potential applications to data mining procedure.

show abstract

“…Indirect clustering is also combined with GMM in [32]. A discussion on the selection of possible features takes place in [33]. In our work, by combining vine copulas with dimension reduction, we are capable of addressing the drawback of increased computational burden while also harvesting the synergy between the C-Vine's hierarchical structure and the ordered variables, as discussed in [34].…”

mentioning

confidence: 99%

C-Vine Copula Mixture Model for Clustering of Residential Electrical Load Pattern Data

Sun

Konstantelos

Štrbac

2017

IEEE Trans. Power Syst.

View full text Add to dashboard Cite

Abstract-The ongoing deployment of residential smart meters in numerous jurisdictions has led to an influx of electricity consumption data. This information presents a valuable opportunity to suppliers for better understanding their customer base and designing more effective tariff structures. In the past, various clustering methods have been proposed for meaningful customer partitioning. This paper presents a novel finite mixture modeling framework based on C-vine copulas (CVMM) for carrying out consumer categorization. The superiority of the proposed framework lies in the great flexibility of pair copulas towards identifying multi-dimensional dependency structures present in load profiling data. CVMM is compared to other classical methods by using real demand measurements recorded across 2,613 households in a London smart-metering trial. The superior performance of the proposed approach is demonstrated by analyzing four validity indicators. In addition, a decision tree classification module for partitioning new consumers is developed and the improved predictive performance of CVMM compared to existing methods is highlighted. Further case studies are carried out based on different loading conditions and different sets of large numbers of households to demonstrate the advantages and to test the scalability of the proposed method.Index Terms-Clustering, customer classification, C-vine, decision trees, mixture models, pair-copula construction, smart meters. I. INTRODUCTIONlectricity market liberalization has largely unbundled the distribution and supply services in many jurisdictions, providing customers with the freedom to select their electricity supplier. In this competitive environment, retail companies can improve the commercial attractiveness of their product by formulating tariffs aimed at different customer types. An important part of the tariff design process is the identification of meaningful customer classes that exhibit different consumption patterns, enabling the development of diversifiable products. Moreover, electrical customer classification can also play a crucial role in load forecasting [1][2] and modeling [3], electricity market development [4], energy system planning and operation [5] and theft detection [6]. Naturally, information on customer type (e.g. industrial, commercial, residential) provides important information regarding the likely electricity consumption pattern and intensity. However, for further partitioning and exploratory analysis to be carried out effectively, high-frequency demand measurements are necessary [7]. As such, the advent of smart metering has led to large-scale availability of consumption data that render clustering analysis increasingly possible.Load profile clustering aims to allocate consumers into a small number of homogeneous groups, ensuring that elements of the same cluster are similar between them, while being dissimilar to elements of different clusters. A large number of clustering techniques have been proposed in the past and applied to electrical load ...

show abstract

Feature Construction and Calibration for Clustering Daily Load Curves from Smart-Meter Data

Cited by 117 publications

References 24 publications

Electricity Consumption Clustering Using Smart Meter Data

Electricity Consumption Clustering Using Smart Meter Data

A Novel Data Mining Procedure Generating a Typical Electrical Energy Daily Shape Based on Values From Smart Metering

C-Vine Copula Mixture Model for Clustering of Residential Electrical Load Pattern Data

Contact Info

Product

Resources

About