A Dedicated Mixture Model for Clustering Smart Meter Data: Identification and Analysis of Electricity Consumption Behaviors

Abstract

Abstract:The large amount of data collected by smart meters is a valuable resource that can be used to better understand consumer behavior and optimize electricity consumption in cities. This paper presents an unsupervised classification approach for extracting typical consumption patterns from data generated by smart electric meters. The proposed approach is based on a constrained Gaussian mixture model whose parameters vary according to the day type (weekday, Saturday or Sunday). The proposed methodology is applied to a real dataset of Irish households collected by smart meters over one year. For each cluster, the model provides three consumption profiles that depend on the day type. In the first instance, the model is applied on the electricity consumption of users during one month to extract groups of consumers who exhibit similar consumption behaviors. The clustering results are then crossed with contextual variables available for the households to show the close links between electricity consumption and household socio-economic characteristics. At the second instance, the evolution of the consumer behavior from one month to another is assessed through variations of cluster sizes over time. The results show that the consumer behavior evolves over time depending on the contextual variables such as temperature fluctuations and calendar events.

Smart Meter Traffic in a Real LV Distribution Network

“…where N S is the number of OFDM symbols to be transmitted. From (2) it can be deduced that the number of samples to be transmitted is:…”

“…where T frame is given by (2), N frames is the number of frames required to transmit the message data in total, ε r is the dielectric constant of the power lines, c 0 is the speed of light and N c and D c can be equal to N u , N su , N r and D u , D su , D r respectively depending on the type of area under examination.…”

“…Identifying such parameters is consequently beneficial to designing more efficient ICT systems for Advanced Metering Infrastructure.Energies 2018, 11, 1156 2 of 27 load-shifting. On the other hand, the smart meters can be a useful interaction tool between the energy provider and the end user, via which the consumers can be actively involved in reducing their consumption [2].Smart meters have been widely employed both for national roll-outs as well as for the realization of smart grid projects [3]. Overall, it is expected that until 2020 around 200 million smart meters will be deployed with an estimated investment of 35 billion € [4].…”

“…Energies 2018, 11, 1156 2 of 27 load-shifting. On the other hand, the smart meters can be a useful interaction tool between the energy provider and the end user, via which the consumers can be actively involved in reducing their consumption [2].…”

The Functional Latent Block Model for the Co-Clustering of Electricity Consumption Curves

“…The advantages of the functional LBM that is developed in this work are the following: first, the whole set of functional PCA scores are modelled and not just the first as in Ben Slimen et al (2016); second, the parameterization remains parsimonious since the data are assumed to live in block-specific functional subspaces; finally, the functional PCAs are carried out block by block, enabling detection of detailed phenomena in the data structure. In addition, although clustering techniques have already been considered for the analysis of electricity consumption curves (Abreu et al, 2012;Keyno et al, 2009;Tsekouras et al, 2007;Melzi et al, 2017), this work proposes the first use of a functional co-clustering technique to provide both a segmentation of households (rows) and days (columns) in interpretable groups for an electricity operator such as EDF.…”