A Data-Driven Customer Segmentation Strategy Based on Contribution to System Peak Demand

Abstract

Advanced metering infrastructure (AMI) enables utilities to obtain granular energy consumption data, which offers a unique opportunity to design customer segmentation strategies based on their impact on various operational metrics in distribution grids. However, performing utility-scale segmentation for unobservable customers with only monthly billing information, remains a challenging problem. To address this challenge, we propose a new metric, the coincident monthly peak contribution (CMPC), that quantifies the contribution of individual customers to system peak demand. Furthermore, a novel multi-state machine learning-based segmentation method is developed that estimates CMPC for customers without smart meters (SMs): first, a clustering technique is used to build a databank containing typical daily load patterns in different seasons using the SM data of observable customers. Next, to associate unobservable customers with the discovered typical load profiles, a classification approach is leveraged to compute the likelihood of daily consumption patterns for different unobservable households. In the third stage, a weighted clusterwise regression (WCR) model is utilized to estimate the CMPC of unobservable customers using their monthly billing data and the outcomes of the classification module. The proposed segmentation methodology has been tested and verified using real utility data.

Bibliometric study of distribution system state estimation: advances and challenges

“…Later, it was included and analyzed the impact and implementation of synchronized or non-synchronized D-PMU. These advances and developments can be found in several state-of-the-art reviews [2][3][4][5][6][7]. In [2,4] technologies, obstacles, challenges, and components of a DSSE are presented and analyzed.…”

Uncovering Hidden Factors in Electricity Consumption Based on Gaussian Mixture Estimation

“…Statistical methods characterize the inherent similarities in historical electricity data and classify residential loads into several typical load patterns. The Gaussian mixture model (GMM) is a popular method that is used to extract the typical load patterns [5]. In [6], a multi-stage probabilistic method is proposed to estimate the monthly and hourly PV generation sequentially by GMM and maximum likelihood estimation (MLE).…”

Electric Utility Customer Segmentation from Advanced Metering System Data Using K-Shape Clustering — A Norwegian Case Study

“…Customer segmentation, according to Electric Power Research Institute (EPRI), is "a method of identifying homogeneous groups of consumers within a greater population based on common purchasing patterns and behavioral traits" [1]. When electricity is the commodity in question, the energy consumption data of consumers can be processed using several customer segmentation methods in vogue [2]- [5]. With the advent of smart meters and the accompanying advanced metering infrastructure (AMI), the required data that forms the backbone for customer segmentation methods is easily accessible, and improvements in the methods used for effectively segmenting customers are on the rise.…”

“…Applications of utility-scale customer segmentation include targeting customers for unique demand response programs, investment in AMI, improving energy profile modeling, design of unique customer incentive programmes, etc. [2]- [5]. Data from AMS could be utilised to more accurately group customers with similar electric consumption behaviour, where "behaviour" could represent time series characteristics such as periodicity, amplitude, trend, etc.…”