Electricity Customer Classification Research Articles

Symmetrical Uncertainty-Based Feature Subset Generation and Ensemble Learning for Electricity Customer Classification

The use of actual electricity consumption data provided the chance to detect the change of customer class types. This work could be done by using classification techniques. However, there are several challenges in computational techniques. The most important one is to efficiently handle a large number of dimensions to increase customer classification performance. In this paper, we proposed a symmetrical uncertainty based feature subset generation and ensemble learning method for the electricity customer classification. Redundant and significant feature sets are generated according to symmetrical uncertainty. After that, a classifier ensemble is built based on significant feature sets and the results are combined for the final decision. The results show that the proposed method can efficiently find useful feature subsets and improve classification performance.

Local characterization‐based load shape factor definition for electricity customer classification

Normally, electricity customer classification is based on the uncertain customer information found in the customer information system, such as customer type, contract type, and so on. Now that automatic meter‐reading (AMR) system is becoming common, customer classification and load profiling can be done by using actual consumption data.Different consumption behaviors are represented as different geometrical patterns in the actual consumption data. Based on this fact, in our study, a local characterization‐based method is used to define load shape factors from actual consumption data by detecting the local geometrical patterns of load diagrams. These load shape factors are evaluated during customer classification, and they are proved to be better than actual consumption data for customer classification. © 2017 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

Electricity clustering framework for automatic classification of customer loads

Abstract Clustering in energy markets is a top topic with high significance on expert and intelligent systems. The main impact of is paper is the proposal of a new clustering framework for the automatic classification of electricity customers’ loads. An automatic selection of the clustering classification algorithm is also highlighted. Finally, new customers can be assigned to a predefined set of clusters in the classification phase. The computation time of the proposed framework is less than that of previous classification techniques, which enables the processing of a complete electric company sample in a matter of minutes on a personal computer. The high accuracy of the predicted classification results verifies the performance of the clustering technique. This classification phase is of significant assistance in interpreting the results, and the simplicity of the clustering phase is sufficient to demonstrate the quality of the complete mining framework.

Structured Literature Review of Electricity Consumption Classification Using Smart Meter Data

Smart meters for measuring electricity consumption are fast becoming prevalent in households. The meters measure consumption on a very fine scale, usually on a 15 min basis, and the data give unprecedented granularity of consumption patterns at household level. A multitude of papers have emerged utilizing smart meter data for deepening our knowledge of consumption patterns. This paper applies a modification of Okoli’s method for conducting structured literature reviews to generate an overview of research in electricity customer classification using smart meter data. The process assessed 2099 papers before identifying 34 significant papers, and highlights three key points: prominent methods, datasets and application. Three important findings are outlined. First, only a few papers contemplate future applications of the classification, rendering papers relevant only in a classification setting. Second; the encountered classification methods do not consider correlation or time series analysis when classifying. The identified papers fail to thoroughly analyze the statistical properties of the data, investigations that could potentially improve classification performance. Third, the description of the data utilized is of varying quality, with only 50% acknowledging missing values impact on the final sample size. A data description score for assessing the quality in data description has been developed and applied to all papers reviewed.

Classification of new electricity customers based on surveys and smart metering data

This paper proposes a process for the classification of new residential electricity customers. The current state of the art is extended by using a combination of smart metering and survey data and by using model-based feature selection for the classification task. Firstly, the normalized representative consumption profiles of the population are derived through the clustering of data from households. Secondly, new customers are classified using survey data and a limited amount of smart metering data. Thirdly, regression analysis and model-based feature selection results explain the importance of the variables and which are the drivers of different consumption profiles, enabling the extraction of appropriate models. The results of a case study show that the use of survey data significantly increases accuracy of the classification task (up to 20%). Considering four consumption groups, more than half of the customers are correctly classified with only one week of metering data, with more weeks the accuracy is significantly improved. The use of model-based feature selection resulted in the use of a significantly lower number of features allowing an easy interpretation of the derived models.

Subspace Frequency Analysis--Based Field Indices Extraction for Electricity Customer Classification

In electricity customer classification, the most important task is to avoid the curse of dimensionality problem, as the consumption diagrams have a large number of dimensions. To avoid the curse of dimensionality problem, field indices (load shape factor) are often used instead of consumption diagrams. Field indices are directly extracted from consumption diagrams according to a predefined formula. Previous studies show that the most important thing for defining such a formula is to find meaningful time intervals from consumption diagrams. However, the inconvenient thing is that there are still a lack of details to explain how to define such time intervals. In our study, we propose a data mining--based method named SFATIE to support the extraction of field indices. The performance of the proposed method is evaluated by comparing it with other dimensionality reduction methods during the classification. For the classification, most often we have used classification methods like C5.0, SVM, Neural Net, Bayes Net, and Logistic. The experimental results show that our method is better or close to other dimensionality reduction methods. In addition, the experimental results show that our proposed method can produce the good quality of field indices and that these indices can improve the performance of electricity customer classification.

Two-Stage Pattern Recognition of Load Curves for Classification of Electricity Customers

This paper describes a two-stage methodology that was developed for the classification of electricity customers. It is based on pattern recognition methods, such as k-means, Kohonen adaptive vector quantization, fuzzy k-means, and hierarchical clustering, which are theoretically described and properly adapted. In the first stage, typical chronological load curves of various customers are estimated using pattern recognition methods, and their results are compared using six adequacy measures. In the second stage, classification of customers is performed by the same methods and measures, together with the representative load patterns of customers being obtained from the first stage. The results of the first stage can be used for load forecasting of customers and determination of tariffs. The results of the second stage provide valuable information for electricity suppliers in competitive energy markets. The developed methodology is applied on a set of medium voltage customers of the Greek power system, and the obtained results are presented and discussed.

Comparisons Among Clustering Techniques for Electricity Customer Classification

The recent evolution of the electricity business regulation has given new possibilities to the electricity providers for formulating dedicated tariff offers. A key aspect for building specific tariff structures is the identification of the consumption patterns of the customers, in order to form specific customer classes containing customers exhibiting similar patterns. This paper illustrates and compares the results obtained by using various unsupervised clustering algorithms (modified follow-the-leader, hierarchical clustering, K-means, fuzzy K-means) and the self-organizing maps to group together customers with similar electrical behavior. Furthermore, this paper discusses and compares various techniques-Sammon map, principal component analysis (PCA), and curvilinear component analysis (CCA)-able to reduce the size of the clustering input data set, in order to allow for storing a relatively small amount of data in the database of the distribution service provider for customer classification purposes. The effectiveness of the classifications obtained with the algorithms tested is compared in terms of a set of clustering validity indicators. Results obtained on a set of nonresidential customers are presented.

Electricity customer classification using frequency–domain load pattern data

In competitive electricity markets, electricity customer classification is becoming increasingly important, due to new degrees of freedom the electricity providers have been given in formulating dedicated tariff options for different customer classes. Several customer classification techniques have been proposed in the literature, in which the load patterns are typically represented by time–domain data. However, a good load pattern representation requires using several data for each customer, causing possible difficulties in storing a large amount of data in the electricity company's databases. In order to reduce the number of data to be stored for each customer, an original solution is proposed in this paper, based on post-processing the results of time–domain measurements to obtain a reduced set of data defined in the frequency domain. The new set of data is successively used in a customer classification procedure, e.g. a suitable clustering technique, whose adequacy can be assessed by means of properly defined indicators. This paper provides the mathematical background for the frequency–domain data definition and investigates on the effectiveness of the customer classification for different choices of the number of data to be stored. Results obtained on a set of customers belonging to a real distribution system are presented and discussed. These results show that the proposed representation is effective in reducing the number of data stored while maintaining a satisfactory level of classification adequacy.

Emergent electricity customer classification

Various techniques for electricity customer classification are presented and discussed, with the focus on highlighting the behaviour of electricity customers. The surveyed techniques include classical approaches (applications of statistics and deterministic clustering algorithms), as well as methods based on artificial intelligence (neural networks and fuzzy systems). The classification techniques are illustrated by using various sets of features characterising the shape of the load patterns. Different approaches for feature selection, both in the time and in the frequency domain, are discussed. A number of specific metrics, some of which were originally developed by the authors, are applied in order to quantify the classification adequacy and to identify the most suitable classification techniques. Detailed results obtained from real life applications are provided.

Load Pattern-Based Classification of Electricity Customers

Accurate knowledge of the customers' consumption patterns represents a worthwhile asset for electricity providers in competitive electricity markets. Various approaches can be used for grouping customers that exhibit similar electrical behavior into customer classes. In this paper, we focus on two approaches for customer classification-a modified follow-the-leader algorithm and the self-organizing maps. We include an overview of basic theory for these methods and discuss the performance of the customer classification on the real case of a set of customers supplied by a distribution company. We compare the results obtained from the two approaches by means of two suitably defined adequacy indicators and discuss the potential applications of the surveyed approaches.

Customer characterization options for improving the tariff offer

This paper deals with the classification of electricity customers on the basis of their electrical behavior. Starting from an extensive field measurement-based database of customer daily load diagrams, the authors searched for the most appropriate indices or sets of indices to be used for customer classification. They propose two original measures to quantify the degree of adequacy of each index. Using the indices as distinguishing features, they adopt an automatic clustering algorithm to form customer classes. Each customer class is then represented by its load profile. They use the load profiles to study the margins left to a distribution company for fixing dedicated tariffs to each customer class. They take into account new degrees of freedom available in the competitive electricity markets, which increase flexibility in the tariff definition under imposed revenue caps. Results of a case study performed on a set of customers of a large distribution company are presented.

Customer Characterization Options for Improving the Tariff Offer

This paper deals with the classification of electricity customers on the basis of their electrical behavior. Starting from an extensive field measurement-based database of customer daily load diagrams, the authors searched for the most appropriate indices or sets of indices to be used for customer classification. They propose two original measures to quantify the degree of adequacy of each index. Using the indices as distinguishing features, they adopt an automatic clustering algorithm to form customer classes. Each customer class is then represented by its load profile. They use the load profiles to study the margins left to a distribution company for fixing dedicated tariffs to each customer class. They take into account new degrees of freedom available in the competitive electricity markets, which increase flexibility in the tariff definition under imposed revenue caps. Results of a case study performed on a set of customers of a large distribution company are presented.

Residential demand for electric space heating in Finland

The sensitivity of residential demand for electric space heating in Finland to changes in the price of electricity and substitute fuels, income, climate and demographic factors is estimated using the dynamic flow-adjustment model. The unit of investigation is the individual electricity distributing utility and the time period studied the years 1975–1982, inclusive. The estimates obtained for the whole country and for a classification of electricity customers into rural and urban consumer categories reveal the considerable impact of the explanatory variables and the own-price elasticity in particular as well as the existence of discernible regional differences.