Emergent electricity customer classification
Authors:
- 1 January 2005
- journal article
- Published by Institution of Engineering and Technology (IET) in IEE Proceedings - Generation, Transmission and Distribution
- Vol. 152 (2) , 164-172
Abstract
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.Keywords
This publication has 26 references indexed in Scilit:
- Customer characterization options for improving the tariff offerIEEE Transactions on Power Systems, 2003
- Distribution and power quality regulation under electricity competition. A comparative study2002
- Data mining in a power company customer databaseElectric Power Systems Research, 2000
- Power quality following deregulationProceedings of the IEEE, 2000
- Neural-network-based demand forecasting in a deregulated environmentIEEE Transactions on Industry Applications, 2000
- Managing customer and distribution utility costsIEEE Transactions on Power Delivery, 1999
- Application of load survey systems to proper tariff designIEEE Transactions on Power Systems, 1997
- A bottom-up approach to residential load modelingIEEE Transactions on Power Systems, 1994
- Estimation of diversity and kWHR-to-peak-kW factors from load research dataIEEE Transactions on Power Systems, 1994
- Residential Load Shape Modelling Based on Customer BehaviorIEEE Transactions on Power Apparatus and Systems, 1985