Load profile assignment of low voltage customers for power retail market applications

To facilitate retail choice in a competitive power market, the knowledge of hourly load shape by customer class is necessary. Requiring a meter as a prerequisite for lower voltage customers to choose a power supplier is not considered practical at the present time. A technique which uses load research and customers´ monthly energy usage data for a preliminary screening of customer load profiles is presented. Two data mining techniques, namely, the fuzzy c-means (FCM) method and an artificial neural network (ANN) based pattern recognition technique, are utilised in this work. The proposed method can be used by the Energy Service Provider (ESP) to assign customers to specific load profiles with certainty factors. Customers with less certainty in the assignment will need meter installation or further investigation in order to determine which classes they belong to. Test data are from actual measurement and the customer information system (CIS) of Taiwan Power Company (TPC). Promising results on assigning existing under 220 V customers to their proper load profiles are illustrated.