The new emerged operating conditions in the power sector are forcing the power-market participants to develop new tools. Among them, load profiles are a key issue in retail power markets. For various types of small consumers without quarterhourly load measurements, determination of typical load profiles (TLPs) could serve as a tool for determining of their load diagrams. Their main function is in billing of consumers who have deviated from their contracted schedules. Moreover, a simple and straightforward method for assigning a TLP to a particular eligible consumer also needs to be established. In this paper, a methodology for allocating consumers' load profiles using probabilistic neural network (PNN) is presented. It is based on the preprocessed measured load profiles (MLPs), using wavelet multiresolution analysis, clustered with a FCM clustering algorithm with an appropriate cluster-validity measure. The results demonstrate the efficiency of the formation procedure for the proposed TLPs.Index Terms-Cluster analysis, fuzzy logic, load profiles, power distribution, probabilistic neural networks, wavelet analysis.
Abshaci-Information concerning the consumer's Load Profile (LP) in a deregulated environment is of initial importance lor load balancing purposes and for billing the consumers, which deviated from contracted schedules. Establishment of a system that enables consumers, without the quarter-hourly load measuremeuts, to participate at the retail market, requires the Typical Load Profiles (TLP) of the various types of consumers. Furthermore, simple and straightforward method for the TLP assignment to the particular eligible consumers should be established. In the paper, a methodology for consumer's load profdes classification is presented. The Measured Load Profiles (MLP) are classified by hierarchic clustering method and fuzzy logic. Probability neural network is used to assign the TLP to the particular group of consumers. The results demonstrate that the proposed method is efficient for and assigning TLP to the consumers.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.