Home // SMART 2016, The Fifth International Conference on Smart Cities, Systems, Devices and Technologies // View article

Automated Categorization of Consumers Based on Consumption Forecast in Smart Grid

Authors:
Kálmán Tornai
András Oláh

Keywords: Consumer categorization; Clustering methods; Classification methods; Time series forecast; Feedforward Neural Network

Abstract:
Deploying smart meters in Smart Grid systems entails that large amount of measurement data is acquired. By processing and analyzing the data, relevant information can be obtained about the power consumers. One of the most important tasks is determining the main characteristics of the consumer in order to find the best suitable category. This categorization may be essential i) to optimize and estimate the load of transportation grid; ii) to provide the best rate for the consumer as well as the supplier in case of free market of electricity; iii) to forecast and to plan correctly the required amount of energy from power-plants to minimize the difference between the demand and supply. In this paper, a categorization method based on forecasting consumption time series will be introduced to categorize consumers with different consumption patterns with good performance. The performance of the method was subject of analysis, and the new algorithm is proved to be usable in real applications.

Pages: 1 to 7

Copyright: Copyright (c) IARIA, 2016

Publication date: May 22, 2016

Published in: conference

ISSN: 2308-3727

ISBN: 978-1-61208-4763

Location: Valencia, Spain

Dates: from May 22, 2016 to May 26, 2016