Presenting user behavior from main meter data

摘要

The ongoing upgrade of household electricity meters to smart meters rises the developments of new efficient energy services and optimal consumption. Tools and algorithms have been built to disaggregate the meters' data and provide analyses of the user's consumption. This paper introduces an open architecture and a unified framework for deducing the user's behavior from its smart main electricity meter data and presenting the results in a natural language. The framework allows a fast exploration and integration of a variety of machine learning algorithms combined with data recovery mechanisms for improving the recognition's accuracy. Consequently, the framework generates natural language reports of the user's behavior from the recognized appliances. The framework separates its concerns and uses open standard interfaces for exchanging data. The framework has been validated through comprehensive experiments that are related to an EU Smart Grid project.