Towards a Platform for Testing and Developing Privacy-Preserving Data Mining Applications for Smart Grids

The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-642-40776-5_25. Abstract. In this paper we analyse the trade-off between privacy-preservation methods and the quality of data mining applications, within the specific context of the smart grid. The use of smart meters to automate data collection is set to solve the problem of electricity theft, which is a serious concern in developing nations. Nevertheless, the unlimited use of data from smart meters allows for potentially private information to be discovered. There is a demand for methods to quantify the tradeoff between privacy-preservation and quality of a classification model. We describe the research and development of an agent-based simulation platform to evaluate the balance between privacy-preservation mechanisms and methods for electricity theft detection. We have implemented a proof-of-concept model and validated it against real data collected from smart meters.