Privacy-friendly power flexibility trading (PRIVATEFLEX)

Privacy is often an obstacle to a broader use of flexibility of household electricity consumption in demand control ('DR'). If user data cannot be deciphered by external parties, privacy can be guaranteed. The first objective of this project is to use calculation-on-encrypted data ('COED') to keep flex data local and private, and at the same time to allow the flex to be traded on an aggregated level. The second objective is to better characterize flex with machine learning both at local and aggregate level, since residential flex is characterized by different types of uncertainty and is highly context dependent.