17 Dec 2020 @ 14:00 CET Duration: 1h Recent works in renewable energy sources (RES) forecasting, have shown the interest of using spatially distributed time series and assumed that data could be gathered centrally and used, either at the RES power plant level, or at the level of a system operator. However, data is distributed in terms of ownership, limitation in data transfer capabilities and with agents being reluctant to share their data anyway. The goal of this presentation is to rethink those learning problems by reformulating them as distributed learning problems and exploring two paradigms: privacy-preserving analytics and data markets. It will start by presenting the paradigm of collaborative RES forecasting and the challenges to implement a privacy layer for data from multiple owners. Then, the different algorithmic solutions for that data markets are discussed together with its applicability to RES forecasting. In this context, agents will be incentivized to collaborate, either through monetization of data or a privacy protocol for data exchange. This Webinar is proposed by the European H2020 Smart4RES project (http://www.smart4RES.eu)
