Rewarding cooperative virtual power plant formation using scoring rules. (15th December 2016)

• Record Type: Journal Article
• Authors: Robu, Valentin; Chalkiadakis, Georgios; Kota, Ramachandra; Rogers, Alex; Jennings, Nicholas R.
• Is Part Of: Energy. Volume 117:Part 1(2016)
• Page Start: 19
• Page End: 28
• Publication Date: 2016-12-15
• Subjects: Multi-agent systems -- Cooperative virtual power plants -- Scoring rules -- Coalition formation -- Game theory -- Artificial intelligence; Power resources -- Periodicals; Power (Mechanics) -- Periodicals; Energy consumption -- Periodicals; 333.7905
• DOI: 10.1016/j.energy.2016.10.077
• Languages: English
• ISSNs: 0360-5442

Abstract

Abstract: Virtual Power Plants (VPPs) are fast emerging as a viable means of integrating small and distributed energy resources (DERs), like wind and solar, into the electricity supply network (Grid). VPPs are formed via the aggregation of a large number of DERs, so that they exhibit the characteristics of a traditional generator in terms of predictability and robustness. In this work, we promote the formation of such "cooperative" VPPs (CVPPs) using techniques from the field of distributed Artificial Intelligence and game theory. In particular, we design a payment mechanism that encourages DERs to join CVPPs with increased size and visibility to the network operator. Our method is based on strictly proper scoring rules and incentivises the provision of accurate predictions of expected electricity generation from member DERs, which aids in the planning of the supply schedule at the Grid. We empirically evaluate our approach using the real-world setting of 16 commercial wind farms in the UK, and we show that it incentivises real DERs to form CVPPs, and outperforms the current state of the art payment mechanism developed for this problem. Highlights: New method for rewarding estimates of generation in virtual power plants. Accurate reports are incentivised using strictly proper scoring rules. Model tested using real forecasting data from 16 wind farm locations of Ecotricity. Method incentivises VPP formation due to reduction in joint forecasting error.