Modeling competition of virtual power plants via deep learning. (1st January 2021)

• Record Type: Journal Article
• Authors: Löschenbrand, Markus
• Is Part Of: Energy. Volume 214(2021)
• Publication Date: 2021-01-01
• Subjects: Neural networks -- Nash game -- Virtual power plants -- Renewables -- DC-OPF; Power resources -- Periodicals; Power (Mechanics) -- Periodicals; Energy consumption -- Periodicals; 333.7905
• DOI: 10.1016/j.energy.2020.118870
• Languages: English
• ISSNs: 0360-5442

Abstract

Abstract: Traditionally, models pooling flexible demand and generation units into Virtual Power Plants have been solved via separated approaches, decomposing the problem into parts dedicated to market clearing and separate parts dedicated to managing the state-constraints. The reason for this is the high computational complexity of solving dynamic, i.e. multi-stage, problems under competition. Such approaches have the downside of not adequately modeling the direct competition between these agents over the entire considered time period. This paper approximates the decisions of the players via 'actor networks' and the assumptions on future realizations of the uncertainties as 'critic networks', approaching the tractability issues of multi-period optimization and market clearing at the same time. Mathematical proof of this solution converging to a Nash equilibrium is provided and supported by case studies on the IEEE 30 and 118 bus systems. Utilizing this approach, the framework is able to cope with high uncertainty spaces extending beyond traditional approximations such as scenario trees. In addition, the paper suggests various possibilities of parallelization of the framework in order to increase computational efficiency. Applying this process allows for parallel solution of all time periods and training the approximations in parallel, a problem previously only solved in succession. Highlights: A single-level model for competition between aggregators of flexible demand, generators and hybrids combining both. A versatile and computationally efficient framework to derive Nash equilibria for stochastic multistage models. A decomposition concept to parallelize training of agents and time periods. A bi-level model to transform area based market clearing results into physical transmission grid results.