Coordination of Electric Thermal Systems for Distributed Demand-Side Management: A Gossip-based Cooperative Approach

In this paper we propose a distributed and cooperative approach to address the problem of coordinating the electric power demand of electric thermal systems in an urban environment. We model the network of electric thermal systems as a multi-agent system where each agent has only access to local information and ignores any global data such as the state of the whole network or its topology. Furthermore, no central coordinator or aggregator of information is assumed to exist. The proposed method is based on the design of a randomized and asynchronous gossip-based local interaction policy among heterogeneous devices interconnected by a communication peer to-peer network over the internet. We provide preliminary formal results on the convergence properties of the approach and numerical simulations to validate the performance of the proposed method.