Online Decentralized and Cooperative Dispatch for Multi-Microgrids

Microgrid usually associated with distributed renewable energy sources plays a key role in reducing the requirement of traditional power sources and the emission of CO2. Connecting multiple microgrids to the electric power grid can facilitate a more powerful and reliable operation. Microgrids need decentralized dispatch with the requirement of security and privacy, and at the same time, they need to cooperate to satisfy the constraints from the power grid. We consider online decentralized and cooperative dispatch problem in this paper. In order to capture the randomness in the wind and solar power generation and the system dynamics, we formulate the problem as a decentralized Markov decision process (Dec-MDP). We propose a new method to calculate the approximate Q-value functions by constructing the initial feasible policy with reasonable space and time complexity. Bayesian games (BGs) is applied to model the decentralized dispatch with delayed communication in order not to slow down the online decision-making. Also, the alternating minimization method is used to solve this BGs based on the approximate Q-value functions. Numerical results demonstrate that the proposed algorithm is very effective in reducing the state space and computing time and achieving the requirement of real-time scheduling. Motivated by the problem of decentralized dispatch of multi-microgrids in grid-connected mode, we consider the online decentralized operation and pay special attention to the grid tie-line power fluctuation. This problem is challenging due to the randomness of the renewable power generation, the global constraints about multiple microgrids, and the correlation among stages. We model the decentralized dispatch problem as a rolling horizon Dec-MDP and provide an approximate solution method, namely, alternately minimizing among different microgrids at the online stage and calculating approximate value functions in the offline preparation process. The approximate value functions make the online decision turn out to be a single-stage decentralized decision problem. Online decision calculation based on delayed communication is to guarantee all the microgrids to start conducting an action immediately while receiving the information related to them. We hope this paper brings insight onto the tie-line power fluctuation stabilization while multiple microgrids connecting to the same point of interconnection.