31 August 2021 in IEEE Transactions on Smart Grid
This paper proposes a price-maker bidding and offering model for networked microgrids (NMG) in a pool-based day-ahead electricity market. The objective of this model is to maximize the net revenue of NMG by coordinating the joined individual microgrids to submit aggregated offers/bids to the market operator. A hybrid stochastic-robust optimization framework is developed to offset multiple associated uncertainties. The bidding and offering model is first formulated as a hard-to-solve mixed-integer nonlinear programming (MINLP) problem, which is later converted to its easy-to-solve mixed-integer linear programming (MILP) counterpart. To resolve privacy concerns of each microgrid and improve the scalability of the proposed bidding and offering model, a coordinated scheduling framework for NMG based on the Dantzig-Wolfe decomposition (DWD) method is proposed to obtain the global optimum. Numerical simulations with real-world measured data validate the effectiveness of the proposed price-maker bidding model, which is shown to outperform existing price-taker models.
19 December 2024 in IEEE Access
Combined heat and power microgrids (CHPMGs) have become increasingly popular recently due to their ability to offer cost-effective and resilient solutions to support critical infrastructures. As the centerpiece of a CHPMG, an autonomous real-time multi-energy management system can leverage advanced metering infrastructure to monitor and dispatch various distributed energy resources (DERs), minimize operational costs, and improve the overall system reliability. In this paper, a novel real-time energy management system (EMS) for CHPMGs is proposed using a data-driven model-free safe deep reinforcement learning method. The energy management problem in CHPMGs is first formulated into a constrained Markov decision process (CMDP). A safe deep deterministic policy gradient (SDDPG) method is then applied to solve the developed CMDP. SDDPG features an actor-critic structure, in which the actor network learns the optimal control policy, and the critic network learns to evaluate the state-action value. To satisfy CHPMGs operational constraints during the training process, two sets of neural networks are proposed to approximate the constrained system parameters. A mathematical optimization-based safety layer is also constructed upon the actor network to analytically correct the agent’s actions into safe actions satisfying specific constraints. The proposed method is validated by case studies using real-world data; it is also compared with conventional deep reinforcement learning (DRL) and optimization-based approaches with and without accurate uncertainty data.