Combined Carbon Capture and Utilization with Peer-to-Peer Energy Trading for Multi-Microgrids Using Multi-Agent Proximal Policy Optimization

Microgrids integrated with distributed renewable energy is regarded as a crucial evolution towards economical and environmentally sustainable power systems. Carbon capture and utilization (CCU) technologies and peer-to-peer (P2P) energy trading schemes are two potential strategies for mitigating carbon emissions by capturing the emitted $\rm CO_{2}$ or trading surplus renewable energy, respectively. Hence, a collaborative energy scheduling model that combines CCU with P2P energy trading is needed under the coupling of multiple energy domains, including electricity, $\rm CO_{2}$ , and natural gas. In this paper, we investigate a novel multi-microgrid framework that jointly considers CCU and P2P trading, aiming at reducing costs and mitigating carbon emissions. Correspondingly, an energy-coupled, decision-interdependent multi-microgrid energy scheduling problem is developed that involves the stochastic system states, such as intermittent renewable generation and unpredictable loads. We regard each microgrid as an agent and adopt a multi-agent proximal policy optimization (MAPPO) algorithm for distributing the interdependent energy scheduling actions to each agent. This algorithm can cope with the high-dimensional continuous action space, and find the energy coordination policy without requiring system future statistical information. In particular, we introduce the CTDE mechanism, which alleviates the non-stationarity of the environment via C entralized T raining and alleviates the curse of dimensionality via D ecentralized E xecution. Extensive simulation results demonstrate that the proposed joint CCU-P2P energy coordination model and CTDE-based MAPPO outperform in achieving economic and environmental benefits.