Low Carbon Optimal Learning Scheduling for Power Systems with Carbon Catchment Devices and Carbon Flow Theory

In allusion to the problems that the current research on power scheduling does not integrate the carbon emission flow with the power flow as well as the intelligence of the solution algorithm still needs to be explored, a low-carbon optimal learning and scheduling method of power systems that took into account the carbon capture device and the carbon emission flow theory was proposed. Firstly, the power system’s carbon emission flow model was constructed at the equipment and the system level respectively. Secondly, a bi-level alternating optimal scheduling model, which includes system day-ahead scheduling and load demand response adjustment, was established by considering each link of source-grid-load-storage of the power system, and a deep reinforcement learning algorithm was adopted to solve the model. Finally, the effectiveness and applicability of the proposed theoretical approach in reducing operating costs and carbon emissions were verified through actual example simulations.