Abstract
Aiming at the problems of complex characteristics such as nonlinearity, multivariable, and strong coupling in the energy optimization process of thermal power plant station under the carbon reduction constraints due to the multiple types of equipment and large amount of operation data in the multi-energy system (MES), an energy optimization method of multi-energy system considering distributed photovoltaic coordinated carbon reduction is proposed in this paper. Firstly, the energy characteristic model of the MES in the production process of energy input, output and conversion is established. The interaction between various systems, equipment and other elements of the MES is deeply studied, and the energy characteristic analysis method of the MES is proposed. Secondly, the relationship between fuel balance, heat balance, power balance, and carbon emission of the MES is analyzed, and the carbon emission intensity model of the MES is established. Then, an energy optimization model of the MES with the objectives of minimizing operating cost and maximizing carbon emission reduction is established, and a deep reinforcement learning algorithm is used to solve the model. Finally, based on the operation data of a power plant in a certain area in Northeast china, a MES simulation model is established to simulate and verify the effectiveness of the energy optimization method proposed in this paper.