Abstract: Equipment off-design characteristics pose a serious challenge to the accuracy of economic dispatch of integrated energy system (IES). Therefore, a low-carbon economic dispatch model based on the deep neural network (DNN) for IES under off-design conditions is proposed in this paper. Firstly, based on an energy hub (EH) model and an efficiency correction model, a dynamic energy hub (DEH) model with variable efficiency is developed. The EH model portrays the connection between multiple energy carriers, and the efficiency correction model based on DNN predicts the nonlinear variation in efficiency. Based on the DEH model, a low-carbon economic dispatch model with the objective of minimizing the operating cost is proposed. The results show that the proposed method can be adopted to realize low-carbon economic operation, and effectively increase the computational speed and precision of optimal dispatch.