基于深度神经网络的变工况下综合能源系统低碳经济调度

Low-carbon Economic Dispatch of Integrated Energy System Under Off-design Conditions Based on Deep Neural Network

设备变工况特性给综合能源系统(integrated energy system,IES)经济调度的准确性带来了严峻挑战。为此,提出了一种基于深度神经网络(deep neural network,DNN)的变工况下IES低碳经济调度方法。首先,基于能量枢纽模型(energy hub,EH)和效率修正模型,建立具有可变效率的动态能量枢纽模型(dynamic energy hub,DEH)。其中,EH模型刻画多能源之间的耦合关系,基于DNN的效率修正模型提取设备效率的非线性特征。在此基础上,提出了以总运行成本最小为目标函数的IES低碳经济调度模型。算例分析表明,所提方法能实现IES低碳经济运行,有效提高调度模型的求解速度和精度。

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.