考虑子系统特性的分布式电氢耦合系统多时间尺度优化

Multi-Time-Scale Operational Optimization of a Distributed Electro-Hydrogen Coupling System Considering Subsystem Characteristics

为了促进新能源的消纳,研究分布式电氢耦合系统的多时间尺度运行优化非常有必要。首先,从不确定性与响应特性2个维度分析了电能、氢能、热能系统的特性;然后构建了日前-日内-实时的多时间尺度运行优化模型;接着采用深度强化学习对优化模型进行求解;最后,以某一区域的分布式电氢耦合系统为例进行算例分析,算例结果不仅验证了深度强化学习的有效性,同时验证了电氢耦合系统在新能源消纳方面的效果。

To promote the absorption of new energy,investigating multi-time-scale operational optimization of distributed electro-hydrogen coupling systems is essential.First,the characteristics of electric,hydrogen,and thermal energy systems are analyzed in terms of uncertainty and response characteristics.A multi-time-scale operational optimization model of day-ahead,day-in,and real-time is then constructed.Deep reinforcement learning is then used to solve the optimization model.Finally,an example of a distributed electro-hydrogen coupling system in a region is analyzed.The results of the example verify not only the effectiveness of deep reinforcement learning but also the effects of the electro-hydrogen coupling system on new energy consumption.