基于神经网络的混合储能系统能量管理策略

Energy Management Mode of Hybrid Energy Storage System Based on Neural Network Algorithm

针对目前诸多储能系统由于输出功率波动程度较大而导致的发电成本升高的问题,提出新型混合储能系统能量管理策略。综合锂离子电池的温度、锂离子电池和超级电容的荷电状态三个参考量,通过模糊控制对低通滤波器的时间常数进行调节,将超出目标值的功率偏差在两种储能介质之间进行初步分配;而后引入功率依从指数的概念,模拟功率依从指数与储能设备参数之间的关系;通过遗传算法对混合储能系统的功率分配进一步优化。仿真分析表明,提出的管理策略能够使功率波动程度大幅度降低,并使发电成本降低到近乎接近最低的水平,证明了上述能量管理策略的正确和有效性。

In order to solve the problem of high generation cost caused by large fluctuation of output power in man⁃y energy storage systems,a new energy management strategy of hybrid energy storage system is proposed.Based on the temperature of lithium ion battery,the charging state of lithium ion battery and supercapacitor,the time constant of low pass filter was adjusted through fuzzy control,and the power deviation beyond the target value was initially dis⁃tributed between the two energy storage media.Then the concept of power compliance index was introduced to simu⁃late the relationship between power compliance index and parameters of energy storage equipment.Finally,the power allocation of hybrid energy storage system was further optimized by genetic algorithm.The simulation results show that the management strategy can greatly reduce the fluctuation of power and the generation cost to the lowest level,which proves the correctness and effectiveness of the energy management strategy.