基于遗传算法的混合储能平抑风电功率波动的优化策略

Optimization Strategy of Hybrid Energy Storage to Stabilize Wind Power Fluctuation Based on Genetic Algorithm

为了减少风力发电的波动性和随机性对电网造成的冲击,常通过配置储能系统进行风电功率波动的平抑,对此提出了一种基于遗传算法的混合储能风电平抑功率优化策略。首先,基于小波包分解将风电信息分解为高频和低频信号,形成初始功率分配策略;其次,根据当前时刻策略的平抑结果与上一时刻的平抑结果作为评估指标,形成遗传算法的适应度函数;最后,通过拉丁超立方采样生成样本空间内均匀分布的初始种群,通过多次迭代实现功率分配最优策略。以某风电场实际24 h风电数据为例进行算法的验证,结果表明:该算法可以实现混合储能的优化功率分配,相较于未经优化的功率分配策略展示出明显的优势。

In order to reduce the impact of the volatility and randomness of wind power generation on the power grid, energy storage systems are deployed to stabilize the fluctuation of wind power. A hybrid energy storage wind power stabilization power optimization strategy based on genetic algorithm is proposed. Firstly, the wind power is decomposed into high frequency and low frequency signals based on wavelet packet decomposition to form an initial power allocation strategy.Secondly, the fitness function of genetic algorithm is formed according to the stabilization result of the current strategy and the stabilization result of the previous time as evaluation indexes.Finally, the Latin hypercube sampling is used to generate the uniformly distributed initial population in the sample space, and the optimal strategy of power allocation is realized through multiple iterations. In this paper, the actual 24 hours wind power data of a wind farm is taken as an example to verify the algorithm. The results show that the algorithm can realize the optimal power allocation of hybrid energy storage, which shows obvious advantages compared with the unoptimized power allocation strategy.