基于Surrogate的预装式储能电站布局优化

Layout Optimization of Pre-installed Energy Storage Power Station Based on Surrogate

为解决预装式储能电站内部布局优化的问题,同时兼顾集装箱内部通风散热效果最好与储能容量最大,提出一种基于Surrogate的预装式储能电站布局优化方案,以进、出风口半径、通风道宽度为决策变量,利用拉丁超立方抽样法生成样本,设计箱体内部设备排布方案及通风口方案,利用有限元软件ANSYSWorkbench仿真计算箱体内温度分布情况;基于热分析结果,使用Surrogate建模方法构建优化模型,采用粒子群算法求解优化模型,得到最佳布局及散热方案。最后,算例验证了方法的适用性。此方法的提出,解决了当前预装式储能电站优化方案中存在的主观性偏强或求解不优的问题,有利于推动预装式储能电站设计的进一步发展。

To optimize the internal layout of the pre-installed energy storage power station, and to achieve the best heat ventilation and dissipation with largest energy storage capacity, we propose a surrogate-based layout optimization method for the pre-installed energy storage power station. In this method, tuner radius and air duct width are set to be decision variables so as to design the layout scheme of internal devices in the cabinet using the Latin hypercube sampling method. The finite element software ANSYS Workbench is used to obtain the temperature distribution in the cabinet. Based on those data, the Surrogate modeling method is used to build an optimization model, and the particle swarm algorithm is used to solve the optimization model to obtain the optimal layout and heat dissipation scheme. In the end, the applicability of the method is validated by the calculation examples. The method can be adopted to solve the problems of the subjectivity and non-optimum resolution by the current pre-installed energy storage power station optimization schemes and promote its development.