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.