The M‐shaped boom is a support structure that can be packed and launched and deployed in orbit using stored elastic strain energy. This work attempts a method to optimize the M boom. The response surface method was used to fit the finite element (FE) results to obtain surrogate models for the strain storage and the fundamental frequency in the deployed state, and the average errors between the surrogate model results and FE results were 1.56% and 0.9% respectively. The influence of different design variables on the results is analyzed by using surrogate models. Considering the requirements of boom deployment, a non‐dominated sorting genetic algorithm is used for multi‐objective optimization. The optimization targets the maximum strain stored energy and the maximum fundamental frequency, with the constraint of boom mass. The optimization results are at the Pareto frontier.