The planning, design and construction of substation is the key content of power engineering construction. The rapid prediction of the full life cycle cost of substation has guiding significance for the construction of substation. In this paper, a substation full life cycle cost prediction model based on quantum particle swarm optimization least squares support vector machine is established. The relevant characteristic index of the substation life cycle is used as the input of the model, and the output is the substation full life cycle cost. The simulation results are compared with the prediction results of QPSO optimized LS-SVM, PSO optimized LS-SVM, traditional LS-SVM, BP neural network four prediction models and related performance indicators. The simulation results show that the QPSO optimized LS-SVM model has better prediction accuracy, and can predict and evaluate the life cycle cost quickly and accurately during substation design and construction, and improve the economics of substation construction.