The central air conditioning system and other equipment in buildings consume a large amount of electrical energy, leading to the continuous increase in energy consumption in the construction sector in our country. To address the above?mentioned issue, firstly, a mathematical model is established for the energy consumption of each equipment in the central air conditioning system based on its working principle, and the decision variables are selected. Then, with the objective of minimizing the total energy consumption of the central air conditioning system, an energy?saving optimization model for the central air conditioning system is established, taking into account the constraints such as variable bounds, coupling relationships between equipment, and energy conservation principles. Next, the real?time indoor cooling load and the set temperature are taken as known values, while the decision variables are taken as input variables, and the total energy consumption of the central air conditioning system is taken as the output variable to reduce the complexity of the model. Subsequently, an improved particle swarm optimization (PSO) algorithm is proposed based on dynamic weight coefficients and acceleration factors. The method achieves collaborative optimal control of the decision variables to search for the optimal solution of the energy?saving optimization model for the central air conditioning system. Finally, the ISPO algorithm is compared with the standard particle swarm optimization algorithm through simulation analysis. The results show that IPSO achieves superior performance and better convergence. The optimized total energy consumption of the air conditioning system is significantly reduced compared to the pre?optimized state, thus validating the effectiveness of the proposed model and method.