Abstract: Building energy consumption cannot be accurately predicted due to the influence of complex meteorological parameters. In response to this situation, an energy system management software and algorithm based on meteorological parameters are proposed. Using DeST to simulate a public building and obtain meteorological parameters and building energy consumption, a BP neural network energy consumption prediction model was established using meteorological parameters as input. Genetic algorithm was used to optimize the model. The results show that the optimized model had higher prediction accuracy. In order to achieve real-time monitoring and analysis of building energy consumption data, a set of energy system management platform based on meteorological parameters has been developed using B/S architecture, which can implement dynamic management.