Aiming at the vehicle routing problem of joint distribution of multi-center hybrid fleet under time-varying road network, considering the opening of multi distribution centers, joint distribution of fuel vehicles and electric vehicles, continuous change of vehicle speed and other factors, an optimization model aiming at minimizing the sum of vehicle fixed cost, operation cost and time window penalty cost was constructed. According to the characteristics of the problem, a hybrid heuristic algorithm was designed to solve it. In the algorithm, the K-means clustering method was used to generate the initial population, and then the variable neighborhood search algorithm was used for search optimization to improve the solution performance of the algorithm. Several groups of experiments were designed to compare and analyze the algorithms, the effectiveness of the algorithm was verified. The research results enrich the relevant theoretical research on timevarying road network and hybrid fleet vehicle routing problem, and provide a theoretical basis for transportation enterprises to formulate reasonable transportation schemes.