This paper focuses on the impact of promotional activities on the order volume of e-commerce users and the influence of unexpected events such as the COVID-19 pandemic on logistics transportation volume. The VMD algorithm is utilized to preprocess the data, and a CNN_BILSTM_RF prediction model and simulated annealing optimization model are constructed. Various software tools such as Matlab and SPSS are comprehensively employed to address the issue of freight allocation for different routes in logistics transportation. Firstly, the VMD algorithm is used to denoise the grouped data, and the CNN_BILSTcM_RF prediction model is constructed using Matlab to forecast the freight volume between DC25 and DC62, yielding conclusions such as 1774.2, 2041.5, 2718.6, 2160.9, 2251.3, and so on. Secondly, the maximum freight volume and load factor for the remaining routes after shutting down the DC5 and DC9 routes are predicted and calculated. A simulated annealing model is then applied to optimize the solution, resulting in conclusions such as 11.7288, 11.332, and so on for the overall network load. Lastly, the routes are evaluated, and the optimal transportation routes are identified as DC14-DC8, DC14-DC9, and DC36-DC4, with the addition of a new route between stations 8 and 10 to alleviate their burden, among other conclusions.