| In the actual logistics and distribution process,transportation vehicles often face the occurrence of traffic jam interference incidents in the process of performing tasks,resulting in high energy consumption and high carbon emissions of distribution vehicles.Therefore,how to rationally optimize logistics and distribution interference management issues under the carbon tax mechanism,reduce carbon emissions,and seek a win-win situation for corporate interests and environmental green development is particularly important.In this paper,a congestion prediction model based on machine learning is established.Under the carbon tax mechanism,support vector machines are used to predict congestion periods for short-term traffic flows.Taking the occurrence of traffic congestion as the interference event of logistics distribution,considering the three goals of carbon emission deviation cost,path deviation and cost deviation,a low-carbon logistics distribution interference management model under the carbon tax mechanism is constructed.According to the disturbance management strategy,a disturbance measurement method combining the congestion prediction model and the carbon tax mechanism is proposed.Then,an improved quantum ant colony algorithm(IQACO)is proposed.The proposed algorithm uses the ant colony algorithm information update strategy to maintain group memory,improves state transition rules and pheromone update methods,and proposes an improved adaptive quantum rotation angle adjustment strategy to improve the efficiency of the algorithm,thereby improving the performance and performance of the algorithm.Solve the problem of low-carbon logistics and distribution interference management.Finally,combined with reference data,the effectiveness of the improved quantum ant colony algorithm(IQACO)and low-carbon logistics distribution interference management model is explained.Through the benchmark test(CEC2017),the comparison of Solomon calculation examples,and the comparison of different scheduling methods and algorithms,the advantages of the improved quantum ant colony algorithm are explained.In addition,this paper develops a logistics scheduling management system,uses the Spring Boot framework to design the system interface,builds system functions,and facilitates the management of all information;uses Matlab’s GUI program to design a separate scheduling management module,and an improved quantum ant Group algorithm(IQACO)is a distribution algorithm that combines the results of congestion classification prediction to generate a plan with the lowest operating interference deviation.The logistics dispatch management system can realize the functions of information entry,interference distribution plan generation,congestion classification prediction and information management as a whole. |
