Energy Commodity Logistics Planning method based on Machine Learning method

Abstract

In order to cope with the increasingly fierce competition in the market of refined oil products, improve the level of logistics operation and achieve logistics efficiency, a transportation scheduling method of refined oil logistics based on dynamic programming model was proposed to improve transportation efficiency, reduce logistics costs and increase enterprise benefits. Firstly, the basic ideas of logistics and transportation scheduling of refined oil were analyzed, and the comprehensive system of logistics and transportation scheduling of refined oil was constructed. The statistical analysis and sampling of logistics and transportation scheduling of refined oil were carried out by adopting the adaptive dynamic programming method, from which the characteristic values of association rules which could reflect the level of logistics and transportation scheduling of refined oil were extracted. Big data information fusion method is used to optimize the dynamic planning and transportation mode of refined oil logistics and transportation scheduling, and the spatial dynamic programming model of refined oil logistics and transportation scheduling is established. Combined with pattern recognition and path optimization method, the optimal design of refined oil logistics and transportation scheduling model is realized. The simulation results show that this method has good adaptability to transport scheduling of refined oil logistics, and the transportation efficiency of refined oil logistics is improved, the route is optimized, the level of enterprise guarantee is improved, and the logistics cost is reduced, which provides a strong guarantee for expanding the market and increasing the efficiency.