Search Results (1)

Due to the imbalance between supply and demand, liner container transportation often faces the problem of low slot utilization, which will occur in the shipping process, such as dry container demand exceeding the available dry slots and reefer slots not being fully utilized. This makes it important and challenging to maintain a balance between the actual demand and the limited number of slots allocated for liner container transport. Therefore, this study proposes a flexible allocation method: expanding the types of containers that can be loaded in the same slot. This method is suitable for handling each dynamic arrival container booking request by shipping enterprises, making decisions to accept or reject, and flexibly allocating shipping slots. In order to maximize the total revenue generated by accepting container booking requests during the entire booking acceptance cycle, we establish a dynamic programming model for the flexible allocation of slots. For model solving, we use the Q-learning reinforcement learning algorithm. Compared with traditional heuristic algorithms, this algorithm can improve solving efficiency and facilitate decision-making at the operational level of shipping enterprises. In terms of model performance, examples of different scales are used for comparison and training; the results are compared with the model without flexible allocation, and it is proved that the model proposed in this paper can obtain higher returns than the model without flexible allocation. The results show that the model and Q-learning algorithm can help enterprises solve the problem of the flexible allocation of shipping slots, and thus, this research has practical significance. Full article