Depth intensive learning-based train running scheduling method and system

Abstract

The invention relates to a depth intensive learning-based train running scheduling method and system. The method comprises the steps of first, collecting information about all schedulable trains of one station in a real scene and timetable of the schedulable trains and information about all schedulable drivers, so as to form original information; regularizing the collected original information; building a train depth intensive learning model by using the regularized data information; performing offline training and learning by using the depth intensive learning model, so as to obtain a trained train depth intensive learning model; and performing train running scheduling by the depth intensive learning-based train running scheduling system by using the trained depth intensive learning model. The depth intensive learning-based train running scheduling method and system make scheduling more intelligent, the technological processing process is simple and highly flexible, and the optimization efficiency is high.

Description

technical field [0001] The invention relates to the field of railway transportation scheduling, in particular to a train operation scheduling technology based on deep reinforcement learning. Background technique [0002] Train operation scheduling is an important part of railway traffic scheduling and command work, and its computer automatic calculation and solution problem is the core technology and difficulty of my country's railway information construction. At present, no matter whether it is the establishment of related optimization models or the solution to the corresponding models, there are no satisfactory research results that meet the actual needs. Moreover, the complexity of the train operation environment determines that the train operation scheduling problem is a large-scale complex combinatorial optimization problem, which makes the current research on the train operation scheduling problem somewhat one-sided. Therefore, it is of great significance both in theo...

AI Technical Summary

Problems solved by technology

At present, neither the establishment of relevant optimization models nor the solution of the corresponding models have satisfactory research results that meet the actual needs.

Moreover, the complexity of the train operation environment determines that the train operation scheduling problem is a large-scale complex combinatorial optimization problem, which makes the current research on the train operation scheduling problem somewhat one-sided.

[0004] Although the above-mentioned existing methods can solve the problem of train operation scheduling to a certain extent, there are many limitations respectively.

Among them, the precise algorithm has the problem of complex design, and the algorithm is difficult to meet the complex constraint conditions; although the heuristic algorithm has strong global search ability and high calculation efficiency, its processing process is complicated, the calculation is difficult, and the efficiency of optimization is relatively high. Low; the train operation simulation algorithm can better simulate the real train operation scheduling scene, but it needs to build a model operation platform, and the optimization efficiency is relatively low

Therefore, the existing train operation scheduling solutions all have various disadvantages in train operation scheduling

Images