Research On Bus Scheduling Rules Based On Big Data

Improve the bus service level is an effective way for the implementation of bus priority. With the development of intelligent public transit, the bus system will produce a large amount of data in the process of operation, which provide the basis for public transport planning and management departments make decisions. Based on bus IC card data and bus GPS data, by means of data processing and data analysis and data mining, we can get effective passenger flow and vehicle running information to make the forecast which can provide decision support for bus dispatching.This paper first introduces the analysis of bus data source, tell the data produce model of bus intelligent system under the background of intelligent transportation, and preprocessing of Bus data, which include two different types of data preprocessing steps based on the IC card data and GPS data. Then this paper studies the data mining and analysis of the bus data, introduces the basic concept of data mining and the commonly used algorithms; For IC card data mining, this paper studies the division of flow time based on IC card data mining and analysis of some passenger flow index and passenger flow forecast based on BP neural network. For bus GPS data mining, this paper studies the route matching of bus GPS, and the moving characteristic of the bus in the running process and the bus running time forecast based on the BP neural networkBased on the data mining, this paper studies the bus scheduling, this paper mainly studied the plan making of the timetable, which means establish a bus timetable model based on passenger waiting cost minimum, crowded degree minimum, bus company operation cost minimum according to the IC passenger flow data, and solve the model by using genetic algorithm. For dynamic scheduling, this paper studies the vehicle scheduling model under abnormal events, and station scheduling of the real-time scheduling and scheduling between stations, as well as dynamic stranded station scheduling and dynamic scheduling of the bus signal priority, reducing the occurrence of bunching and large interval, which can improve the service level of the bus transit.At last, according to research contents mentioned above, verify the above data processing, data mining and analysis, as well as the research content of the bus schedule by using examples.