ynzhang, Yiying Zhang and Anca Ralescu
Adv. Artif. Intell. Mach. Learn., 3 (3):1234-1247
1. ynzhang: Tianjin University of Science & Technology
2. Yiying Zhang: College of Artificial Intelligence Tianjin University of Science and Technology Tianjin,300450,China
3. Anca Ralescu: EECS Department,University of Cincinnati 2600 Clifton Ave Cincinnati OH 45221-0030, USA
DOI: 10.54364/AAIML.2023.1172
Article History: Received on: 10-May-23, Accepted on: 12-Jul-23, Published on: 19-Jul-23
Corresponding Author: ynzhang
Email: ynzhangtju@126.com
Citation: Yanan Zhang, et al. Hybrid Vehicle Timetable Scheduling Under Fuzzy Decision Making.. Advances in Artificial Intelligence and Machine Learning. 2023;3(3):72.
The challenge of designing timetables for public transit lies in adjusting departure times to accommodate varying passenger flow, providing high-quality service, and optimizing the allocation of resources. The timetable design method proposed in this study, is based on both fuzzy constraint and fuzzy goal, vehicle usage degree and passenger satisfaction, with big and small size vehicles. Decision-making on size of the vehicles to be used, and time interval at certain time state is discussed. Two strategies are investigated including minimizing total cost per minute, and random selection of vehicle size followed by maximizing the degree of fuzzy constraints. Cost of timetable evaluates from four criteria: cost of waiting time, travel time, bus services time, and vehicle drive distance. Heuristic algorithms are designed to solve this problem, and integer programming is used in producing timetable. Different strategies are compared on the basis of current experimental results, and show that random selection of vehicle size followed by maximizing the degree of fuzzy constraints is a flexible and effective way in generating a timetable.