Demand Response Mechanism of Customized Bus Based on Space-Time Clustering

The response of the reserved demand is crucial to the operation of the customized bus, however, the demand of passengers is scattered in time and space. Transportation enterprises often rely on experience to determine whether to respond to the reserved demand and it is likely to reduce the attractiveness of the customized bus. The customized bus demand response mechanism based on temporal and spatial clustering was proposed. The reserved demands are filtered by response on space-time dimension. Firstly, in time dimension, the response is based on hierarchical clustering algorithm to reserve demand with close travel time. Then response from the spatial dimension using the DBSCAN cluster algorithm is to eliminate special request with relatively isolated spatial location and fewer people, obtaining popularization request with the convergence of time and space. In order to verify the effectiveness of the response mechanism, several examples are performed. The calculation results show that only 69% of reserved demand and 75% of passengers can be responded by setting the parameter empirical values. By appropriately adjusting parameters, when the minimum retention time span is not more than 3 minutes, the minimum number of passengers to get reserved demands is not greater than 2, the value of meeting the condition of proximity to the place of arrival is not less than 1000m, the input parameter neighborhood of the DBSCAN clustering algorithm is not less than 400m, and the lower limit of the number of passengers in a category is not more than 4, it can be respond to 75% of reserved demands and 80% of passengers. The principle of response that meets most of customized requirements and appropriately eliminates special demands was contented. It can be seen that the mechanism has great applicability to response customized demands, and can provide decision-making basis for transport enterprises to open customized bus lines.