Similarity-based bus services assignment with capacity constraint for staggered bus stops

Document Type

Journal Article

Publication Date


Subject Area

place - asia, place - urban, mode - bus, operations - performance, operations - scheduling, operations - capacity, planning - service level, ridership - commuting


Assignment, Bus stop, Capacity, Dynamic time warping, Pareto efficiency, Similarity, Time series


The assignment of bus services to appropriate stops is a crucial parameter in ensuring a high level of service for commuters at staggered bus stops. In this study, an innovative similarity-based assignment method is proposed to assign a set of bus services to a set of stop areas in such a configuration, while considering the capacity constraint of the bus stop areas. First, a new concept of the time series of bus stop occupancy is introduced to dynamically track if a bus stop is occupied by a specific bus service. Then, a dynamic time warping-based algorithm is proposed to measure the similarity level of the time series of bus stop occupancy between different bus services. Considering both capacity constraint and performance of similarity level at each bus stop area, bus services assignment can be modelled as a Pareto efficiency problem. We can trade off within the Pareto efficient solutions and determine the best assignment scheme. Finally, the performance of our proposed method is evaluated using data collected from four staggered bus stops in Singapore. To evaluate the model’s stability and reliability, sensitivity analyses are conducted to test the effect of (i) pre-defined bus arrival rate, (ii) time interval used for creating the time series of bus stop occupancy, and (iii) day of week on staggered bus stop performance. The proposed method developed in this study can help transit agencies and operators determine the appropriate bus service assignment within a staggered bus stop configuration.


Permission to publish the abstract has been given by Elsevier, copyright remains with them.


Transportation Research Part E Home Page: