Activity-Based Freight Transport Modeling: A Surrogate-Based Optimization Model to Estimate Freight Vehicles Time-Dependent Routing and Scheduling

conference paper
The spatial and temporal catachrestic of freight road transport is important to study daily patterns of freight
activities. This requires a model that can reproduce these spatial-temporal patterns. This paper proposes a
surrogate-based optimization method to calibrate a data-driven time-dependent vehicle routing and
scheduling model that can be used for understanding and simulating freight vehicles activities. This model
seeks to capture and replicate the tour-based behaviour of carriers and their tactical decisions. The model
can learn and synthesize the most likely tour flows from shipment flow data, partially observed tours, and
travel times between traffic analysis zones per time interval. This model allows for descriptive analysis of
freight transport and policy assessment for freight and traffic management. The results show that the model
is able to fit the data accurately and generate tours with reasonably close aggregate features to the ground
truth.
TNO Identifier
981768
Source title
TRB 101st Annual Meeting of the Transportation Research Board
Pages
1-17
Files
To receive the publication files, please send an e-mail request to TNO Repository.