Bus Network Design and Frequency Setting in the Post-COVID-19 Pandemic: The Case of London

Abstract

A transit network design frequency setting model is proposed to cope with the postpandemic passenger demand. The multiobjective transit network design and frequency setting problem (TNDFSP) seeks to find optimal routes and their associated frequencies to operate public transport services in an urban area. The objective is to redesign the public transport network to minimize passenger costs without incurring massive changes to its former composition. The proposed TNDFSP model includes a route generation algorithm (RGA) that generates newlines in addition to the existing lines to serve the most demanding trips, and passenger assignment (PA) and frequency setting (FS) mixed-integer programming models that distribute the demand through the modified bus network and set the optimal number of buses for each line. Computational experiments were conducted on a test network and the network comprising the Royal Borough of Kensington and Chelsea in London.

A transit network design and frequency setting model with graph neural network and deep reinforcement learning

“…To overcome the limitations of sequential optimization, [24] used reinforcement learning to simultaneously optimize the three key components of BNDFS: the number of bus routes, route design, and service frequency. The TNDFSP model in [25] includes a mixed-integer programming model for route generation algorithm (RGA), passenger allocation (PA), and frequency setting (FS). [26] developed a model using the Transformer architecture( [27]) that produces a fractional solution for the multiple traveling salesman problem (mTSP).…”