Linkage Problem in Location Optimization of Dedicated Bus Lanes on a Network. Issue 6 (June 2023)

• Record Type: Journal Article
• Authors: Bayrak, Murat; Guler, S. Ilgin
• Is Part Of: Transportation research record. Volume 2677:Issue 6(2023)
• Page Start: 433
• Page End: 447
• Publication Date: 2023-06
• Subjects: bus lane -- bus transit systems -- optimization -- optimization -- planning and analysis -- public transportation -- transportation network modeling; Transportation -- Periodicals; Roads; Transport -- Périodiques; Routes -- Périodiques; Routes -- Conception et construction -- Périodiques; Roads; Transportation; 388.05
• DOI: 10.1177/03611981221148490
• Languages: English
• ISSNs: 0361-1981

Abstract

Methods for identifying optimal decisions for dedicated bus lane locations (DBLs) on a network have been extensively studied in the literature. However, the impacts in relation to changes to car and bus delays of deploying a DBL on a given link largely depend on where other DBLs exist on the network. Therefore, for a network-wide location optimization or a bus lane design problem, linkages exist between decision variables. Typically used metaheuristic methods to optimize DBL locations, such as genetic algorithms (GAs), do not perform well for such problems with linkages between decision variables. To this end, this paper has two novel contributions to the literature by (a) demonstrating that the linkage problem exists, and (b) testing different heuristic algorithms that are more suitable than GAs for optimizing the locations of DBL on a network. The linkage problem in the location optimization of DBLs is demonstrated by enumerating all possible bus lane locations in a small grid network. Next, optimization algorithms that do not enumerate all possible bus lane locations that are capable of learning linkages between decision variables, namely Bayesian algorithm and a population-based incremental learning algorithm, are proposed. These algorithms are compared with two types of GAs in relation to consistency and quality of the solutions, and exploration capability. Results show that algorithms that can learn linkages between decision variables perform better than the GAs.