Genetic-based algorithms for cash-in-transit multi depot vehicle routing problems: economic and environmental optimization

• Published in: Environment, development and sustainability Vol. 25; no. 1; pp. 557 - 586
• Main Authors: Ge, Xianlong, Jin, Yuanzhi, Zhang, Long
• Format: Journal Article
• Language: English
• Published: Dordrecht Springer Netherlands 01.01.2023; Springer Nature B.V
• Subjects: Algorithms; business development; case studies; Chromosomes; Commercial banks; Decision makers; Decision making; Earth and Environmental Science; Ecology; Economic Geology; Economic Growth; Environment; Environmental Economics; Environmental Management; Genetic algorithms; Goal programming; Optimization; Performance tests; Population density; risk; Risk analysis; Risk factors; Route planning; Sustainable Development; Time dependence; Trade; Traffic; Traffic congestion; Traffic flow; Traffic information; Traffic jams; Transportation planning; Vehicle routing; Vehicles; Risk constraints; Bi-objective optimization; Multi depot vehicle routing problem; Cash-in-transit; Goal programming
• ISSN: 1387-585X; 1573-2975
• DOI: 10.1007/s10668-021-02066-9

With the gradual increase of commercial banks and the expansion of their branches, the demand for cash transportation inflates sharply, bringing opportunities to the business development of Cash-In-Transit (CIT) sectors. However, the branches are often distributed in densely populated areas where traffic jams occur from time to time, which poses a severe challenge to the route planning of CIT vehicles. In addition, risk factors need to be considered during the optimization process because the goods transported belong to valuables. In order to effectively deal with the routing problem of CIT sectors, this paper established a bi-objective model and a goal programming model of Risk-Constrained Multi Depot Vehicle Routing Problems (RCMDVRPs) using real-time traffic data. Based on the traditional genetic algorithm, a Hybrid Genetic Algorithm with Intensification procedures (HGAI) is proposed to solve the goal programming model by using a three-level linked list structure to express chromosomes visually. Then, a new Self-constrained Hybrid Genetic Algorithm (SHGA) is designed for the bi-objective model. Besides, an online path updating strategy is developed to guide remote vehicles against time-dependent traffic flows. Finally, the HGAI is performed on benchmark instances to verify its accuracy. Experimental results of performance test show that the algorithm can achieve a gap of about 3% compared with the Best Known Result (BKR). The results of a case study also show that the two models and the corresponding algorithms are feasible and can be used to solve large-scale problems according to the special preferences and goals of decision-makers.