A Last-mile Facility Allocation Problem with Traffic Congestion and Natural Disaster

Abstract

Managing distribution in urban areas can be much more challenging in the twenty-first century. The population density carries accessibility issues to education, healthcare, infrastructure, and services through traffic congestion and pollution. It is worth noting that some areas simultaneously deal with traffic congestion and natural disasters. This issue may interfere with last-mile logistics, mainly when extreme conditions occur. One way to overcome this issue is by placing distribution facilities in unaffected areas to maximise last-mile logistics despite extreme conditions. However, the facility location problem regarding traffic congestion and natural disasters remains limited. This paper proposes Expected coverage problems with traffic congestion and natural disaster (ECP-CN), the extension model of facility location problems involving traffic congestion and natural disasters. ECP-CN consists of flexibility where the facilities will be in non-disaster areas rather than congestion-free areas whenever the ideal condition is not met. The algorithm used to solve the problem is a Genetic Algorithm (GA). The algorithm has converged to an optimal solution, showing a high initial demand coverage, subsequent improvements, and significant fluctuations. Further exploration of parameter settings or diversity-enhancing mechanisms may be optional. This result indicated that GA could locate the facilities in non-disaster areas while maintaining maximum demand coverage in all sample sizes.