20 April 2023 in Artificial Intelligence
10 February 2023 in arXiv
Mobile parcel lockers have been recently proposed by logistics operators as a technology that could help reduce traffic congestion and operational costs in urban freight distribution. Given their ability to relocate throughout their area of deployment, they hold the potential to improve customer accessibility and convenience. In this study, we formulate the Mobile Parcel Locker Problem (MPLP) , a special case of the Location-Routing Problem (LRP) which determines the optimal stopover location for MPLs throughout the day and plans corresponding delivery routes. A Hybrid Q Learning Network based Method (HQM) is developed to resolve the computational complexity of the resulting large problem instances while escaping local optima. In addition, the HQM is integrated with global and local search mechanisms to resolve the dilemma of exploration and exploitation faced by classic reinforcement learning methods. We examine the performance of HQM under different problem sizes (up to 200 nodes) and benchmarked it against the exact approach and Genetic Algorithm (GA). Our results indicate that HQM achieves better optimisation performance with shorter computation time than the exact approach solved by the Gurobi solver in large problem instances. Additionally, the average reward obtained by HQM is 1.96 times greater than GA, which demonstrates that HQM has a better optimisation ability. Further, we identify critical factors that contribute to fleet size requirements, travel distances, and service delays. Our findings outline that the efficiency of MPLs is mainly contingent on the length of time windows and the deployment of MPL stopovers. Finally, we highlight managerial implications based on parametric analysis to provide guidance for logistics operators in the context of efficient last-mile distribution operations.
1 January 2022 in SSRN Electronic Journal
Public transport is the enabler of social and economic development, as it allows the movement of people and provides access to opportunities that otherwise might have been unattainable. Access to public transport is a key aspect of social equity, with step-free access improving the inclusivity of the transport network in particular for mobility impaired population groups. Thus, this study develops a two-step algorithm for determining the optimal allocation of resources for the refurbishment of public transit metro stations to provide step-free accessibility in pubic transport networks. The first step consists of k-shortest path finding algorithm between every origin-destination pair in the network. The non step-free shortest paths are then fed into the second step of the algorithm, a mixed-integer linear optimization problem that selects the station to be refurbished considering inequality as well as population, costs, budget and demand constraints, whilst considering the impact of construction times and disruptions on the journeys. The developed methodology is applied to enhance the accessibility of the London Underground. In doing so, several demographic components, including population in each borough or districts, economic background, and disability reported, are parameterised and factored into the determination of the optimal solution. Our analysis shows in average above 5% increase in step-free trips per borough and 8% increase overall in the London boroughs. Thanks to the refurbishments over 850,000 daily step-free journeys can be made through the London Underground transport system and at least additional 3% of the paths will be made step-free and helping each existing step-free journey to take around 4% shorter journey time.