Fleet Sizing for the Flash Delivery Problem from Multiple Depots a Case Study in Amsterdam

TL;DR

This paper introduces a novel fleet sizing approach for flash delivery that optimizes grouping and routing of requests, improving operational efficiency in a real-world Amsterdam case study.

Contribution

It presents a new method combining request grouping and integer linear programming for fleet sizing in flash delivery, validated on real data.

Findings

Proposed approach outperforms fixed routing and non-pooled strategies.

Effective request pooling reduces fleet size and operational costs.

Insights into delay tolerance and store count impact on delivery efficiency.

Abstract

In this paper, we present a novel approach for fleet sizing in the context of flash delivery, a time-sensitive delivery service that requires the fulfilment of customer requests in minutes. Our approach effectively combines individual delivery requests into groups and generates optimized operational plans that can be executed by a single vehicle or autonomous robot. The groups are formed using a modified routing approach for the flash delivery problem. Combining the groups into operational plans is done by solving an integer linear problem. To evaluate the effectiveness of our approach, we compare it against three alternative methods: fixed vehicle routing, non-pooled deliveries and a strategy encouraging the pooling of requests. The results demonstrate the value of our proposed approach, showcasing its ability to optimize the fleet and improve operational efficiency. Our experimental analysis is based on a real-world dataset provided by a Dutch retailer, allowing us to gain valuable insights into the design of flash delivery operations and to analyze the effect of the maximum allowed delay, the number of stores to pick up goods from and the employed cost functions.