Dynamic Lookahead Policies for Stochastic-Dynamic Inventory Routing in Bike Sharing Systems

Abstract

We present the stochastic-dynamic inventory routing problem for bike sharing systems (SDIRP). The objective of the SDIRP is to avoid unsatisfied demand by dynamically relocating bikes during the day. To anticipate potential future demands in the current inventory decisions, we present a dynamic lookahead policy (DLA). The policy simulates future demand over a predefined horizon. Because the heterogeneous demand patterns over the course of the day, the DLA horizons are time-dependent and autonomously parametrized by means of value function approximation, a method of approximate dynamic programming. We compare the DLA with conventional relocation strategies from the literature and lookahead policies with static horizons. Our study based on real-world data by the bike sharing system of Minneapolis (Minnesota, USA) reveals the benefits of both anticipation by lookaheads as well as the time-dependent horizons of the DLA. We additionally show how the DLA is able to autonomously adapt to the demand patterns.