A Predictive Fleet Management Strategy for On-Demand Mobility Services: A Case Study in Munich

Abstract

The global market for MoD services is in a state of rapid and challenging transformation, with new market entrants in Europe, such as Uber, MOIA, and CleverShuttle, competing with traditional taxi providers. Rapid developments in available algorithms, data sources, and real-time information systems offer new possibilities of maximizing the efficiency of MoD services. In particular, the use of demand predictions is expected to contribute to a reduction in operational costs and an increase in overall service quality. This paper examines the potential of predictive fleet management strategies applied to a large-scale real-world taxi dataset for the city of Munich. A combination of state-of-the art dispatching algorithms and a predictive RHC optimization for idle vehicle rebalancing was developed to determine the scale by which a fleet size can be reduced without affecting service quality. A simulation study was conducted over a one-week period in Munich, which showed that predictive fleet strategies clearly outperform the present strategy in terms of both service quality and costs. Furthermore, the results showed that current taxi fleets could be reduced to 70% of their original size without any decrease in performance. In addition, the results indicated that the reduced fleet size of the predictive strategy was still 20% larger compared to the theoretical optimum resulting from a bipartite matching approach.

The Optimal Size of a Heterogeneous Air Taxi Fleet in Advanced Air Mobility: A Traffic Demand and Flight Scheduling Approach

“…Ehlers et al [45] also demonstrated a further possibility for evaluating a mixed fleet based on an economic efficiency compared to other fleet compositions via a Fleet Efficiency Factor. Recent works based on regression methods are focusing on fleet sizing summarized under the term Mobility on Demand for shared bikes [46][47][48][49], cars and taxis [50][51][52]. Similarities can be found also for the optimum mix and size of air taxi fleets in the aviation industry [53][54][55][56].…”

Streamlining advanced taxi assignment strategies based on legal analysis

“…Nowadays, in the taxi dispatching domain, the nearest-taxi/nearest-request (NTNR) strategy is often used as baseline. It assigns customers to the closest available taxis if there are more available taxis than customers (like FCFS), but allocates each available taxi to the closest waiting customer if there are less taxis than customers [12,13]. The availability of real-time GPS data streams as well as support for Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) communication has spawned interest in novel ICT platforms that support taxi fleet management.…”

The Influence of Public Transport Delays on Mobility on Demand Services

“…For the high demand location Marienplatz, censoring might have occurred in up to 24% of all data points. Such censored demand only occurs for the carsharing service, but not the taxi service, as taxi street-hailing is less common in Munich [35], and as Munich has a significant oversupply in taxis [36].…”