Optimal Design and Implementation of an Open-source Emulation Platform for User-Centric Shared E-mobility Services

TL;DR

This work tackles the lack of open, user-centric tools for shared E-mobility by delivering an open-source emulation platform that supports multi-modal routing under energy constraints. It combines a modular platform with SUMO/OpenStreetMap data and two optimization approaches: a Multi-Modal Energy-Constrained Ant Colony Optimization (MMEC-ACO) and Q-Learning, evaluated on the Dublin City Centre map using a reduced graph representation and E-hubs. Results show $Q$-Learning achieves better travel-time cost in over 90% of instances, though MMEC-ACO can reach optimal cost faster in some runs; for a fixed origin–destination pair $(O,D)$, MMEC-ACO converges in under 2 seconds while Q-Learning converges around 20 seconds, with a roughly 20% cost improvement for the 2-second runtime. Overall, the platform enables researchers to simulate, optimize, and visualize energy-aware, user-centric MaaS scenarios, promoting transparency and comparability across studies.

Abstract

With the rising concern over transportation emissions and pollution on a global scale, shared electric mobility services like E-cars, E-bikes, and E-scooters have emerged as promising solutions to mitigate these pressing challenges. However, existing shared E-mobility services exhibit critical design deficiencies, including insufficient service integration, imprecise energy consumption forecasting, limited scalability and geographical coverage, and a notable absence of a user-centric perspective, particularly in the context of multi-modal transportation. More importantly, there is no consolidated open-source platform which could benefit the E-mobility research community. This paper aims to bridge this gap by providing an open-source platform for shared E-mobility. The proposed platform, with an agent-in-the-loop approach and modular architecture, is tailored to diverse user preferences and offers enhanced customization. We demonstrate the viability of this platform by providing a comprehensive analysis for integrated multi-modal route-optimization in diverse scenarios of energy availability, user preferences and E-mobility tools placement for which we use modified Ant Colony Optimization algorithm so called Multi-Model Energy Constrained ACO (MMEC-ACO) and Q-Learning algorithms. Our findings demonstrate that Q-learning achieves significantly better performance in terms of travel time cost for more than 90\% of the instances as compared to MMEC-ACO for different scenarios including energy availability, user preference and E-mobility tools distribution. For a fixed (O, D) pair, the average execution time to achieve optimal time cost solution for MMEC-ACO is less than 2 seconds, while Q-learning reaches an optimal time cost in 20 seconds on average. For a run-time of 2 seconds, Q-learning still achieves a better optimal time cost with a 20\% reduction over MMEC-ACO's time cost.

Figures (5)

• Figure 1: System Architecture Diagram
• Figure 2: Different interfaces to illustrate the platform's visualisation module
• Figure 3: Illustration of the Multi-Modal Route Optimization Scenario highlighting the E-mobility docking stations and possible multi-modal routes
• Figure 4: Average Execution Times and Travel time Cost for the MMEC-ACO and Q-learning algorithms against different number of Ants and Episodes
• Figure 5: Bar Plot showing the Comparative Time Cost of Q-learning against MMEC-ACO corresponding to 3 different simulation aspects