University of Twente Student Theses

Login

Improving Operational Efficiency In EV Ridesharing Fleets By Predictive Exploitation of Idle Times

Provoost, Jesper C. (2021) Improving Operational Efficiency In EV Ridesharing Fleets By Predictive Exploitation of Idle Times.

[img] PDF
1MB
Abstract:In dynamic ridesharing systems which are operated with an electric fleet, charging is an essential but complex decision-making process. Most contemporary electric vehicle (EV) taxi services require drivers to make egoistic decisions on where, when and how long to charge, leading to decentralized ad-hoc charging strategies. Moreover, knowledge about the current state of the mobility system is often lacking or simply not shared between vehicles, making it impossible to make a system-optimal decision. As a consequence, transport and resource efficiency are likely to be suboptimal, impacting the profitability of the service from the operator's perspective. Most existing approaches to intelligent charging control work do not combine time, location and duration into a comprehensive control algorithm or are unsuitable for real-time operation in networks with thousands of road segments. We therefore present a real-time predictive charging method for dynamic ridesharing services with a single operator. This method, called Idle Time Exploitation (ITX), predicts the periods where vehicles are idle and exploits these periods to harvest energy. It relies on Graph Convolutional Networks (GCNs) and a linear assignment algorithm to devise an optimal pairing of vehicles and charging stations, in pursuance of maximizing the exploited idle time. Our approach works on large-scale graph representations of the road network and enables fine-grained decision-making. We evaluated our approach through extensive simulation studies on real-world datasets from New York City. As a reference, multiple baselines were devised with varying levels of complexity. The results demonstrate that ITX outperforms all baseline methods by at least 5% (equivalent to $70,000 for a 6,000 vehicle operation) per week in terms of a monetary reward function which was modeled to replicate the profitability of a real-world ridesharing system. Moreover, ITX can reduce delays by at least 4.68% in comparison with baseline methods and generally increase passenger comfort by facilitating a better spread of customers across the fleet. Our results also demonstrate that ITX enables vehicles to harvest energy during the day, stabilizing battery levels and increasing resilience to unexpected surges in demand. Lastly, compared to the best-performing baseline strategy, peak loads are reduced by 17.39% which benefits grid operators and paves the way for more sustainable use of the electrical grid.
Item Type:Essay (Master)
Clients:
KTH Royal Institute of Technology, Stockholm, Sweden
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:54 computer science, 55 traffic technology, transport technology
Programme:Computer Science MSc (60300)
Link to this item:http://purl.utwente.nl/essays/88681
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page