| Title |
A multi-agent system for context-aware electric vehicle fleet routing: A step towards more sustainable urban operations |
| ID_Doc |
74645 |
| Authors |
Jelen, G; Babic, J; Podobnik, V |
| Title |
A multi-agent system for context-aware electric vehicle fleet routing: A step towards more sustainable urban operations |
| Year |
2022 |
| Published |
|
| DOI |
10.1016/j.jclepro.2022.134047 |
| Abstract |
This paper presents a multi-agent system for context-aware routing of electric vehicle fleets, which provides a means for cost-effective planning and utilization of resources in contemporary urban operations. The multi-agent system consists of three main parts: Model, Routing Algorithms and Platform. The case study of cleaning urban areas in the city of Split with electric cleaners is used to evaluate the multi-agent system. The model consists of three main entities: Electric Vehicle, Charging Station and Depot. The electric vehicle is defined more generally to ensure the application and reusability of the model in different business and research domains. The routing algorithms of the multi-agent system are defined with artificial intelligence utilization models. The utilization models predict the use of parking lots and charging stations, based on which the routing algorithms navigate the electric vehicles in the space. The utilization models use the CatBoost machine learning method and a contextually enriched dataset that uses point-of-interest data as context. The multi-agent platform for contextual routing of electric vehicles is used for validation and evaluation of multi-agent models and comparative analysis of routing algorithms under defined contextual conditions. Using context-aware routing algorithms, the multi-agent system for the case study showed a 5.6% improvement in urban cleaning operations and an 18.5% improvement in vehicle charging at charging stations. |
| Author Keywords |
Electric vehicle routing problem; Multi-agent system; Contextually enriched data; Data science; Sustainable urban operations |
| Index Keywords |
Index Keywords |
| Document Type |
Other |
| Open Access |
Open Access |
| Source |
Science Citation Index Expanded (SCI-EXPANDED) |
| EID |
WOS:000888794800002 |
| WoS Category |
Green & Sustainable Science & Technology; Engineering, Environmental; Environmental Sciences |
| Research Area |
Science & Technology - Other Topics; Engineering; Environmental Sciences & Ecology |
| PDF |
|