Big Data Analytics and Network Calculus Enabling Intelligent Management of Autonomous Vehicles in a Smart City
- 27 September 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 6 (2) , 2021-2034
Abstract
Artificial intelligence and big data analytics enable autonomous vehicles (AVs) to dramatically change future intelligent transportation in smart cities. AVs are envisaged to evolve to a service rather than a product in the future. To provide best user experience of such services, three primary factors, namely, waiting time, travel time, and supply of AV services, are taken into consideration in a multi-objective optimization. Conventional optimization of services relies on traffic flow analysis over a queuing network model. However, due to the mobility of vehicles and the transfer uncertainty of road networks, the queuing network analysis is too complicated and practically intractable. For accuracy and convenient processing, network calculus (NC) is extended to model the queueing problem in this paper. The optimal number of available AVs can be identified by guaranteeing the waiting time of customers. The satisfaction of AV services can be viewed as a supply and demand problem, and optimized by bipartite graph matching. In order to reduce the average travel time, especially for rush hours with heavy traffic, we further propose a new online AVs fleet management scheme with congestion control for smart cities. It is shown that the intelligent management of AV fleet can be efficiently achieved, outperforming the cases of traditional vehicles. NC-assisted AI enables an efficient intelligent transportation paradigm in smart cities, while achieving substantial energy saving.Keywords
Funding Information
- National Natural Science Foundation of China (61471058, 61631005)
- Hong Kong, Macau, and Taiwan Science and Technology Cooperation Projects (2016YFE0122900)
- Beijing Municipal Science and Technology Commission, Adminitrative Commission of Zhongguancun Science Park (201702005)
- 111 project of China (B16006)
This publication has 29 references indexed in Scilit:
- Bipartite matching approach to optimal resource allocation in device to device underlaying cellular networkElectronics Letters, 2014
- Kernel Ridge Regression2013
- A Vehicular Mobility Model Based on Real Traffic Counting Data2011
- MODELING TRAFFIC FLOWS WITH QUEUEING MODELS: A REVIEWAsia-Pacific Journal of Operational Research, 2007
- The Hungarian method for the assignment problemNaval Research Logistics (NRL), 2004
- Taxi Dispatch System Based on Current Demands and Real-Time Traffic ConditionsTransportation Research Record: Journal of the Transportation Research Board, 2004
- ARIMA models to predict next-day electricity pricesIEEE Transactions on Power Systems, 2003
- Application of network calculus to guaranteed service networksIEEE Transactions on Information Theory, 1998
- Molecular Geometry Optimization with a Genetic AlgorithmPhysical Review Letters, 1995
- Algorithms for the Assignment and Transportation ProblemsJournal of the Society for Industrial and Applied Mathematics, 1957