Future UAV-Based ITS: A Comprehensive Scheduling Framework

• Published in: IEEE access Vol. 7; pp. 75678 - 75695
• Main Authors: Ghazzai, Hakim, Menouar, Hamid, Kadri, Abdullah, Massoud, Yehia
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Batteries; Computer interfaces; Docking; Energy consumption; Geographical distribution; Intelligent transportation system; Intelligent transportation systems; Missions; Monitoring; New technology; Optimization; Particle swarm optimization; planning; Rechargeable batteries; Scheduling; Stations; Task analysis; Traffic control; Trajectory; Unmanned aerial vehicles
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2019.2921269

Multi-rotor unmanned aerial vehicles (UAVs) have been recently recognized as one of the top emerging technologies to be utilized in various smart city domains such as intelligent transportation systems (ITS). They represent an innovative mean to complement existing technologies to surveil transportation network, control traffic, and monitor incidents. The UAVs usually operate for time-limited missions due to their limited battery capacity. Hence, they need to frequently return to their docking stations to recharge their batteries, which handicaps their mission coverage and performance. When designing a UAV-based ITS infrastructure, it is crucial to leverage the UAV fleet effectively. In this paper, a generic management framework of UAVs for ITS applications is developed. The problem of docking/charging station placement is first investigated to find optimized locations for a given number of stations to be installed by the ITS operator. To this end, two fundamental criteria are taken into account: i) the flying time required by the UAV to reach the mission/incident location and ii) the risk of battery failure during the UAV operation. The two algorithms, namely a penalized weighted k-means algorithm and the particle swarm optimization algorithm, are designed for this purpose. Once the docking stations are placed, a UAV scheduling program is formulated to optimally cover the pre-known missions while minimizing the total energy consumption of the fleet and respecting a coverage efficiency targeted by the ITS operator. The proposed proactive scheduling approach employs multiple UAVs in sequential and parallel ways to cover spatially and temporally distributed events in the geographical area of interest over a long period.