Paper Info
Title
Intelligent Joint Trajectory Design And Resource Allocation In Uav-Based Data Harvesting System
Abstract
With the development of Internet of Things (IoT) technology, wireless sensor networks (WSNs) composed of multiple sensor nodes (SNs) have been able to provide a large number of high-quality services, such as continuous environmental monitoring, automatic control, and transmission of data for intelligent decision-making. SNs in WSNs are typically energy limited and often exist in large numbers, which are widely distributed in hard-to-reach areas. Hence, it is difficult to collect data from SNs without infrastructure support such as base stations (BSs). The low cost and high maneuverability of unmanned aerial vehicles (UAVs) provide an efficient solution for data acquisition in WSNs but with the challenge of control system of the UAV. In this paper, we proposed a deep reinforcement learning based UAV control system to intelligently solve the data harvesting problem in WSNs. Our optimization target is to jointly optimize the trajectory of the UAV and the bandwidth resources of the airborne base station to maximize the data acquisition success rate when the UAV is limited in energy. The objective function and constraints of this problem are highly non-convex. To solve this problem, we first modeled the movement of the UAV and the bandwidth allocation of the airborne base station in each time slot as a Markov decision process (MDP). Then we designed a deep reinforcement learning architecture to solve the above MDP. Compared with the existing data harvesting algorithms, the proposed method has a great improvement in data acquisition success rate.
Year
DOI
Venue
2020
10.1109/ICCA51439.2020.9264486
2020 IEEE 16TH INTERNATIONAL CONFERENCE ON CONTROL & AUTOMATION (ICCA)
DocType
ISSN
Citations 
Conference
1948-3449
0
PageRank 
References 
Authors
0.34
0
5
Name
Order
Citations
PageRank
Siyu Luo100.34
Junkai Liu200.68
Siyu Chen382.15
Jienan Chen4178.93
Jifeng Guo500.34