Onboard Deep Deterministic Policy Gradients for Online Flight Resource Allocation of UAVs

被引：7

作者：

Li, Kai ^{[1
]}

Emami, Yousef ^{[1
]}

Ni, Wei ^{[2
]}

Tovar, Eduardo ^{[1
]}

Han, Zhu ^{[3
]}

机构：

[1] Real-Time and Embedded Computing Systems Research Centre (CISTER), Porto

[2] Data61 Commonwealth Scientific and Industrial Research Organization (CSIRO), Sydney, 2122, NSW

[3] Electrical and Computer Engineering Department, University of Houston, Houston, 77004, TX

来源：

IEEE Networking Letters | 2020年 / 2卷 / 03期

关键词：

data collection; deep reinforcement learning; flight control; Unmanned aerial vehicles;

D O I：

10.1109/LNET.2020.3002341

中图分类号：

学科分类号：

摘要：

In Unmanned Aerial Vehicle (UAV) enabled data collection, scheduling data transmissions of the ground nodes while controlling flight of the UAV, e.g., heading and velocity, is critical to reduce the data packet loss resulting from buffer overflows and channel fading. In this letter, a new online flight resource allocation scheme based on deep deterministic policy gradients (DDPG-FRAS) is studied to jointly optimize the flight control of the UAV and data collection scheduling along the trajectory in real time, thereby asymptotically minimizing the packet loss of the ground sensor networks. Numerical results confirm that the proposed DDPG-FRAS can gradually converge, while enlarging the buffer size can reduce the packet loss by 47.9%. © 2019 IEEE.

引用

页码：106 / 110

页数：4

共 19 条

[1]

Chamola V., Hassija V., Gupta V., Guizani M., A comprehensive review of the COVID-19 pandemic and the role of IoT, drones, AI, blockchain, and 5G in managing its impact, Ieee Access, 8, pp. 90225-90265, (2020)

[2]

Li L., Xu Y., Zhang Z., Yin J., Chen W., Han Z., A prediction-based charging policy and interference mitigation approach in the wireless powered Internet of Things, Ieee J. Sel. Areas Commun., 37, 2, pp. 439-451, (2019)

[3]

Xiao L., Lu X., Xu D., Tang Y., Wang L., Zhuang W., UAV relay in VANETs against smart jamming with reinforcement learning, Ieee Trans. Veh. Technol., 67, 5, pp. 4087-4097, (2018)

[4]

Liu Z., Chinese Solar-Powered Drone Morning Star Spreads Its Wings in Successful Test Flight. [Online], (2018)

[5]

Li K., Ni W., Duan L., Abolhasan M., Niu J., SWPT: A joint-scheduling model for wireless powered sensor networks, Proc. Ieee Global Commun. Conf. (GLOBECOM), Singapore, pp. 1-6, (2017)

[6]

Yu X., Zhou X., Zhang Y., Collision-free trajectory generation for UAVs using Markov decision process, Proc. Int. Conf. Unmanned Aircraft Syst. (ICUAS), Miami, FL, Usa, pp. 56-61, (2017)

[7]

Ragi S., Chong E.K., UAV guidance algorithms via partially observable Markov decision processes, Handbook of Unmanned Aerial Vehicles, pp. 1775-1810, (2015)

[8]

Cao D., Yin Z., Yang W., Kang G., An energy-efficient transmission scheme for buffer-aided UAV relaying networks, Proc. Ieee Int. Conf. Signal Process. Commun. Comput. (ICSPCC), Dalian, China, pp. 1-5, (2019)

[9]

Li K., Ni W., Duan L., Abolhasan M., Niu J., Wireless power transfer and data collection in wireless sensor networks, Ieee Trans. Veh. Technol., 67, 3, pp. 2686-2697, (2018)

[10]

Li K., Ni W., Abolhasan M., Tovar E., Reinforcement learning for scheduling wireless powered sensor communications, Ieee Trans. Green Commun. Netw., 3, 2, pp. 264-274, (2019)

← 1 2 →