Deployment and Association of Multiple UAVs in UAV-Assisted Cellular Networks With the Knowledge of Statistical User Position

Wang, Leiyu; Zhang, Haixia; Guo, Shuaishuai; Yuan, Dongfeng

doi:10.1109/twc.2022.3150429

Cited by 74 publications

(13 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Over the past few years, DRL has received significant attention due to its impressive success in intricate tasks such as international Go, games, and controlling complex machinery for various operations [33]- [35]. This success has propelled the application of DRL methods in UAV-assisted data collection for IoT networks [11], [27]- [30]. Nevertheless, the action space considered in these studies is typically confined to either continuous or discrete domains [36]- [40].…”

Section: B Drl Methods In Uav-assisted Data Collectionmentioning

confidence: 99%

Deep Reinforcement Learning for Fresh Data Collection in UAV-assisted IoT Networks

Wang

Liu

et al. 2020

IEEE INFOCOM 2020 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)

View full text Add to dashboard Cite

Unmanned aerial vehicles (UAVs) have the potential to greatly aid Internet of Things (IoT) networks in missioncritical data collection, thanks to their flexibility and costeffectiveness. However, challenges arise due to the UAV's limited onboard energy and the unpredictable status updates from sensor nodes (SNs), which impact the freshness of collected data. In this paper, we investigate the energy-efficient and timely data collection in IoT networks through the use of a solarpowered UAV. Each SN generates status updates at stochastic intervals, while the UAV collects and subsequently transmits these status updates to a central data center. Furthermore, the UAV harnesses solar energy from the environment to maintain its energy level above a predetermined threshold. To minimize both the average age of information (AoI) for SNs and the energy consumption of the UAV, we jointly optimize the UAV trajectory, SN scheduling, and offloading strategy. Then, we formulate this problem as a Markov decision process (MDP) and propose a meta-reinforcement learning algorithm to enhance the generalization capability. Specifically, the compound-action deep reinforcement learning (CADRL) algorithm is proposed to handle the discrete decisions related to SN scheduling and the UAV's offloading policy, as well as the continuous control of UAV flight. Moreover, we incorporate meta-learning into CADRL to improve the adaptability of the learned policy to new tasks. To validate the effectiveness of our proposed algorithms, we conduct extensive simulations and demonstrate their superiority over other baseline algorithms.

show abstract

Section: B Drl Methods In Uav-assisted Data Collectionmentioning

confidence: 99%

Deep Reinforcement Learning for Fresh Data Collection in UAV-assisted IoT Networks

Wang

Liu

et al. 2020

IEEE INFOCOM 2020 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)

View full text Add to dashboard Cite

show abstract

“…A similar problem has been addressed by the authors in [ 17 ] for non-orthogonal multiple-access (NOMA) networks. In [ 8 ], the authors jointly optimized the UmBS deployment and the UE-UmBS association to design an energy-efficient UmBS deployment technique. In [ 18 ], the authors first leveraged the Poisson point process to get the location information of the ground UE and then designed a framework to provide network connectivity on demand.…”

Section: Related Workmentioning

confidence: 99%

“…However, despite the potential features of UmBS, its deployment in real-world scenarios faces challenges too. The main challenges include the following: estimation of ground UEs position information [ 6 , 7 ], association of UEs to their serving UmBS [ 8 ], association of the UmBS to the core network [ 9 ], resource allocation [ 10 , 11 ], channel characterization [ 12 ], energy optimization [ 13 ], and trajectory optimization [ 14 , 15 ]. In particular, two issues are major and significantly affect the design of the UmBS deployment algorithm.…”

Section: Introductionmentioning

confidence: 99%

Q-learning-based UAV-mounted base station positioning in a disaster scenario for connectivity to the users located at unknown positions

Mandloi

Arya

2023

J Supercomput

View full text Add to dashboard Cite

Due to its flexibility, cost-effectiveness, and quick deployment abilities, unmanned aerial vehicle-mounted base station (UmBS) deployment is a promising approach for restoring wireless services in areas devastated by natural disasters such as floods, thunderstorms, and tsunami strikes. However, the biggest challenges in the deployment process of UmBS are ground user equipment’s (UE’s) position information, UmBS transmit power optimization, and UE-UmBS association. In this article, we propose Localization of ground UEs and their Association with the UmBS (LUAU), an approach that ensures localization of ground UEs and energy-efficient deployment of UmBSs. Unlike existing studies that proposed their work based on the known UEs positional information, we first propose a three-dimensional range-based localization approach (3D-RBL) to estimate the position information of the ground UEs. Subsequently, an optimization problem is formulated to maximize the UE’s mean data rate by optimizing the UmBS transmit power and deployment locations while taking the interference from the surrounding UmBSs into consideration. To achieve the goal of the optimization problem, we utilize the exploration and exploitation abilities of the Q-learning framework. Simulation results demonstrate that the proposed approach outperforms two benchmark schemes in terms of the UE’s mean data rate and outage percentage.

show abstract

“…However, there are differences in the needs of students with different cognitive levels for learning resources [9][10][11][12]. To prevent students from becoming "knowledge lost" when faced with a huge load of learning resources, it is necessary to predict students' cognitive levels and correlate them with the appropriate expertise for their learning [13][14][15]. Knowledge networks play an important role in how students acquire and share knowledge.…”

Section: Introductionmentioning

confidence: 99%

An Analysis of the Categories and Structures of Expertise for Students’ Cognitive States

Niu¹

2023

Int. J. Emerg. Technol. Learn.

View full text Add to dashboard Cite

Knowledge networks play an important role in the process of knowledge acquisition and sharing by students. An analysis of their complex structural features is required for the connectivity between students and knowledge. Existing research lacks insight into the internal structural features of knowledge networks constructed from expertise. There is also a lack of effective methods for constructing personalised knowledge networks for students' cognitive states. This paper analyses the categories and structures of expertise for students' cognitive states, and presents in detail a grey prediction algorithm to identify students' cognitive states. Then, the paper presents a typological description of the knowledge nodes in the expertise network for students' cognitive states, and analyses the knowledge network structure from the perspectives of paths and statistical properties. After that, the paper gives a method for analysing the knowledge flow of the expertise network. The experimental results validate the effectiveness of the proposed method.

show abstract

Deployment and Association of Multiple UAVs in UAV-Assisted Cellular Networks With the Knowledge of Statistical User Position

Cited by 74 publications

References 40 publications

Deep Reinforcement Learning for Fresh Data Collection in UAV-assisted IoT Networks

Deep Reinforcement Learning for Fresh Data Collection in UAV-assisted IoT Networks

Q-learning-based UAV-mounted base station positioning in a disaster scenario for connectivity to the users located at unknown positions

An Analysis of the Categories and Structures of Expertise for Students’ Cognitive States

Contact Info

Product

Resources

About