Multi-UAV-Enabled Load-Balance Mobile-Edge Computing for IoT Networks

Yang, Lüxi; Yao, Haipeng; Wang, Jingjing; Jiang, Chunxiao; Benslimane, Abderrahim; Liu, Yunjie

doi:10.1109/jiot.2020.2971645

Cited by 282 publications

(118 citation statements)

References 30 publications

Supporting

Mentioning

116

Contrasting

Unclassified

Order By: Relevance

“…Therefore, similar to LCAD, these protocols do not consider the traffic characteristics or URN bottlenecks. A multi-UAV-aided MEC architecture has been proposed [ 6 ] as a joint multi-UAV deployment and task scheduling optimization for IoT networks. This paper proposed the task scheduling method using deep reinforcement learning in terms of the role of the Multi-access Edge Computing (MEC) node.…”

Section: Related Studiesmentioning

confidence: 99%

“…Several methods have recently been developed in the literature for UAV-assisted network protocols that address the issues of high mobility in the network and unpredictable change in topology of the mobile nodes [ 1 , 2 , 3 , 4 , 5 , 6 ]. Unlike a fixed ground relay station, a UAV relay node (URN) moves along with the ground vehicular nodes (GVNs) to support a reliable network through a continuous line-of-sight (LoS) link.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Q-LBR: Q-Learning Based Load Balancing Routing for UAV-Assisted VANET

Roh

Han

Ham

et al. 2020

Sensors

View full text Add to dashboard Cite

Although various unmanned aerial vehicle (UAV)-assisted routing protocols have been proposed for vehicular ad hoc networks, few studies have investigated load balancing algorithms to accommodate future traffic growth and deal with complex dynamic network environments simultaneously. In particular, owing to the extended coverage and clear line-of-sight relay link on a UAV relay node (URN), the possibility of a bottleneck link is high. To prevent problems caused by traffic congestion, we propose Q-learning based load balancing routing (Q-LBR) through a combination of three key techniques, namely, a low-overhead technique for estimating the network load through the queue status obtained from each ground vehicular node by the URN, a load balancing scheme based on Q-learning and a reward control function for rapid convergence of Q-learning. Through diverse simulations, we demonstrate that Q-LBR improves the packet delivery ratio, network utilization and latency by more than 8, 28 and 30%, respectively, compared to the existing protocol.

show abstract

Section: Related Studiesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Q-LBR: Q-Learning Based Load Balancing Routing for UAV-Assisted VANET

Roh

Han

Ham

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…The authors in [ 73 ] proposed a DRL-based task-scheduling mechanism for a UIoT network. Their main objective was to improve the efficiency of task execution for each UAV by using DRL.…”

Section: Mac Protocols For Uiotmentioning

confidence: 99%

“…DRLTS [ 73 ] adopts a multi-UAV DRL-based approach to improve the efficiency of the task-execution process for each IoT device. According to the performance evaluation, with an increase in the number of iterations, the total reward converges to an ideal value.…”

Section: Comparison Of Mac Protocols For Uiotmentioning

confidence: 99%

“…Therefore, this protocol produces overhead. Moreover, in most of the AI-based algorithms [ 23 , 70 , 71 , 72 , 73 , 74 ], certain values must be stored in each iteration and used later to make decisions. However, in the learning phase, the overheads increase, but after the algorithm converges to the optimal point, the overheads start to decrease.…”

Section: Comparison Of Mac Protocols For Uiotmentioning

confidence: 99%

See 1 more Smart Citation

Medium Access Control Protocols for the Internet of Things Based on Unmanned Aerial Vehicles: A Comparative Survey

Khisa

Moh

2020

Sensors

View full text Add to dashboard Cite

The Internet of Things (IoT), which consists of a large number of small low-cost devices, has become a leading solution for smart cities, smart agriculture, smart buildings, smart grids, e-healthcare, etc. Integrating unmanned aerial vehicles (UAVs) with IoT can result in an airborne UAV-based IoT (UIoT) system and facilitate various value-added services from sky to ground. In addition to wireless sensors, various kinds of IoT devices are connected in UIoT, making the network more heterogeneous. In a UIoT system, for achieving high throughput in an energy-efficient manner, it is crucial to design an efficient medium access control (MAC) protocol because the MAC layer is responsible for coordinating access among the IoT devices in the shared wireless medium. Thus, various MAC protocols with different objectives have been reported for UIoT. However, to the best of the authors’ knowledge, no survey had been performed so far that dedicatedly covers MAC protocols for UIoT. Hence, in this study, state-of-the-art MAC protocols for UIoT are investigated. First, the communication architecture and important design considerations of MAC protocols for UIoT are examined. Subsequently, different MAC protocols for UIoT are classified, reviewed, and discussed with regard to the main ideas, innovative features, advantages, limitations, application domains, and potential future improvements. The reviewed MAC protocols are qualitatively compared with regard to various operational characteristics and system parameters. Additionally, important open research issues and challenges with recommended solutions are summarized and discussed.

show abstract

Improved search and rescue optimization based load balancing scheme of CCTV footage on edge computing environment

Deshpande

Dinesh

Umredkar

et al. 2022

Concurrency and Computation

View full text Add to dashboard Cite

Nowadays, data centers and servers are rising in size by order of magnitude due to increasing CCTV footages. Therefore, load balancing (LB) becomes a primary concern in scalable computing system involves mobile edge cloud computing environment. In mobile edge cloud computing system, a mobile user offloading their task to neighboring edge server for supporting realistic application. But while user is situated in a hot spot, various edge servers are over-loaded as a result of sudden offloading task from the mobile user. The LB process can be considered as an optimization problem, which can be resolved by the use of metaheuristic optimization algorithms. This article introduces an Improved Search and Rescue Optimization based LB Scheme for Edge Computing Environment (ISROLBS-ECE). The presented ISROLBS-ECE technique majorly concentrates on the distribution of offloading tasks to neighboring edge servers effectively. In addition, the ISROLBS-ECE technique involves the hybridization of chaotic concept into the conventional search and rescue optimization (SRO) approach. In the ISROLBS-ECE technique, the moderately lightest and task arrival nodes are employed as target node for allocating new task whereas rest of the nodes are not provisionally allocated tasks to accomplish dynamic balancing of the network. The experimental validation of the ISROLBS-ECE technique is tested and the outcomes are investigated under various aspects. The comparative study shows the better performance of the ISROLBS-ECE approach over other recent techniques.

show abstract

Multi-UAV-Enabled Load-Balance Mobile-Edge Computing for IoT Networks

Cited by 282 publications

References 30 publications

Q-LBR: Q-Learning Based Load Balancing Routing for UAV-Assisted VANET

Q-LBR: Q-Learning Based Load Balancing Routing for UAV-Assisted VANET

Medium Access Control Protocols for the Internet of Things Based on Unmanned Aerial Vehicles: A Comparative Survey

Improved search and rescue optimization based load balancing scheme of CCTV footage on edge computing environment

Contact Info

Product

Resources

About