Intelligent Task Offloading and Energy Allocation in the UAV-Aided Mobile Edge-Cloud Continuum

Cheng, Zhipeng; Gao, Zhibin; Liwang, Minghui; Huang, Lianfen; Du, Xiaojiang; Guizani, Mohsen

doi:10.1109/mnet.010.2100025

Cited by 24 publications

(10 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Cheng et al [66] proposed a DRL-based joint deep reinforcement learning (FDRL) framework to effectively reduce the training loss and privacy leakage during training phase. They also proposed a joint optimization algorithm for task offloading and resource allocation method based on FDRL.…”

Section: Mdp and Rlmentioning

confidence: 99%

Task partitioning and offloading in IoT cloud-edge collaborative computing framework: a survey

2022

View full text Add to dashboard Cite

Internet of Things (IoT) is made up with growing number of facilities, which are digitalized to have sensing, networking and computing capabilities. Traditionally, the large volume of data generated by the IoT devices are processed in a centralized cloud computing model. However, it is no longer able to meet the computational demands of large-scale and geographically distributed IoT devices for executing tasks of high performance, low latency, and low energy consumption. Therefore, edge computing has emerged as a complement of cloud computing. To improve system performance, it is necessary to partition and offload some tasks generated by local devices to the remote cloud or edge nodes. However, most of the current research work focuses on designing efficient offloading strategies and service orchestration. Little attention has been paid to the problem of jointly optimizing task partitioning and offloading for different application types. In this paper, we make a comprehensive overview on the existing task partitioning and offloading frameworks, focusing on the input and core of decision engine of the framework for task partitioning and offloading. We also propose comprehensive taxonomy metrics for comparing task partitioning and offloading approaches in the IoT cloud-edge collaborative computing framework. Finally, we discuss the problems and challenges that may be encountered in the future.

show abstract

Section: Mdp and Rlmentioning

confidence: 99%

Task partitioning and offloading in IoT cloud-edge collaborative computing framework: a survey

2022

View full text Add to dashboard Cite

show abstract

“…The past decade has witnessed the expeditious evolution of communication and computing technologies, and their innovative applications in many emerging fields such as the Internet of Vehicles and E-health, where massive amount of data is generated, exchanged and utilized. This development brings both technical challenges and great opportunities for a wide range of machine learning (ML)-based applications, since ML holds considerable promise to fast decisions and inferences without human intervention [1], [2]. Besides, device-to-device (D2D) communications enabled multi-layer heterogeneous wireless networks are becoming one of main components of 5G/6G networks, where the complicated network topologies could impose great challenges to the implementations of ML [3].…”

Section: Introductionmentioning

confidence: 99%

Hybrid Architectures for Distributed Machine Learning in Heterogeneous Wireless Networks

Cheng¹,

Fan²,

Liwang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

The ever-growing data privacy concerns have transformed machine learning (ML) architectures from centralized to distributed, leading to federated learning (FL) and split learning (SL) as the two most popular privacy-preserving ML paradigms. However, implementing either conventional FL or SL alone with diverse network conditions (e.g., device-to-device (D2D) and cellular communications) and heterogeneous clients (e.g., heterogeneous computation/communication/energy capabilities) may face significant challenges, particularly poor architecture scalability and long training time. To this end, this article proposes two novel hybrid distributed ML architectures, namely, hybrid split FL (HSFL) and hybrid federated SL (HFSL), by combining the advantages of both FL and SL in D2D-enabled heterogeneous wireless networks. Specifically, the performance comparison and advantages of HSFL and HFSL are analyzed generally. Promising open research directions are presented to offer commendable reference for future research. Finally, primary simulations are conducted upon considering three datasets under non-independent and identically distributed settings, to verify the feasibility of our proposed architectures, which can significantly reduce communication/computation cost and training time, as compared with conventional FL and SL.

show abstract

“…Operation optimization has taken a significant share of research contributions in this area [9], [11], [13]- [19], [22]. Among the aforementioned works, UAV optimal positioning was studied in [11] and [16], where drone placement/trajectory, power, and bandwidth allocation were optimized for a laser-powered drone acting as a flying BS that serves a multitude of users with the aim of total flight time and the communications data rate maximization [11], and communication throughput maximization over a finite interval of time [16].…”

Section: Introductionmentioning

confidence: 99%

“…Among the aforementioned works, UAV optimal positioning was studied in [11] and [16], where drone placement/trajectory, power, and bandwidth allocation were optimized for a laser-powered drone acting as a flying BS that serves a multitude of users with the aim of total flight time and the communications data rate maximization [11], and communication throughput maximization over a finite interval of time [16]. On a different note, power management optimization was realized in [13] and [22]. Energy allocation and task offloading in a UAV-aided mobile-edge cloud continuum were optimized [13], and operation time was optimized by exploiting battery dynamics and opportunistically nullifying propulsion energy consumption by resting on buildings rooftops [22].…”

Section: Introductionmentioning

confidence: 99%

“…On a different note, power management optimization was realized in [13] and [22]. Energy allocation and task offloading in a UAV-aided mobile-edge cloud continuum were optimized [13], and operation time was optimized by exploiting battery dynamics and opportunistically nullifying propulsion energy consumption by resting on buildings rooftops [22]. Moreover, many recent studies have considered both information and energy relaying amongst airborne nodes providing wireless coverage [14], [17]- [19].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

On the Optimization of Laser-Powered UAV-Assisted Backscatter Communications

Abd‐Elhady¹,

Diaz-Vilor²,

Çelik³

et al. 2022

Preprint

View full text Add to dashboard Cite

<p>This paper studies the joint trajectory and resource allocation problem for a laser-powered unmanned aerial vehicle (UAV) assisted data aggregation framework. The considered system incorporates semi-passive nodes that establish their wireless communication links with the UAV via bistatic backscatter communications enabled by a battery-powered power beacon source. We aim to optimize the UAV trajectory while minimizing the laser energy consumption throughout the whole flight by tuning the laser power and the power beacon radiated temporal power profiles. Towards this aim, we first adopt path discretization to approximate the optimal control problem of interest into a non-linear programming one whilst accounting for the UAV dynamics constraints and available power budget restrictions. Then, we solve the problem by successive convex approximation (SCA) over the joint set of variables and determine the problem feasibility by a data collection maximization problem. Moreover, we propose a low-complexity solution for the feasibility problem. Finally, the conducted simulations show that the proposed algorithm provides 50% collected data increase and almost 50% laser energy reduction under different operation conditions such as laser station position, maximum laser output power, start and end points of the trajectory, power beacon battery capacity, and the permissible flight length.</p>

show abstract

Intelligent Task Offloading and Energy Allocation in the UAV-Aided Mobile Edge-Cloud Continuum

Cited by 24 publications

References 10 publications

Task partitioning and offloading in IoT cloud-edge collaborative computing framework: a survey

Task partitioning and offloading in IoT cloud-edge collaborative computing framework: a survey

Hybrid Architectures for Distributed Machine Learning in Heterogeneous Wireless Networks

On the Optimization of Laser-Powered UAV-Assisted Backscatter Communications

Contact Info

Product

Resources

About