Computation Offloading in UAV-Enabled Edge Computing: A Stackelberg Game Approach

Yuan, Xinwang; Zhidong, Xie; Tan, Xin

doi:10.3390/s22103854

Cited by 17 publications

(13 citation statements)

References 26 publications

(12 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are some researchers who has considered each fog node's time-energy efficiency and priority to propose a task offloading scheme called F air T ask Offloading (FTO) [26]. Some studies have focused on the partial offloading approach to achieve a trade-off between energy consumption [10] and task processing delay [11,12]. The authors have introduced a new dynamic edge computing model and designed an online primal-dual algorithm to offload tasks as they arrive in [27].…”

Section: Task Offloading In Edge Computing (Ec)mentioning

confidence: 99%

“…To minimize the overall offloading time, the authors designed a delay-dependent priority-aware task offloading strategy by assigning a priority to each task based on its deadline in [7]. These papers concentrate on partial offloading strategies or co-optimize offloading decisions and resource allocation in [8][9][10][11][12]. However, most of the related researches only focus on task offloading to tackle the problems of service response latency and energy consumption limitation, ignoring that the service requests from users are highly dynamic for actual situations.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic Computation Offloading with Deep Reinforcement Learning in Edge Networks

Bai

et al. 2022

Preprint

View full text Add to dashboard Cite

With the booming proliferation of user requests in the Internet of Things (IoT) network, Edge Computing (EC) is emerging as a promising paradigm to provide flexible and reliable services. Considering the resource constraints of IoT devices, for some delay-aware user requests, a heavy workload IoT device may not respond on time. EC spurs a popular wave of offloading user requests to edge servers at the edge of the network. The orchestration for user-requested offloading schemes is a remarkable challenge for the execution time and energy consumption for IoT devices in edge networks. To address this challenge, we propose a dynamic computation offloading strategy consisting of the following two parts: (i) we propose the concept of intermediate nodes, which can minimize the time and energy cost to process the current task by dynamically combining task offloading and service migration strategies; and (ii) based in the current network’s workload state, we model such intermediate node selection problem as multiple dimensional Markov Decision Process (MDP) spaces and implement deep reinforcement learning algorithms to reduce the large MDP space and achieve fast decision-making. Experimental results show that this strategy performs better than existing baseline approaches on the reduction of delay and energy consumption.

show abstract

Section: Task Offloading In Edge Computing (Ec)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Dynamic Computation Offloading with Deep Reinforcement Learning in Edge Networks

Bai

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Considering that the vehicle needs to determine its task offloading strategy in real time in a dynamic network environment, this research proposes a multiuser noncooperative computing offloading game to adjust the task offload probability of each vehicle in the vehicle edge computing network and consider the vehicle at the same time, , while taking into account the distance from the vehicle to the edge computing access point. Furthermore, the research constructed a distributed optimal response algorithm based on the computational unloading game model to maximize the utility of each vehicle [ 9 ]. Chen et al constructed the user unloading problem under the three-tier architecture suitable for mobile and computing scenarios and proposed a distributed balanced computing algorithm to determine the user's computing task unloading decision [ 10 ].…”

Section: Related Workmentioning

confidence: 99%

Cloud Computing Image Processing Application in Athlete Training High-Resolution Image Detection

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

The rapid development of Internet of things mobile application technology and artificial intelligence technology has given birth to a lot of services that can meet the needs of modern life, such as augmented reality technology, face recognition services, and language recognition and translation, which are often applied to various fields, and some other aspects of information communication and processing services. It has been used on various mobile phone, computer, or tablet user clients. Terminal equipment is subject to the ultralow latency and low energy consumption requirements of the above-mentioned applications. Therefore, the gap between resource-demanding application services and resource-limited mobile devices will bring great problems to the current and future development of IoT mobile applications. Based on the local image features of depth images, this paper designs an image detection method for athletes’ motion posture. First, according to the characteristics of the local image, the depth image of the athlete obtained through Kinect is converted into bone point data. Next, a 3-stage exploration algorithm is used to perform block matching calculations on the athlete’s bone point image to predict the athlete’s movement posture. At the same time, using the characteristics of the Euclidean distance of the bone point image, the movement behavior is recognized. According to the experimental results, for some external environmental factors, such as sun illumination and other factors, the image detection method designed in this paper can effectively avoid their interference and influence and show the movement posture of athletes, showing excellent accuracy and robustness in predicting the movement posture of athletes and action recognition. This method can simplify a series of calibration tasks in the initial stage of 3D video surveillance and infer the posture of the observation target and recognize it in real time. The one that has good application values has specific reference values for the same job.

show abstract

“…During the last two decades, unmanned aerial vehicles have experienced enormous development [1,2]. Since unmanned aerial vehicles (UAVs) were released for general civil use, the number of incidents involving them have been constantly increasing.…”

Section: Introductionmentioning

confidence: 99%

Multi-Sensory Data Fusion in Terms of UAV Detection in 3D Space

Dudczyk¹,

Czyba

Skrzypczyk

2022

Sensors

View full text Add to dashboard Cite

The paper focuses on the problem of detecting unmanned aerial vehicles that violate restricted airspace. The main purpose of the research is to develop an algorithm that enables the detection, identification and recognition in 3D space of a UAV violating restricted airspace. The proposed method consists of multi-sensory data fusion and is based on conditional complementary filtration and multi-stage clustering. On the basis of the review of the available UAV detection technologies, three sensory systems classified into the groups of passive and active methods are selected. The UAV detection algorithm is developed on the basis of data collected during field tests under real conditions, from three sensors: a radio system, an ADS-B transponder and a radar equipped with four antenna arrays. The efficiency of the proposed solution was tested on the basis of rapid prototyping in the MATLAB simulation environment with the use of data from the real sensory system obtained during controlled UAV flights. The obtained results of UAV detections confirmed the effectiveness of the proposed method and theoretical expectations.

show abstract

Computation Offloading in UAV-Enabled Edge Computing: A Stackelberg Game Approach

Cited by 17 publications

References 26 publications

Dynamic Computation Offloading with Deep Reinforcement Learning in Edge Networks

Dynamic Computation Offloading with Deep Reinforcement Learning in Edge Networks

Cloud Computing Image Processing Application in Athlete Training High-Resolution Image Detection

Multi-Sensory Data Fusion in Terms of UAV Detection in 3D Space

Contact Info

Product

Resources

About