An autonomous computation offloading strategy in Mobile Edge Computing: A deep learning-based hybrid approach

This paper studies mobile edge computing (MEC) networks where multiple wireless devices (WDs) offload their computation tasks to multiple edge servers and one cloud server. Considering different real-time computation tasks at different WDs, every task is decided to be processed locally at its WD or to be offloaded to and processed at one of the edge servers or the cloud server. In this paper, we investigate low-complexity computation offloading policies to guarantee quality of service of the MEC network and to minimize WDs’ energy consumption. Specifically, both a linear programing relaxation-based (LR-based) algorithm and a distributed deep learning-based offloading (DDLO) algorithm are independently studied for MEC networks. We further propose a heterogeneous DDLO to achieve better convergence performance than DDLO. Extensive numerical results show that the DDLO algorithms guarantee better performance than the LR-based algorithm. Furthermore, the DDLO algorithm generates an offloading decision in less than 1 millisecond, which is several orders faster than the LR-based algorithm.

Download Full-text

Task Offloading and Scheduling Strategy for Intelligent Prosthesis in Mobile Edge Computing Environment

Wireless Communications and Mobile Computing ◽

10.1155/2022/2890473 ◽

2022 ◽

Vol 2022 ◽

pp. 1-13

Author(s):

Ping Qi

Keyword(s):

Deep Learning ◽

Energy Consumption ◽

Learning Algorithm ◽

Problem Definition ◽

Edge Computing ◽

Computation Offloading ◽

Mobile Edge Computing ◽

Intent Recognition ◽

Scheduling Strategy ◽

Task Offloading

Traditional intent recognition algorithms of intelligent prosthesis often use deep learning technology. However, deep learning’s high accuracy comes at the expense of high computational and energy consumption requirements. Mobile edge computing is a viable solution to meet the high computation and real-time execution requirements of deep learning algorithm on mobile device. In this paper, we consider the computation offloading problem of multiple heterogeneous edge servers in intelligent prosthesis scenario. Firstly, we present the problem definition and the detail design of MEC-based task offloading model for deep neural network. Then, considering the mobility of amputees, the mobility-aware energy consumption model and latency model are proposed. By deploying the deep learning-based motion intent recognition algorithm on intelligent prosthesis in a real-world MEC environment, the effectiveness of the task offloading and scheduling strategy is demonstrated. The experimental results show that the proposed algorithms can always find the optimal task offloading and scheduling decision.

Download Full-text

Efficient Multiuser Computation for Mobile-Edge Computing in IoT Application Using Optimization Algorithm

Applied Bionics and Biomechanics ◽

10.1155/2021/9014559 ◽

2021 ◽

Vol 2021 ◽

pp. 1-12

Author(s):

Tawfiq Hasanin ◽

Aisha Alsobhi ◽

Adil Khadidos ◽

Ayman Qahmash ◽

Alaa Khadidos ◽

...

Keyword(s):

Deep Learning ◽

Optimization Algorithm ◽

Computing System ◽

Edge Computing ◽

Bald Eagle ◽

Computation Offloading ◽

Mobile Edge Computing ◽

Cloud Data ◽

Expected Time ◽

Search Optimization

Mobile edge computing (MEC) is a paradigm novel computing that promises the dramatic effect of reduction in latency and consumption of energy by computation offloading intensive; these tasks to the edge clouds in proximity close to the smart mobile users. In this research, reduce the offloading and latency between the edge computing and multiusers under the environment IoT application in 5G using bald eagle search optimization algorithm. The deep learning approach may consume high computational complexity and more time. In an edge computing system, devices can offload their computation-intensive tasks to the edge servers to save energy and shorten their latency. The bald eagle algorithm (BES) is the advanced optimization algorithm that resembles the strategy of eagle hunting. The strategies are select, search, and swooping stages. Previously, the BES algorithm is used to consume the energy and distance; to improve the better energy and reduce the offloading latency in this research and some delays occur when devices increase causes demand for cloud data, it can be improved by offering ROS (resource) estimation. To enhance the BES algorithm that introduces the ROS estimation stage to select the better ROSs, an edge system, which offloads the most appropriate IoT subtasks to edge servers then the expected time of execution, got minimized. Based on multiuser offloading, we proposed a bald eagle search optimization algorithm that can effectively reduce the end-end time to get fast and near-optimal IoT devices. The latency is reduced from the cloud to the local; this can be overcome by using edge computing, and deep learning expects faster and better results from the network. This can be proposed by BES algorithm technique that is better than other conventional methods that are compared on results to minimize the offloading latency. Then, the simulation is done to show the efficiency and stability by reducing the offloading latency.

Download Full-text

Computation offloading and resource allocation based on distributed deep learning and software defined mobile edge computing

Computer Networks ◽

10.1016/j.comnet.2021.108732 ◽

2022 ◽

pp. 108732

Author(s):

Zhongyu Wang ◽

Tiejun Lv ◽

Zheng Chang

Keyword(s):

Resource Allocation ◽

Deep Learning ◽

Edge Computing ◽

Computation Offloading ◽

Mobile Edge Computing

Download Full-text

Computation Offloading Game in Multiple UAV-Enabled Mobile Edge Computing Networks

IET Communications ◽

10.1049/iet-com.2020.0131 ◽

2020 ◽

Author(s):

Yanling Ren ◽

Zhibin Xie ◽

Zhenfeng Ding ◽

xiyuan sun ◽

Jie Xia ◽

...

Keyword(s):

Edge Computing ◽

Computation Offloading ◽

Mobile Edge Computing

Download Full-text

Multi-Objective Whale Optimization Algorithm for Computation Offloading Optimization in Mobile Edge Computing

Sensors ◽

10.3390/s21082628 ◽

2021 ◽

Vol 21 (8) ◽

pp. 2628

Author(s):

Mengxing Huang ◽

Qianhao Zhai ◽

Yinjie Chen ◽

Siling Feng ◽

Feng Shu

Keyword(s):

Optimization Algorithm ◽

Edge Computing ◽

Solution Set ◽

Whale Optimization Algorithm ◽

Computation Offloading ◽

Mobile Edge Computing ◽

Multi Objective ◽

Whale Optimization ◽

Artificial Immune System Algorithm

Computation offloading is one of the most important problems in edge computing. Devices can transmit computation tasks to servers to be executed through computation offloading. However, not all the computation tasks can be offloaded to servers with the limitation of network conditions. Therefore, it is very important to decide quickly how many tasks should be executed on servers and how many should be executed locally. Only computation tasks that are properly offloaded can improve the Quality of Service (QoS). Some existing methods only focus on a single objection, and of the others some have high computational complexity. There still have no method that could balance the targets and complexity for universal application. In this study, a Multi-Objective Whale Optimization Algorithm (MOWOA) based on time and energy consumption is proposed to solve the optimal offloading mechanism of computation offloading in mobile edge computing. It is the first time that MOWOA has been applied in this area. For improving the quality of the solution set, crowding degrees are introduced and all solutions are sorted by crowding degrees. Additionally, an improved MOWOA (MOWOA2) by using the gravity reference point method is proposed to obtain better diversity of the solution set. Compared with some typical approaches, such as the Grid-Based Evolutionary Algorithm (GrEA), Cluster-Gradient-based Artificial Immune System Algorithm (CGbAIS), Non-dominated Sorting Genetic Algorithm III (NSGA-III), etc., the MOWOA2 performs better in terms of the quality of the final solutions.

Download Full-text