Multi-Server Multi-User Multi-Task Computation Offloading for Mobile Edge Computing Networks

Huang, Liang; Xu, Feng; Zhang, Luxin; Qian, Liping; Wu, Yuan

doi:10.3390/s19061446

Cited by 99 publications

(42 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…B ENEFITING from the improvement of computing power and big data, deep learning has achieved unprecedented development in many applications, i.e., speech and audio processing [1], natural language processing [2], object detection [3], and so on. In recent years, it also achieves dramatic development in the field of wireless communications, e.g., modulation classification [4], symbol detection [5], end-to-end communication [6], and mobile edge computing [7], [8], [9].…”

Section: Introductionmentioning

confidence: 99%

Data Augmentation for Deep Learning-Based Radio Modulation Classification

et al. 2020

Self Cite

View full text Add to dashboard Cite

Deep learning has recently been applied to automatically classify the modulation categories of received radio signals without manual experience. However, training deep learning models requires massive volume of data. An insufficient training data will cause serious overfitting problem and degrade the classification accuracy. To cope with small dataset, data augmentation has been widely used in image processing to expand the dataset and improve the robustness of deep learning models. However, in wireless communication areas, the effect of different data augmentation methods on radio modulation classification has not been studied yet. In this paper, we evaluate different data augmentation methods via a state-ofthe-art deep learning-based modulation classifier. Based on the characteristics of modulated signals, three augmentation methods are considered, i.e., rotation, flip, and Gaussian noise, which can be applied in both training phase and inference phase of the deep learning algorithm. Numerical results show that all three augmentation methods can improve the classification accuracy. Among which, the rotation augmentation method outperforms the flip method, both of which achieve higher classification accuracy than the Gaussian noise method. Given only 12.5% of training dataset, a joint rotation and flip augmentation policy can achieve even higher classification accuracy than the baseline with initial 100% training dataset without augmentation. Furthermore, with data augmentation, radio modulation categories can be successfully classified using shorter radio samples, leading to a simplified deep learning model and shorter the classification response time.

show abstract

Section: Introductionmentioning

confidence: 99%

Data Augmentation for Deep Learning-Based Radio Modulation Classification

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…They jointly optimized user association and computation offloading while considering the computing resource allocation. Synthetically using local, edge and remote cloud computing models, the authors in [16] proposed a linear programing relaxation-based algorithm and a distributed deep learning-based offloading algorithm to guarantee QoS of the MEC network and to minimize MDs' energy consumption in the multi-user multi-task and multi-server MEC networks. Li et al in [27] studied the MECO management problem in heterogenous network to minimize the network-level energy consumption and developed an iterative solution framework to obtain transmission power allocation strategy and computation offloading scheme.…”

Section: Related Workmentioning

confidence: 99%

“…Recently, plenty of ink has been poured on the problem of mobile edge computation offloading (MECO) [6,7], and many novel offloading schemes have been proposed to optimize either computing overhead [8,9] or communication resources [10,11]. From the aspects of mobile user number, type of computation tasks, and the involved MEC servers, these research work mainly considered the network scenarios of multi-user single server [12], multi-user multi-server [13], multi-task multi-server [14], and multi-user multi-task multi-server [15,16]. There is no doubt that the related literature provides precious viewpoints for the performance optimization and resource allocation of MEC.…”

Section: Introductionmentioning

confidence: 99%

Cross-Server Computation Offloading for Multi-Task Mobile Edge Computing

Shi¹,

Xia²,

Gao³

2020

Information

View full text Add to dashboard Cite

As an emerging network architecture and technology, mobile edge computing (MEC) can alleviate the tension between the computation-intensive applications and the resource-constrained mobile devices. However, most available studies on computation offloading in MEC assume that the edge severs host various applications and can cope with all kinds of computation tasks, ignoring limited computing resources and storage capacities of the MEC architecture. To make full use of the available resources deployed on the edge servers, in this paper, we study the cross-server computation offloading problem to realize the collaboration among multiple edge servers for multi-task mobile edge computing, and propose a greedy approximation algorithm as our solution to minimize the overall consumed energy. Numerical results validate that our proposed method can not only give near-optimal solutions with much higher computational efficiency, but also scale well with the growing number of mobile devices and tasks.

show abstract

“…Many papers studied resource allocation within a MEC infrastructure to optimize the procecing time [15][16][17][18]. On the other hand, many state of the art works studied resource allocation within a MEC infrastructure to optimize the energy consumption [13,19,20]. In [21], the authors investigate a resource allocation policy to maximize the available processing capacity for MEC IoT networks with constrained power and unpredictable tasks.Unfortunatly, most of them consider users with a unique task only.…”

Section: Introductionmentioning

confidence: 99%

Efficient Multi-task offloading with energy and computational resources optimization in a mobile edge computing node

Ghmary¹,

Chanyour²,

Hmimz³

et al. 2019

IJECE

View full text Add to dashboard Cite

<span>With the fifth-generation (5G) networks, Mobile edge computing (MEC) is a promising paradigm to provide near computing and storage capabilities to smart mobile devices. In addition, mobile devices are most of the time battery dependent and energy constrained while they are characterized by their limited processing and storage capacities. Accordingly, these devices must offload a part of their heavy tasks that require a lot of computation and are energy consuming. This choice remains the only option in some circumstances, especially when the battery drains off. Besides, the local CPU frequency allocated to processing has a huge impact on devices energy consumption. Additionally, when mobile devices handle many tasks, the decision of the part to offload becomes critical. Actually, we must consider the wireless network state, the available processing resources at both sides, and particularly the local available battery power. In this paper, we consider a single mobile device that is energy constrained and that retains a list of heavy offloadable tasks that are delay constrained. Therefore, we formulated the corresponding optimization problem, and proposed a Simulated Annealing based heuristic solution scheme. In order to evaluate our solution, we carried out a set of simulation experiments. Finally, the obtained results in terms of energy are very encouraging. Moreover, our solution performs the offloading decisions within an acceptable and feasible timeframes.</span>

show abstract

Multi-Server Multi-User Multi-Task Computation Offloading for Mobile Edge Computing Networks

Cited by 99 publications

References 36 publications

Data Augmentation for Deep Learning-Based Radio Modulation Classification

Data Augmentation for Deep Learning-Based Radio Modulation Classification

Cross-Server Computation Offloading for Multi-Task Mobile Edge Computing

Efficient Multi-task offloading with energy and computational resources optimization in a mobile edge computing node

Contact Info

Product

Resources

About