Smart computational offloading for mobile edge computing in next-generation Internet of Things networks

Ali, Zaiwar; Abbas, Ziaul Haq; Abbas, Ghulam; Numani, Abdullah; Bilal, Muhammad

doi:10.1016/j.comnet.2021.108356

Cited by 28 publications

(18 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some other works address the issues of quality insurance and energy consumption in relation to delay. The authors in [6] proposed deep learning-based offloading technique to minimize the cost function which considers service delay, energy consumption, radio and computing resources of mobile devices and mobile edge servers. In another work [7], the authors construct a MEC-based computation offloading framework considering the delay cost, energy computation cost and bandwidth cost for vehicular networks.…”

Section: Related Workmentioning

confidence: 99%

Deep Q-Learning based resource allocation and load balancing in a mobile edge system serving different types of user requests

Yildiz

Sokullu

2023

Journal of Electrical Engineering

View full text Add to dashboard Cite

With the expansion of the communicative and perceptual capabilities of mobile devices in recent years, the number of complex and high computational applications has also increased rendering traditional methods of traffic management and resource allocation quite insufficient. Recently, mobile edge computing (MEC) has emerged as a new viable solution to these problems. It can provide additional computing features at the edge of the network and allow alleviation of the resource limit of mobile devices while increasing the performance for critical applications especially in terms of latency. In this work, we addressed the issue of reducing the service delay by choosing the optimal path in the MEC network, which consists of multiple MEC servers that has different capabilities, applying network load balancing where multiple requests need to be handled simultaneously and routing selection based on a deep- Q network (DQN) algorithm. A novel traffic control and resource allocation method is proposed based on deep Q-learning (DQL) which allows reducing the end-to-end delay in cellular networks and in the mobile edge network. Real life traffic scenarios with various types of user requests are considered and a novel DQL resource allocation scheme which adaptively assigns computing and network resources is proposed. The algorithm optimizes traffic distribution between servers reducing the total service time and balancing the use of available resources under varying environmental conditions.

show abstract

Section: Related Workmentioning

confidence: 99%

Deep Q-Learning based resource allocation and load balancing in a mobile edge system serving different types of user requests

Yildiz

Sokullu

2023

Journal of Electrical Engineering

View full text Add to dashboard Cite

show abstract

“…Context of IoT "Extensive" and "intensive" are a couple of relative concepts, which refers to investing in the production of materials and labor on the same land area and adopting the method of expanding the cultivated land area to improve agricultural products in the present work [9]. Intensive production information and labor force investment refer to the unit product amount of the invested product materials and accomplishment of agricultural business in the same land area.…”

Section: Agricultural Intensive Development In Thementioning

confidence: 99%

The Panel Spatial Econometric Analysis for Development of Green Intensive Agriculture Based on Edge Computing and Internet of Things

Shi

2022

Journal of Environmental and Public Health

View full text Add to dashboard Cite

To further promote the modernization of agriculture and the prosperity of green industry, the analyses are made on the intensive level of agriculture by using spatial econometric model under the Internet of Things (IoT), and the optimal defense strategy is adopted for edge network equipment to ensure the security of agricultural information. Initially, the present work introduces the related concepts of agricultural intensive development and analyzes the important role of IoT in the development process of agricultural modernization. Next, it briefly explains the spatial econometric analysis method, introduces two basic spatial analysis models-spatial lag model (SLM) and spatial error model (SEM), and explains their principles in detail. Then, it signifies the characteristics of IoT and edge computing (EC) and designs the optimal defense strategy of edge network equipment from the perspective of IoT. Finally, the simulation experiment is carried out based on the edge network defense strategy, and the spatial econometric analysis is carried out by taking the agricultural intensive development of counties in a Chinese province as an example. The experimental results show that with the increase of the number of edge network devices, the optimal strategy of edge network defense can be adopted while consuming certain computing resources. The agricultural technology input and intensive level in the jurisdiction have high spatial correlation, so it is necessary to establish a spatial econometric model for analysis. Additionally, the statistics of SLM is higher than that of SEM, which shows that SLM can better reflect the technology investment and spatial correlation than SEM does. Both industrial and agricultural division of labor and agricultural production link division of labor can promote the level of intensification, among which the promotion of industrial and agricultural division of labor is not very significant, while the promotion of agricultural production link division of labor is very significant.

show abstract

“…The maximum computation capacity of SUE n W Channel bandwidth P Transmission power σ 2 Noise power u t,n…”

Section: Problem Formulationmentioning

confidence: 99%

“…Involving the placement of small servers at the edge of the cellular network, a new distributed architecture known as mobile edge computing (MEC) has been proposed by the European Telecommunication Standard Institute (ETSI) [1]. In the MEC architecture, distributed mobile edge servers called cloudlets are deployed at the edge of wireless network to provide computing resources and storage with high bandwidth and low delay [2].…”

Section: Introductionmentioning

confidence: 99%

“…The operation of the SAda algorithm is distributed and can improve the offloading performance by learning from the previous offloading experience. (2) Considering the spatiotemporal dynamics of the user's device, the perceptual function is also integrated into the algorithm. The user devices that require the task processing service are called the task user equipment (TUE), and the user device that can serve the TUE for the task processing is the service user equipment (SUE).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Self-Adaptive Learning of Task Offloading in Mobile Edge Computing Systems

Huang

Deng

Kang

et al. 2021

Entropy

View full text Add to dashboard Cite

Mobile edge computing (MEC) focuses on transferring computing resources close to the user's device, and it provides high-performance and low-delay services for mobile devices. It is an effective method to deal with computationally intensive and delay-sensitive tasks. Given the large number of underutilized computing resources for mobile devices in urban areas, leveraging these underutilized resources offers tremendous opportunities and value. Considering the spatiotemporal dynamics of user devices, the uncertainty of rich computing resources and the state of network channels in the MEC system, computing resource allocation in mobile devices with idle computing resources will affect the response time of task requesting. To solve these problems, this paper considers the case in which a mobile device can learn from a neighboring IoT device when offloading a computing request. On this basis, a novel self-adaptive learning of task offloading algorithm (SAda) is designed to minimize the average offloading delay in the MEC system. SAda adopts a distributed working mode and has a perception function to adapt to the dynamic environment in reality; it does not require frequent access to equipment information. Extensive simulations demonstrate that SAda achieves preferable latency performance and low learning error compared to the existing upper bound algorithms.

show abstract

Smart computational offloading for mobile edge computing in next-generation Internet of Things networks

Cited by 28 publications

References 16 publications

Deep Q-Learning based resource allocation and load balancing in a mobile edge system serving different types of user requests

Deep Q-Learning based resource allocation and load balancing in a mobile edge system serving different types of user requests

The Panel Spatial Econometric Analysis for Development of Green Intensive Agriculture Based on Edge Computing and Internet of Things

Self-Adaptive Learning of Task Offloading in Mobile Edge Computing Systems

Contact Info

Product

Resources

About