A Machine Learning Approach for Task and Resource Allocation in Mobile-Edge Computing-Based Networks

Wang, Sihua; Chen, Mingzhe; Liu, Xuanlin; Yin, Changchuan; Cui, Shuguang; Poor, H. Vincent

doi:10.1109/jiot.2020.3011286

Cited by 69 publications

(30 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, we can tune it to take more or less long-term decisions. Wang et al [73] propose a multi-stack reinforcement learning algorithm for resource allocation in mobile edge computing. They use multi-stack to take advantage of a historical resource allocation scheme and avoid learning the same scheme.…”

Section: Learning Methodsmentioning

confidence: 99%

“…Reinforcement learning [70] x x [53] x x x [69] x x [56] x [73] x [51] x x x x Decomposition and iteration algorithm [59] x x x Deep Neural Network [48] x x x Game theory [67] x x Interior-point (IPA) alogrithm [45] x x ef iciently and respond to users' requests. In this section, we irst show in Section 4.1 the different aspects to take into account for modelling the requesting devices' tasks.…”

Section: Two Ixed Usersmentioning

confidence: 99%

See 1 more Smart Citation

A resource management survey for mission-critical and time-critical applications in multiaccess edge computing

Santi¹,

Mitton²

2021

ITU-J FET

View full text Add to dashboard Cite

Multiaccess Edge Computing (MEC) brings additional computing power in proximity of mobile users, reducing latency, saving energy and alleviating the network's bandwidth. This proximity is beneficial, especially for mission-critical applications where each second matters, such as disaster management or military operations. Moreover, it enables MEC resources embedded on mobile units like drones or robots that are flexible to be deployed for mission-critical applications. However, the MEC servers are capacity-limited and thus need an acute management of their resources. The mobile resources also need a smart deployment scheme to deliver their services efficiently. In this survey, we review mission-critical applications, resource allocation and deployment of mobile resources techniques in the context of the MEC. First, we introduce the technical specifics and uses of MEC in mission-critical applications to highlight their needs and requirements. Then, we discuss the resource allocation schemes for MEC and assess their fit depending on the application needs. In the same fashion, we finally review the deployment of MEC mobile resources. We believe this work could serve as a helping hand to design efficient MEC resource management schemes that respond to challenging environments such as mission-critical applications.

show abstract

Section: Learning Methodsmentioning

confidence: 99%

Section: Two Ixed Usersmentioning

confidence: 99%

A resource management survey for mission-critical and time-critical applications in multiaccess edge computing

Santi¹,

Mitton²

2021

ITU-J FET

View full text Add to dashboard Cite

show abstract

“…e power price and interference price adjust the channel and power allocation of the link to maximize the network utility. Literature [8][9][10][11] comprehensively considered factors such as link effective capacity, network interference and flow conservation, and established a congestion avoidance model for joint power control and channel allocation. Furthermore, a congestion avoidance mechanism based on genetic algorithm is proposed.…”

Section: Introductionmentioning

confidence: 99%

Joint Resource Allocation Optimization of Wireless Sensor Network Based on Edge Computing

Liu

Zhu

2021

Complexity

View full text Add to dashboard Cite

Resource allocation has always been a key technology in wireless sensor networks (WSN), but most of the traditional resource allocation algorithms are based on single interface networks. The emergence and development of multi-interface and multichannel networks solve many bottleneck problems of single interface and single channel networks, it also brings new opportunities to the development of wireless sensor networks, but the multi-interface and multichannel technology not only improves the performance of wireless sensor networks but also brings great challenges to the resource allocation of wireless sensor networks. Edge computing changes the traditional centralized cloud computing processing method into a method that reduces computing storage capacity to the edge of the network and faces users and terminals. Realize the advantages of lower latency, higher bandwidth, and fast response. Therefore, this paper proposes a joint optimization algorithm of resource allocation based on edge computing. We establish a wireless sensor allocation model and then propose our algorithm model combined with the advantages of edge computing. Compared with the traditional allocation algorithm (PCOA, MCMH, and TDMA), it can further improve the resource utilization, reduce the network energy consumption, increase network capacity, and reduce the complexity of the schemes.

show abstract

“…More detailed hybrid models can combine edge server placement, resource allocation and run-time reallocation, also optimizing for proximity [15]. Some of these heuristic reallocation algorithms can minimize both computing and network delay, penalizing for longer computing times of over-capacity edge servers [16], [17]. Furthermore, cloud offloading from the edge environment [18], [19] is sometimes a viable option.…”

Section: Introductionmentioning

confidence: 99%

Weathering the Reallocation Storm: Large-Scale Analysis of Edge Server Workload

Lovén

Peltonen

Harjula

et al. 2021

2021 Joint European Conference on Networks and Communications &Amp; 6G Summit (EuCNC/6G Summit)

View full text Add to dashboard Cite

Efficient service placement and workload allocation methods are necessary enablers for the actively studied topic of edge computing. In this paper, we show that under certain circumstances, the number of superfluous workload reallocations from one edge server to another may grow to a significant proportion of all user tasks -a phenomenon we present as a reallocation storm. We showcase this phenomenon on a city-scale edge server deployment by simulating the allocation of user task workloads in a number of scenarios capturing likely edge computing deployments and usage patterns. The simulations are based on a large real-world data set of city-wide Wi-Fi network connections in 2013-2014, with more than 47M connections over ca. 800 access points. We identify the conditions for avoiding the reallocation storm for three common edge-based reallocation strategies, and study the latency-workload trade-off related to each strategy. As a result, we find that the superfluous reallocations vanish when the edge server capacity is increased above a certain threshold, unique for each reallocation strategy, peaking at ca. 35% of top ES workload. Further, while a reallocation strategy aiming to minimize reallocation distance consistently resulted in the worst reallocation storms, the two other strategies, namely, a random reallocation strategy, and a bottom-up strategy which always chooses the edge server with the lowest workload as a reallocation target, behave nearly identically in terms of latency as well as the reallocation storm in dense edge deployments. Since the random strategy requires much less coordination, we recommend it over the bottom-up one in dense ES deployments.

show abstract

A Machine Learning Approach for Task and Resource Allocation in Mobile-Edge Computing-Based Networks

Cited by 69 publications

References 30 publications

A resource management survey for mission-critical and time-critical applications in multiaccess edge computing

A resource management survey for mission-critical and time-critical applications in multiaccess edge computing

Joint Resource Allocation Optimization of Wireless Sensor Network Based on Edge Computing

Weathering the Reallocation Storm: Large-Scale Analysis of Edge Server Workload

Contact Info

Product

Resources

About