Fuzzy Workload Orchestration for Edge Computing

Sonmez, Cagatay; Özgövde, Atay; Ersoy, Cem

doi:10.1109/tnsm.2019.2901346

Cited by 122 publications

(219 citation statements)

References 31 publications

Supporting

Mentioning

219

Contrasting

Order By: Relevance

“…Similarly to cloud, in the edge computing context, most of the relative studies proposed static models alongside with the optimization of a single performance criterion, e.g., energy consumption or response time. Towards this direction, Sonmez et al [33] proposed a two-stage fuzzy mechanism for offloading requests to edge and cloud infrastructure. The set of fuzzy rules are empirically decided and the VM (Virtual Machine) utilization modeling is threshold-based, which is applicable only for specific types of IoT applications.…”

Section: Performance Modeling and Resource Allocation In Cloud And Edmentioning

confidence: 99%

Edge Computing Resource Allocation for Dynamic Networks: The DRUID-NET Vision and Perspective

Dechouniotis

Αθανασόπουλος

Leivadeas

et al. 2020

Sensors

View full text Add to dashboard Cite

The potential offered by the abundance of sensors, actuators, and communications in the Internet of Things (IoT) era is hindered by the limited computational capacity of local nodes. Several key challenges should be addressed to optimally and jointly exploit the network, computing, and storage resources, guaranteeing at the same time feasibility for time-critical and mission-critical tasks. We propose the DRUID-NET framework to take upon these challenges by dynamically distributing resources when the demand is rapidly varying. It includes analytic dynamical modeling of the resources, offered workload, and networking environment, incorporating phenomena typically met in wireless communications and mobile edge computing, together with new estimators of time-varying profiles. Building on this framework, we aim to develop novel resource allocation mechanisms that explicitly include service differentiation and context-awareness, being capable of guaranteeing well-defined Quality of Service (QoS) metrics. DRUID-NET goes beyond the state of the art in the design of control algorithms by incorporating resource allocation mechanisms to the decision strategy itself. To achieve these breakthroughs, we combine tools from Automata and Graph theory, Machine Learning, Modern Control Theory, and Network Theory. DRUID-NET constitutes the first truly holistic, multidisciplinary approach that extends recent, albeit fragmented results from all aforementioned fields, thus bridging the gap between efforts of different communities.

show abstract

Section: Performance Modeling and Resource Allocation In Cloud And Edmentioning

confidence: 99%

Edge Computing Resource Allocation for Dynamic Networks: The DRUID-NET Vision and Perspective

Dechouniotis

Αθανασόπουλος

Leivadeas

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Ahvar [67] Aït-Salaht [85] Bittencourt [78] Borgia [86] Borylo [71] Boubin [87] Chen [81] De Maio [88] Elgazar [83] Fahs [89] Fricker [72] Gu [80] Habak [20] Liu [77] Liu [50] Mahmud [90] Penner [52] Rodrigues [73] Sardellitti [82] Singh [40] Skarlat [46] Sonmez [91] Tang [79] Tärneberg [75] Wang [45] Wang [70] Wang [92] Wang [93] Xia [94] Yi [76] Zamani [74] 3.4. Objective user.…”

Section: Objective Estimation Discovery Allocation Sharing Optimizationmentioning

confidence: 99%

“…They implemented the framework in a testbed by using the OpenStack and Kubernetes technologies and the orchestration is performed in a centralized way. Sonmez et al [91] propose a workload orchestrator using fuzzy logic evaluated using the EdgeCloudSim simulator. The orchestration is performed in a centralized way and considers only task placement.…”

Section: Multi-perspectivementioning

confidence: 99%

“…Indeed, the arrival times or any other required task information may not be available in advance. For their online solution, Sonmez et al [91] use fuzzy logic for their workload orchestrator while Wang et al [92] propose the MOERA algorithm for solving their formulated mixed nonlinear problem using the regularization technique and convex programming. Also considering online placement, Wang et al [93] propose an approximation algorithm building upon a baseline algorithm giving an optimal solution in the case of a linear application graph.…”

Section: Resource Management At the Edgementioning

confidence: 99%

“…Note that this will mean that there are 1800 video tasks generated per minute in parallel with around 5 user tasks. Hence, a model similar to earlier works [91] where a Poisson process is used to create task arrival patterns is not realistic. Such a model will miss to represent the periodic arrival of video tasks that represent 99% of all tasks.…”

Section: Task Arrival Patternmentioning

confidence: 99%

See 2 more Smart Citations