Characterization of task response time in a fog-enabled IoT network using queueing models with general service times

Ibrahim, Amira; Al-Mahdi, Hassan; Nassar, Hamed

doi:10.1016/j.jksuci.2021.09.008

Cited by 6 publications

(11 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The cloud serving process is modeled as an M/G/∞ queuing system. A related work using the same queueing systems is provided in [37] to derive expressions for the TR time under the baseline virtualization mode. In [38], fog nodes are modeled as an open Jackson queueing network that can be utilized to decide and measure the QoS guarantees with respect to the TR time.…”

Section: Related Workmentioning

confidence: 99%

Characterization of task response time in fog enabled networks using queueing theory under different virtualization modes

et al. 2022

Self Cite

View full text Add to dashboard Cite

Much research has focused on task offloading in fog-enabled IoT networks. However, there is an important offloading issue that has hardly been addressed—the impact of different virtualization modes on task response (TR) time. In the present article, we bridge this gap, introducing three virtualization modes, and characterizing the TR time under each. In each mode the virtual machines (VM) at the fog are customized differently, leveraging VM elasticity. In the perfect virtualization mode, the VM is customized to match exactly the computational load of the incoming task. This ensures that each task, regardless of which VM it goes to, will have the same service time. In the semiperfect virtualization mode, a less stringent, thus more practical, alternative, the VM is customized to match roughly the computational load of the incoming task. This results in a uniformly distributed task service time. Finally, in the baseline virtualization mode, the VM is customized to just be fast, with no regard to the computational load of the incoming task. This mode, which just re-scales the processing time of the task, is the default in existing research, and is re-introduced here for only comparison purposes. We characterize the TR time for the three modes leveraging M/G/1 and M/G/m queueing models, with the queueing stability condition identified for each mode. The obtained analytical results are successfully validated by discrete event Monte Carlo simulation. The numerical results show that the first mode results in the shortest TR time, followed by the second mode, then the third mode. That is, if virtualization is managed adequately, significant improvement in TR time can be gained.

show abstract

Section: Related Workmentioning

confidence: 99%

Characterization of task response time in fog enabled networks using queueing theory under different virtualization modes

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…The number of IoT devices is estimated to amount to 75 billion by 2025 due to the rapid development of related technologies 2 . IoT end devices may need to access the cloud to receive services once in a while due to battery and processing system limitations 3 . Based on projections made, if the processing is done centrally by conventional cloud computing systems, the resulting large amounts of data generated will impose a heavy load on the network 4 .…”

Section: Introductionmentioning

confidence: 99%

“…The advantage of fog computing relies on its ability to provide computational resources in the vicinity of IoT devices, significantly reduce the time needed to access computational resources, and enable fast processing of IoT requests. For example, sensors, cameras, smartphones, tablets, and laptops can minimize the latency rate by relying on fog computing instead of cloud computing 3 …”

Section: Introductionmentioning

confidence: 99%

“…2 IoT end devices may need to access the cloud to receive services once in a while due to battery and processing system limitations. 3 Based on projections made, if the processing is done centrally by conventional cloud computing systems, the resulting large amounts of data generated will impose a heavy load on the network. 4 For instance, just self-driving vehicles generate data at an estimated rate of about 1 Gbps.…”

Section: Introductionmentioning

confidence: 99%

“…For example, sensors, cameras, smartphones, tablets, and laptops can minimize the latency rate by relying on fog computing instead of cloud computing. 3 Although fog computing fits the processing of IoT applications, it has major challenges regarding the provision and management of fog resources. Resource and process management, scheduling, and assigning resources to tasks are recognized as fundamental concepts in distributed systems.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

The improvement of wavefront cellular learning automata for task scheduling in fog computing

Jassbi

Teymori

2023

Trans Emerging Tel Tech

View full text Add to dashboard Cite

The rapid advancement of the “Internet of Things” (IoT) devices has led to the emergence of different types of IoT applications that need immediate response and low delay to operate. The emergence of fog computing has provided a proper platform to process fast‐emerging IoT applications. Nevertheless, to name the disadvantages of fog computing devices, it can be said that they are typically distributed, dynamic, and resource‐limited. Therefore, it seems a substantial challenge to schedule fog computational resources effectively to perform heterogeneous and delay‐sensitive IoT tasks. The problem of scheduling tasks aimed at minimizing the energy consumption of fog nodes is formulated in this article, while meeting the requirements of the quality of service (QoS) of IoT tasks, including response time. Minimizing the deadline time and balancing the network load are also considered in the mathematical model. In the next stage, a new algorithm is introduced based on a wavefront cellular learning automata (WCLA) called the wavefront cellular learning automata improved by genetic algorithm (WCLA + GA). WCLA + GA is indeed a modified version of WCLA that has been improved using the genetic algorithm. In this version, the WCLA reinforcement signal is regulated by a genetic algorithm that accelerates the automata convergence rate. WCLA + GA is then utilized to schedule fog tasks. Simulating the proposed method followed by comparing it with other methods demonstrates that WCLA + GA performs task scheduling significantly better in terms of response time, energy consumption, and percentage of tasks that meet their deadline.

show abstract

Adaptive Thresholds for Task Offloading in IoT-Edge-Cloud Networks

Al-Tuhafi

Al-Hemiary

2023

2023 International Conference on Cyber Management and Engineering (CyMaEn)

View full text Add to dashboard Cite

Characterization of task response time in a fog-enabled IoT network using queueing models with general service times

Cited by 6 publications

References 34 publications

Characterization of task response time in fog enabled networks using queueing theory under different virtualization modes

Characterization of task response time in fog enabled networks using queueing theory under different virtualization modes

The improvement of wavefront cellular learning automata for task scheduling in fog computing

Adaptive Thresholds for Task Offloading in IoT-Edge-Cloud Networks

Contact Info

Product

Resources

About