Adaptive Performance Modeling Framework for QoS-Aware Offloading in MEC-Based IIoT Systems
| Autor: | Chhabi Rani Panigrahi, Bibudhendu Pati, Sujit Bebortta, Dilip Senapati |
|---|---|
| Rok vydání: | 2022 |
| Předmět: |
Service (systems architecture)
Computer Networks and Communications Computer science Network packet Distributed computing Computer Science Applications Resource (project management) Hardware and Architecture Server Signal Processing Scalability Computation offloading Latency (engineering) Edge computing Information Systems |
| Zdroj: | IEEE Internet of Things Journal. 9:10162-10171 |
| ISSN: | 2372-2541 |
| Popis: | The extensive growth in Industrial Internet of Things (IIoT) applications have tremendously increased the demands for low latency and resource sensitive computing to accomplish critical industrial automations. This has leveraged the use of some proficient computing paradigms like Multi-access Edge Computing (MEC) which facilitates a low latency and scalable solution for execution of industrial workloads. However, continual generation of industrial data has imposed a substantial amount of stress on the resource constrained MEC systems. In this perspective, our study proposes a Consolidated Stochastic Computation Offloading (CSCO) framework to address the increasing computational demands of MEC-based IIoT systems. The proposed framework efficiently handles industrial workloads by modeling them as stochastic processes to observe the number of data packets denied service due to finite number of busy MEC servers. We provide an analytical solution corresponding to the loss probability of data packets denied service at the MEC servers. This leads to the development of a computation offloading mechanism for time-critical tasks. Further, we provide the expression for Conditional Waiting Time (CWT) and Unconditional Waiting Time (UWT) of the data packets waiting to be offloaded to the remote cloud servers. Through extensive numerical simulations it is inferred that the proposed CSCO framework provides promising results in characterizing the stochastic behavior of MEC-based IIoT systems, thereby providing a low-latency, and resource sensitive solution for the considered system. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|