A latency-aware and energy-efficient computation offloading in mobile fog computing: a hidden Markov model-based approac
- PDF / 2,620,426 Bytes
- 30 Pages / 439.37 x 666.142 pts Page_size
- 69 Downloads / 175 Views
A latency‑aware and energy‑efficient computation offloading in mobile fog computing: a hidden Markov model‑based approach Fatemeh Jazayeri1 · Ali Shahidinejad1 · Mostafa Ghobaei‑Arani1 Accepted: 20 October 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract In recent years, Fog Computing (FC) is known as a good infrastructure for the Internet of Things (IoT). Using this architecture for the mobile applications in the IoT is named the Mobile Fog Computing (MFC). If we assume that an application includes some modules, thus, these modules can be sent to the Fog or Cloud layer because of the resource limitation or increased runtime at the mobile. This increases the efficiency of the whole system. As data is entered sequentially, and the input is given to the modules, the number of executable modules increases. So, this research is conducted to find the best place in order to run the modules that can be on the mobile, Fog, or Cloud. According to the proposed method, when the modules arrive at gateway, then, a Hidden Markov model Auto-scaling Offloading (HMAO) finds the best destination to execute the module to create a compromise between the energy consumption and execution time of the modules. The evaluation results obtained regarding the parameters of the energy consumption, execution cost, delay, and network resource usage shows that the proposed method on average is better than the local execution, First-Fit (FF), and Q-learning based method. Keywords Mobile fog computing · Offloading · Hidden Markov model · Energy efficiency · Latency-aware
* Ali Shahidinejad a.shahidinejad@qom‑iau.ac.ir Fatemeh Jazayeri fatemehjazayeri97.stu@qom‑iau.ac.ir Mostafa Ghobaei‑Arani m.ghobaei@qom‑iau.ac.ir 1
Department of Computer Engineering, Qom Branch, Islamic Azad University, Qom, Iran
13
Vol.:(0123456789)
F. Jazayeri et al.
1 Introduction The increasing growth of information technology has made mobile devices such as essential components of human life. In recent years, many devices have been connected to the Internet, including smart gadgets, wearables, smart cars, mobile phones, industrial gadgets, and more. Large amounts of data enter these devices, and they also have limitations in energy and resources such as CPU, storage, and memory [1]. Many applications with computing or delay restrictions have low performance while running on the MDs, especially for the IoT devices while sending, storing, and limited computing resources [2]. Cloud computing is an excellent platform to overcome the hardware constraints and save the energy for the MDs on the IoT by offloading the computations to Cloud [3, 4]. The European Telecommunications Standards Institute (ETSI) and Open Fog Consortium have been provided with some standards and definitions for computation offloading [5]. There is a serious problem that the traditional central Cloud is usually far from its users. Therefore, the performance of the mobile applications can be increased, and the energy consumption of the MDs can be reduced by of
Data Loading...
