Autonomous computation offloading and auto-scaling the in the mobile fog computing: a deep reinforcement learning-based
- PDF / 3,900,161 Bytes
- 20 Pages / 595.276 x 790.866 pts Page_size
- 73 Downloads / 162 Views
ORIGINAL RESEARCH
Autonomous computation offloading and auto‑scaling the in the mobile fog computing: a deep reinforcement learning‑based approach Fatemeh Jazayeri1 · Ali Shahidinejad1 · Mostafa Ghobaei‑Arani1 Received: 28 March 2020 / Accepted: 16 September 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract The Fog Computing (FC) paradigm is rapidly becoming an appropriate framework for the infrastructure related to the Internet of Things (IoT). FC can be a good framework for mobile applications in the IoT. This architecture is referred to as the Mobile Fog Computing (MFC). Modules in the applications can be sent to the Fog or Cloud layer in the event of the lack of resources or increased runtime on 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 was 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, first, the Fog Devices (FDs) were locally evaluated using a greedy technique; namely, the sibling nodes followed by the parent and in the second step, a Deep Reinforcement Learning (DRL) algorithm found the best destination to execute the module so as to create a compromise between the power consumption and execution time of the modules. The evaluation results obtained regarding the parameters of the power consumption, execution cost, delay, and network resource usage showed that the proposed method on average is better than the local execution, First-Fit (FF), and standard DRL by 18, 6, and 2%, respectively. Keywords Mobile fog computing · Offloading · Deep reinforcement learning · Power efficiency · Delay
1 Introduction With the rapid development of the information and communication technology industry, Mobile Devices (MDs) have become an integral part of our daily lives that can provide us with convenient communication at almost any time and place. Billions of smart devices, such as wearables, smart cars, sensors, cameras, smartphones, lipsticks, industrial components, etc., are expected to connect to the Internet in the next few years. However, the gap between the limited capacity of the local computing resources of the tools and the demand for complex applications is increasing day * 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
by day due to the limitation of the MDs in terms of size, weight, battery life, heat dissipation, and computational capacity (Ning et al. 2019c). Many computing-sensitive or delay-sensitive applications have poor performance while running on the MDs, especially for the IoT tools that are mainly capable of sending, storing, and limited computing resources (Jia et al. 2019). Cloud computing provides a promising opportunity to overcome the hardw
Data Loading...
