Downloads: 0 | Views: 297

Research Paper | Computer Science and Information Technology | China | Volume 12 Issue 6, June 2023 | Popularity: 4.8 / 10

Rate This Article!      

Distributed Deep Learning Based Framework to Optimize Real-Time Offloading in Mobile Edge Computing Networks

Mourita Mozib

Abstract: Mobile edge computing MEC has emerged as a promising technology for enabling low latency and high bandwidth applications by leveraging computational resources at the edge of the network. However, efficient offloading of computation from mobile devices to edge servers remains a challenging problem due to the heterogeneity of devices, network conditions, and workload characteristics. In this thesis, we propose a distributed deep learning based framework that optimizes real time offloading in MEC networks. The framework leverages deep reinforcement learning algorithms to dynamically allocate resources and manage offloading decisions based on real time network conditions and workload demands. We evaluate the proposed framework using a simulation based approach and show that it achieves significant improvements in offloading performance compared to existing approaches. The simulation results demonstrate that the proposed framework can reduce the offloading latency by up to 60 and improve the energy efficiency by up to 40 compared to existing approaches.

Keywords: Mobile Edge Computing, Deep Learning, RealTime Offloading, Distributed Framework, Resource Allocation

Edition: Volume 12 Issue 6, June 2023

Pages: 1812 - 1827

DOI: https://www.doi.org/10.21275/SR23603125305

Make Sure to Disable the Pop-Up Blocker of Web Browser

Click to Cite this Article

Similar Articles