Summary of Combinatorial Client-master Multiagent Deep Reinforcement Learning For Task Offloading in Mobile Edge Computing, by Tesfay Zemuy Gebrekidan et al.
Combinatorial Client-Master Multiagent Deep Reinforcement Learning for Task Offloading in Mobile Edge Computing
by Tesfay Zemuy Gebrekidan, Sebastian Stein, Timothy J.Norman
First submitted to arxiv on: 18 Feb 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Distributed, Parallel, and Cluster Computing (cs.DC); Networking and Internet Architecture (cs.NI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary Medium Difficulty Summary: Recently, mobile applications have rapidly increased in complexity, requiring more computational power from user devices (UDs) such as tablets and smartphones. Mobile Edge Computing (MEC) is a promising technology to meet these demands by offloading tasks between UDs and MEC servers. Deep Reinforcement Learning (DRL) is gaining attention for its ability to adapt to dynamic changes and minimize online computational complexity. However, existing DRL-based task-offloading algorithms focus on UDs’ constraints, ignoring server storage limitations. Our proposed novel combinatorial client-master Multi-Agent DRL (CCM_MADRL) algorithm addresses this limitation by considering both UDs’ and servers’ constraints, resulting in superior convergence compared to existing MADDPG and heuristic algorithms. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Low Difficulty Summary: Imagine using your phone or tablet to play games, watch videos, or recognize faces – but it’s slow because the device can’t handle all that processing power. That’s where Mobile Edge Computing (MEC) comes in. MEC helps devices by offloading tasks to powerful servers in the cloud. Deep Learning is a type of AI that can learn and adapt to changing conditions, making it perfect for this task. However, previous attempts at solving this problem ignored the limitations of those servers’ storage space. Our new approach, called CCM_MADRL, takes into account both device and server constraints, making it much more effective than before. |
Keywords
» Artificial intelligence » Attention » Deep learning » Reinforcement learning
