University of Twente Student Theses
AI-based Rate Control in IIoT Networks for Improved Energy Efficiency
Vuurens, B. (2024) AI-based Rate Control in IIoT Networks for Improved Energy Efficiency.
|
PDF
1MB |
| Abstract: | In a Wi-Fi-based industrial IoT (IIoT) network, there are sensors and devices with different Quality of Service (QoS) requirements. In Wi-Fi, one of the methods to achieve QoS requirements is rate control. Many existing algorithms for rate control focus on achieving the highest possible performance. However, in IIoT, it might be beneficial to sacrifice some performance for lower energy consumption, therefore improving the lifespan of IIoT devices and reducing the operation cost of the network. The improvement in energy efficiency is particularly important in IoT networks because devices are usually battery-constrained. This research proposes a deep reinforcement learning (DRL) algorithm to improve energy efficiency while maintaining the QoS requirements. The DRL algorithm adjusts the Modulation and Coding Scheme (MCS) and transmission power to optimise for energy efficiency. We show that the algorithm is able to reduce energy consumption while maintaining QoS requirements. |
| Item Type: | Essay (Bachelor) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 54 computer science |
| Programme: | Computer Science BSc (56964) |
| Link to this item: | https://purl.utwente.nl/essays/100821 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page