Summary of Teacher-student Learning Based Low Complexity Relay Selection in Wireless Powered Communications, by Aysun Gurur Onalan et al.
Teacher-Student Learning based Low Complexity Relay Selection in Wireless Powered Communications
by Aysun Gurur Onalan, Berkay Kopru, Sinem Coleri
First submitted to arxiv on: 3 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Networking and Internet Architecture (cs.NI); Signal Processing (eess.SP)
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 In a breakthrough in Radio Frequency Energy Harvesting (RF-EH) networks, researchers have developed novel techniques for relay selection, scheduling, and power control to improve network performance under non-linear energy harvesting conditions. The paper proposes two convolutional neural network (CNN) architectures for joint relay selection and classification, as well as a teacher-student learning approach to reduce runtime complexity. Additionally, the authors introduce a dichotomous search-based algorithm to determine the best architecture for the student network. These innovations have the potential to significantly enhance the performance of massive Internet-of-things applications. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Radio Frequency Energy Harvesting (RF-EH) networks are special kinds of internet that can send energy and information to devices far away. This is important because some devices don’t have enough power to do their job. Researchers wanted to make these networks better by solving a complex problem called “joint relay selection, scheduling, and power control”. They came up with two new ways to do this using special kinds of computer programs called neural networks. These programs are like super-smart calculators that can learn and get better over time. The researchers also used another technique to make the calculations faster without losing accuracy. This could be very important for making sure devices can talk to each other in a big internet-of-things network. |
Keywords
* Artificial intelligence * Classification * Cnn * Neural network
