Summary of Contextual Bandits with Non-stationary Correlated Rewards For User Association in Mmwave Vehicular Networks, by Xiaoyang He et al.
Contextual Bandits with Non-Stationary Correlated Rewards for User Association in MmWave Vehicular Networks
by Xiaoyang He, Xiaoxia Huang, Lanhua Li
First submitted to arxiv on: 8 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
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 This paper proposes a low-complexity semi-distributed contextual correlated upper confidence bound (SD-CC-UCB) algorithm for user association in millimeter wave (mmWave) vehicular communication. The algorithm relies on learning transmission rate and predicting it based on vehicle location and velocity to establish an up-to-date user association without explicit measurement of channel state information (CSI). SD-CC-UCB efficiently identifies candidate base stations that support high transmission rates by leveraging correlated distributions of transmission rates across locations. To refine the learning transmission rate, each vehicle uses Thompson Sampling algorithm considering interference among vehicles and handover overhead. The proposed algorithm achieves network throughput within 100%-103% of a benchmark algorithm requiring perfect instantaneous CSI, demonstrating its effectiveness in vehicular communications. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about finding the best way to connect cars to base stations using high-frequency radio waves. The problem is that the signal strength changes quickly and it’s hard to get accurate information. The authors propose a new algorithm called SD-CC-UCB that can make decisions without needing perfect information. It uses data from the car’s location and speed to predict the best connection. The algorithm also takes into account other cars and handovers, which helps it make better decisions. Tests show that this algorithm works well and is almost as good as a more complex method. |
