CompHub 实时聚合多平台的数据类(Kaggle、天池…)和OJ类(Leetcode、牛客…)比赛。本账号会推送最新的比赛消息,欢迎关注!
更多比赛信息见 CompHub主页
以下内容摘自比赛主页(点击文末阅读原文进入)
Part1赛题介绍
题目
Next-Gen WiFi Throughput Prediction Challenge by ITU AI/ML in 5G Challenge
举办平台
主办方
International Telecommunication Union (ITU)
背景
Multi-Access Point Coordination (MAPC) is one of the new features to be included in next-generation Wi-Fi networks. It represents a radical change in the way traditional Wi-Fi networks work. Following the MAPC framework, access points (APs) can agree on how to share spectrum resources, improving network efficiency by reducing interference on the WLAN network.
Coordinated Spatial Reuse (c-SR) takes advantage of MAPC by allowing multiple APs to transmit simultaneously. In c-SR, APs exchange the Received Signal Strength Indicator (RSSI) from their neighbouring stations to a controller to build groups of APs that can perform simultaneous transmissions. Creating these compatible AP groups means finding subsets of those APs that do not cause unacceptable interference to the others when transmitting at the same time.
Part2时间安排
Competition closes on 31 December 2022.
Final submissions must be received by 23:59 PM GMT.
Part3奖励机制
-
1st place: $500 USD
-
2nd place: $300 USD
-
3rd place: $200 USD
There are 2000 Zindi points for this challenge. You can read more about Zindi points here.
Part4赛题描述
In this challenge, you need to use machine learning to predict the throughput (performance) that a subset of APs can achieve in a c-SR network. This will allow network devices to derive the optimal set of groups in WLAN settings.
We have provided a synthetic dataset with data from multiple random WLAN deployments. The dataset contains:
-
the RSSI overheard by all stations in a neighbourhood
-
the subset of APs selected to collaboratively transmit in a given transmission opportunity (TXOP) using c-SR
-
the achieved throughput.
The goal is to build a model to predict the achievable throughput given arandom combination of APs that aim to transmit simultaneously.