Performance Monitoring for AI-based CSI Feedback via Proxy

Jiajia Guo; Shaodan Ma

doi:10.1109/FCN60432.2023.10543881

Performance Monitoring for AI-based CSI Feedback via Proxy

Jiajia Guo^*, Shaodan Ma

^*Corresponding author for this work

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

1 Citation (Scopus)

Abstract

Artificial intelligence (AI) has shown great potential in channel state information (CSI) feedback problems. However, the existing works focus on further improving the performance of AI-enabled autoencoder-based CSI feedback but ignore some new problems caused by the introduction of AI. In this work, the performance monitoring for AI-based CSI feedback is considered and a proxy-based performance monitoring framework is proposed. This is the first work that considers performance monitoring. Specifically, we use the knowledge distillation technique to transfer the knowledge learned by the complicated decoder at the base station to the lightweight proxy decoder at the user. The lightweight proxy decoder is then used to predict the CSI reconstruction accuracy. Simulation on a public channel dataset shows that the performance monitoring method proposed in this work can predict feedback performance with high quality, and the classification accuracy is over 95%.

Original language	English
Title of host publication	2023 International Conference on Future Communications and Networks, FCN 2023 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350396034
DOIs	https://doi.org/10.1109/FCN60432.2023.10543881
Publication status	Published - 2023
Externally published	Yes
Event	2023 International Conference on Future Communications and Networks, FCN 2023 - Queenstown, New Zealand Duration: 17 Dec 2023 → 20 Dec 2023

Publication series

Name	2023 International Conference on Future Communications and Networks, FCN 2023 - Proceedings

Conference

Conference	2023 International Conference on Future Communications and Networks, FCN 2023
Country/Territory	New Zealand
City	Queenstown
Period	17/12/23 → 20/12/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Access to Document

10.1109/FCN60432.2023.10543881

Cite this

Guo, J., & Ma, S. (2023). Performance Monitoring for AI-based CSI Feedback via Proxy. In 2023 International Conference on Future Communications and Networks, FCN 2023 - Proceedings (2023 International Conference on Future Communications and Networks, FCN 2023 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/FCN60432.2023.10543881

@inproceedings{7ef9234002c74fd3b15d470c01ad1a8a,

title = "Performance Monitoring for AI-based CSI Feedback via Proxy",

abstract = "Artificial intelligence (AI) has shown great potential in channel state information (CSI) feedback problems. However, the existing works focus on further improving the performance of AI-enabled autoencoder-based CSI feedback but ignore some new problems caused by the introduction of AI. In this work, the performance monitoring for AI-based CSI feedback is considered and a proxy-based performance monitoring framework is proposed. This is the first work that considers performance monitoring. Specifically, we use the knowledge distillation technique to transfer the knowledge learned by the complicated decoder at the base station to the lightweight proxy decoder at the user. The lightweight proxy decoder is then used to predict the CSI reconstruction accuracy. Simulation on a public channel dataset shows that the performance monitoring method proposed in this work can predict feedback performance with high quality, and the classification accuracy is over 95\%.",

author = "Jiajia Guo and Shaodan Ma",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 International Conference on Future Communications and Networks, FCN 2023 ; Conference date: 17-12-2023 Through 20-12-2023",

year = "2023",

doi = "10.1109/FCN60432.2023.10543881",

language = "English",

series = "2023 International Conference on Future Communications and Networks, FCN 2023 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2023 International Conference on Future Communications and Networks, FCN 2023 - Proceedings",

}

Guo, J & Ma, S 2023, Performance Monitoring for AI-based CSI Feedback via Proxy. in 2023 International Conference on Future Communications and Networks, FCN 2023 - Proceedings. 2023 International Conference on Future Communications and Networks, FCN 2023 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 2023 International Conference on Future Communications and Networks, FCN 2023, Queenstown, New Zealand, 17/12/23. https://doi.org/10.1109/FCN60432.2023.10543881

Performance Monitoring for AI-based CSI Feedback via Proxy. / Guo, Jiajia; Ma, Shaodan.
2023 International Conference on Future Communications and Networks, FCN 2023 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2023. (2023 International Conference on Future Communications and Networks, FCN 2023 - Proceedings).

Research output: Chapter in Book/Conference Proceeding/Report › Conference Paper published in a book › peer-review

TY - GEN

T1 - Performance Monitoring for AI-based CSI Feedback via Proxy

AU - Guo, Jiajia

AU - Ma, Shaodan

PY - 2023

Y1 - 2023

N2 - Artificial intelligence (AI) has shown great potential in channel state information (CSI) feedback problems. However, the existing works focus on further improving the performance of AI-enabled autoencoder-based CSI feedback but ignore some new problems caused by the introduction of AI. In this work, the performance monitoring for AI-based CSI feedback is considered and a proxy-based performance monitoring framework is proposed. This is the first work that considers performance monitoring. Specifically, we use the knowledge distillation technique to transfer the knowledge learned by the complicated decoder at the base station to the lightweight proxy decoder at the user. The lightweight proxy decoder is then used to predict the CSI reconstruction accuracy. Simulation on a public channel dataset shows that the performance monitoring method proposed in this work can predict feedback performance with high quality, and the classification accuracy is over 95%.

AB - Artificial intelligence (AI) has shown great potential in channel state information (CSI) feedback problems. However, the existing works focus on further improving the performance of AI-enabled autoencoder-based CSI feedback but ignore some new problems caused by the introduction of AI. In this work, the performance monitoring for AI-based CSI feedback is considered and a proxy-based performance monitoring framework is proposed. This is the first work that considers performance monitoring. Specifically, we use the knowledge distillation technique to transfer the knowledge learned by the complicated decoder at the base station to the lightweight proxy decoder at the user. The lightweight proxy decoder is then used to predict the CSI reconstruction accuracy. Simulation on a public channel dataset shows that the performance monitoring method proposed in this work can predict feedback performance with high quality, and the classification accuracy is over 95%.

UR - https://www.webofscience.com/wos/woscc/full-record/WOS:001244885000027

UR - https://www.scopus.com/pages/publications/85196082885

U2 - 10.1109/FCN60432.2023.10543881

DO - 10.1109/FCN60432.2023.10543881

M3 - Conference Paper published in a book

T3 - 2023 International Conference on Future Communications and Networks, FCN 2023 - Proceedings

BT - 2023 International Conference on Future Communications and Networks, FCN 2023 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 International Conference on Future Communications and Networks, FCN 2023

Y2 - 17 December 2023 through 20 December 2023

ER -

Performance Monitoring for AI-based CSI Feedback via Proxy

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this