LLM-ABR：透過大型語言模型設計適應性比特率算法

LLM-ABR: Designing Adaptive Bitrate Algorithms via Large Language Models

April 2, 2024

作者: Zhiyuan He, Aashish Gottipati, Lili Qiu, Francis Y. Yan, Xufang Luo, Kenuo Xu, Yuqing Yang

cs.AI

摘要

我們提出了LLM-ABR，這是第一個利用大型語言模型（LLMs）的生成能力來自主設計適應不同網絡特性的自適應位元率（ABR）算法的系統。在強化學習框架內運行，LLM-ABR賦予LLMs設計關鍵組件，如狀態和神經網絡架構的能力。我們在不同網絡環境下評估LLM-ABR，包括寬頻、衛星、4G和5G。LLM-ABR在各種網絡設置中始終優於默認的ABR算法。

English

We present LLM-ABR, the first system that utilizes the generative capabilities of large language models (LLMs) to autonomously design adaptive bitrate (ABR) algorithms tailored for diverse network characteristics. Operating within a reinforcement learning framework, LLM-ABR empowers LLMs to design key components such as states and neural network architectures. We evaluate LLM-ABR across diverse network settings, including broadband, satellite, 4G, and 5G. LLM-ABR consistently outperforms default ABR algorithms.