請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/92129
標題: | 離線元強化學習應用於伺服器風扇控制邏輯 Thermal and Energy Management with Fan Control Through Offline Meta Reinforcement Learning |
作者: | 顏紹宇 Shao-Yu Yen |
指導教授: | 吳沛遠 Pei-Yuan Wu |
關鍵字: | 強化學習,離線元強化學習,伺服器風扇控制,伺服器熱傳管理, Reinforcement Learning,Offline Meta-reinforcement Learning,Server Fan Control,Server Thermal Management, |
出版年 : | 2024 |
學位: | 碩士 |
摘要: | 伺服器散熱系統攸關整體運作效能,由於伺服器體積大、流道劃分複雜,每個流道又同時會受眾多不同風扇之影響,且熱傳與流場特性均為非線性,所以傳統上對於風扇散熱控制需透過工程師進行大規模量測調教找出最適當的風扇曲線,風扇邏輯設計上耗時且不易針對不同客戶的硬體需求與機房環境進行風扇曲線之客製化設計。故我們透過導入離線元強化學習的方法優化伺服器風扇控制邏輯之應用,根據事先蒐集的風扇控制與溫控收益反饋資料訓練模型快速找出最佳的控制策略,我們在穩態控制測試項目中不僅能維持CPU在理想的溫度之下並且模型的風扇曲線與基準模型相比總功率節省了21%,此外在CPU壓力測試環節中我們的模型亦優化了18%的能耗數據。 Reinforcement learning has drawn great attention in various fields such as computer vision, natural language processing, robotics, and so on. In this work, we present an empirical study involving three distinct offline meta-reinforcement learning approaches for the task of fan control, focusing on thermal and energy management. Our fan control models enable adaptive fan speed control that can not only protect the device from heat crash but also effectively reduce power consumption. To better assess the fan control performance, besides the industry-standard steady-state test, we also conduct CPU-stress test to simulate a more general deployment scenario for the server where the workload is more random and dynamic. Compared to the commercially available technique, our solution improves the performance of power consumption by up to 21% reduction for a real 2U-server in the worst thermal setting of the hardware configuration. Our solution can be widely applied to the thermal and energy management of server systems. |
URI: | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/92129 |
DOI: | 10.6342/NTU202400536 |
全文授權: | 未授權 |
顯示於系所單位: | 電信工程學研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-112-1.pdf 目前未授權公開取用 | 1.42 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。