| 引用本文: | 杨世贵,王媛媛,刘韦辰,姜徐,赵明雄,方卉,杨宇,刘迪.基于强化学习的温度感知多核任务调度.软件学报,2021,32(8):2408-2424 |
| |
|
| |
|
|
| 本文已被：浏览 4193次 下载 8270次 |
码上扫一扫！ |
|
|
| 基于强化学习的温度感知多核任务调度 |
|
杨世贵1, 王媛媛1,2,3, 刘韦辰4, 姜徐5, 赵明雄1, 方卉1, 杨宇1, 刘迪1,4
|
|
1.云南大学 软件学院, 云南 昆明 650504;2.中国科学院 信息工程研究所, 北京 100093;3.中国科学院大学 网络空间安全学院, 北京 100049;4.School of Computer Science and Engineering, Nanyang Technological University, Singapore;5.东北大学 计算机科学与工程学院, 辽宁 沈阳 110169
|
|
| 摘要: |
| 随着计算机中内核数量的增多，温度感知的多核任务调度算法成为计算机系统中的一个研究热点.近年来，机器学习在各个领域展现出巨大的潜力，很多基于机器学习的系统温度管理研究工作应运而生.其中，强化学习因其较强的自适应性，被广泛地运用于温度感知的任务调度算法中.然而，目前基于强化学习的温度感知任务调度算法系统建模不够准确，很难做到温度、性能和复杂度的较好权衡.因此，提出一种基于强化学习的多核温度感知调度算法——ReLeTA.在该算法中提出了更全面的状态建模方式和更加有效的奖励函数，从而帮助系统进一步降低温度.实验部分通过3个不同的真实计算机平台验证该方法，实验结果表明了该方法的有效性以及可扩展性，与现有方法相比，ReLeTA可以更好地控制系统温度. |
| 关键词: 温度感知 多核系统 强化学习 Q-Learning |
| DOI：10.13328/j.cnki.jos.006190 |
| 分类号:TP316 |
| 基金项目:国家自然科学基金（61902341） |
|
| Temperature-aware Task Scheduling on Multicores Based on Reinforcement Learning |
|
YANG Shi-Gui1, WANG Yuan-Yuan1,2,3, LIU Wei-Chen4, JIANG Xu5, ZHAO Ming-Xiong1, FANG Hui1, YANG Yu1, LIU Di1,4
|
|
1.School of Software, Yunnan University, Kunming 650504, China;2.Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093, China;3.School of Cyber Security, University of Chinese Academy of Sciences, Beijing 100049, China;4.School of Computer Science and Engineering, Nanyang Technological University, Singapore;5.School of Computer Science and Engineering, Northeastern University, Shenyang 110169, China
|
| Abstract: |
| With the increase of the number of cores in computers, temperature-aware multi-core task scheduling algorithms have become a research hotspot in computer systems. In recent years, machine learning has shown great potential in various fields, and thus many work using machine learning techniques to manage system temperature have emerged. Among them, reinforcement learning is widely used for temperature-aware task scheduling algorithms due to its strong adaptability. However, the state-of-the-art temperature-aware task scheduling algorithms based on reinforcement learning do not effectively model the system, and it is difficult to achieve a better trade-off among temperature, performance, and complexity. Therefore, this study proposes a new multi-core temperature-aware scheduling algorithm based on reinforcement learning-ReLeTA. In the new algorithm, a more comprehensive state modeling method and a more effective reward function are proposed to help the system further reduce the temperature. Experiments are conducted on three different real computer platforms. The experimental results show the effectiveness and scalability of the proposed method. Compared with existing methods, ReLeTA can control the system temperature better. |
| Key words: temperature-aware multicore system reinforcement learning Q-Learning |
|
|
|
|
