电子学报 ›› 2022, Vol. 50 ›› Issue (2): 366-373.DOI: 10.12263/DZXB.20201211

• 学术论文 • 上一篇    下一篇

基于LSTM和GRNN的容器配额优化算法

周泓岑1, 白恒1, 才振功1, 蔡亮1, 顾静2, 汤志敏2   

  1. 1.浙江大学软件学院, 浙江 宁波 315000
    2.阿里巴巴集团, 浙江 杭州 310000
  • 收稿日期:2020-10-29 修回日期:2021-01-08 出版日期:2022-02-25
    • 作者简介:
    • 周泓岑 男,1994年8月出生,四川达州人.现为浙江大学软件工程硕士研究生.主要研究方向为云计算、运筹优化、深度学习.
      白 恒 男,1995年7月出生,山西吕梁人.现为浙江大学软件工程硕士研究生.主要研究方向为云计算、容器化、大数据.E-mail: zhouhongcen@zju.edu.cn
      才振功(通讯作者) 男,1983年出生,河南商丘人.博士.现为浙江大学软件学院副研究员,硕士生导师.主要研究方向为云计算、边缘计算、软件工程.E-mail: cstcaizg@zju.edu.cn
    • 基金资助:
    • 国家重点研发计划 (2019YFB1600700); 阿里巴巴-浙江大学前沿技术联合研发中心 (XT622019000187); 阿里巴巴创新研究计划 (AIR)合作项目; 浙江大学-中移在线联合创新实验室 (CMOS01HT20180623)

Container Quota Optimization Algorithm Based on GRNN and LSTM

ZHOU Hong-cen1, BAI Heng1, CAI Zhen-gong1, CAI Liang1, GU Jing2, TANG Zhi-min2   

  1. 1.College of Software Technology, Zhejiang University, Ningbo, Zhejiang 315000, China
    2.Alibaba Group, Hangzhou, Zhejiang 310000, China
  • Received:2020-10-29 Revised:2021-01-08 Online:2022-02-25 Published:2022-02-25
    • Supported by:
    • National Key Research and Development Program of China (2019YFB1600700); Alibaba-Zhejiang University Joint Institute of Frontier Technologies (AZFT) (XT622019000187); Coorperation Program of Alibaba Innovation Research Project; Zhejiang University-China Mobile Online Joint Innovation Laboratory (CMOS01HT20180623)

摘要:

为了实现容器配额设置自动化和集群资源利用最大化,本文设计了一种容器配额优化算法.本文在长短期记忆(Long Short-Term Memory,LSTM)神经网络和广义回归神经网络(Generalized Regression Neural Network,GRNN)的基础上设计了深度神经网络(Long short-term memory and GRNN Network,LGN),并使用改进量子粒子群算法优选网络结构超参数,以实现自动调参和更快的收敛速度.容器配额优化算法步骤如下:首先根据历史数据使用LGN训练资源容量模型,然后使用改进的量子粒子群算法优化模型参数,最后使用资源容量模型计算容器配额.通过与谷歌容器垂直自动扩展器(Vertical Pod Autoscaler,VPA)和水平自动扩展器(Horizontal Pod Autoscaler,HPA)生成的配额进行对比发现,本文提出的优化算法较VPA和HPA降低了至少10%的资源分配总量,同时提升了至少6%的资源利用率.

关键词: 容器配额, 容量模型, 广义回归神经网络, 长短期记忆神经网络, 量子粒子群算法

Abstract:

In order to realize the automation of container quota setting and the maximization of cluster resource utilization, this paper designed a container quota optimization algorithm. In this paper, LGN(long short-term memory and GRNN network) was designed based on the LSTM(long short-term memory) and the GRNN(generalized regression neural network). Also, the improved quantum particle swarm algorithm was used to optimize the hyperparameters of the network structure to achieve automatic parameter adjustment and faster convergence speed. The steps of the container quota optimization algorithm are as follows. First, LGN is used to train the resource capacity model based on historical data. Then the improved quantum particle swarm algorithm is adopted to optimize the model parameters. Finally, the resource capacity model is designed to calculate container quotas. By comparing with the quotas generated by Google Container VPA(vertical pod autoscaler) and HPA(horizontal pod autoscaler), the optimization algorithm proposed in this paper has at least 10% lower total resource allocation and 6% higher resource utilization.

Key words: container quota, capacity model, generalized regression neural network(GRNN), long short-term memory(LSTM), quantum particle swarm optimization

中图分类号: