一种面向工作负载预测的基于小波变换的特征提取方法

doi:10.3969/j.issn.1006-2475.2020.05.001

计算机与现代化 ›› 2020, Vol. 0 ›› Issue (05): 1-.doi: 10.3969/j.issn.1006-2475.2020.05.001

• 人工智能 • 下一篇

一种面向工作负载预测的基于小波变换的特征提取方法

(1.贵州大学计算机科学与技术学院，贵州贵阳550025;2.贵州省先进计算与医疗信息服务工程实验室，
贵州贵阳550025;3.中国科学院国家天文台，北京100101)

收稿日期:2020-02-06 出版日期:2020-05-20 发布日期:2020-05-21
作者简介:王可(1991-)，男，山东菏泽人，硕士研究生，研究方向：大规模数据分析处理，E-mail: wangke9926@gmail.com; 通信作者：李晖(1982-)，男，湖南衡阳人，教授，博士，研究方向：大规模数据管理与分析，数据挖掘，E-mail: cse.huili@gzu.edu.cn; 陈梅(1964-)，女，贵州贵阳人，教授，研究方向：数据库技术，数据挖掘，E-mail: gychm@gzu.edu.cn; 戴震宇(1985-)，男，贵州贵阳人，实验师，研究方向：大规模数据分析处理，E-mail: zydai@gzu.edu.cn; 朱明(1966-)，男，广西玉林人，研究员，博士，研究方向：科学数据处理，射电天文学，E-mail: mz@nao.cas.cn。
基金资助:
国家自然科学基金资助项目(61462012, 61562010, 71964009); 贵州省高层次创新型人才项目(2017)

A Wavelet Transform-based Feature Extraction Method for Workload Prediction

(1. College of Computer Science and Technology, Guizhou University, Guiyang 550025, China;
2. Guizhou Engineering Laboratory for Advance Computing and Medical Information Service, Guiyang 550025, China;
3. National Astronomical Observatories, Chinese Academy of Sciences, Beijing 100101, China)

Received:2020-02-06 Online:2020-05-20 Published:2020-05-21

摘要/Abstract

摘要： 在资源受限条件下，根据数据挖掘任务在执行过程中实时产生的资源和任务状态来准确地预测任务执行时间是非常重要的。为有效地使用时间序列数据实现准确预测，提出一种降载策略来确定预测的切入点和数据处理方案。该策略使用动态时间规整(Dynamic Time Warping, DTW)距离度量子序列与整个序列之间相似度的变化以确定用于预测的数据，然后利用小波变换计算小波系数并提取小波系数的能量值作为预测的特征，最后预测任务执行时间。实验结果表明，该方法提取的特征信息包含原序列较多信息，在预测任务执行时间方面具有较高的准确性。

关键词: 降载, 小波变换, 特征提取, 任务执行时间预测

Abstract: In resource constraints condition, it is very important to make accurate predictions of the task execution time based on time-series resource and task status generated in real-time during task execution. In order to use time-series data effectively to realize accurate prediction, a load shedding strategy is proposed to determine the time points of prediction and data processing scheme. This strategy uses dynamic time warping (DTW) distance to measure the variation of similarity between subsequences and entire sequences and determine the data used for prediction. Then we use wavelet transform to calculate the wavelet coefficients of the time-series and extract the energy value of wavelet coefficients as the features of prediction. After that, we conduct the prediction for task execution time. Experiments show that the features extracted by this method contain most information than the entire sequence and result in high accuracy in predicting the task execution time.

Key words: load shedding, wavelet transform, feature extraction, task execution time prediction

中图分类号:

TP391

王可1,2，李晖1,2，陈梅1,2，戴震宇1,2，朱明3. 一种面向工作负载预测的基于小波变换的特征提取方法[J]. 计算机与现代化, 2020, 0(05): 1-.

WANG Ke1,2, LI Hui1,2, CHEN Mei1,2, DAI Zhen-yu1,2, ZHU Ming3. A Wavelet Transform-based Feature Extraction Method for Workload Prediction[J]. Computer and Modernization, 2020, 0(05): 1-.

参考文献

［1］ TATBUL N, CETINTEMEL U, ZDONIK S, et al. Load shedding in a data stream manager［C］// Proceedings of the 29th International Conference on Very Large Data Bases. 2003:309-320.
［2］ CHI Y, YU P S, WANG H X, et al. Loadstar: A load shedding scheme for classifying data streams［C］// Proceedings of the 2005 SIAM International Conference on Data Mining. 2005:346-357.
［3］ BABCOCK B, DATAR M, MOTWANI R. Load shedding for aggregation queries over data streams［C］// Proceedings of the 20th International Conference on Data Engineering. 2004:350-361.
［4］ BABCOCK B, BABU S, DATAR M, et al. Models and issues in data stream systems［C］// Proceedings of the 21st ACM SIGMOD-SIGACT-SIGART Symposium on Principles of Database Systems. 2002:1-16.
［5］ ABADI D J, CARNEY D, CETINITEMEL U, et al. Aurora: A new model and architecture for data stream management［J］. The International Journal on Very Large Data Bases, 2003,12(2):120-139.
［6］ DAS A, GEHRKE J, RIEDEWALD M. Approximate join processing over data streams［C］// Proceedings of the 2003 ACM SIGMOD International Conference on Management of Data. 2003:40-51.
［7］ WANG H X, FAN W, YU P S, et al. Mining concept-drifting data streams using ensemble classifiers［C］// Proceedings of the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2003:226-235.
［8］ GEDIK B, WU K L, YU P S, et al. Adaptive load shedding for windowed stream joins［C］// Proceedings of the 14th ACM International Conference on Information and Knowledge Management. 2005:171-178.
［9］ CARNEY D, CETINTEMEL U, CHERNIACK M, et al. Monitoring streams: A new class of data management applications［C］// Proceedings of the 28th International Conference on Very Large Data Bases. 2002:215-226.
［10］GILBERT A C, KOTIDIS Y, MUTHUKRISHNAN S, et al. One-pass wavelet decompositions of data streams［J］. IEEE Transactions on Knowledge and Data Engineering, 2003,15(3):541-554.
［11］GABER M M, ZASLAVSKY A, KRISHNASWAMY S. Mining data streams: A review［J］. ACM SIGMOD Record, 2005,34(2):18-26.
［12］陈华辉,施伯乐,钱江波,等. 基于小波概要的并行数据流聚类［J］. 软件学报, 2010,21(4):644-658.
［13］BOX G E P, JENKINS G M. Time Series Analysis: Forecasting and Control［M］. San Francisco: Holden-Day, 1970.
［14］HIPEL K W, MCLEOD A I. Time Series Modelling of Water Resources and Environmental Systems［M］. Amsterdam: Elsevier, 1994.
［15］DAUBECHIES I. Ten Lectures on Wavelets［M］. Philadelphia: Society for Industrial and Applied Mathematics, 1992.
［16］HOLSCHNEIDER M. Wavelets: An Analysis Tool［M］. Oxford: Oxford Science Publications, 1995.
［17］CHUI C K. An Introduction to Wavelets［M］. San Diego: Academic Press, 1992.
［18］ZHANG H, HO T B, ZHANG Y, et al. Unsupervised feature extraction for time series clustering using orthogonal wavelet transform［J］. Informatica, 2006,30(3):305-319.
［19］POPIVANOV I, MILLER R J. Similarity search over time-series data using wavelets［C］// Proceedings of the 18th International Conference on Data Engineering. 2002:212-221.
［20］CHAN F K P, FU A W C, YU C. Harr wavelets for efficient similarity search of time-series: With and without time warping［J］. IEEE Transactions on Knowledge and Data Engineering, 2003,15(3):686-705.
［21］WYSE N, DUBES R, JAIN A K. A critical evaluation of intrinsic dimensionality algorithms［M］// Pattern Recognition in Practice. San Mateo: Morgan Kaufmann Publishers, 1980:415-425.
［22］ZHOU M, WONG M H. Efficient online subsequence searching in data streams under dynamic time warping distance［C］// Proceedings of the 24th International Conference on Data Engineering. 2008:686-695.
［23］李正欣,张凤鸣,李克武,等. 一种支持DTW距离的多元时间序列索引结构［J］. 软件学报, 2014,25(3):560-575.
［24］DELFINO B, MASSUCCO S, MORINI A, et al. Implementation and comparison of different under frequency load-shedding schemes［C］// Proceedings of the 2001 IEEE Power Engineering Society Summer Meeting. 2001,1:307-312.

[1]	张晓东1, 白广芝1, 李敏1, 李昊洋2. 基于经验小波变换的油气井产量预测模型 [J]. 计算机与现代化, 2024, 0(12): 53-58.
[2]	刘云海1, 冯广1, 吴晓婷2, 杨群2. 复杂施工场景下的安全帽佩戴检测算法[J]. 计算机与现代化, 2024, 0(12): 66-71.
[3]	余晨曦, 谷林. 基于人体骨架的电梯内异常行为识别预警[J]. 计算机与现代化, 2024, 0(09): 114-120.
[4]	岳有军1, 2, 张远锟1, 赵辉1, 2, 王红君1, 2. 基于多尺度特征与注意力模块的室内场景识别方法[J]. 计算机与现代化, 2024, 0(08): 37-42.
[5]	赵小明, 潘婷, 刘伟锋. 基于图像分类的自动绘画心理分析方法[J]. 计算机与现代化, 2024, 0(08): 92-97.
[6]	武丽1, 张征浩2, 葛彩成2, 俞俊2. 基于改进SCNN网络的车道线检测算法[J]. 计算机与现代化, 2024, 0(07): 87-92.
[7]	周超, 丛鑫, 訾玲玲, 肖谷平. 基于DNN与注意力机制的推荐算法模型[J]. 计算机与现代化, 2024, 0(06): 1-7.
[8]	刘力霈, 杨晓利, 李振伟. 基于边中心网络特征提取的癫痫脑电分类研究[J]. 计算机与现代化, 2024, 0(05): 22-26.
[9]	袁世一. 基于经验模态分解与极限学习机的粮食产量模型预测[J]. 计算机与现代化, 2024, 0(03): 47-53.
[10]	王秋忆, 周浩, 郑婷婷. 改进RetinaNet的电力设备目标检测方法[J]. 计算机与现代化, 2024, 0(01): 47-52.
[11]	周成诚, 曾庆军, 杨康, 胡家铭, 韩春伟. 基于高效通道注意力模块的运动想象脑电识别[J]. 计算机与现代化, 2023, 0(12): 19-23.
[12]	杨柳青, 王冲. 基于极大熵的Web服务资源个性化推荐方法[J]. 计算机与现代化, 2023, 0(09): 32-37.
[13]	胡睿杰, 车逗. 红外小目标检测方法综述[J]. 计算机与现代化, 2023, 0(08): 79-86.
[14]	王欣怡, 尹四清, 洪军. 融合注意力机制的非对称深度监督哈希[J]. 计算机与现代化, 2023, 0(05): 26-31.
[15]	潘凤, 王杰, 张艳莎, 谭棉, 何兴, 王林, . 基于双分支特征拼接的行人重识别[J]. 计算机与现代化, 2023, 0(05): 93-99.

一种面向工作负载预测的基于小波变换的特征提取方法

A Wavelet Transform-based Feature Extraction Method for Workload Prediction

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价