Generating Complex, Realistic Cloud Workloads using Recurrent Neural Networks

被引：9

作者：

Bergsma, Shane ^{[1
]}

Zeyl, Timothy ^{[1
]}

Senderovich, Arik ^{[2
]}

Beck, J. Christopher ^{[2
]}

机构：

[1] Huawei Res, Vancouver, BC, Canada

[2] Univ Toronto, Toronto, ON, Canada

来源：

PROCEEDINGS OF THE 28TH ACM SYMPOSIUM ON OPERATING SYSTEMS PRINCIPLES, SOSP 2021 | 2021年

关键词：

cloud workload modeling; trace generation; recurrent neural networks; deep learning; survival analysis;

D O I：

10.1145/3477132.3483590

中图分类号：

TP31 [计算机软件];

学科分类号：

081202 ; 0835 ;

摘要：

Decision-making in large-scale compute clouds relies on accurate workload modeling. Unfortunately, prior models have proven insufficient in capturing the complex correlations in real cloud workloads. We introduce the first model of large-scale cloud workloads that captures long-range interjob correlations in arrival rates, resource requirements, and lifetimes. Our approach models workload as a three-stage generative process, with separate models for: (1) the number of batch arrivals over time, (2) the sequence of requested resources, and (3) the sequence of lifetimes. Our lifetime model is a novel extension of recent work in neural survival prediction. It represents and exploits inter-job correlations using a recurrent neural network. We validate our approach by showing it is able to accurately generate the production virtual machine workload of two real-world cloud providers.

引用

页码：376 / 391

页数：16

共 50 条

[11] Generation of Realistic Navigation Paths for Web Site Testing Using Recurrent Neural Networks and Generative Adversarial Neural Networks
Pavanetto, Silvio
Brambilla, Marco
WEB ENGINEERING, ICWE 2020, 2020, 12128 : 244 - 258
[12] Modeling and Forecasting Http Requests-Based Cloud Workloads Using Autoregressive Artificial Neural Networks
Syu, Yang
Wang, Chien-Min
PROCEEDINGS OF 2018 3RD INTERNATIONAL CONFERENCE ON COMPUTER AND COMMUNICATION SYSTEMS (ICCCS), 2018, : 139 - 145
[13] Robust Pinning Control of Complex Dynamical Networks using Recurrent Neural Networks
Sanchez, Edgar N.
Rodriguez, David I.
2014 IEEE SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE IN CONTROL AND AUTOMATION (CICA), 2014, : 83 - 89
[14] Complex Gated Recurrent Neural Networks
Wolter, Moritz
Yao, Angela
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 2018, 31
[15] CloudMix: Generating Diverse and Reducible Workloads for Cloud Systems
Han, Rui
Zong, Zan
Zhang, Fan
Luis Vazquez-Poletti, Jose
Jia, Zhen
Wang, Lei
2017 IEEE 10TH INTERNATIONAL CONFERENCE ON CLOUD COMPUTING (CLOUD), 2017, : 496 - 503
[16] Generating Image Captions in Arabic Using Root-Word Based Recurrent Neural Networks and Deep Neural Networks
Jindal, Vasu
THIRTY-SECOND AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTIETH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / EIGHTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2018, : 8093 - 8094
[17] Predicting Host CPU Utilization in Cloud Computing using Recurrent Neural Networks
Duggan, Martin
Mason, Karl
Duggan, Jim
Howley, Enda
Barrett, Enda
2017 12TH INTERNATIONAL CONFERENCE FOR INTERNET TECHNOLOGY AND SECURED TRANSACTIONS (ICITST), 2017, : 67 - 72
[18] Generating pseudo well logs for a part of the upper Bakken using recurrent neural networks
Tatsipie, Nelson R. K.
Sheng, James J.
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING, 2021, 200
[19] Complex Unitary Recurrent Neural Networks Using Scaled Cayley Transform
Maduranga, Kehelwala D. G.
Helfrich, Kyle E.
Ye, Qiang
THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, : 4528 - 4535
[20] Generating Realistic Aircraft Trajectories Using Generative Adversarial Networks
Lukes, Petr
Kulmon, Pavel
2023 24TH INTERNATIONAL RADAR SYMPOSIUM, IRS, 2023,

← 1 2 3 4 5 →