Long Short Term Memory Recurrent Neural Network (LSTM-RNN) Based Workload Forecasting Model For Cloud Datacenters

被引：221

作者：

Kumar, Jitendra ^{[1
]}

Goomer, Rimsha ^{[2
]}

Singh, Ashutosh Kumar ^{[1
]}

机构：

[1] Natl Inst Technol, Dept Comp Applicat, Kurukshetra, Haryana, India

[2] Univ Southern Calif, Dept Comp Sci, Viterbi Sch Engn, Los Angeles, CA USA

来源：

6TH INTERNATIONAL CONFERENCE ON SMART COMPUTING AND COMMUNICATIONS | 2018年 / 125卷

关键词：

Cloud Computing; Resource Scaling; Forecasting; Deep Learning;

D O I：

10.1016/j.procs.2017.12.087

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

In spite of various gains, cloud computing has got few challenges and issues including dynamic resource scaling and power consumption. Such affairs cause a cloud system to be fragile and expensive. In this paper we address both issues in cloud datacenter through workload prediction. The workload prediction model is developed using long short term memory (LSTM) networks. The proposed model is tested on three benchmark datasets of web server logs. The empirical results show that the proposed method achieved high accuracy in predictions by reducing the mean squared error up to 3.17 x 10(-3). (C) 2018 The Authors. Published by Elsevier B.V.

引用

页码：676 / 682

页数：7

共 20 条

[1]

[Anonymous], REFERENTIAL KNN REGR

[2] Dual time-scale distributed capacity allocation and load redirect algorithms for cloud systems [J].