Large Data Transfer Predictability and Forecasting using Application-Aware SDN

Deepak Nadig, Byrav Ramamurthy, Brian Bockelman, David R Swanson

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Network management for applications that rely on large-scale data transfers is challenging due to the volatility and the dynamic nature of the access traffic patterns. Predictive analytics and forecasting play an important role in providing effective resource allocation strategies for large data transfers. We propose a predictive analytics solution for large data transfers using an application-aware software defined networking (SDN) approach. We perform extensive exploratory data analysis to characterize the GridFTP connection transfers dataset and present various strategies for its use with statistical forecasting models. We develop a univariate autoregressive integrated moving average (ARIMA) based prediction framework for forecasting GridFTP connection transfers. Our prediction model tightly integrates with an application-aware SDN solution to preemptively drive network management decisions for GridFTP resource allocation at a U.S. CMS Tier-2 site. Further, our framework has a mean absolute percentage error (MAPE) ranging from 6% to 10% when applied to make rolling forecasts.

Original languageEnglish (US)
Title of host publication2018 IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2018
PublisherIEEE Computer Society
ISBN (Electronic)9781538681343
DOIs
StatePublished - May 8 2019
Event12th IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2018 - Indore, India
Duration: Dec 16 2018Dec 19 2018

Publication series

NameInternational Symposium on Advanced Networks and Telecommunication Systems, ANTS
Volume2018-December
ISSN (Print)2153-1684

Conference

Conference12th IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2018
CountryIndia
CityIndore
Period12/16/1812/19/18

Fingerprint

data exchange
Data transfer
networking
Network management
management decision
Resource allocation
resources
data analysis
traffic
present
management
software
Software defined networking

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Communication

Cite this

Nadig, D., Ramamurthy, B., Bockelman, B., & Swanson, D. R. (2019). Large Data Transfer Predictability and Forecasting using Application-Aware SDN. In 2018 IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2018 [8710165] (International Symposium on Advanced Networks and Telecommunication Systems, ANTS; Vol. 2018-December). IEEE Computer Society. https://doi.org/10.1109/ANTS.2018.8710165

Large Data Transfer Predictability and Forecasting using Application-Aware SDN. / Nadig, Deepak; Ramamurthy, Byrav; Bockelman, Brian; Swanson, David R.

2018 IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2018. IEEE Computer Society, 2019. 8710165 (International Symposium on Advanced Networks and Telecommunication Systems, ANTS; Vol. 2018-December).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nadig, D, Ramamurthy, B, Bockelman, B & Swanson, DR 2019, Large Data Transfer Predictability and Forecasting using Application-Aware SDN. in 2018 IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2018., 8710165, International Symposium on Advanced Networks and Telecommunication Systems, ANTS, vol. 2018-December, IEEE Computer Society, 12th IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2018, Indore, India, 12/16/18. https://doi.org/10.1109/ANTS.2018.8710165
Nadig D, Ramamurthy B, Bockelman B, Swanson DR. Large Data Transfer Predictability and Forecasting using Application-Aware SDN. In 2018 IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2018. IEEE Computer Society. 2019. 8710165. (International Symposium on Advanced Networks and Telecommunication Systems, ANTS). https://doi.org/10.1109/ANTS.2018.8710165
Nadig, Deepak ; Ramamurthy, Byrav ; Bockelman, Brian ; Swanson, David R. / Large Data Transfer Predictability and Forecasting using Application-Aware SDN. 2018 IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2018. IEEE Computer Society, 2019. (International Symposium on Advanced Networks and Telecommunication Systems, ANTS).
@inproceedings{a7b8fa38c8084c2485f9221f9e1813aa,
title = "Large Data Transfer Predictability and Forecasting using Application-Aware SDN",
abstract = "Network management for applications that rely on large-scale data transfers is challenging due to the volatility and the dynamic nature of the access traffic patterns. Predictive analytics and forecasting play an important role in providing effective resource allocation strategies for large data transfers. We propose a predictive analytics solution for large data transfers using an application-aware software defined networking (SDN) approach. We perform extensive exploratory data analysis to characterize the GridFTP connection transfers dataset and present various strategies for its use with statistical forecasting models. We develop a univariate autoregressive integrated moving average (ARIMA) based prediction framework for forecasting GridFTP connection transfers. Our prediction model tightly integrates with an application-aware SDN solution to preemptively drive network management decisions for GridFTP resource allocation at a U.S. CMS Tier-2 site. Further, our framework has a mean absolute percentage error (MAPE) ranging from 6{\%} to 10{\%} when applied to make rolling forecasts.",
author = "Deepak Nadig and Byrav Ramamurthy and Brian Bockelman and Swanson, {David R}",
year = "2019",
month = "5",
day = "8",
doi = "10.1109/ANTS.2018.8710165",
language = "English (US)",
series = "International Symposium on Advanced Networks and Telecommunication Systems, ANTS",
publisher = "IEEE Computer Society",
booktitle = "2018 IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2018",

}

TY - GEN

T1 - Large Data Transfer Predictability and Forecasting using Application-Aware SDN

AU - Nadig, Deepak

AU - Ramamurthy, Byrav

AU - Bockelman, Brian

AU - Swanson, David R

PY - 2019/5/8

Y1 - 2019/5/8

N2 - Network management for applications that rely on large-scale data transfers is challenging due to the volatility and the dynamic nature of the access traffic patterns. Predictive analytics and forecasting play an important role in providing effective resource allocation strategies for large data transfers. We propose a predictive analytics solution for large data transfers using an application-aware software defined networking (SDN) approach. We perform extensive exploratory data analysis to characterize the GridFTP connection transfers dataset and present various strategies for its use with statistical forecasting models. We develop a univariate autoregressive integrated moving average (ARIMA) based prediction framework for forecasting GridFTP connection transfers. Our prediction model tightly integrates with an application-aware SDN solution to preemptively drive network management decisions for GridFTP resource allocation at a U.S. CMS Tier-2 site. Further, our framework has a mean absolute percentage error (MAPE) ranging from 6% to 10% when applied to make rolling forecasts.

AB - Network management for applications that rely on large-scale data transfers is challenging due to the volatility and the dynamic nature of the access traffic patterns. Predictive analytics and forecasting play an important role in providing effective resource allocation strategies for large data transfers. We propose a predictive analytics solution for large data transfers using an application-aware software defined networking (SDN) approach. We perform extensive exploratory data analysis to characterize the GridFTP connection transfers dataset and present various strategies for its use with statistical forecasting models. We develop a univariate autoregressive integrated moving average (ARIMA) based prediction framework for forecasting GridFTP connection transfers. Our prediction model tightly integrates with an application-aware SDN solution to preemptively drive network management decisions for GridFTP resource allocation at a U.S. CMS Tier-2 site. Further, our framework has a mean absolute percentage error (MAPE) ranging from 6% to 10% when applied to make rolling forecasts.

UR - http://www.scopus.com/inward/record.url?scp=85066024106&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066024106&partnerID=8YFLogxK

U2 - 10.1109/ANTS.2018.8710165

DO - 10.1109/ANTS.2018.8710165

M3 - Conference contribution

T3 - International Symposium on Advanced Networks and Telecommunication Systems, ANTS

BT - 2018 IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2018

PB - IEEE Computer Society

ER -