skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Network Bandwidth Utilization Forecast Model on High Bandwidth Network

Abstract

With the increasing number of geographically distributed scientific collaborations and the scale of the data size growth, it has become more challenging for users to achieve the best possible network performance on a shared network. We have developed a forecast model to predict expected bandwidth utilization for high-bandwidth wide area network. The forecast model can improve the efficiency of resource utilization and scheduling data movements on high-bandwidth network to accommodate ever increasing data volume for large-scale scientific data applications. Univariate model is developed with STL and ARIMA on SNMP path utilization data. Compared with traditional approach such as Box-Jenkins methodology, our forecast model reduces computation time by 83.2percent. It also shows resilience against abrupt network usage change. The accuracy of the forecast model is within the standard deviation of the monitored measurements.

Authors:
;
Publication Date:
Research Org.:
Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
Sponsoring Org.:
Computational Research Division
OSTI Identifier:
1136782
Report Number(s):
LBNL-6677E
DOE Contract Number:
DE-AC02-05CH11231
Resource Type:
Technical Report
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; Forecasting, Network, Time series analysis

Citation Formats

Yoo, Wucherl, and Sim, Alex. Network Bandwidth Utilization Forecast Model on High Bandwidth Network. United States: N. p., 2014. Web. doi:10.2172/1136782.
Yoo, Wucherl, & Sim, Alex. Network Bandwidth Utilization Forecast Model on High Bandwidth Network. United States. doi:10.2172/1136782.
Yoo, Wucherl, and Sim, Alex. Mon . "Network Bandwidth Utilization Forecast Model on High Bandwidth Network". United States. doi:10.2172/1136782. https://www.osti.gov/servlets/purl/1136782.
@article{osti_1136782,
title = {Network Bandwidth Utilization Forecast Model on High Bandwidth Network},
author = {Yoo, Wucherl and Sim, Alex},
abstractNote = {With the increasing number of geographically distributed scientific collaborations and the scale of the data size growth, it has become more challenging for users to achieve the best possible network performance on a shared network. We have developed a forecast model to predict expected bandwidth utilization for high-bandwidth wide area network. The forecast model can improve the efficiency of resource utilization and scheduling data movements on high-bandwidth network to accommodate ever increasing data volume for large-scale scientific data applications. Univariate model is developed with STL and ARIMA on SNMP path utilization data. Compared with traditional approach such as Box-Jenkins methodology, our forecast model reduces computation time by 83.2percent. It also shows resilience against abrupt network usage change. The accuracy of the forecast model is within the standard deviation of the monitored measurements.},
doi = {10.2172/1136782},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Mon Jul 07 00:00:00 EDT 2014},
month = {Mon Jul 07 00:00:00 EDT 2014}
}

Technical Report:

Save / Share:
  • With the increasing number of geographically distributed scientific collaborations and the scale of the data size growth, it has become more challenging for users to achieve the best possible network performance on a shared network. We have developed a forecast model to predict expected bandwidth utilization for high-bandwidth wide area network. The forecast model can improve the efficiency of resource utilization and scheduling data movements on high-bandwidth network to accommodate ever increasing data volume for large-scale scientific data applications. Univariate model is developed with STL and ARIMA on SNMP path utilization data. Compared with traditional approach such as Box-Jenkins methodology,more » our forecast model reduces computation time by 83.2%. It also shows resilience against abrupt network usage change. The accuracy of the forecast model is within the standard deviation of the monitored measurements.« less
  • The choice of technologies for the delivery of very high bandwidth throughout a facility capable of ultimately achieving gigabits per second performance, is a crucial one for any high technology facility. The components of a high bandwidth delivery system include high performance sources and sinks in the form of central facilities (major mainframes, large file storage and specialized peripherals) and powerful, full bandwidth distributed local area networks (LANs). In order to deliver bandwidth among the sources and sinks, a ubiquitous inter-/intra-building cable plant consisting of single mode and multimode fiber as well as twisted pair copper is required. The selectionmore » of the glue'' to transport and interconnect the LANs with the central facility over the pervasive cable plant is the focus of this paper. A design philosophy for high performance communications systems is proposed. A description of the traditional problems that must be overcome to provide very high bandwidth beyond the narrow confines of a computer center is given. The advantages of ATM switching and SONET physical transport are explored in the structured design presentation. The applicability of Asynchronous Transfer Mode (ATM) switching (interconnection) and Synchronous Optical NETwork (SONET) (transport) for high bandwidth delivery is described using the environment and requirements of Sandia National Laboratories as a context to examine the suitability of those technologies. The synergy and utility of ATM and SONET in the campus network are explored. Other methods for distributing high data rates are compared and contrasted to ATM and SONET with respect to cable plant impact, reliability/availability, maintainability, and capacity. Sandia is implementing a standards based foundation utilizing a pervasive single mode fiber cable plant, SONET transport, and ATM switching to meet the goals of gigabit networking.« less
  • With the increasing number of geographically distributed scientific collaborations and the growing sizes of scientific data, it has become challenging for users to achieve the best possible network performance on a shared network. In this paper, we have developed a model to forecast expected bandwidth utilization on high-bandwidth wide area networks. The forecast model can improve the efficiency of the resource utilization and scheduling of data movements on high-bandwidth networks to accommodate ever increasing data volume for large-scale scientific data applications. A univariate time-series forecast model is developed with the Seasonal decomposition of Time series by Loess (STL) and themore » AutoRegressive Integrated Moving Average (ARIMA) on Simple Network Management Protocol (SNMP) path utilization measurement data. Compared with the traditional approach such as Box-Jenkins methodology to train the ARIMA model, our forecast model reduces computation time up to 92.6 %. It also shows resilience against abrupt network usage changes. Finally, our forecast model conducts the large number of multi-step forecast, and the forecast errors are within the mean absolute deviation (MAD) of the monitored measurements.« less
  • This compilation of diverse conservation and renewable energy projects across the United States was prepared through the enthusiastic participation of solar and alternate energy groups from every state and region. Compiled and edited by the Center for Renewable Resources, these projects reflect many levels of innovation and technical expertise. In many cases, a critique analysis is presented of how projects performed and of the institutional conditions associated with their success or failure. Some 2000 projects are included in this compilation; most have worked, some have not. Information about all is presented to aid learning from these experiences. The four volumesmore » in this set are arranged in state sections by geographic region, coinciding with the four Regional Solar Energy Centers. The table of contents is organized by project category so that maximum cross-referencing may be obtained. This volume includes information on the Western Solar Utilization Network Region. (WHK)« less
  • This paper presents pathChirp, a new active probing tool for estimating the available bandwidth on a communication network path. Based on the concept of ''self-induced congestion,'' pathChirp features an exponential flight pattern of probes we call a chirp. Packet chips offer several significant advantages over current probing schemes based on packet pairs or packet trains. By rapidly increasing the probing rate within each chirp, pathChirp obtains a rich set of information from which to dynamically estimate the available bandwidth. Since it uses only packet interarrival times for estimation, pathChirp does not require synchronous nor highly stable clocks at the sendermore » and receiver. We test pathChirp with simulations and Internet experiments and find that it provides good estimates of the available bandwidth while using only a fraction of the number of probe bytes that current state-of-the-art techniques use.« less