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

Title: pathChirp: Efficient Available Bandwidth Estimation for Network Paths

Abstract

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 sender 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.

Authors:
Publication Date:
Research Org.:
Stanford Linear Accelerator Center, Menlo Park, CA (US)
Sponsoring Org.:
USDOE Office of Science (US)
OSTI Identifier:
813038
Report Number(s):
SLAC-PUB-9732
TRN: US200315%%210
DOE Contract Number:
AC03-76SF00515
Resource Type:
Technical Report
Resource Relation:
Other Information: PBD: 30 Apr 2003
Country of Publication:
United States
Language:
English
Subject:
99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; P CODES; DATA TRANSMISSION; INTERNET; MONITORING

Citation Formats

Cottrell, Les. pathChirp: Efficient Available Bandwidth Estimation for Network Paths. United States: N. p., 2003. Web. doi:10.2172/813038.
Cottrell, Les. pathChirp: Efficient Available Bandwidth Estimation for Network Paths. United States. doi:10.2172/813038.
Cottrell, Les. Wed . "pathChirp: Efficient Available Bandwidth Estimation for Network Paths". United States. doi:10.2172/813038. https://www.osti.gov/servlets/purl/813038.
@article{osti_813038,
title = {pathChirp: Efficient Available Bandwidth Estimation for Network Paths},
author = {Cottrell, Les},
abstractNote = {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 sender 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.},
doi = {10.2172/813038},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Wed Apr 30 00:00:00 EDT 2003},
month = {Wed Apr 30 00:00:00 EDT 2003}
}

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 83.2percent. It also shows resilience against abrupt network usage change. The accuracy of the forecast model is within the standard deviation of the monitored measurements.« less
  • The authors address the problem of computing a multipath, consisting of possibly overlapping paths, to transmit data from the source node s to the destination node d over a computer network while ensuring deterministic bounds on end-to-end delay or delivery rate.They consider two generic routing problems within the framework wherein bandwidth can be reserved, and guaranteed, once reserved, on various links of the communication network. The first problem requires that a message of finite length be transmitted from s to d within {tau} units of time. The second problem requires that a sequential message of r units be transmitted atmore » a rate of {eta} such that maximum time difference between two units that are received out of order is no more than q. They propose a polynomial-time algorithm to the first problem based on an adaptation of the classical Ford-Fulkerson`s method. They present simulation results to illustrate the applicability of the proposed algorithm. They show the second problem to be NP-complete, and propose a polynomial-time approximately solution.« less
  • The U.S. Department of Energy (DOE) has set a goal to reduce the cost of seawater desalination systems to $0.50/ cubic meter (m 3) through the development of technology pathways to reduce energy, capital, operating, soft, and system integration costs.1 In support of this goal and to evaluate the technology pathways to lower the energy and carbon intensity of desalination while also reducing the total water cost, DOE is undertaking a comprehensive study of the energy consumption and carbon dioxide (CO 2) emissions for desalination technologies and systems. This study is being undertaken in two phases. Phase 1, Survey ofmore » Available Information in Support of the Energy-Water Bandwidth Study of Desalination Systems, collected the background information that will underpin Phase 2, the Energy Water Bandwidth Study for Desalination Systems. This report (Volume 1) summarizes the results from Phase 1. The results from Phase 2 will be summarized in Volume 2: Energy Water Bandwidth Study for Desalination Systems (Volume 2). The analysis effort for Phase 2 will utilize similar methods as other industry-specific Energy Bandwidth Studies developed by DOE,2 which has provided a framework to evaluate and compare energy savings potentials within and across manufacturing sectors at the macroscale. Volume 2 will assess the current state of desalination energy intensity and reduction potential through the use of advanced and emerging technologies. For the purpose of both phases of study, energy intensity is defined as the amount of energy required per unit of product water output (for example, kilowatt-hours per cubic meter of water produced). These studies will expand the scope of previous sectorial bandwidth studies by also evaluating CO 2 intensity and reduction opportunities and informing a techno-economic analysis of desalination systems. Volume 2 is expected to be completed in 2017.« 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
  • This report unveils new algorithms for actively measuring (not estimating) available bandwidths with very low intrusion, computing cross traffic, thus estimating the physical bandwidth, provides mathematical proof that the algorithms are accurate, and addresses conditions, requirements, and limitations for new and existing algorithms for measuring network bandwidths. The paper also discusses a number of important terminologies and issues for network bandwidth measurement, and introduces a fundamental parameter -Maximum Burst Size that is critical for implementing algorithms based on multiple packets.