A Competitive-Market Approach to Distributed Resource Allocation

Abstract

Resource allocation is an issue in any system for which resources are in short supply. In computer networks, the resources in question are bandwidth, buffer space, and processing time, and they are allocated at multiple scales of time and quantity (e.g. from a single user's packets over a 30 second interval to a network providers backbone capacity for a 1 year interval). For military networks and computers, these resources may be scarce or limited during attack, at remote sites, etc. Decisions about resource allocation should be made in accordance with some overall policy. In many instances, this policy is referred to as the "fairness" in making resource allocation decisions. A policy that is reasonable in one situation (e.g., "normally, everyone shares equally the available bandwidth') may be unsuitable in another situation (e.g., "in times of emergency, high priority tasks get their bandwidth requests satisfied before low priority tasks are considered"). In this report, we summarize the progress we have made in applying resource pricing principles to network and computer resource allocation. In each section we explain what we did, and why it is useful, followed by a list of the "outputs" of that effort. We conclude by summarizing the major findings, and describing some future directions and open problems.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 2002
Accession Number
ADA410933

Entities

People

  • Douglas S. Reeves

Organizations

  • North Carolina State University

Tags

Communities of Interest

  • Cyber

DTIC Thesaurus Topics

  • Bandwidth
  • Communication Systems
  • Computer Communications
  • Computer Network Security
  • Computer Networks
  • Computer Science
  • Computers
  • Denial Of Service Attack
  • Economic Impact
  • Engineering
  • Information Security
  • Internet
  • Intervals
  • Motivation
  • Network Protocols
  • Networks
  • Standards

Fields of Study

  • Computer science

Readers

  • Economics
  • Parallel and Distributed Computing.
  • Systems Analysis and Design

Technology Areas

  • Space