Real-Time Radio Wave Propagation for Mobile Ad-Hoc Network Emulation and Simulation Using General Purpose Graphics Processing Units (GPGPUs)

Abstract

Large scale experimentation and analysis of mobile ad-hoc networks (MANETs) is an expensive and time consuming task. Even with the best planning, the environment at the time of the experiment is unpredictable, making large scale controlled experiments impossible to perform. By simulating the physical medium it is possible to create a repeatable environment. Real-time radio wave propagation path loss calculations are a key component in creating a virtual environment for MANET simulation, emulation and experimentation. There are many algorithms available for computing the radio wave propagation path loss. In this paper we investigate the use of the Longley-Rice model computed using graphics processing units (GPUs). The goal of this effort is to solve the Longley-Rice algorithm in real-time for thousands of transmitters and receivers. We will discuss the choice of the Longley-Rice algorithm, algorithm modification for GPUs, precision issues and optimization. This method will be demonstrated in the context of a dedicated high performance computing system for MANET simulation, emulation and experimentation.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 01, 2014
Accession Number
ADA601670

Entities

People

  • Brian J. Heinz
  • Dale R. Shires
  • David Richie
  • Song J. Park

Organizations

  • United States Army Research Laboratory

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Ad Hoc Networks
  • Algorithms
  • Application Software
  • Computer Programs
  • Computers
  • Floating Point Operations
  • Graphics
  • Graphics Processing Unit
  • High Performance Computing
  • Kernels (Operating System)
  • Mesh Networks
  • Military Research
  • Mobile Ad Hoc Networks
  • Network Emulation
  • Radio Waves
  • Simulations
  • Wave Propagation

Fields of Study

  • Computer science
  • Physics

Readers

  • Computer Networking
  • Parallel and Distributed Computing.
  • Space/Atmospheric Physics.