The Development of a Parallel Ray Launching Algorithm for Wireless Network Planning

Authors:
Nik Bessis;Gordon J. Clapworthy;Zhihua Lai;Guillaume De La Roche;Pierre Kuonen;Jie Zhang
Affiliations:
University of Bedfordshire, UK;University of Bedfordshire, UK;University of Bedfordshire, UK;University of Applied Science of Western Switzerland, Switzerland;University of Applied Science of Western Switzerland, Switzerland;University of Bedfordshire, UK
Venue:
International Journal of Distributed Systems and Technologies
Year:
2011

Citing 7
Cited 0

Parallel Scientific Computation: A Structured Approach Using BSP and MPI

Parallel Scientific Computation: A Structured Approach Using BSP and MPI
The Grid 2: Blueprint for a New Computing Infrastructure

The Grid 2: Blueprint for a New Computing Infrastructure
Operating System Concepts

Operating System Concepts
Programming the grid with POP-C++

Future Generation Computer Systems - Special section: Data mining in grid computing environments
Essentials of Radio Wave Propagation

Essentials of Radio Wave Propagation
A Performance Evaluation of a Grid-Enabled Object-Oriented Parallel Outdoor Ray Launching for Wireless Network Coverage Prediction

ICWMC '09 Proceedings of the 2009 Fifth International Conference on Wireless and Mobile Communications
Femtocells: Technologies and Deployment

Femtocells: Technologies and Deployment

Quantified Score

Hi-index	0.00

Visualization

Abstract

Propagation modeling has attracted much interest because it plays an important role in wireless network planning and optimization. Deterministic approaches such as ray tracing and ray launching have been investigated, however, due to the running time constraint, these approaches are still not widely used. In previous work, an intelligent ray launching algorithm, namely IRLA, has been proposed. The IRLA has proven to be a fast and accurate algorithm and adapts to wireless network planning well. This article focuses on the development of a parallel ray launching algorithm based on the IRLA. Simulations are implemented, and evaluated performance shows that the parallelization greatly shortens the running time. The COST231 Munich scenario is adopted to verify algorithm behavior in real world environments, and observed results show a 5 times increased speedup upon a 16-processor cluster. In addition, the parallelization algorithm can be easily extended to larger scenarios with sufficient physical resources.