Parallel GPU Processing for Fast Radio Signal Propagation Computation in GRASS-RaPlaT (original) (raw)

GPU computation acceleration of GRASS GIS modules for predicting radio-propagation

2015

GPGPU (General-Purpose Computing on Graphics Processing Units) is a parallel computation technique that has become very popular with the advent of high performance and relatively low priced programmable GPU (Graphics Processing Unit) adapters and of the software tools required for general computing (compilers for computing languages such as OpenCL, etc.). GPU computing can offer massive computation acceleration for algorithms that fulfill certain requirements and map well to the GPU architecture. GPUs were originally developed for displaying and processing raster images, and so can be applied efficiently for fast processing of the rasterized geographic and other maps used in geographic information systems such as GRASS GIS (Geographic Resources Analysis Support System / Geographic Information System). GRASS-RaPlaT (Radio Planning Tool for GRASS) is a GRASS add-on for simulating radio signal propagation in actual geographic environments. In the case of large areas and relatively high...

A GRASS GIS parallel module for radio-propagation predictions

International Journal of Geographical Information Science, 2014

Geographical information systems are ideal candidates for the application of parallel programming techniques, mainly because they usually handle large data sets. To help us deal with complex calculations over such data sets, we investigated the performance constraints of a classic master-worker parallel paradigm over a message-passing communication model. To this end, we present a new approach that employs an external database in order to improve the calculation/communication overlap, thus reducing the idle times for the worker processes. The presented approach is implemented as part of a parallel radio-coverage prediction tool for the GRASS environment. The prediction calculation employs digital elevation models and land-usage data in order to analyze the radio coverage of a geographical area. We provide an extended analysis of the experimental results, which are based on real data from an LTE network currently deployed in Slovenia. Based on the results of the experiments, which were performed on a computer cluster, the new approach exhibits better scalability than the traditional master-worker approach. We successfully tackled real-world data sets, while greatly reducing the processing time and saturating the hardware utilization.

GPU performance impact of the Durkin's radio propagation algorithm

2013 21st Telecommunications Forum Telfor (TELFOR), 2013

Network simulators are important tools when used by researchers. However, complex simulations for largescale networks (especially if the scenarios are realistic, i.e. introducing terrain details) results in unreasonably long response from the simulator. High performance parallel resources like GPU devices are solution for obtaining results in reasonable time. Additionally, the latest GPU generations have architecture that enables the developer to configure different input parameters, in order to achieve better performance. In this paper we evaluate the performance impact of these configurations for various resolutions of terrains. The obtained results show that there is an impact on the performance, however it is not significant.

GRASS-RaPlaT − an Open-Source Tool for Radio Coverage Calculations

network is a complex and expensive task which requires careful planning to achieve the required radio signal coverage. Commercial radio network planning tools are available, but they are expensive and inflexible in the sense that they are often limited to a particular radio network technology, its frequency band(s) and a fixed set of channel models. This led us to develop an open-source radio coverage simulation tool with user-extendible set of radio propagation models, which is especially suitable for research work but at the same time also for professional communication network planning. The tool, GRASS-RaPlaT, is based on the open-source Geographical Resources Analysis Support System (GRASS) and currently includes modules for a number of channel models, a module for sectorization according to given antenna radiation patterns, a module for calculating and storing the complete radio network coverage data, and a number of supporting modules, e.g. for adapting input data and analyzin...

Parallel Cellular Automata Based Simulation of Radio Signal Propagation

Environmental monitoring is an increasing interest due to serious impacts of climate change on socioeconomic factors and human health. In these applications, radio links are the key technology allowing sensors to connect into networks that can operate on various topologies and ranges. In this paper we propose a framework for easing exploration of radio link possibilities, taking into account geographical topologies. Massive parallel execution on GPUs and cellular method were utilized in order to compute radio propagation and estimate the strength of received power. Several physical simulations could be federated for evaluating their consistency related to the described phenomena.

3-D Ray Tracing Based GPU Accelerated Field Prediction Radio Channel Simulator

2019 IEEE 89th Vehicular Technology Conference (VTC2019-Spring), 2019

A ray tracing simulator for urban and indoor environments is introduced. The simulator uses NVIDIA graphics processing unit (GPU) accelerated CUDA parallel computing platform and programming mode and the OptiX Ray Tracing Engine. As a use case, channel characteristics for Global Navigation Satellite System (GNSS) satellites are simulated and compared with measurements in an urban area. The speedup achieved by parallel processing allows computation of multiple relevant reflections characteristic of a satellite channel.

Radio coverage calculations of terrestrial wireless networks using an open-source GRASS system

WSEAS Transactions on Communications

Radio network planning and dimensioning have significant impact on the overall system capacity of the cellular communication systems. Various commercial network planning and dimensioning tools with different radio signal propagation models implemented are available on the market. Their price and especially inflexibility led us to look for an open-source solution. The present paper describes usage of the open-source Geographical Resources Analysis Support System (GRASS) for the radio signal coverage calculation. GRASS modules calculating radio coverage prediction for a number of different radio channel models were developed which, together with module considering antenna radiation pattern influence, compute radio signal coverage for a defined cell. The complete network coverage is computed with modules for generating a data base table (e.g. MySQL, PostgreSQL), arranging the values in increasing order and determining maximal received power at each receive location. Additional modules ...

Using Cray T3E for the parallel calculation of cellular radio coverage

1998

A ray tracing based cellular coverage simulator has been parallelized in order to speed up excecution. The simulator has been developed for accurate prediction of radio wave propagation in urban microcells. It combines a vertical plane model simulating the wave propagation over the buildings and a horizontal plane model simulating the wave propagation in the street canyons between the buildings. The horizontal plane calculation is made by ray tracing using multiple diffractions around the corners of building. The parallel version has been implemented for a distributed memory machine, CRAY T3E. Parallelization of the vertical and horizontal plane calculations reduces the execution times considerably. Results indicate that only a small number of processors are required for efficient parallel execution. The load balancing algorithm has an important role in obtaining good speedups.

Parallel radio-wave propagation modeling with image-based ray tracing techniques

2010

Ray tracing is a technique based on the numerical simulation of geometrical optics and the uniform theory of diffraction, two well-known approximate methods for estimating a highfrequency electromagnetic field, based on the ray theory of field propagation. Radio-wave propagation prediction models based on ray tracing play an important role in wireless network planning, as they take into account diverse physical phenomena such as reflection, diffraction and foliage attenuation and are considered critical for the analysis of long term evolution (LTE) systems, which requires a detailed description of the wireless channel. A major practical drawback of these models is that they can easily become very computationally expensive, as the required level of accuracy and the corresponding areas of study increase.

PARALLELIZATION OF PROPAGATION MODEL SIMULATION

In this paper a sequential radio wave propagation simulator has been parallelized in order to speed up the execution. Only outdoor propagation in microcells is considered in this simulator. The simulator combines a vertical plane model which simulates the wave propagation over the building roofs and a horizontal plane model which simulates the wave propagation in the street canyons between the buildings. The horizontal plane model is implemented as a ray tracing model using multiple diffraction. Two different parallel implementations have been used in two parallel platforms. Digital workstation with POSIX threads and Cray T3E with distributed memory were used. Simulator for Cray was implemented by using message passing since threads can not be used in distributed memory computer. Parallelization of the vertical and horizontal plane models reduces the execution times considerably as they are the most time consuming parts. Results for different environments are very promising. Significant speedup can be achieved in both tested parallel environments. Work required to gain good improvements is minimal compared to the received speedups.