Distributed and Parallel Net Imaging

TL;DR

This paper presents a distributed, parallel imaging system designed for large-scale astronomical data analysis, enabling real-time detection of luminosity variations with high data throughput using a network of standard workstations.

Contribution

It introduces a novel distributed parallel network architecture for real-time astronomical imaging and event detection, capable of handling terabytes of data daily.

Findings

Supports up to 256 workstations for large-scale data processing

Enables online discrimination of interesting astronomical events

Manages many terabytes of data per day efficiently

Abstract

A very complex vision system is developed to detect luminosity variations connected with the discovery of new planets in the Universe. The traditional imaging system can not manage a so large load. A private net is implemented to perform an automatic vision and decision architecture. It lets to carry out an on-line discrimination of interesting events by using two levels of triggers. This system can even manage many Tbytes of data per day. The architecture avails itself of a distributed parallel network system based on a maximum of 256 standard workstations with Microsoft Window as OS.