ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login

An algorithm for using distributed computing resources based on the Edge computing principles

Journal: Software & Systems (Vol.36, No. 1)

Publication Date:

Authors : ; ; ;

Page : 107-114

Keywords : calculation offload; rest api; virtual machine; asynchronous calls; amqp; messaging bus; distributed computing;

Source : Downloadexternal Find it from : Google Scholarexternal

Abstract

The article describes the issues of implementing the algorithm for distributing computational tasks over a set of distributed computing resources with subsequent aggregation of the results. This algorithm is the key one in the framework of the data center implementation project based on the sharing economy principles. The mechanism prototype is implemented in Python 3.8 using the PostgreSQL 14 DBMS, the message passing system is implemented on the basis of RabbitMQ 3.9, the computing node platform is CentOS 8 Stream OS. The purpose of the work is to implement a scalable distributed computing mechanism for using as the main instrument of task distribution and aggregation of results within the framework of the data center concept based on the sharing economy principles. The subject of the study is the methods of computing power redundancy and use, aggregation of the working results of software algorithms. The proposed mechanism solves the computing distribution problem with subsequent aggregation of results among computing nodes with different technical characteristics. There is an implemented interface suitable for integrating into client information systems as a means of uploading calculations with access in the REST API gateway format. The theoretical significance of the work is in combining the existing principles and ideas of Edge computing to solve a different class of problems, where the problem is the lack of a computing resource for information system tasks, and not insufficient characteristics of the existing model. The practical significance is in the development of an application tool for using external computing power to solve a wide class of client tasks, which gives the possibility of organizing commercial interaction between owners of unused computing resources and owners of information systems that lack computing power.

Last modified: 2023-08-07 19:52:40