Currently, there are many different approaches for organization of the distributed calculations in computer network technology grid, metacomputing (BOINC, PVM, and others). The main drawback of most existing approaches is that they are designed to create centralized distributed computing systems. In this article we propose to organize the solution of such problems as multivariate modeling, through the creation of distributed computations in computer networks based on decentralized multi-agent system. When used as a computing environment a computer network on a large scale can cause threats to the security of distributed computing from the intruders. One of these threats is getting the calculation about the result by the attacker. A false result can leads in the modeling process to adopt is not optimal or wrong decisions. We developed a method of protecting distributed computing from the threat of receiving false result.
Machine Learning in a Multi-Agent System for Distributed Computing Management
