Method and Algorithms for Adaptive Multiagent Resource Scheduling in Heterogeneous Distributed Computing Environments

This article deals with the creation of new methods and algorithms for resource scheduling in heterogeneous distributed computing systems using the example of cloud computing environments (CCEs) that reduce the execution time of many incoming tasks by using those computing resources which give the highest real performance in relation to a specific task received. To this end, it is proposed to apply a multiagent approach to organizing the scheduling process: each element of the CCE includes a software agent that has the most complete and up-to-date information about the features of its computer, and the set of these agents jointly select the most appropriate tasks and subtasks taking into account the available information. The principles of construction and the method of operation of the adaptive multiagent CCE resource manager and the algorithms for the operation of resource agents and tasks are described, and the efficiency of the algorithms developed is studied using a distributed software model.