A distributed algorithm for managing resources in a hierarchical network

Abstract This article introduces a distributed algorithm for designing and managing distributed systems and computer communication networks. This algorithm can be implemented as a part of operating system software to make decisions about process transfer and message routing in a hierarchical network. The algorithm uses dynamic information about the state of processors and applications in the local and wide area network. This information consists of processors' and applications' queue lengths and is broadcast to directly connected processors. The algorithm uses broadcast information to make decisions about process transfer and message routing while considering processor availability and system security. The algorithm causes processors' queue lengths to become balanced on each network hierarchy level. The number of process transfers is calculated and depends on network partitioning and the threshold values used by the algorithm. The convergence of the algorithm is proven. Performance of the proposed algorithm is evaluated analytically using the elapsed time of process transfer or message transfer and the waiting time to begin transfer.