Control instability in distributed queueing systems

摘要

The Huberman-Hogg model of computational ecosystems is applied to resources with queues. The previous theoretical results indicate that instabilities, due to delayed information, can be controlled by adaptive mechanisms, particularly schemes which employ diverse past horizons. A stochastic learning automaton, with rewards based on queueing parameters, is implemented to test the theoretical results. The effects of the learning step size and horizon are shown for systems with various delays and traffic intensities. Long horizons permit non-adaptive agents to achieve similar results, with the possible loss of responsiveness to dynamic environments.