摘要：The current research focus on the areas such as definition and system structure of cognitive networks (CNs), with the lack of autonomic decision-making theory and approach. In this paper, we proposed an autonomic decision-making approach based on influence diagram for CNs. Utilizing influence diagram to choose and execute the action which maximized the network overall performance can effectively predict the trend in network performance, archive autonomic decision-making and avoid network performance deterioration. The simulation results show that the CNs autonomic decision-making approach given network the abilities of learning, reasoning and autonomic decision-making without any human intervention. As a result, the network cognition has been archived while the network Quality of Service (QoS) has been guaranteed.
