RMLAB: Energy-Efficient Resource Management for Cognitive Internet of Things Based on Learning Automata

The mobility of the nodes and their limited energy supply in cognitive Internet of Things networks leads to complexity of network conditions. So that having efficient energy mechanism is considered important in these networks and can reduce energy consumption in the network. network elements (including nodes, policies and behaviors) are not able to create intelligent adaptation to the environment in which they operate due to being limited in their status, scope and response mechanisms and compatibility in these networks is usually passive. for this reason energy efficiency algorithms are expected to be able to adapt themselves to environmental changes through a preventive solution. On the other hand The Administration Command of the Islamic Republic of Iran(Farja) is in contact with a large amount of information in various social, security, economic and cultural fields in order to work in the field of order and security. therefore to achieve aforementioned purposes. this paper presents a new RMLAB solution for energy efficiency based on Learning Automata from the perspective of cognitive networks. which is self organizing, self aware and dynamically regulated by use of learning automata to send network nodes to manage energy consumption and one of the main strengths of this method compared to existing methods is that network able to organize, manage and rebuild itself. the experimental results show that examining energy efficiency from perspective of cognitive network leads to improvement of quality of service parameters, including throughput and end to end delay in network compared with other energy efficiency methods.