A Learning Based Factorization Approach for Uniform Distribution of Data in M2M Communication

Now-a-days, Machine-to-Machine (M2M) communication can be accomplished with execution of Internet-of-Things (IoT) that is carried out in wireless networks. Extensive M2M access in leads to BS congestion that causes access probability and delay deterioration. Class bar can directly influences flow of machine based communication with controlling factors to eliminate overload. Here, randomly accessibly resources are shared between H2H or M2M communication devices, various investigation based on this controlling scheme considers only limited preambles allocated to M2M traffic. Moreover, whenever communication lacks in massive accessibility in M2M communications, it is appropriate to quickly fulfil requests from devices with accessible preambles, specifically time based IoT environment. To overcome this, a novel Factorization function (FF) with transformation is introduced to Learning automata which leads to enhanced LA algorithm that is specified as FF-LA in this work. Simulation outcomes depict that FF-LA scheme can work effectually to control traffic and can attain theoretical optimality. BS implementation with FF can significantly control M2M traffic by dynamically handling class bar with H2H traffic interference and offer quality of service to both H2H and M2M traffic.