Data Traffic Optimization in Wireless Local Area Networks with Artificial Neural Networks

In recent years, quality of service (QoS) has been rapidly increasing in wireless local area networks (WLANs) with the increasing technology. In many studies, various methods and different algorithms are used to improve the quality of service in WLANs. RTS Threshold Value (RTSTV), Fragmentation Threshold Value (FTV) and Buffer Size (BS) are affect service quality directly at MAC (Medium Access Control) layer in WLAN. Channel utilization, data traffic received and data traffic sent parameters are important improve quality of service in WLANs. In this study, RTSED, PED and AB parameters were optimized by using Artificial Neural Networks (ANN) in WLAN and ideal values of received data traffic and received data traffic were obtained. Using the Riverbed Modeler simulation tool, 11 nodes and 27 different input values were selected to obtain channel utilization status. With the ANN Modeling of the results of the data traffic sent and data traffic received provides the estimation of the performance in the WLAN. It is observed that the average squared error value of 1000 epoch training result is less than 10(-6), and that the test and estimation abilities are larger than 10(-6). According to this value, it means that the improved YSA model can not memorize, it can establish a relation between input and output data. Thus, it is proved that the best learning values are obtained with these results obtained by the developed model.