VARIMA(3,1,3) Model based RTT Estimation using RSSI

The Received Signal Strength (RSS) of wireless Lan (WLAN) varies due to environmental changes and technical factors such as obstacle in the signal path, path loss, link quality and climatical changes. Many of the protocols takes the RSS as a parameter to improve the performance of the data communication. In the cross-layer architecture, the network parameters from a layer are used by the non-adjacent layers which is considered as violation of standard in ISO-OSI reference model. TCP protocol from transport layer needs the RSS of the sender which is from the physical layer, to improve the performance of the congestion control mechanism. The RSS is one of the influencing parameters for estimating the Round-Trip Time (RTT) of a packet which is then used to calculate the size of the congestion window size of TCP. Whenever the link quality decreases, the corresponding RSS decreases and RTT increases. Therefore, it is necessary to relate RSS and RTT. This relation of RTT and RSS my be used to determine the congestion window size which improves the performance of TCP. In this paper, we use the time series analysis to model the RSS and RTT. In order to model the RSS and RTT, we collected RSS and RTT values from different location. Based on the exploratory data analysis, we found that Vector Auto Regressive Integrated Moving Average (VARIMA) is suitable to model the RSS and RTT. The proposed model VARIMA(3,1,3) is closely suited for prediction of RSS and RTT.