Investigations on futuristic mobility predictions in mobile ad hoc networks using parametric auto regressive technique

Abstract

This research work proposes a mobility prediction model using Auto Regressive Integrated Moving Average (ARIMA) for estimating the futuristic mobility speed of a node in Mobile Ad hoc Networks (MANETs). The mobility prediction promotes the route discovery process for the selection of moderate mobility nodes to provide reliable routing. The ARIMA is a time series forecasting approach, which uses autocorrelation to predict the future mobility of nodes. The proposed ARIMA model trains the Random Waypoint Mobility (RWP) and Random Walk (RW) dataset to forecast the mobility of the nodes. newlineIn this research, the proposed ARIMA algorithm is designed to predict future mobility models by varying the delay and (p, d, q) parameters. The Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC), Correlated AIC (AICc), Auto-Correlation Function (ACF), and Partial Auto-Correlation Function (PACF) parameters are evaluated for the predicted mobility dataset. These parameters estimate the predicted model s quality, stationary, and reliability. Different scenarios of speed values are examined for the proposed models. newlineThe performance newline