Autoregressive, moving average and mixed autoregressive-moving average processes for forecasting QOS in ad hoc networks for real-time service support

The dynamic nature of Wireless networks, such as ad-hoc networks, makes them more difficult to provide QoS, because it's hard to keep routing state information up-to-date. Nodes may join, leave, and rejoin the ad-hoc networks at any time and any location. An important issue in the Internet, and consequently in every network connected to it, is support for multimedia applications (video, voice). These applications have specific requirements in terms of delay and bandwidth [14], [15] which challenge the original design goals of the IP's best effort service model, and call for alternate service models [12], [13] and traffic management schemes that can offer the required quality of service (QoS). QoS routing offers serious challenges even for today's Internet [1]. Different service types (e.g., voice, live video, and document transfer) have significantly different objectives for delay, bandwidth, and packet loss [2]. The notion of QoS, as mentioned in [3], is a guarantee by the network to satisfy a set of predetermined service performance constraints for the user in terms of the end-to-end delay statistics, available bandwidth, probability of packet loss, and so on. In this paper, we try to reduce the degree of degradation of QoS and at the same time ameliorate the estimation of the QoS of these networks. In fact, we present methods for forecasting resources to meet the QoS requirements in ad-hoc networks based on AutoRegressive (AR), Moving Average (MA) and Mixed AutoRegressive-Moving Average (ARMA) processes. The results obtained show that the combination of the ad hoc routing protocol: DSR with forecasting QoS mechanisms for real-time service support based on AR, MA and ARMA processes performs better.