Optimization of mobile updates using Particle filter

The mobile usage of Internet is characterized by frequent changes of the access network and consequently, changes of the application's IP address or port. Intermediate NAT devices can exchange additionally the transport and network headers. Not using the current IP and port parameter leads to lost packets and service interruption. To overcome these problems, the applications send updates or keep-a-lives in regular basis, for example Dead-Peer-Detection in IKE. These messages inform the communication participants that the host is reachable. The main shortcoming is that the updates are performed at constant intervals regardless of the network properties. The problem oscillates in mobile environment where frequent network changes are expected. The result is wasted resources and long disconnection intervals. The key idea in this work is to set the update intervals proportional to the probability for network change. The probability density function is built using the past disconnections, thus the history is used to optimize the update intervals. Novel framework based on particle filter is derived and simulated in this paper. The new method outperforms significantly the classical constant updates. Many protocols in mobile environment can profit from the new framework, like SIP, IKE, Routing protocols etc.