Threshold-based load balancing for multiple home agents in mobile IP networks

摘要

Mobile IP is an extension of the IP protocol designed to provide seamless connectivity to mobile nodes roaming over the Internet. Under certain conditions of traffic, such as in Mobile IP networks supporting multimedia applications overhead can cause significant delays at the mobility agents, i.e. foreign and home agents. Some multiple home agents protocol extensions have been proposed to avoid potential bottlenecks in single home agents configurations. Due to the highly unpredictable nature of the IP data traffic, efficient load balancing applied in such schemes is crucial to the overall performance improvement. In this paper we propose a novel threshold-based dynamic load balancing policy that uses a realistic datasharing model operational at each home agent. A discrete event computer simulator is developed to study the system performance with the proposed load balancing policy. We also introduce two new policy tuning parameters the number of information queue slices and the retry latency, by which we control the load balancing benefit. Due to the relatively large number of simulation parameters, results are presented for typical configuration scenarios. In general, in all the results obtained, our threshold-based load balancing policy provides a significant performance improvement. The proposed architecture efficiently uses parallel processing for handling the overhead generated by the load balancing, which results in minimal performance degradation.