Abstract
We address the issues related to aggregation of anycast groups for scalable anycast routing. Anycast is a new network service that allows a sender to access anyone in a group that shares the same anycast address. Anycast has numerous potential applications. However, it also introduces new issues. One of the issues is that the size of the anycast routing tables is significantly increased The main goals of this study are to reduce the size of routing tables and to improve network end-to-end performance. Particularly, we propose three group-aggregation algorithms with different objectives: (1) group-aggregation for minimizing the routing table size, (2) group-aggregation for balancing interface load, and (3) integrated group-aggregation. These algorithms take full advantages of the anycast semantics. Our evaluation results show that our group-aggregation algorithms can efficiently reduce the size of routing tables by 90% while achieving high network performance in terms of the average end-to-end delay.
