Designing Server Sets for Anycast CDN Using Genetic Algorithm
Chihiro Kato, Noriaki Kamiyama · 2024
In recent years, there has been growing interest in the effective operation of any cast Content Delivery Networks (CDN). Existing anycast CDNs answer the same set of cache servers (CSes) for all content requests without considering the geographical distribution of popularity of contents. It has also been reported that the appropriateness of the selection of delivery servers decreases as the number of servers assigned to the same IP address increases in anycast delivery. To solve these problems, we propose a new anycast distribution method that incorporates the spatial locality of the popularity of content. Specifically, we propose an algorithm that creates multiple CS sets consisting of a small number of CSs and assigns the optimal CS set to each content by minimizing the number of CSes in the CS set. The algorithm aims to reduce the dispersion of delivery delay by minimizing the number of CSes in the CS set, while covering a wide range of countries. Using a genetic algorithm, we construct CS sets that incorporates spatially biased ASes and verify its effectiveness through computer simulation. Numerical evaluation results show that the proposed method can effectively cover about 80% of requests of highly popular content with about 15 ASes. It is expected that the proposed method can effectively cover the requirements for most of the contents with a small number of CS sets and improve the quality of user experience.