The Compression of Pending Interest Table with Bloom Filter in Content Centric Network

Content Centric Network (CCN) is an emerging information centric network design. There are a lot of studies focusing on caching, applications and so on to make CCN getting perfect, while the scalability of Pending Interest Table (PIT) is still one of the primary concerns of high-speed forwarding. In this paper, we make an attempt to compress PIT with bloom filter. This paper has two contributions: First, we propose a compressed PIT architecture and point out Counting Bloom Filter shoud not be used in the PIT compression because of incorrect deletion. Second, we propose United Bloom Filter, a new extension of bloom filter, to compress PIT effectively. Experiments show our approach can reduce storage space requirement by about 40% while incurs only 0.1% error probability at most. The communication can easily be recovered from the errors through retransmission.