Fast similarity search in peer-to-peer networks

Abstract

Peer-to-peer (P2P) systems show numerous advantages over centralized systems, such as load balancing, scalability, and fault tolerance, and they require certain functionality, such as search, repair, and message and data transfer. In particular, structured P2P networks perform an exact search in logarithmic time proportional to the number of peers. However, keyword similarity search in a structured P2P network remains a challenge. Similarity search for service discovery can significantly improve service management in a distributed environment. As services are often described informally in text form, keyword similarity search can find the required services or data items more reliably. This paper presents a fast similarity search algorithm for structured P2P systems. The new algorithm, called P2P fast similarity search (P2PFastSS), finds similar keys in any distributed hash table (DHT) using the edit distance metric, and is independent of the underlying P2P routing algorithm. Performance analysis shows that P2PFastSS carries out a similarity search in time proportional to the logarithm of the number of peers. Simulations on PlanetLab confirm these results and show that a similarity search with 34,000 peers performs in less than three seconds on average. Thus, P2PFastSS is suitable for similarity search in large-scale network infrastructures, such as service description matching in service discovery or searching for similar terms in P2P storage networks. Abstract-Peer-to-peer (P2P) systems show numerous advantages over centralized systems, such as load balancing, scalability, and fault tolerance, and they require certain functionality, such as search, repair, and message and data transfer. In particular, structured P2P networks perform an exact search in logarithmic time proportional to the number of peers. However, keyword similarity search in a structured P2P network remains a challenge. Similarity search for service discovery can significantly improve service management in a distributed environment. As services are often described informally in text form, keyword similarity search can find the required services or data items more reliably. This paper presents a fast similarity search algorithm for structured P2P systems. The new algorithm, called P2P Fast Similarity Search (P2PFastSS), finds similar keys in any distributed hash table (DHT) using the edit distance metric, and is independent of the underlying P2P routing algorithm. Performance analysis shows that P2PFastSS carries out a similarity search in time proportional to the logarithm of the number of peers. Simulations on PlanetLab confirm these results and show that a similarity search with 34,000 peers performs in less than three seconds on average. Thus, P2PFastSS is suitable for similarity search in large-scale network infrastructures, such as service description matching in service discovery or searching for similar terms in P2P storage networks.

Mobile P2P Fast Similarity Search

“…While CPU time is minimized, storage space is required to store the deletion neighborhood. As reported in [2], the overhead of P2PFastSS in bandwidth for searching is 5.6 and for indexing 7 for a similar word of length 7, redundancy factor 5 and k = 1. Due to parallel execution, P2PFastSS is only 1.5 times slower than exact search.…”

“…Similarity search algorithms for structured P2P networks have been proposed by Ahmed et al [1], introducing a routing algorithm based on Bloom filters and Wong et al [6], introducing a routing algorithm in a keyword metric space. However, P2PFastSS [2] is the only algorithm that supports fast similarity searches that runs on existing DHTs without modifying the routing algorithm.…”

A Cloud Storage overlay to aggregate heterogeneous Cloud services

“…Contentbased search used in PiCsMu allows for the lookup of files without knowing an exact keyword by using P2PFastSS [3], a similarity algorithm based on the edit distance metric (Levenshtein) [10]. The search is enabled by storing multiple keywords as DHT keys, pointing to the corresponding PiCsMu Index entities.…”

PeerCollaboration

“…Based on that, the DHT layer provides the interfaces put() and get() to the upper layers. On top of the DHT, P2PVote, P2PFastSS [2], and P2PFileSharing are built. The incentive scheme PSH [1] is built into P2PVote and P2PFileSharing.…”

“…PSH has been compared to TFT, and two variants of PSH: PSH r, and CompactPSH. Second, the underlying algorithm of P2PFastSS [2], FastSS and its variants have been evaluated in a simulation and on PlanetLab. FastSS has been compared to Burkhard-Keller tree, dynamic programming, NR-grep, keyword tree, neighborhood generation, and n-grams.…”