Queries Routing In Super-Peer-Based System: Simulation and Evaluation

摘要: Peer-to-peer (P2P) computing is currently attracting enormous attention. P2P systems have emerged as a popular way to share huge volumes of data. In such each peer database management system in itself, ex-posing its own schema. A fundamental problem that confronts peer-to-peer applications the efficient location node stores desired data item. settings, main objective search across databases by processing incoming query without overly consuming bandwidth. this paper, we propose an architecture based on (super-)peers, and focus routing. Our approach considers (super-)Peers having similar interests are grouped together for routing method. groups, called Knowledge-Super- Peers (KSP), super-peers submit queries often processed members group. KSP specific super-peer which contains knowledge about: 1. super- peers 2. The others super-peers. Knowledge extracted using mining techniques (e.g. decision tree algorithms) starting from transit network. advantage distributed that, it avoids making semantic mapping, between heterogeneous sources owned time decides route other (super- )peers. set improves robustness mechanism scalability Network. Compared with baseline approach, our proposal shows better performance new simulator respect important criteria response time, precision recall. Index Terms—Peer-to-peer, Query Routing, Knowledge- Super-Peers, Data Mining, Scalability.