•  
  •  
 

Journal of Undergraduate Research

Keywords

hyperweb search, index replication, hypercube 1 topology, data node

College

Physical and Mathematical Sciences

Department

Computer Science

Abstract

The hyperweb is a network based on a modified hypercube1 topology. It is used to create a peerto- peer network for a distributed database (such as a genealogical database.) Two major drawbacks that a peer-to-peer network suffers are a low reliability rate for individual nodes and a slower search speed as the system grows. Both of these problems can be addressed by replicating data across several nodes. First, any particular node has a relatively high probability of being down so a copy of the information a node contains is stored on several other nodes, thereby decreasing the total probability of information being unavailable. Second, when performing a search, a node can query the closest node in the hyperweb, thereby avoiding the extra time required to travel further across the hyperweb. The most difficult problem associated with adding replicating nodes is deciding where they should be placed so that the maximum increase in speed is achieved at the lowest cost.

Download

Share

COinS