| 摘要 |
A distributed index for discovering distributed data sources and computing resources based on predicates on attributes is provided. Proposed is a non-altruistic scheme for indexing distributed data, in which nodes are provided with incentives to cooperate in the referencing of data and the routing of search requests for indexed data. Indexed data is mapped to a dynamic routing graph, in which nodes earn credits each time they route a search request. Participatory nodes along a search request traversal continually modify local routing decisions in a manner necessary to maximize profit. Thus, routing paths as a whole are able to dynamically adapt to changing query workloads and access patterns. Dynamic adaptation also occurs by automatic load-balancing of recipients of frequently routed searches, known as "hot spots", for frequently request data, "hot items", as a result of an incentive to replicate the indexing strategy of a more profitable node.
|
