Analysis of Cost-Aware Policies for Intersection Caching in Search Nodes

摘要

We propose static, dynamic and hybrid cost-aware policies for intersection caching and we introduce three different strategies to solve a query computing list intersections. We run experiments over a simulation framework using real data for both document collection and text queries. We observe that: a) cost-aware policies outperform cost-oblivious policies, b) static policies are better than dynamic policies (as in posting list caching), c) hybrid policies outperform the previous ones achieving up to 29% of cost savings and d) computing strategies that try to maximize cache usage have a better performance than the a-priori most efficient ones.