Update-based cache replacement policies in wireless data access

Abstract

Most of cache replacement schemes are access-based replacement policies since they are based on object access frequency/time information. However, update information is extremely important since an updated object makes itself invalid, and the object hit information becomes useless. In this paper, we propose two update-based replacement policies, the least access-to-update ratio (LA2U) and least access-to-update difference (LAUD) in wireless data access, based on both update frequency and access frequency. Extensive simulations have been carried out to evaluate the proposed policies. Simulation results show that the proposed update-based policies outperform access-based policies at most cases. It is concluded that considering update information in designing replacement policies can increase cache performance, especially, when updates are heavy