PINE-guided cache replacement policy for location-dependent data in mobile environment
F. Mary Magdalene Jane, Rahul Parameswaran, Ruth Naveena Nadarajan, Maytham H. Safar · 2008
Caching frequently accessed items on the mobile client is an important technique to enhance data availability and to improve data access time. Cache replacement policies are used to find a suitable subset of items for eviction from the cache due to limited cache size. The existing policies rely on Euclidean space and consider Euclidean distance as an important parameter for eviction. However, in practice the position and movement of objects are constrained to spatial networks where the important distance measure is the network distance. In this paper we propose a cache replacement policy, which considers the network density, network distance and probability of access as important factors for eviction. We make use of an already proven technique called Progressive incremental network expansion to compute the network distance more efficiently. A series of simulation experiments have been conducted to evaluate the performance of the policy. Results indicate that the proposed cache replacement scheme performs significantly better than the existing policies FAR and PAID and WPRRP.