Distributed cache replacement method for geospatial data using spatiotemporal locality-based sequence

Abstract

Specific features of tile access patterns can be applied in a cache replacement strategy to a limited distributed high-speed cache for the cloud-based networked geographic information services (NGISs), aiming to adapt to changes in the access distribution of hotspots. By taking advantage of the spatiotemporal locality, the sequential features in tile access patterns, and the cache reading performance in the burst mode, this article proposes a tile sequence replacement method, which involves structuring a Least Recently Used (LRU) stack into three portions for the different functions in cache replacement and deriving an expression for the temporal locality and popularity of the relevant tile to facilitate the replacement process. Based on the spatial characteristics of both the tiles and the cache burst mode with regard to reading data, the proposed method generates multiple tile sequences to reflect spatiotemporal locality in tile access patterns. Then, we measure the caching value by a technique based on a weighted-based method. This technique draws on the recent access popularity and low caching costs of tile sequences, with the aim of balancing the temporal and spatial localities in tile access. It ranks tile sequences in a replacement queue to adapt to the changes in accessed hotspots while reducing the replacement frequency. Experimental results show that the proposed method effectively improves the hit rate and utilization rate for a limited distributed cache while achieving satisfactory response performance and high throughput for users in an NGIS. Therefore, it can be adapted to handle numerous data access requests in NGISs in a cloud-based environment.