A Global User-Driven Model for Tile Prefetching in Web Geographical Information Systems

Abstract

A web geographical information system is a typical service-intensive application. Tile prefetching and cache replacement can improve cache hit ratios by proactively fetching tiles from storage and replacing the appropriate tiles from the high-speed cache buffer without waiting for a client’s requests, which reduces disk latency and improves system access performance. Most popular prefetching strategies consider only the relative tile popularities to predict which tile should be prefetched or consider only a single individual user's access behavior to determine which neighbor tiles need to be prefetched. Some studies show that comprehensively considering all users’ access behaviors and all tiles’ relationships in the prediction process can achieve more significant improvements. Thus, this work proposes a new global user-driven model for tile prefetching and cache replacement. First, based on all users’ access behaviors, a type of expression method for tile correlation is designed and implemented. Then, a conditional prefetching probability can be computed based on the proposed correlation expression mode. Thus, some tiles to be prefetched can be found by computing and comparing the conditional prefetching probability from the uncached tiles set and, similarly, some replacement tiles can be found in the cache buffer according to multi-step prefetching. Finally, some experiments are provided comparing the proposed model with other global user-driven models, other single user-driven models, and other client-side prefetching strategies. The results show that the proposed model can achieve a prefetching hit rate in approximately 10.6% ~ 110.5% higher than the compared methods.

An enhanced active caching strategy for data-intensive computations in distributed GIS

“…Markov Chain model is a well-known active caching algorithm which use a Markov Chain to predict client's next movements [24,25]. Although these methods have several advantages for GIS, they are primarily used by clients that separately read data from the server in advance for caching based on their own behavior, potentially leading to cache waste (duplication of data units in a cache buffer or data that are cached but will not be used soon) in distributed GIS [26].…”

“…Correlation-based models such as data replicas based on the fuzzy logic system (FLSDR) [32], global user-driven model for tile prefetching (GUDC) [26] and prefetching scheme based on spatial-temporal attribute prediction (STAP) [33] dynamically cache the related data into a high-speed cache buffer to prepare the data for service in advance. FLSDR selects some data as an optimal replica with a minimum response time considering both the data queue and the data transfer.…”

“…Considering information from a typical historical access log [26] that is used by the application, the data with the highest popularity may not be accessed again. Moreover, the relationships or popularities of all of the data in distributed GIS change continuously during system operation [25].…”

“…We can compute the relationships between all of the data based on their historical scheduling records considering both global access correlations [26,29] and the timeliness of their access correlations [34]. Because a large amount of spatial data is stored in distributed GIS and it is impossible to dynamically adjust the data placement among all of the clusters for reasons related to various computational tasks, the spatial data will be stored in the storage nodes randomly and evenly.…”

“…, the access correlations, the correlation steps and the correlation times between d i and d j can be separately computed as follows based on typical data correlation mining algorithm [26] within the vector Q k :…”