The World Wide Web has become the primary means for information dissemination. Due to the limited resources of the network bandwidth, users always suffer from long time waiting. Web prefetching and web caching are the...The World Wide Web has become the primary means for information dissemination. Due to the limited resources of the network bandwidth, users always suffer from long time waiting. Web prefetching and web caching are the primary approaches to reducing the user perceived access latency and improving the quality of services. In this paper, a Stochastic Petri Nets (SPN) based integrated web prefetching and caching model (IWPCM) is presented and the performance evaluation of IWPCM is made. The performance metrics, access latency, throughput, HR (hit ratio) and BHR (byte hit ratio) are analyzed and discussed. Simulations show that compared with caching only model (CM), IWPCM can further improve the throughput, HR and BHR efficiently and reduce the access latency. The performance evaluation based on the SPN model can provide a basis for implementation of web prefetching and caching and the combination of web prefetching and caching holds the promise of improving the QoS of web systems.展开更多
A scheme for high-speed data transfer via the Internet for Web service in an extremely large delay environment is proposed. With the wide-spread use of Internet services in recent years, WLAN Internet service in high-...A scheme for high-speed data transfer via the Internet for Web service in an extremely large delay environment is proposed. With the wide-spread use of Internet services in recent years, WLAN Internet service in high-speed trains has commenced. The system for this is composed of a satellite communication system between the train and the ground station, which is characterized by extremely large latency of several hundred milliseconds due to long propagation latency. High-speed web access is not available to users in a train in such an extremely large latency network system. Thus, a prefetch scheme for performance acceleration of Web services in this environment is proposed. A test-bed system that implements the proposed scheme is implemented and is its performance in this test-bed is evaluated. The proposed scheme is verified to enable high-speed Web access in the extremely large delay environment compared to conventional schemes.展开更多
W eb预取技术是减少网络延迟,提高服务质量的主要解决方案之一.利用Z ip f第一法则和第二法则分别对W eb高频区对象和低频区对象建立访问流行度模型,进而提出一种基于W eb对象流行度的PPM预测模型.实验表明,该模型除继承了传统PPM模型...W eb预取技术是减少网络延迟,提高服务质量的主要解决方案之一.利用Z ip f第一法则和第二法则分别对W eb高频区对象和低频区对象建立访问流行度模型,进而提出一种基于W eb对象流行度的PPM预测模型.实验表明,该模型除继承了传统PPM模型简单易实现的特点外,在缩减模型规模的同时预测精度也有一定程度的提高,并且控制了由预取引起的网络流量.展开更多
提出了一种自适应PPM(Prediction by Partial Match)预测模型:PAPPM。该模型能在预测过程中使用基于熵的自适应选阶策略选择最优阶,降低了预测开销。而且,它能根据当前用户访问的Web序列实时地更新预测模型,保证了预测模型的新鲜度。实...提出了一种自适应PPM(Prediction by Partial Match)预测模型:PAPPM。该模型能在预测过程中使用基于熵的自适应选阶策略选择最优阶,降低了预测开销。而且,它能根据当前用户访问的Web序列实时地更新预测模型,保证了预测模型的新鲜度。实验表明,PAPPM提高了预测精度和预测命中率,适用于在线Web预取。展开更多
基金Supported by the National Natural Science Foundation of China under Grant No. 60472044. The authors would like to thank research fellow Dr. Yun Shi of China State Post Bureau and Professor Dr. Jun Zou of Tsinghua University for their helpful and constructive comments.
文摘The World Wide Web has become the primary means for information dissemination. Due to the limited resources of the network bandwidth, users always suffer from long time waiting. Web prefetching and web caching are the primary approaches to reducing the user perceived access latency and improving the quality of services. In this paper, a Stochastic Petri Nets (SPN) based integrated web prefetching and caching model (IWPCM) is presented and the performance evaluation of IWPCM is made. The performance metrics, access latency, throughput, HR (hit ratio) and BHR (byte hit ratio) are analyzed and discussed. Simulations show that compared with caching only model (CM), IWPCM can further improve the throughput, HR and BHR efficiently and reduce the access latency. The performance evaluation based on the SPN model can provide a basis for implementation of web prefetching and caching and the combination of web prefetching and caching holds the promise of improving the QoS of web systems.
文摘A scheme for high-speed data transfer via the Internet for Web service in an extremely large delay environment is proposed. With the wide-spread use of Internet services in recent years, WLAN Internet service in high-speed trains has commenced. The system for this is composed of a satellite communication system between the train and the ground station, which is characterized by extremely large latency of several hundred milliseconds due to long propagation latency. High-speed web access is not available to users in a train in such an extremely large latency network system. Thus, a prefetch scheme for performance acceleration of Web services in this environment is proposed. A test-bed system that implements the proposed scheme is implemented and is its performance in this test-bed is evaluated. The proposed scheme is verified to enable high-speed Web access in the extremely large delay environment compared to conventional schemes.
文摘提出了一种自适应PPM(Prediction by Partial Match)预测模型:PAPPM。该模型能在预测过程中使用基于熵的自适应选阶策略选择最优阶,降低了预测开销。而且,它能根据当前用户访问的Web序列实时地更新预测模型,保证了预测模型的新鲜度。实验表明,PAPPM提高了预测精度和预测命中率,适用于在线Web预取。