Cost efficient broadcast based cache invalidation for mobile environments

To improve the performance of mobile computers, a number of broadcast based cache invalidation schemes have been proposed in the past to support object locality. However most of these schemes have focused on providing support for client disconnection and reducing query delay. The size of invalidation reports and the effect of invalidating items cached by many clients are also important issues that must be addressed in order to provide cost-efficient cache invalidation in a mobile environment. In this paper, we propose two techniques, Validation-Invalidation Reports (VIR) and the Delayed Requests Scheme (DRS) to address these issues. VIR uses a combination of validation and invalidation reports, allowing the server to construct and broadcast smaller reports at each interval, thus improving downlink channel utilization. DRS addresses the problem where multiple clients request for the same data items. It introduces a "cool down" period after an invalidation, to reduce the number of uplink requests sent by clients. Simulation results show that compared to the original TS approach [1], the proposed schemes lower transmission cost associated with cache invalidation by between 5%-25% in the downlink channel and between 10%-40% in the uplink channel.

[1]  Rafael Alonso,et al.  Broadcast disks: data management for asymmetric communication environments , 1995, SIGMOD '95.

[2]  Jun Cai,et al.  Energy‐efficient selective cache invalidation , 1999, Wirel. Networks.

[3]  Daniel Barbará,et al.  Sleepers and workaholics: Caching strategies in mobile environments (Extended version) , 1995, The VLDB Journal.

[4]  Philip S. Yu,et al.  Energy-efficient caching for wireless mobile computing , 1996, Proceedings of the Twelfth International Conference on Data Engineering.

[5]  Dik Lun Lee,et al.  Adaptive cache invalidation methods in mobile environments , 1997, Proceedings. The Sixth IEEE International Symposium on High Performance Distributed Computing (Cat. No.97TB100183).

[6]  Guohong Cao,et al.  Proactive Power-Aware Cache Management for Mobile Computing Systems , 2002, IEEE Trans. Computers.

[7]  Bharat K. Bhargava,et al.  Maintaining consistency of data in mobile distributed environments , 1995, Proceedings of 15th International Conference on Distributed Computing Systems.

[8]  Beng Chin Ooi,et al.  An Evaluation of Cache Invalidation Strategies in Wireless Environments , 2001, IEEE Trans. Parallel Distributed Syst..

[9]  Sandeep K. S. Gupta,et al.  A Strategy to Manage Cache Consistency in a Disconnected Distributed Environment , 2001, IEEE Trans. Parallel Distributed Syst..

[10]  Jun Cai,et al.  Broadcast-Based Group Invalidation: An Energy-Efficient Cache Invalidation Strategy , 1997, Inf. Sci..

[11]  Ahmed K. Elmagarmid,et al.  Bit-Sequences: An adaptive cache invalidation method in mobile client/server environments , 1997, Mob. Networks Appl..

[12]  Guohong Cao,et al.  A scalable low-latency cache invalidation strategy for mobile environments , 2000, MobiCom '00.

[13]  Tomasz Imielinski,et al.  Sleepers and workaholics: caching strategies in mobile environments , 1994, SIGMOD '94.