Abstract

The exponential growth of mobile data users and services places a heavy burden on the limited wireless bandwidth of cellular data networks. The situation will be exacerbated with the advent of high bandwidth multimedia applications for mobile devices. In this paper, we propose an architecture, called the Cellular-based Ad hoc Peer Data Sharing system (CAPS), that can reduce the load on the cellular network while improving the wireless data access latency. In CAPS, mobile hosts in a cellular network form an overlay multi-hop wireless network. This ad hoc network acts as a ‘virtual cache’ that enables data sharing among mobile hosts. Participating mobiles share the contents of their local caches with other mobiles. A subset of mobile hosts keep track of the location of objects with minimal overhead to facilitate fast location discovery in the peer-to-peer ad hoc network. Using CAPS, popular objects can be obtained over the fast ad hoc channel without accessing the cellular infrastructure, thereby reducing the load on the cellular network and improving data access latency. We evaluate the performance of this proposed architecture through simulations using ns-2, varying control parameters across a variety of scenarios, and find that CAPS reduces the timeouts of the user requests by 70–90% and reduces the traffic at the base station by up to 60%.

Keywords: Cellular data networks; Peer data sharing; WLAN-based ad hoc networks

Article Outline

1. Introduction

2. Related work

3. Network model

4. Architecture overview

4.1. Extending the cellular network with peer data sharing

4.2. Ad hoc object discovery

4.3. Electing directory nodes

5. Operation of the CAPS system

5.1. A simple illustration of the CAPS operation

5.2. Non-directory node operation

5.3. Directory node operation

5.4. Electing dnodes

5.5. Object location directory data structure

5.6. Updating the location directory

5.7. Handing off location directory

6. Performance evaluation

6.1. Simulation Model

6.2. Simulation results

6.2.1. User request arrival rate

6.2.2. Number of mobile hosts

6.2.3. Impact of user access patterns

6.2.4. Impact of the percentage of dnodes

6.2.5. Energy consumption

7. Conclusion

References

Vitae