Expected traffic reduction by content-oriented incentive in peer-assisted content delivery networks

Content services that deliver large-volume content files have been growing rapidly. In these services, it is crucial for the service provider and the network operator to minimize traffic volume in order to lower the cost charged for bandwidth and the cost for network infrastructure, respectively. To reduce the traffic, traffic localization has been discussed; network traffic is localized when requested content files are served by an other nearby altruistic client instead of the source servers. With this mechanism, the concept of the peer-assisted content delivery network (CDN) can localize the overall traffic and enable service providers to minimize traffic without deploying or borrowing distributed storage. To localize traffic effectively, content files that are likely to be requested by many clients should be cached locally. We present a traffic engineering scheme for peer-assisted CDN models. Its key idea is to control the behavior of clients by using a content-oriented incentive mechanism. This approach optimizes traffic flows by letting altruistic clients download content files that are most likely to contribute to localizing network traffic. To let altruistic clients request the desired files, we combine content files while keeping the price equal to that for a single content. We discuss the performance of our proposed algorithm considering the cache replacement algorithms.