Abstracts of Related Papers: Panda

J. Li, M. Yarvis, and P. Reiher Securing Distributed Adaptation, OpenArch 2001.

Open architecture networks provide applications with fine-grained control over network elements. With this control comes the risk of misues and new challenges to security beyond those present in conventional networks. One particular security requirement is the ability of applications to protect the secrecy and integrity of transmitted data while still allowing trusted active elements within the network to operate on that data.

This paper describes mechanisms for identifying trusted nodes within a network and securely deploying adaptation instructions to those nodes while proteccting application data from unauthorirzed access and modification. Promising experimental results of our implementation within the Conductor adaptaiton framework will also be presented, suggesting that such features can be incorporated into real networks.

P. Reiher, R. Guy, M. Yarvis, and A. Rudenko Automated Planning for Open Architectures, Openarch 2000 short paper, March 2000.

End-to-end connections experience a high level of diversity in network characteristics. At one extreme, an application may receive highly degraded service, leaving the application unusable. At another extreme, the costs to guarantee some level of service may be undesirably high to the user or the overall system. Open architecture networks help applications push adaptation technology into the network and reduce the effects of poor network characteristics. Automated planning is important for the services that are supported by the open architecture. The remedies that modify an application's data stream to adjust it to unfavorable network conditions should be located and ordered to provide good data transfer and network resource use. The search for good plans is a hard AI problem and requires additional research.

M. Yarvis, P. Reiher, and G. Popek A Reliability Model for Distributed Adaptation, Openarch 2000, March 2000.

End-to-end connectivity is growing increasingly diverse, with orders of magnitude differences in characteristics throughout the network. At the same time, most applications assume a level of network characteristics below which they either provide no service, or service at a cost higher than the user is willing to pay. Open architecture networks can help applications degrade gracefully when network conditions are poor by pushing adaptation technology into the network. Unfortunately, since adaptation seeks to change the data stream during transmission, it is incompatible with the traditional model for reliable data streams.

A new model of reliability is required to allow general adaptation of reliable data streams. We propose one possible model that provides reliable delivery of the semantic meaning in the data stream despite adaptation. We present this model in the context of Conductor, a framework for distributed adaptation. By using a reliability model that is compatible with adaptation, Conductor allows arbitrary, distributed components to operate on a data stream without reducing end-to-end reliability. While Conductor is one possible adaptation service, it is also an example of the type of reliability model required in open architecture networks.

B. Scott Michel, K. Nikoloudakis, P. Reiher, and L. Zhang URL Forwarding and Compression in Adaptive Web Caching, Infocom 2000, March 2000.

Web caching is gneerally acknowledged as an important service for alleviating focused overloads when certain web servers' contents suddenly become popular. Cooperative caching systems are more effective than independent caches due to the larger collective backing store that cooperation creates. One such system currently being developed at UCLA,Adaptive Web Caching (AWC), uses an application-level forwarding table to locate the nearest copy of a requested URL's contents. This paper describes one specific design in AWC, a simple URL table compression algorithm allowing efficient content information sharing among neighboring caches. The compression algorithm is based on a hierarchical URL decomposition to aggregate URLs sharing common prefixes and an incremental hashing function to minimize collisions between prefixes. The algorithm's collision rate is derived analytically and verified with five sets of Web trace data. The results demonstrate that the collision rate is bounded and has little impact on page fetching latency. Finally, this compression method is compared ot the Summary Cache method.

Back to the main Panda page.