Fractal: a mobile code-based framework for dynamic application protocol adaptation

  • Authors:

  • H. Lufei;W. Shi

  • Affiliations:

  • Department of Computer Science, Wayne State University, Detroit, MI;Department of Computer Science, Wayne State University, Detroit, MI

  • Venue:
  • Journal of Parallel and Distributed Computing - 19th International parallel and distributed processing symposium
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

The rapid growth of heterogeneous devices and diverse networks in our daily life, makes it is very difficult, if not impossible, to build a one-size-fits-all application or protocol, which can run well in such a dynamic environment. Adaptation has been considered as a general approach to address the mismatch problem between clients and servers; however, we envision that the missing part, which is also a big challenge, is how to inject and deploy adaptation functionality into the environment. In this paper we propose a novel application level protocol adaptation framework, Fractal, which uses the mobile code technology for protocol adaptation and leverages existing content distribution networks (CDN) for protocol adaptors (mobile codes) deployment. To the best of our knowledge, Fractal is the first application level protocol adaptation framework that considers the real deployment problem using mobile code and CDN. To evaluate the proposed framework, we have implemented two case studies: an adaptive message encryption protocol and an adaptive communication optimization protocol. In the adaptive message encryption protocol, Fractal always chooses a proper encryption algorithm according to different application requirements and device characteristics. And the adaptive communication optimization protocol is capable of dynamically selecting the best one from four communication protocols, including Direct sending, Gzip, Bitmap, and Vary-sized blocking, for different hardware and network configurations. In comparison with other adaptation approaches, evaluation results show the proposed adaptive approach performs very well on both the client side and server side. For some clients, the total communication overhead reduces 41% compared with no protocol adaptation mechanism, and 14% compared with the static protocol adaptation approach.