Acta Metallurgica Sinica(English letters) ›› 2014, Vol. 21 ›› Issue (3): 46-55.doi: 10.1016/S1005-8885(14)60300-9

• Networks • Previous Articles     Next Articles

Credibility protection for resource sharing and collaborating in non-center network computing environments

徐小龙 TU Qun Wang Xin-Heng 王汝传   

  1. 1. College of Computer, Nanjing University of Posts and Telecommunications, Nanjing 210003, China 2. State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210046, China 3. School of Computing, University of the West of Scotland, Paisley PA1 2BE, United Kingdom
  • Received:2013-08-29 Revised:2014-01-08 Online:2014-06-30 Published:2014-06-30
  • Supported by:

    This work was supported by the National Natural Science Foundation of China (61202004).

Abstract:

Non-center network computing environments have some unique characteristics, such as instability, heterogeneity, autonomy, distribution and openness, which bring serious issues of security and reliability. This article proposes a brand-new credibility protection mechanism for resource sharing and collaboration in non-center network computing environments. First, the three-dimensional hierarchical classified topology (3DHCT) is proposed, which provides a basic framework for realizations of the identity credibility, the behavior credibility and the capability credibility. Next, the agent technology is utilized to construct the credibility protection model. This article also proposes a new comprehensive credibility evaluation algorithm with simple, efficient, quantitative and able to meet the requirements of evaluating behavior credibility and the capability credibility evaluation as well. The Dempster-Shafer theory of evidence and the combination rule are used to achieve the evaluation of the capability credibility. The behavior credibility is evaluated with the current and historical performance of nodes for providers and consumers to realize more accurate prediction. Based on the non-center network computing simulation test platform, simulation is been conducted to test the performance and validity of the proposed algorithms. Experiment and analysis show that the proposed algorithms are suitable for large-scale, dynamic network computing environments, and able to maintain the credibility for networks without relying on central node, make a non-center network gradually evolve into an orderly, stable and reliable computing environment efficiently.

Key words:

non-center network computing, agent, credibility, evidence