Abstract :
Summary form only given. Since 1995, the Performance and Dependability Symposium (PDS) has been a high-quality international forum for researchers and practitioners to report on the state-of-the-art of the evaluation of the impact of faults on the operation and performance of computer and communication systems. Where in the early years of PDS the considered faults were typically accidental (hardware failures, software bugs, operator errors), in recent years intentional and malicious faults and attacks have become a major concern as well. This trend is further reinforced in this year´s PDS program. PDS continues its tradition of being a high-quality conference bridging the gap between new developments from a methodological point of view, and the application thereof in the evaluation of a system in terms of its performance and dependability (both seen in a broad sense). In this tradition, PDS serves the need of both academia and industry. This year´s program presents therefore a mixture of methodological, algorithmic and architectural papers and experience reports, always with an element of quantification, either model-based or experimental. Upon the call for papers, we received close to 100 full-paper submissions. Each submitted paper was reviewed by at least 3 PC members and at least one external expert reviewer. At the plenary PC meeting, hosted by Imperial College in London, Feb. 9 and 10, 2006, the 23 papers you find in the PDS section of these proceedings were selected. As many as 25 PC members took part in this plenary meeting. The selection process has been very competitive, and we thank all authors for submitting their papers for consideration in the PDS program.
