Research on Grade Optimization Self-tuning Method for System Dependability Based on Autonomic Computing

In order to enhance the service performance, the preservation and increase of system dependability are researched and a system dependability self-tuning method is proposed based on autonomic computing. The self-tuning method attempts to achieve the sustained growth of system dependability by on-line evaluation, dynamic prediction and tuning of self-tuning scheme. There are four tuning methods random interval, settled interval, dependability threshold value and event trigger, which are discussed in the simulation experimentation. The tuning effects that affect system dependability increment are analyzed, and the optimal tuning opportunities for each tuning method are given. The result of simulation experiment shows that the tuning methods will ensure the positive increase of system dependability increment except random interval.