Active Fault-Tolerant System for Open Distributed Computing

Abstract

Computer systems are growing in complexity and sophistication as open distributed systems and new technologies are used to achieve higher reliability and performance. Open distributed systems are some of the most successful structures ever designed for the computer community together with their undisputed benefits for users. However, this structure has also introduced a few side-effects, most notably the unanticipated runtime events and reconfiguration burdens imposed by the environmental changes. In this paper, we design a model that exploits the knowledge of pre-fault behavior to predict the suspected environmental faults and failures. Further, it can analyse the current underlying environmental behavior, in terms of current faults and failures. Therefore, this model mainly provides proactive as well as real-time fault-tolerant approaches in order to address unanticipated events and unpredictable hazards in distributed systems. Therefore, providing active fault tolerance could have a major impact with the growing requirements to support autonomic computing to overcome their rapidly growing complexity and to enable their further growth.