“Trustworthy and resilient monitoring system for cloud infrastructures”
in Proceedings of the Middleware 2011 Workshop on Posters and Demos Track, Lisbon, Portugal, Dec. 2011, pp. 3:1–3:2.http://dx.doi.org/10.1145/2088960.2088963.
Abstract: Current monitoring systems for cloud infrastructure run locally or are based on centralized model approaches such as HP Openview, Microsoft Operation Manager and ArcSight. Additionally, they do not look deep into resilience and delivering trustworthy data of its own services under crash or Byzantine failures caused by attackers or any other kind of sources. This work proposes a fault and intrusion tolerant (FIT) monitoring system for cloud computing infrastructures. We assume Byzantine failure model and use state machine replication for providing the trustworthy and resilient monitoring service.
Research line(s): Timeliness and Adaptation in Dependable Systems (TADS)