Authors:
Kyriakos Kritikos
;
Chrysostomos Zeginis
;
Andreas Paravoliasis
and
Dimitris Plexousakis
Affiliation:
ICS-FORTH, Greece
Keyword(s):
Complex Event Processing, Event Pattern, Detection, Service.
Abstract:
A modern service-based application (SBA) operates in a cross-cloud, highly dynamic environment while comprises
various components at different abstraction levels that might fail. To support cross-level SBA adaptation,
a cross-cloud Service Level Objective (SLO) monitoring and evaluation system is required, able to produce
the right events that must trigger suitable adaptation actions. While most research focuses on SBA monitoring,
SLO evaluation is usually restricted in a centralised, single-cloud form, not amenable to heavy workloads that
could incur in a complex SBA system. Thus, a fast and scalable event generation and processing system is
needed, able to scale well to handle such a load. Such a system must address the cross-level event composition,
suitable for detecting complex problematic situations. This paper closes this gap by proposing a novel complex
event processing framework, scalable and distributable across the whole SBA architecture. This framework
can cover any kind
of event combination, no matter how complex it is. It also supports event pattern management
while exploits a publish-subscribe mechanism to: (a) synchronise with the modification of adaptation
rules directly involving these event patterns; (b) enable the decoupling from an SBA management system.
(More)