Autonomic resource provisioning for software business processes
Information and Software Technology
Decentralized web service orchestration: a reflective approach
Proceedings of the 2008 ACM symposium on Applied computing
The VLDB Journal — The International Journal on Very Large Data Bases
Autonomic business processes scalable architecture: position paper
BPM'07 Proceedings of the 2007 international conference on Business process management
A dynamically self-configurable service process engine
World Wide Web
Autonomic internet-scale workflows
Proceedings of the 3rd International Workshop on Monitoring, Adaptation and Beyond
Dynamic workflow adaptation over adaptive infrastructures
KES-AMSTA'11 Proceedings of the 5th KES international conference on Agent and multi-agent systems: technologies and applications
QoS prediction for composite web services with transactions
ICSOC'06 Proceedings of the 4th international conference on Service-oriented computing
International Journal of Systems and Service-Oriented Engineering
Hi-index | 0.00 |
An increasing amount of Web services are being implemented using process management tools and languages (BPML, BPEL, etc.). The main advantage of processes is that designers canexpress complex business conversations at a high level ofabstraction, even reusing standardized business protocols. Thedownside is that the infrastructure behind the Web service becomesmore complex. This is particularly critical for Web services that may be subjected to high variability in demand and suffer from unpredictable peaks of heavy load. In this paper we present a flexible architecture for process execution that has been designed to support autonomicscalability. The system runs on a cluster of computers and reacts toworkload variations by altering its configuration in order to optimallyuse the available resources. Such changes happen automaticallyand without any human intervention. This feature completely removesthe need for the manual monitoring and reconfiguration of the system,which in practice is a difficult and time-consuming operation. In thepaper we describe the architecture of the system and present anextensive performance evaluation of its autonomic capabilities.