Web service compositions need to adapt to changes in their constituent web services, in order to maintain functionality and
performance. Therefore, service compositions must be able to detect web service failure and performance degradation resulting
in the violation of service-level agreements. Automated diagnosis and repair are equally important. However, existing standards
and languages for service compositions, such as BPEL, lack constructs for web service monitoring and runtime adaptability,
which are pre-requisites for diagnosis and repair. We present a solution for transparent runtime monitoring, as well as automated
performance degradation detection, diagnosis, and repair for service compositions expressed as BPEL processes. Our solution
uses lightweight monitoring techniques, supports customizable diagnosis and repair strategies, and is compatible with any
standards-compliant BPEL engine.
Keywords Dynamic adaptability – SLA violation detection – Statistical tests – BPEL processes – Performance monitoring