Software Engineering Institute | Carnegie Mellon University
Software Engineering Institute | Carnegie Mellon University

Publications and References: Performance Reasoning Frameworks

Predictable Assembly of Substation Automation Systems: An Experiment Report. 2nd Edition (2002)
Scott Hissam, John Hudak, James Ivers, Mark Klein, Magnus Larsson, Gabriel Moreno, Linda Northrop, Daniel Plakosh, Judith Stafford, Kurt Wallnau, & William Wood

This reports the results of a PECT feasibility study we performed for ABB in the domain of power substation automation. Some ideas and terminology were refined a bit between its publication and that of Volume III, but it is representative of our approach, and does document a number of important concepts, especially the notions of co-refinement and empirical validation.

A Model Problem for an Open Robotics Controller (2004)
Scott A. Hissam & Mark Klein

This report describes the model problem created to support the continued enhancement and development of the prediction-enabled component technology (PECT) reasoning frameworks for an industrial trial in the domain of industrial robotics. The model problem here is an abstract representation of the parallel tasking and component configuration in an industrial robotics controller.

Performance Property Theories for Predictable Assembly from Certifiable Components (PACC) (2004)
Scott Hissam, Mark Klein, John Lehoczky, Paulo Merson, Gabriel Moreno, & Kurt Wallnau

This report develops a queueing-theoretic solution to predict, for a real-time system, the average-case latency of aperiodic tasks managed by a sporadic server. The report applies this theory to a model problem drawn in the domain of industrial robot control.

"Model-Driven Performance Analysis"
Gabriel A. Moreno & Paulo Merson. Proceedings of the 4th International Conference on the Quality of Software Architectures (QoSA 2008). Germany, October 14-17, 2008.

This paper describes how a model-driven engineering approach can be used not only to automatically generate implementations from design models but also to generate the corresponding analysis models for the same design. In particular, it shows how the performance reasoning framework in the SEI PACC Starter Kit can be used to predict the performance of a system from the same specification from which code will be generated.

"Predicting the Behavior of a Highly Configurable Component Based Real-Time System" 2008
Scott A. Hissam, Gabriel A. Moreno, Dan Plakosh, Isak Savo, & Marcin Stelmarczyk. Proceedings of 20th Euromicro Conference on Real-Time Systems (ECRTS 08), Prague, Czech Republic, July 2-4, 2008.

This paper discusses the results from an experiment that demonstrates the ability to predict deadline satisfaction of threads in a real-time system where the functionality performed is based on the configuration of the assembled software components. Presented is the method used to abstract the large, legacy code base of the system software and the application software components in the system, the model of those abstractions based on available architecture documentation and empirically-based, runtime observations, and the analysis of the predictions which yielded objective confidence in the observations and model created which formed the underlying basis for the predictions.

Using Containers to Enforce Smart Constraints for Performance in Industrial Systems (2005)
Scott A. Hissam, Gabriel A. Moreno, & Kurt C. Wallnau

This technical note shows how smart constraints can be embedded in software infrastructure by using containers, so that systems conforming to those constraints are predictable by construction. The use of containers is shown in the context of a model problem in the domain of industrial robotics.

Performance Analysis of Real-Time Component Architectures: A Model Interchange Approach
Gabriel A. Moreno, Connie U. Smith, & Lloyd G. Williams

Model interchange approaches support the analysis of software architecture and design by enabling a variety of tools to automatically exchange performance models using a common schema. This paper builds on the Software Performance Model Interchange Format (S-PMIF), and extends it to support the performance analysis of real-time systems. Specifically, it shows the transformation of designs in CCL to S-PMIF for additional performance analyses.