Andreas Heberle

Construction of Verified Compiler Front-Ends with Program-Checking

This paper describes how program-checking can be used to establish the correctness of a compiler front-end which was generated by unverified compiler construction tools. The basic idea of programchecking is to use an unverified algorithm whose results are checked by a verified component at run time. The approach not only simplifies the construction of a verified compiler front-end because checking the result of the analysis is much simpler to verify than the verification of a high sophisticated compiler front-end. It even allows to define a notion of front-end correctness. Furthermore, we are still able to use existing generators tools without major modifications. Additionally, this work points out the tasks which still have to be verified and it discusses the flexibility of the approach.

Service Level Achievements -- Distributed Knowledge for Optimal Service Selection

In a service-oriented setting, where services are composed to provide end user functionality, it is a challenge to find the service components with best-fit functionality and quality. A decision based on information mainly provided by service providers is inadequate as it cannot be trusted in general. In this paper, we discuss service compositions in an open market scenario where an automated best-fit service selection and composition is based on Service Level Achievements instead. Continuous monitoring updates the actual Service Level Achievements which can lead to dynamically changing compositions. Measurements of real life services exemplify the approach.

Classification vs. Regression - Machine Learning Approaches for Service Recommendation Based on Measured Consumer Experiences

Service functionality can be provided by more than one service consumer. In order to choose the service which creates the most benefit before its consumption, a selection based on previous measurable experiences by other consumers is beneficial. In this paper, we present the results of our analysis of two machine learning approaches to predict the best service within this selection problem. The first approach focuses on classification, predicting the best performing service, while the second approach focuses on regression, predicting service performances which can then be used for the determination of the best candidate. We assessed and compared both approaches for service recommendation w.r.t. The performance gain when selecting the recommended instead of a random service. Our evaluation is based on data measured on real Web services as well as on simulated data. The latter is needed for a more profound analysis of the strengths and weaknesses of each approach. The simulated data has similar statistical properties as the data measured on real Web services. In the real-world case, regression achieved a response time gain of over 92% of the optimum and classification over 83%. In case of simulated data, we could achieve an overall gain of up to 95% using classification, while regression achieved 89%.

Evaluation of the Employment of Machine Learning Approaches and Strategies for Service Recommendation

Service functionality can be provided by more than one service consumer. In order to choose the service with the highest benefit, a selection based on previously measured experiences by other consumers is beneficial. In this paper, we present the results of our evaluation of two machine learning approaches in combination with several learning strategies to predict the best service within this selection problem. The first approach focuses on the prediction of the best-performing service, while the second approach focuses on the prediction of service performances which can then be used for the determination of the best-performing service. We assessed both approaches w. r. t. the overall optimization achievement relative to the worst- and the best-performing service. Our evaluation is based on data measured on real Web services as well as on simulated data. The latter is needed for a more profound analysis of the strengths and weaknesses of each approach and learning strategy when it gets harder to distinguish the performance profile of the service candidates. The simulated data focuses on different aspects of a service performance profile. For the real-world measurement data, 97 % overall optimization achievement and over 82 % best service selection could be achieved within the evaluation.

Cloud Integration Patterns

Enterprises use the cloud for unlimited resource, scalability and elastic provisioning along with being able to use state of the art commodity or specialized solutions available in the cloud. The challenge of this vision is the proper and safe integration of on-premise IT-Landscapes with data and applications in the cloud. To find solutions for integration of classical and cloud environments two approaches, top-down and bottom-up, were used. In the top-down approach cloud integration patterns were specified based on scenarios. In the bottom-up approach cloud integration patterns were based on case study application requirements. Results of this paper are novel cloud integration patterns for various cloud integration scenarios.

Muster in BPM-Systemen mit Geschäftstransaktionen

In diesem Kapitel werden wiederverwendbare Muster zum Transaktionsmanagement vorgestellt. Diese vereinfachen die Implementierung transaktionaler Aspekte in automatisierten Prozessen und steigern gleichzeitig die Entwicklungseffizienz. Die Muster wurden aus realen Anwendungsszenarien abgeleitet, sind in unterschiedlichen fachlichen Kontexten einsetzbar und sind in BPMN beschrieben, damit sie leicht in BPM-Losungen genutzt werden konnen.

Weak subtyping and genericity

In the past, object-oriented design focused on encapsulation and inheritance as primary concepts. As a consequence, there has been a lot of work in the domain of inheritance and the associated problems, i.e. covariant type systems. Recently, parameterized (generic) classes have become more popular in object-oriented design. While the use of genericity in functional languages is well known and delivers no major problems, the situation in object-oriented languages differs: the combination of inheritance with genericity raises problems. This paper describes the theoretical foundations of designing and using generic classes in object-oriented systems. It discusses the possible relationships between generic subclasses as well as those between specialized instances of one generic class. The ideas presented use the concept of context dependent subtypes, so-called weak subtypes, to define criteria for correctness, well-formedness and substitutability.