Cloud computing, mobile computing, Service-Oriented Computing (SOC), and Software as a Service (SaaS) indicate that the Internet emerges to an anonymous service market where service functionality can be dynamically and ubiquitously consumed. Among functionally similar services, service consumers are interested in the consumption of the services which perform best towards their optimization preferences. The experienced performance of a service at consumer side is expressed in its non-functional properties (NFPs). Selecting the best-fit service is an individual challenge as the preferences of consumers vary. Furthermore, service markets such as the Internet are characterized by perpetual change and complexity. The complex collaboration of system environments and networks as well as expected and unexpected incidents may result in various performance experiences of a specific service at consumer side. The consideration of certain call side aspects that may distinguish such differences in the experience of NFPs is reflected in various call contexts.

Service optimization based on a collaborative knowledge base of previous experiences of other, similar consumers with similar preferences is a desirable foundation. The research work described in this dissertation aims at an individually optimized selection of services considering the individual call contexts that have an impact on the performance, or NFPs in general, of a service as well as the various consumer preferences. The presented approach exploits shared measurement information about the NFP behavior of a service gained from former service calls of previous consumptions. Gaining selection/recommendation knowledge from shared experience benefits existing as well as new consumers of a service before its (initial) consumption. Our approach solely focuses on the optimization and collaborative information exchange among service consumers. It does not require the contribution of service providers or other non-consuming entities. As a result, the contribution among the participating entities also contributes to their own overall optimization benefit. With the initial focus on a single-tier optimization, we additionally provide a conceptual solution to a multi-tier optimization approach for which our recommendation framework is prepared in general.

For a consumer-sided optimization, we conducted a literature study of conference papers of the last decade in order to find out what NFPs are relevant for the selection and consumption of services. The ranked results of this study represent what a broad scientific community determined to be relevant NFPs for service selection.

We analyzed two general approaches for the employment of machine learning methods within our recommendation framework as part of the preparation of the actual recommendation knowledge. Addressing a future service market that has not fully developed yet and due to the fact that it seems to be impossible to be aware of the actual NFP data of different Web services at identical call contexts, a real-world validation is a challenge. In order to conduct an evaluation and also validation that can be considered to be close approximations to reality with the flexibility to challenge the machine learning approaches and methods as well as the overall recommendation approach, we used generated NFP data whose characteristics are influenced by measurement data gained from real-world Web services.

For the general approach with the better evaluation results and benefits ratio, we furthermore analyzed, implemented, and validated machine learning methods that can be employed for service recommendation. Within the validation, we could achieve up to 95% of the overall achievable performance (utility) gain with a machine learning method that is focused on drift detection, which in turn, tackles the change characteristic of the Internet being an anonymous service market.

The actual experience of the performance of services at consumers’ side is a desirable foundation for service selection. Considering the knowledge of previous performance experiences from a consumer’s perspective, a service broker can automatically select the best-fitting service out of a set of functionally similar services. In this paper, we present the evaluation of machine learning methods and frameworks which can be employed for service recommendation based on shared experiences of previous consumers. Implemented in a prototype, our approach considers a consumer’s call context as well as its selection preferences (expressed in utility functions). The implementation of the framework aims at the time-critical optimisation of service consumption with focus on runtime aspects and scalability. Therefore, we evaluated and employed high-performance, online and large scale machine learning methods and frameworks. Considering the Internet as a service market with perpetual change, strategies for concept drift have to be found. The evaluation showed that with the current approach, the framework recommended the actual best-fit service instance in 70% of the validation cases, while in 90% of the cases, the best or second best-fit was recommended. Furthermore, within our approach employing the best method, we achieved 94.5% of the overall maximum achievable utility value.

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%.

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.

Among functionally similar services, service consumersare interested in the consumption of the service that performsbest towards their optimization preferences. The experiencedperformance of a service at consumer side is expressed in its nonfunctionalproperties. Selecting the best-fit service is an individualaspect as the preferences of consumers vary. Furthermore, servicemarkets such as the Internet are characterized by perpetualchange and complexity. The complex collaboration of system environmentsand networks result in various performance experiencesat consumer side. Service optimization based on a collaborativeknowledge base of previous experiences of other, similar consumerswith similar preferences is a desirable foundation. In thisarticle, we present a service recommendation framework, whichaims at the optimization at consumer side focusing on the individualpreferences and call contexts. In order to identify relevantnon-functional properties for service selection, we conducted aliterature study of conference papers of the last decade. Theranked results of this study represent what a broad scientificcommunity determined to be relevant non-functional propertiesfor service selection. We furthermore analyzed, implemented, andvalidated machine learning methods that can be employed forservice recommendation. Within our validation, we could achieveup to 95% of the overall achievable performance (utility) gainwith a machine learning method that is focused on conceptdrift, which in turn, tackles the change characteristic of theInternet being a service market. Besides the comprehensive andscientific identification of relevant non-functional properties whenselecting a service, this article describes how machine learningcan be employed for service recommendation based on consumerexperiences in general, including an evaluation and overall proofof concept validation within our framework.

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.