Christoph Lingenfelder

Event-Driven Quality of Service Prediction

Quality of Service Management (QoSM) is a new task in IT-enabled enterprises that supports monitoring, collecting and predicting QoS data. QoSM solutions must be able to efficiently process runtime events, compute and pre dict QoS metrics, and provide real-time visibility and prediction of key perform ance indicators (KPI). Currently, most QoSM systems focus on moni tor ing of QoS constraints, i.e., they report what has been happened. In a way, this provides the awareness of past developments and sets the basis for decisions. However, this kind of knowledge is afterwit. For example, it cannot provide early warnings to prevent the QoS degradation or the violation of commitments. In this paper, we move one step forward to provide QoS prediction. We argue that performance metrics and KPIs can be predicted based on historical data. We present the design and implementation of a novel event-driven QoS prediction system. Integrated into the SOA infrastructure at large, the prediction system can process operational service events in a real-time fashion, in order to predict or refine the prediction of metrics and KPIs.

Open standards and cloud computing: KDD-2009 panel report

At KDD-2009 in Paris, a panel on open standards and cloud computing addressed emerging trends for data mining applications in science and industry. This report summarizes the answers from a distinguished group of thought leaders representing key software vendors in the data mining industry. Supporting open standards and the Predictive Model Markup Language (PMML) in particular, the panel members discuss topics regarding the adoption of prevailing standards, benefits of interoperability for business users, and the practical application of predictive models. We conclude with an assessment of emerging technology trends and the impact that cloud computing will have on applications as well as licensing models for the predictive analytics industry.

Universally Quantified Queries in Language with Order-Sorted Logics

In many applications of Knowledge-Based Systems or deductive databases the user wants to be able to check whether a certain property P(x) holds globally, i.e. whether it can be derived for all the individuals in the data base. Normally knowledge representation systems or logic programming systems cannot answer such requests. In this paper we show that the taxonomy of classes available in standard knowledge representation languages allows to solve this kind of query by dividing the proof into several cases according to the subsort structure present in the knowledge base.