Technical Reports (Computer Science)
Permanent URI for this collection
Browse
Recent Submissions
Item Integrating Data Mining into Feedback Loops for Predictive Context Adaptation(2013-11-29) Rook, Angela; Knauss, Alessia; Damian, Daniela; Muller, Hausi A.; Thomo, AlexRequirements for today's systems are increasingly valid only within certain operating contexts. Requirements engineering and implementation stages of system development must carefully consider how to integrate evolving context related to specific requirements in order for the system to stay relevant and flexible. In this paper we propose to use data mining techniques for predictive context adaptation. Our approach leverages data collected from the past and decides, based on this historical data, which context conditions to monitor in order to predictively identify when a system needs to be adapted to fulfill a particular requirement. We demonstrate our approach on an adaptive mobile application to support the coordination of a team of rowers in an environment with a continually changing operational context.Item Parallel tempered particle filter(2010-05-26T19:57:49Z) Marinakis, DimitriIn this paper, we present the concept of running multiple configuration-exchanging particle filters in parallel; each characterizing an increasingly 'smoothed' version of the target density via the technique of sampling at high temperatures. This technique is used in Markov Chain Monte Carlo to improve mixing where it is known as parallel tempering.Item Dynamic resource allocation in computing clouds through distributed Multiple Criteria Decision Analysis(2010-04-01T00:01:36Z) Yazır, Yağız Onat; Matthews, Chris; Farahbod, Roozbeh; Guitouni, Adel; Neville, Stephen; Ganti, Sudhakar; Coady, YvonneIn computing clouds, it is desirable to avoid wasting resources as a result of under-utilization and to avoid lengthy response times as a result of over-utilization. In this paper, we propose a new approach for dynamic autonomous resource management in computing clouds. The main contribution of this work is two-fold. First, we adopt a distributed architecture where resource management is decomposed into independent tasks, each of which is performed by Autonomous Node Agents that are tightly coupled with the physical machines in a data center. Second, the Autonomous Node Agents carry out configurations in parallel through Multiple Criteria Decision Analysis using the PROMETHEE method. Simulation results show that the proposed approach is promising in terms of scalability, feasibility and flexibility.