This paper gives an overview of the current state of ASoC design methodology and presents preliminary results on evaluating the learning classifier system XCS for the control of a QuadCore. The ASoC design methodology can determine system reliability based on activity, power and temperature analysis, together with reliability block diagrams. The evaluation of the XCS shows that in the evaluated setup, XCS can find optimal operating points, even in changed environments or with changed reward functions. This even works, though limited, without the genetic algorithm the XCS uses internally. The results motivate us to continue the evaluation for more complex setups.
@InProceedings{bernauer_et_al:DagSemProc.08141.6, author = {Bernauer, Andreas and Fritz, Dirk and Sander, Bj\"{o}rn and Bringmann, Oliver and Rosenstiel, Wolfgang}, title = {{Current state of ASoC design methodology}}, booktitle = {Organic Computing - Controlled Self-organization}, pages = {1--17}, series = {Dagstuhl Seminar Proceedings (DagSemProc)}, ISSN = {1862-4405}, year = {2008}, volume = {8141}, editor = {Kirstie Bellman and Michael G. Hinchey and Christian M\"{u}ller-Schloer and Hartmut Schmeck and Rolf W\"{u}rtz}, publisher = {Schloss Dagstuhl -- Leibniz-Zentrum f{\"u}r Informatik}, address = {Dagstuhl, Germany}, URL = {https://drops.dagstuhl.de/entities/document/10.4230/DagSemProc.08141.6}, URN = {urn:nbn:de:0030-drops-15646}, doi = {10.4230/DagSemProc.08141.6}, annote = {Keywords: Dagstuhl Seminar Proceedings, System-on-Chip, design methodology, system reliability, learning classifier system, XCS, ASoC} }
Feedback for Dagstuhl Publishing