Techniques and Visualization Approaches for Analyzing Local and Global Pareto Optimal Sets in Multi-Objective Design Space Exploration
Konferenz: ARCS 2011 - 24th International Conference on Architecture of Computing Systems
22.02.2011 - 23.02.2011 in Como, Italy
Tagungsband: ARCS 2011
Seiten: 11Sprache: EnglischTyp: PDFPersönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt
Taghavi, Toktam; Pimentel, Andy D. (University of Amsterdam, The Netherlands)
VMODEX is an interactive visualization tool to support system-level Design Space Exploration (DSE) of MPSoC architectures. It provides insight into the search process of Multi-Objective Evolutionary Algorithms (MOEAs) that are typically used in the DSE process, and it facilitates the analysis of the DSE results. In this paper we extend VMODEX to enable designers to evaluate and compare the properties of the discovered design points in different subspaces of the explored design space. Several techniques and visualization methods are provided to compare different parts of the design space from various aspects. Furthermore, some Multi-Objective Decision Making (MODM) methods are utilized to help designers with understanding the trade-offs between different criteria and guide them towards the most appropriate solutions among the Pareto optimal solutions. Moreover, new visualization approaches are proposed, which provide the designer with the visual interpretation and detailed analysis of the results of the MODM methods.