Fuzzy decision making in embedded system design

The use of Application Specific Instruction-set Processors (ASIP) is a solution to the problem of increasing complexity in embedded systems design. One of the major challenges in ASIP design is Design Space Exploration (DSE), because of the heterogeneity of the objectives and parameters involved. Typically DSE is a multiobjective search problem, where performance, power, area, etc. are the different optimization criteria. The output of a DSE strategy is a set of candidate design solutions called a Pareto-optimal set. Choosing a solution for system implementation from the Paretooptimal set can be a difficult task, generally because Pareto-optimal sets can be extremely large or even contain an infinite number of solutions. In this paper we propose a methodology to assist the decision-maker in analysis of the solutions to multi-objective problems. By means of fuzzy clustering techniques, it finds the reduced Pareto subset, which best represents all the Pareto solutions. This optimal ...

• Type: Conference
• Year: 2006
• Where: CODES
• Authors: Alessandro G. Di Nuovo, Maurizio Palesi, Davide Patti, Giuseppe Ascia, Vincenzo Catania
• Keywords: CODES 2006, Embedded System, Hardware-Software Codesign, Pareto-optimal Sets, Solutions