Abstract—Design and optimization of embedded systems play an important role in development trend of embedded technology. This paper presents a new approach to design and optimize embedded systems in the design phase based on Pareto multi-objective optimization. We defined a Domain Specific Language and developed the framework which is used to design the architecture model of embedded systems. And we integrated the code generation technology called Text Template Transformation Toolkit to this framework to automatically generate parameters from architectural model. Then we also do multi-objective optimization to select the best trade-off configuration of the embedded system architecture based on Pareto principle and Genetic Algorithm.