Skip to main content

Fast Design Space Exploration of Nonlinear Systems: Part II

Author(s): Terway, Prerit; Hamidouche, Kenza; Jha, Niraj K

To refer to this page use:
Full metadata record
DC FieldValueLanguage
dc.contributor.authorTerway, Prerit-
dc.contributor.authorHamidouche, Kenza-
dc.contributor.authorJha, Niraj K-
dc.identifier.citationTerway, Prerit, Hamidouche, Kenza, Jha, Niraj K. (2022). Fast Design Space Exploration of Nonlinear Systems: Part II. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 41 (9), 2984 - 2999. doi:10.1109/tcad.2021.3119274en_US
dc.description.abstractNonlinear system design is often a multi-objective optimization problem involving search for a design that satisfies a number of predefined constraints. The design space is typically very large since it includes all possible system architectures with different combinations of components composing each architecture. In this article, we address nonlinear system design space exploration through a two-step approach encapsulated in a framework called Fast Design Space Exploration of Nonlinear Systems (ASSENT). In the first step, we use a genetic algorithm to search for system architectures that allow discrete choices for component values or else only component values for a fixed architecture. This step yields a coarse design since the system may or may not meet the target specifications. In the second step, we use an inverse design to search over a continuous space and fine-tune the component values with the goal of improving the value of the objective function. We use a neural network to model the system response. The neural network is converted into a mixed-integer linear program for active learning to sample component values efficiently. We illustrate the efficacy of ASSENT on problems ranging from nonlinear system design to design of electrical circuits. Experimental results show that ASSENT achieves the same or better value of the objective function compared to various other optimization techniques for nonlinear system design by up to 53%. We improve sample efficiency by 6-12× compared to reinforcement learning based synthesis of electrical circuits.en_US
dc.format.extent2984 - 2999en_US
dc.relation.ispartofIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systemsen_US
dc.rightsAuthor's manuscripten_US
dc.titleFast Design Space Exploration of Nonlinear Systems: Part IIen_US
dc.typeJournal Articleen_US

Files in This Item:
File Description SizeFormat 
2104.02464.pdf2.83 MBAdobe PDFView/Download

Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.