Presentation on theme: "Architecture for Exploring Large Design Spaces John R. Josephson, B. Chandrasekaran, Mark Carroll, Naresh Iyer, Bryon Wasacz, Qingyuan Li, Giorgio Rizzoni,"— Presentation transcript:
Architecture for Exploring Large Design Spaces John R. Josephson, B. Chandrasekaran, Mark Carroll, Naresh Iyer, Bryon Wasacz, Qingyuan Li, Giorgio Rizzoni, David Erb
Architecture for exploring large design spaces Threesynergisticcomponents Three synergistic components SeekerFilterViewer
Design Seeker Human initiates automated design search which may work by considering combinations of: generic devices (configurations) alternative components representative parameter values. Designs are evaluated according to multiple criteria using simulation-based and other critics
Big search ! Search may be massive and exhaustive. Largest experiment to date 2,152,698 designs were generated and evaluated, of which 1,796,025 were fully specified. Each fully specified design was evaluated using multiple simulations. Seeker used idle time on 209 workstations to search the space in 6.8 days (wall-clock time). (The maximum number running at any one time was 159.)
Dominance Filter Dominance algorithm
Dominance Filter Design candidate A is said to dominate candidate B if A is superior or equal to B in every criterion of evaluation and strictly superior for at least one criterion. Dominated designs are removed. (This is lossless) Surviving designs are Pareto optimal (improvement on any criterion will reduce value on another) Tolerances may be specified for the comparisons.
Dominance Filter Dominance algorithm Dominance filtering can be very effective.
Effectiveness of dominance filtering Using 4 criteria and reasonably realistic simulation models : Dominance filtering is very effective! Dominance filtering scales very well!
Efficiency of dominance filtering algorithm 1,796,025 1, hours (serial post processing)
Effect of number of criteria In experiment B with 17,711 designs : The effectiveness of dominance filtering apparently tends to decrease as the number of criteria increases.
Interactive Viewer Tradeoffs are explored interactively. FilterViewer
Interactive Viewer visualization of trade-offs zooming to selected regions in trade-off space selection of subsets by structural constraints (not implemented) initiation of more focused search (not implemented) initiation of additional search, e.g., add criteria (not implemented)
Visualizing search results
Exploring large design spaces Human-in-the-loop multi-criterial optimization SeekerFilterViewer
Patent application has been submitted.
Next Steps Technology for composable simulation models Technology for composable simulation models Improved viewer - more types of displays Improved viewer - more types of displays Automatic extraction of generalizations Automatic extraction of generalizations
Design Seeker Essentially: a generator of design a generator of design evaluators for designs evaluators for designs
More generally The Seeker consists of: a generator of choice alternatives a generator of choice alternatives evaluators for choice alternatives evaluators for choice alternatives
Seeker based on client-server User Server Filter Gen In Out Client starter Clients Crit Crit Crit Crit Crit Crit Crit Crit Crit Crit Crit Crit Crit Crit Crit Crit Crit Crit Crit Crit Crit