Machine Learning-Based System Optimization and Uncertainty Quantification for Integrated Systems

  • Hakki M. Torun
  • Mourad Larbi
  • Madhavan SwaminathanEmail author


Increasing complexity and higher integration of electronics leads to new challenges in system optimization. This is because modern systems contain structures with multi-scale geometries whose responses are determined by multi-physics simulations and often times contain components that are electromagnetically coupled. In practice, the use of optimization algorithms in the design cycle of such systems is limited to fine-tuning an already good design, which requires substantial human intervention and CPU time to arrive at an optimum solution. This is mainly due to lack of methods capable of handling high dimensionality at the same time converging to the global optimum regardless of the initial point selection. We therefore present a new, EDA oriented method, utilizing machine learning techniques to perform black-box optimization that starts with zero training data and ensures convergence to global optimum in the minimum amount of CPU time. In order to consider uncertainties in fabrication that are likely to cause deviations in the final design from the optimal design parameters, we present a ML-based uncertainty quantification (UQ) methodology. Although the combination of optimization and UQ algorithms presented in this chapter are fully automated and generic, we demonstrate these methods on an emerging application in system integration and power delivery, namely integrated voltage regulators (IVR). The IVR considered here is based on system in package (SiP) technology.



This work was supported in part by the National Science Foundation under Grant No. CNS 16-24810—Center for Advanced Electronics through Machine Learning (CAEML) and Power Delivery for Electronic Systems (PDES) Consortium, Georgia Tech, USA. The authors would also like to acknowledge Dr. Mohamed L. F. Bellaredj, Dr. Anto K. Davis, and Dr. Colin Pardue for their assistance in simulation and analysis of the IVR.


  1. 1.
    N. Sturcken, E.J. O’Sullivan, N. Wang, P. Herget, B.C. Webb, L.T. Romankiw, M. Petracca, R. Davies, R.E. Fontana, G.M. Decad, I. Kymissis, A.V. Peterchev, L.P. Carloni, W.J. Gallagher, K.L. Shepard, A 2.5d integrated voltage regulator using coupled-magnetic-core inductors on silicon interposer. IEEE J. Solid-State Circuits 48(1), 244–254 (2013)Google Scholar
  2. 2.
    N. Sturcken, M. Petracca, S. Warren, P. Mantovani, L.P. Carloni, A.V. Peterchev, K.L. Shepard, A switched-inductor integrated voltage regulator with nonlinear feedback and network-on-chip load in 45 nm SOI. IEEE J. Solid-State Circuits 47(8), 1935–1945 (2012)CrossRefGoogle Scholar
  3. 3.
    S. Mueller, K.Z. Ahmed, A. Singh, A.K. Davis, S. Mukhopadyay, M. Swaminathan, Y. Mano, Y. Wang, J. Wong, S. Bharathi, H.F. Moghadam, D. Draper, Design of high efficiency integrated voltage regulators with embedded magnetic core inductors, in 2016 IEEE 66th Electronic Components and Technology Conference (ECTC) (2016), pp. 566–573Google Scholar
  4. 4.
    H.M. Torun, M. Swaminathan, Black box optimization of 3D integrated systems, in Computational Modelling of Multi Uncertainty and Multi-Scale Problems (COMUS) (2017)Google Scholar
  5. 5.
    H.M. Torun, M. Swaminathan, A.K. Davis, M.L.F. Bellaredj, A global Bayesian optimization algorithm and its application to integrated system design. IEEE Trans. Very Large Scale Integr. VLSI Syst. 26(4), 792–802 (2018)CrossRefGoogle Scholar
  6. 6.
    H.M. Torun, M. Swaminathan, Black box optimization of 3D integrated systems using machine learning, in 2017 IEEE 26th Conference on Electrical Performance of Electronic Packaging and Systems, EPEPS (2017)Google Scholar
  7. 7.
    H.M. Torun, C.A. Pardue, M.L.F. Belladredj, A.K. Davis, M. Swaminathan, Machine learning driven advanced packaging and system miniaturization of IoT for wireless power transfer solutions, in IEEE 68th Electronic Components Technology Conference, ECTC (2018)Google Scholar
  8. 8.
    H.M. Torun, M. Larbi, M. Swaminathan, A bayesian framework for optimizing interconnects in High-Speed channels, in 2018 IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization (NEMO2018), Reykjavik, Iceland (2018)Google Scholar
  9. 9.
    G. Blatman, B. Sudret, Adaptive sparse polynomial chaos expansion based on least angle regression. J. Comput. Phys. 230(6), 2345–2367 (2011)MathSciNetCrossRefGoogle Scholar
  10. 10.
    M. Larbi, I.S. Stievano, F.G. Canavero, P. Besnier, Variability impact of many design parameters: the case of a realistic electronic link. IEEE Trans. Electromagn. Compat. 60(1), 34–41 (2018). CrossRefGoogle Scholar
  11. 11.
    S.J. Park, B. Bae, J. Kim, M. Swaminathan, Application of machine learning for optimization of 3-D integrated circuits and systems. IEEE Trans. Very Large Scale Integr. VLSI Syst. 25(6), 1856–1865 (2017)CrossRefGoogle Scholar
  12. 12.
    K. Kawaguchi, L.P. Kaelbling, T. Lozano-Pérez, Bayesian optimization with exponential convergence. Adv. Neural Inf. Process. Syst. 2809–2817 (2015)Google Scholar
  13. 13.
    E. Brochu, V.M. Cora, N. de Freitas, A tutorial on Bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning., arXiv:1012.2599 (2010)Google Scholar
  14. 14.
    N. Srinivas, A. Krause, S.M. Kakade, M. Seeger, Gaussian process optimization in the bandit setting: no regret and experimental design. arXiv:0912.3995 (2009)Google Scholar
  15. 15.
    J.R. Gardner, M.J. Kusner, Z.E. Xu, K.Q. Weinberger, J.P. Cunningham, Bayesian optimization with inequality constraints, in Proceedings of the 31st International Conference on Machine Learning, ICML (2014), pp. 937–945Google Scholar
  16. 16.
    Z. Wang, B. Shakibi, L. Jin, N. Freitas, Bayesian multi-scale optimistic optimization, in Artificial Intelligence and Statistics (2014), pp. 1005–1014Google Scholar
  17. 17.
    R. Munos, Optimistic optimization of a deterministic function without the knowledge of its smoothness, in Advances in Neural Information Processing Systems (2011), pp. 783–791Google Scholar
  18. 18.
    M.D. Hoffman, E. Brochu, N. de Freitas, Portfolio allocation for Bayesian optimization. in Proceedings of the Twenty-Seventh Conference on Uncertainty in Artificial Intelligence, UAI (2011), pp. 327–336Google Scholar
  19. 19.
    S. Surjanovic, Virtual library of simulation experiments [Online].
  20. 20.
    D.J. Lizotte, Practical bayesian optimization. Ph.D Thesis, University of Alberta, 2008Google Scholar
  21. 21.
    D.R. Jones, A taxonomy of global optimization methods based on response surfaces. J. Glob. Optim. 21(4), 345–383 (2001)MathSciNetCrossRefGoogle Scholar
  22. 22.
    ANSYS, Ansys HFSS ver. 2015.2 [Online].
  23. 23.
    ANSYS, Ansys Maxwell ver. 2015.2 [Online].
  24. 24.
    D.S. Gardner, G. Schrom, F. Paillet, B. Jamieson, T. Karnik, S. Borkar, Review of on-chip inductor structures with magnetic films. IEEE Trans. Magn. 45(10), 4760–4766 (2009)CrossRefGoogle Scholar
  25. 25.
    M.L.F. Bellaredj, S. Mueller, A.K. Davis, P. Kohl, M. Swaminathan, Y. Mano, Fabrication, characterization and comparison of fr4-compatible composite magnetic materials for high efficiency integrated voltage regulators with embedded magnetic core micro-inductors, in 2017 IEEE 67th Electronic Components and Technology Conference (ECTC) (2017)Google Scholar
  26. 26.
    M. Swaminathan, Power delivery for electronic system consortium (PDES). Georgia Institute of Technology (2017)Google Scholar
  27. 27.
    A. Rong, A.C. Cangellaris, Interconnect transient simulation in the presence of layout and routing uncertainty, in 2011 IEEE 20th Conference on Electrical Performance of Electronic Packaging and Systems (2011), pp. 157–160Google Scholar
  28. 28.
    A.K. Prasad, M. Ahadi, B.S. Thakur, S. Roy, Accurate polynomial chaos expansion for variability analysis using optimal design of experiments, in 2015 IEEE MTT-S International Conference on Numerical Electromagnetic and Multiphysics Modeling and Optimization (NEMO) (2015), pp. 1–4Google Scholar
  29. 29.
    D.V. Ginste, D.D. Zutter, D. Deschrijver, T. Dhaene, P. Manfredi, F. Canavero, Stochastic modeling-based variability analysis of on-chip interconnects. IEEE Trans. Compon. Packag. Manuf. Technol. 2(7), 1182–1192 (2012)CrossRefGoogle Scholar
  30. 30.
    B. Sudret, Uncertainty propagation and sensitivity analysis in mechanical models–contributions to structural reliability and stochastic spectral methods. Habilitation à diriger des recherches, Université Blaise Pascal, Clermont-Ferrand, 2007Google Scholar
  31. 31.
    Z. Zhang, T.W. Weng, L. Daniel, Big-data tensor recovery for high-dimensional uncertainty quantification of process variations. IEEE Trans. Compon. Packag. Manuf. Technol. 7(5), 687–697 (2017)CrossRefGoogle Scholar
  32. 32.
    A.K. Prasad, S. Roy, Accurate reduced dimensional polynomial chaos for efficient uncertainty quantification of microwave/RF networks. IEEE Trans. Microwave Theory Tech. (2017).
  33. 33.
    C. Soize, R. Ghanem, Physical systems with random uncertainties: chaos representations with arbitrary probability measure. SIAM J. Sci. Comput. 26(2), 395–410 (2004)MathSciNetCrossRefGoogle Scholar
  34. 34.
    M. Berveiller, B. Sudret, M. Lemaire, Stochastic finite element: a non intrusive approach by regression. Eur. J. Comput. Mech. 15(1–3), 81–92 (2006)CrossRefGoogle Scholar
  35. 35.
    D.C. Montgomery, Design and Analysis of Experiments (Wiley, New York, 2004)Google Scholar
  36. 36.
    B. Efron, T. Hastie, I. Johnstone, R. Tibshirani, Least angle regression. Ann. Stat. 32(2), 407–499 (2004)MathSciNetCrossRefGoogle Scholar
  37. 37.
    I.M. Sobol, Sensitivity estimates for nonlinear mathematical models. Math. Model. Comput. Exp. 1(4), 407–414 (1993)MathSciNetzbMATHGoogle Scholar
  38. 38.
    B. Sudret, Global sensitivity analysis using polynomial chaos expansions. Reliab. Eng. Syst. Saf. 93(7), 964–979 (2008)CrossRefGoogle Scholar
  39. 39.
    M.D. McKay, R.J. Beckman, W.J. Conover, A comparison of three methods for selecting values of input variables in the analysis of output from a computer code. Technometrics 42(1), 55–61 (2000)CrossRefGoogle Scholar
  40. 40.
    S. Marelli, B. Sudret, UQLab: a framework for uncertainty quantification in matlab, in Proceedings of 2nd International Conference on Vulnerability Risk Analysis and Management, Liverpool (2014), pp. 2554–2563Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Hakki M. Torun
    • 1
  • Mourad Larbi
    • 1
  • Madhavan Swaminathan
    • 1
    Email author
  1. 1.Georgia Institute of TechnologySchool of Electrical & Computer EngineeringAtlantaUSA

Personalised recommendations