Efficient multi-fidelity simulation optimization

Simulation models of different fidelity levels are often available for a complex system. High-fidelity simulations are accurate but time-consuming. Therefore, they can only be applied to a small number of solutions. Low-fidelity simulations are faster and can evaluate a large number of solutions. But their results may contain significant bias and variability. We propose an Multi-fidelity Optimization with Ordinal Transformation and Optimal Sampling (MO2TOS) framework to exploit the benefits of high- and low-fidelity simulations to efficiently identify a (near) optimal solution. MO2TOS uses low-fidelity simulations for all solutions and then assigns a fixed budget of high-fidelity simulations to solutions based on low-fidelity simulation results. We show the benefits of MO2TOS via theoretical analysis and numerical experiments with deterministic simulations and stochastic simulations where noise is negligible with sufficient replications. We compare MO2TOS to Equal Allocation (EA) and Optimal Computing Budget Allocation (OCBA). MO2TOS consistently outperforms both EA and OCBA.

[1]  Chun-Hung Chen,et al.  A Review of Optimal Computing Budget Allocation Algorithms for Simulation Optimization Problem , 2010 .

[2]  Leyuan Shi,et al.  An Optimal Sample Allocation Strategy for Partition-Based Random Search , 2014, IEEE Transactions on Automation Science and Engineering.

[3]  Tongdan Jin,et al.  Designing a Sustainable and Distributed Generation System for Semiconductor Wafer Fabs , 2013, IEEE Transactions on Automation Science and Engineering.

[4]  Karen Willcox,et al.  A Provably Convergent Multifidelity Optimization Algorithm not Requiring High-Fidelity Derivatives , 2010 .

[5]  Yiming Li,et al.  A Coupled-Simulation-and-Optimization Approach to Nanodevice Fabrication With Minimization of Electrical Characteristics Fluctuation , 2006, IEEE Transactions on Semiconductor Manufacturing.

[6]  Chun-Hung Chen,et al.  Simulation Budget Allocation for Further Enhancing the Efficiency of Ordinal Optimization , 2000, Discret. Event Dyn. Syst..

[7]  H. N. Nagaraja,et al.  Order Statistics, Third Edition , 2005, Wiley Series in Probability and Statistics.

[8]  Chun-Hung Chen,et al.  Efficient Simulation-Based Composition of Scheduling Policies by Integrating Ordinal Optimization With Design of Experiment , 2007, IEEE Transactions on Automation Science and Engineering.

[9]  Herbert A. David,et al.  Order Statistics , 2011, International Encyclopedia of Statistical Science.

[10]  Jie Xu,et al.  An Adaptive Hyperbox Algorithm for High-Dimensional Discrete Optimization via Simulation Problems , 2013, INFORMS J. Comput..

[11]  Roxanne Moore,et al.  Value-based global optimization , 2014 .

[12]  Loo Hay Lee,et al.  MO2TOS: Multi-Fidelity Optimization with Ordinal Transformation and Optimal Sampling , 2016, Asia Pac. J. Oper. Res..

[13]  Haitao Liao,et al.  Joint Production and Spare Part Inventory Control Strategy Driven by Condition Based Maintenance , 2010, IEEE Transactions on Reliability.

[14]  R. A. Miller,et al.  Sequential kriging optimization using multiple-fidelity evaluations , 2006 .

[15]  Loo Hay Lee,et al.  Stochastic Simulation Optimization - An Optimal Computing Budget Allocation , 2010, System Engineering and Operations Research.

[16]  Daniel E. Rivera,et al.  Simulation-based optimization of process control policies for inventory management in supply chains , 2006, Autom..

[17]  Mehmet Cakmakci,et al.  A feasibility study using simulation-based optimization and Taguchi experimental design method for material handling—transfer system in the automobile industry , 2012 .

[18]  Chun-Hung Chen,et al.  Efficient Selection of a Set of Good Enough Designs With Complexity Preference , 2012, IEEE Transactions on Automation Science and Engineering.