Data‐driven adaptive nested robust optimization: General modeling framework and efficient computational algorithm for decision making under uncertainty

Abstract

A novel data‐driven adaptive robust optimization framework that leverages big data in process industries is proposed. A Bayesian nonparametric model—the Dirichlet process mixture model—is adopted and combined with a variational inference algorithm to extract the information embedded within uncertainty data. Further a data‐driven approach for defining uncertainty set is proposed. This machine‐learning model is seamlessly integrated with adaptive robust optimization approach through a novel four‐level optimization framework. This framework explicitly accounts for the correlation, asymmetry and multimode of uncertainty data, so it generates less conservative solutions. Additionally, the proposed framework is robust not only to parameter variations, but also to anomalous measurements. Because the resulting multilevel optimization problem cannot be solved directly by any off‐the‐shelf solvers, an efficient column‐and‐constraint generation algorithm is proposed to address the computational challenge. Two industrial applications on batch process scheduling and on process network planning are presented to demonstrate the advantages of the proposed modeling framework and effectiveness of the solution algorithm. © 2017 American Institute of Chemical Engineers AIChE J, 63: 3790–3817, 2017

Optimization under uncertainty in the era of big data and deep learning: When machine learning meets mathematical programming

“…However, uncertainty sets in the conventional robust optimization methodology are typically set a priori using a fixed shape and/or model without providing sufficient flexibility to capture the structure and complexity of uncertainty data. For example, the geometric shapes of uncertainty sets in (4) and (5) A data-driven ARO framework that leverages the power of Dirichlet process mixture model was proposed [25]. The data-driven approach for defining uncertainty set was developed based on Bayesian machine learning.…”

“…Deep learning, one of the most rapidly growing machine learning subfields, demonstrates remarkable power in deciphering multiple layers of representations from raw data without any domain expertise in designing feature extractors [15]. More recently, dramatic progress of mathematical programming [16], coupled with recent advances in machine learning [17], especially in deep learning over the past decade [18], sparks a flurry of interest in data-driven optimization [19][20][21][22][23][24][25][26].…”

A data-driven robust optimization approach to scenario-based stochastic model predictive control

“…Notice that for interior points we have α i = 0. Therefore, the uncertainty set (22) is only defined by boundary points and outliers with α i > 0. In this sense, W is "supported" by boundary points and outliers, and this is why they are referred to as "support vectors".…”

Data-driven stochastic robust optimization: General computational framework and algorithm leveraging machine learning for optimization under uncertainty in the big data era

“…In this subsection, we discuss the relationship between the DDSRO framework proposed in this work and the data-driven adaptive nested robust optimization (DDANRO) framework proposed earlier [8].…”