Data driven robust optimization exam 19032018 the exam is made of two independant parts. Cooperative datadriven distributionally robust optimization. Robust optimization problems where theuncertainty isaprobability. Likelihood robust optimization for datadriven problems. Brown y, constantine caramanis z july 6, 2007 abstract in this paper we survey the primary research, both theoretical and applied, in the. Furthermore, the book has been structured so that the first part could easily be used as the text for a graduate level course in robust optimization. The last decade witnessed an explosion in the availability of data for operations research applications. Distributionally robust optimization in context of data driven problems erick hans delage, ph. Datadriven distributionally robust optimization using the. The law invariance can be exploited to evaluate worstcase expectations via the sample average approximation. Introduction robust optimization is a popular approach to optimization under.
A novel data driven robust model for recipe optimization of crude oil blending is developed by utilizing the obtained uncertainty set. Data driven robust optimization under correlated uncertainty. The application of robust optimization in power systems final project report. Datadriven robust optimization approaches are adopted to. Section 2 presents the model of datadriven distributionally robust polynomial optimization dro for short.
While there are many high optimization ro came from the robust control community, ro is a distinct. The primary goal of this preface is to provide the reader. We propose piecewise linear kernelbased support vector clustering svc as a new approach tailored to datadriven robust optimization. This paper proposes a novel datadriven adaptive robust optimization aro framework for the unit commitment uc problem integrating wind power into smart grids. The new frontier of data driven price optimization duration. We then propose a novel framework for selecting a data driven policy from a given policy class. The approach is flexible and widely applicable, and robust optimization problems built from our new sets are computationally tractable, both theoretically and practically. In section 2, we survey a wide array of optimization classes, and also uncertainty sets, and consider the properties of the robust versions. Datadriven robust optimization based on kernel learning. Datadriven robust optimization for wastewater sludgetobiodiesel. Part of the lecture notes in computer science book series lncs, volume 4614.
They focus on the case where the uncertain parameters u. Different from conventional robust optimization methods, the proposed framework incorporates distributional information to avoid over. This book is devoted to robust optimization a speci. Motivated by this growing availability, we propose a novel schema for utilizing data to design uncertainty sets for robust optimization using statistical hypothesis. Second, the uncertainty set is constructed by combining principle component analysis and robust kernel density estimation based on the historical data of blending effects. Data driven distributionally robust optimization using the wasserstein metric 3 computational e ort is reported to be considerable, and there is no guarantee to nd the global optimum.
Data driven and robust optimization approaches to call centers, with x. The approach is flexible and widely applicable, and robust optimization problems built from our new sets are. Datadriven chance constrained and robust optimization under. Datadriven robust optimization mathematical programming. A datadriven robust optimization approach to operational optimization of industrial steam systems under uncertainty. Datadriven distributionally robust polynomial optimization. As a result, it can utilize characteristic properties of systematically collected data to optimize certain features of any given system. The approach is to formulate a datadriven distributionally robust optimization. Ewo seminar, 2011 pittsburgh, pa robust optimization for risk control in enterprisewide optimization juan pablo vielma department of industrial engineering. Processes free fulltext datadriven robust optimization. The last decade has seen an explosion in the availability of data for operations research applications as part of the big data revolution. Distributionally robust optimization dro online linear programming olp least squares with nonconvex regularization lsnr alternating direction method of multipliers admm. Robust optimization is an important sub eld of optimization that deals with uncertainty in the data of optimization problems.
The application of robust optimization in power systems. This may somewhat explain the scarce of applications of machine learning models in robust optimization all this time. We propose a twostage, online signal control strategy for dynamic networks using a linear decision rule ldr approach and a distributionally robust optimization dro technique. Section 3 situates our work in the context of the literature. Robust optimization uncertain data robust solution robust formulation probabilistic. View the article pdf and any associated supplements and figures. View the article pdf and any associated supplements and figures for a period of 48 hours. To reduce the conservatism and improve the robustness of solutions obtained from the above optimization approaches, industrial data is introduced to constraints, which results in the datadriven chance constrained programming jiang and guan, 2016, calfa et al. Motivated by this growing availability, we propose a novel schema for utilizing data to design uncertainty sets for robust optimization using statistical hypothesis tests. Robust optimization is an emerging area in research that allows addressing different optimization problems and specifically industrial optimization problems where there is a degree of uncertainty in some of the variables involved. Datadriven robust optimization for steam systems in ethylene. In contrast to previous work on distributionally robust optimization that focuses on certain parameters e. A read is counted each time someone views a publication summary such as the title, abstract, and list of authors, clicks on a figure, or views or downloads the fulltext. Datadriven distributionally robust optimization using the wasserstein metric.
A supply chain network is designed for largescale production of biodiesel from wastewater sludge. Datadriven appointmentscheduling under uncertainty. Datadriven learning in dynamic pricing using adaptive. Develop a system level control framework, to incorporate data information with realtime control decisions, balance vacant taxis with minimum total. By solving a quadratic program, the distributional geometry of massive uncertain data can be effectively captured as a compact convex uncertainty set, which considerably reduces conservatism of robust optimization. Sep 19, 2015 we consider optimal decisionmaking problems in an uncertain environment. An alternative streamline of datadriven optimization is the statistical robust optimization, which utilizes data, hypothesis tests, and likelihood to construct t he statistically interpretable. Datadriven robust optimization under correlated uncertainty. Datadriven robust optimization with application to portfolio. Nevertheless, tractability results are available for special cases. Data driven robust optimization is useful in chemical engineering because of the complexity of design problems. We investigate a data driven approach to constructing uncertainty sets for robust optimization problems, where the uncertain problem parameters are modeled as random variables whose joint. Ddr leverages the tractability of robust optimization and enables one to explicitly model the. Smalldata, largescale linear optimization with uncertain.
A field of optimization theory that deals with optimization problems in which a certain measure of robust ness is sought against uncertainty that can be represented as. Under this framework, the objective and constraint functions are only assumed. Robust optimization model for a class of uncertain linear programs. A data driven robust optimization ddro methodology is proposed to deal with uncertainty in the optimization of steam system in an ethylene plant. Robust optimization for risk control in enterprisewide. We propose piecewise linear kernelbased support vector clustering svc as a new approach tailored to data driven robust optimization. In particular, we consider the case in which the distribution of the input is unknown, yet there is some historical data drawn from the distribution. Datadriven robust optimization massachusetts institute of. Worlds best practices for developing winning vehicles is a musthave book for engineers and managers who are working on design, product, manufacturing, mechanical, electrical.
Datadriven adaptive robust unit commitment under wind. Distributionally robust optimization dro online linear programming olp least squares with nonconvex regularization lsnr alternating direction method of multipliers admm su. This book is an authoritative reference that will be very useful to researchers working in this area. Datadriven robust control of insulin therapy matlab. Robust optimization is an active area of research that is likely to find many practical applications in the future. This paper presents a framework that was developed to achieve data driven robust optimization of processes. This article addresses the operational optimization of industrial steam systems under device efficiency uncertainty using a data. For example, data driven robust optimization can be used in complex supply chain optimization. In this paper, we propose a new type of distributionally robust optimization model called the likelihood robust optimization lro model for this class of problems. In robust optimization, random variables are modeled as uncertain parameters belonging to a convex uncertainty set, and the decision maker protects the system against the worst case within that set. Motivated by this growing availability, we propose a novel schema for utilizing data to design uncertainty sets for robust optimization. Data driven optimization models and algorithms youtube.
In contrast to previous work on distributionally robust optimization. Dec 31, 20 the last decade witnessed an explosion in the availability of data for operations research applications. Theory and applications of robust optimization dimitris bertsimas. Boyd, and shie mannor a decision maker is often confronted with situations where he has incomplete knowledge. Nov 28, 2017 data driven optimization models and algorithms simons institute. Leveraging on recent results in robust optimization 4 and value function. Introduction robust optimization is a popular approach to optimization under uncertainty. There are several ways to apply robust optimization. Research 19 proposed a datadriven adaptive robust optimization method for operational optimization.
We study new datadriven distributionally robust optimization models as well. Operational optimization of industrial steam systems under. The main idea is to automatically build a predictive model using a machine a learning. May 06, 2016 data driven robust optimization under correlated uncertainty.
A datadriven multitime scale robust scheduling model for a windhydrothermal power system is presented in this study, according to the characteristic that wind power prediction accuracy increases with the decrease of the time scale. In this work, we apply distributionally robust optimization to handling the. Datadriven robust optimization for crude oil blending under. Selim mankai, france ipag lab, ipag business school. This set is a ball around a density function estimated from data samples, i. Datadriven robust optimization gtest are based on phidivergences see also 32. A case study of production scheduling in ethylene plant. Distributionally robust optimization under moment uncertainty. On the power of robust solutions in twostage stochastic and adaptive optimization problems, with vineet goyal, submitted to mathematics of operations research, 2009. We consider robust optimization for polynomial optimization problems where the uncertainty set is a set of candidate probability density functions.
Datadriven robust optimization with application to portfolio management, working papers 2014104, department of research, ipag business school. If necessary, you can admit the results of previous questions. Robust optimization is a field of optimization theory that deals with optimization problems in which a certain measure of robustness is sought against uncertainty that can be represented as deterministic variability in the value of the parameters of the problem itself andor its solution. Professor shahab mohaghegh, being one of the most innovative and experienced thought leaders in the field of data driven modeling in the upstream, has written a comprehensive and readable book that finally puts to bed the persistent complaints in the industry. The agents aim to cooperatively find, using their collected data, a solution with guaranteed outofsample performance. A data driven multistage adaptive robust optimization framework for planning and scheduling under uncertainty. Datadriven distributionally robust optimization for power. By solving a quadratic program, the distributional geometry of massive uncertain data can be effectively captured as a compact convex uncertainty set, which considerably reduces conservatism of robust optimization problems. Stanford university, 2009 reading committee members. Data driven distributionally robust optimization using the wasserstein metric.
The discussion gives an overview of current t1d therapy practice and the challenges behind closedloop insulin control and presents an ap system designimplemented and evaluated in matlabthat addresses these challenges through the integration of control techniques and datadriven models of patient behavior, showing simulation results on virtual patient models. A data driven robust optimization approach to operational optimization of industrial steam systems under uncertainty. A datadriven robust optimization ddro methodology is proposed to deal with uncertainty in the optimization of steam system in an ethylene plant. Robust optimization methodology and applications 455 cones k1. Datadriven robust optimization for steam systems in. We show that common data driven methods, such as sample average approximation, data driven robust optimization, and certain regularized policies, may perform poorly in this new setting. The models proposed in this paper fall within the scope of datadriven distribu tionally. The purpose of this tutorial is to present a mathematical framework that is wellsuited to the limited information available in reallife problems and captures the decisionmakers attitude towards uncertainty. In this paper, we propose an e ective data driven approach for robust optimization.
1361 780 244 1371 1556 1509 1469 1158 1463 801 1345 390 477 676 385 232 1315 1025 539 616 1347 1381 903 1279 1075 345 102 828 744 378