Informs Annual Meeting 2017

MA60

INFORMS Houston – 2017

MA60

2 - Integrated Modeling to Answer Research Questions at the Intersection of Food-energy-water in Ethiopia Sriram Sankaranarayanan, Johns Hopkins University, Baltimore, MD, 21218, United States, ssankar5@jhu.edu, Ying Zhang, Benjamin Zaitchik, Sauleh Ahmad Siddiqui We present an integrated partial equilibrium model for food and energy markets that computes food production and trade volumes in Ethiopia, and models power generation and transmission from hydel and geothermal power stations. Coupling these models though prices and quantities along their supply chains, we asses shifts in welfare under policy scenarios. We run the model under improved irrigation capabilities, crop rotation strategies, and injection of food aid during crop failure. 3 - Opportunities for Energy Water Nexus Planning and Operation Amro Farid, Dartmouth College, Hanover, NH, United States, Amro.M.Farid@dartmouth.edu This presentation identifies and motivates several opportunities for integrated operations management and planning of the the energy-water nexus (EWN). First, an exposition of the EWN is given. This discussion focuses on the electric power, potable water, and wastewater distributions systems. Second, the paper shifts to opportunities in integrated operations management highlighted by an energy-water nexus supply-side economic dispatch illustration. Thirdly, the discussion shifts to planning opportunities for the energy-water nexus for the sustainable development of water and energy resources. A concluding section

370A Software Tips for the Analytics Classroom Sponsored: INFORMEd Sponsored Session Chair: Thomas G. Groleau, Carthage College, Kenosha, WI, 53140- 1994, United States, tgroleau@carthage.edu 1 - Software Tips for the Analytics Classroom Nilakantan Sundara Raman Narasinganallur, K.J. Somaiya Institute of Management Studies & Research, B 602 Tulip Rachna Garden, Mulund Colony, Mumbai, 400082, India, nilakantan@somaiya.edu Data analytics has come into limelight especially with voluminous data being generated. Big data requires new techniques in analytics and new softwares. Whether prescriptive or predictive, analytics requires faster integration and implementation. When we teach analytics in the classroom, we need to impart understanding with many shortcuts and tips to make the experience useful and skill-building. The presentation will touch upon the presenter’s experience with teaching predictive and prescriptive analytical methods to MBAs in India. 2 - The Role of Simulation Games in the Analytics Classroom Vincent Hargaden, University College Dublin, School of Mechanical & Materials Engineering, Engineering & Materials Science Centre, Belfield, Dublin 4, Ireland, vincent.hargaden@ucd.ie We describe the use and impact of an internet based supply chain simulation game to teach topics in analytics to graduate engineering and business school students. This well-known game from Responsive Learning Technologies requires students to apply forecasting, inventory management, transportation and facility location concepts. Using data from 122 student groups since 2011, we compare performance between engineering and business school student cohorts. 3 - Excel is Great – Until it Isn’t Thomas G. Groleau, Carthage College, 2001 Alford Park Drive, Kenosha, WI, 53140-1994, United States, tgroleau@carthage.edu Microsoft Excel’s all-purpose flexibility makes it a commonly used tool for introductory business statistics or other analytics-oriented classes. However it becomes cumbersome for two or more sample inference and large data sets. While we start our business statistics classes with Excel, we transition to dedicated statistics software (SPSS) as the class progresses. This presentation covers when and how we make that transition. 4 - Faculty Resources on the INFORM-ED Website 370B Optimization in Food-Energy-Water Nexus Sponsored: Energy, Natural Res & the Environment, Energy Sponsored Session Chair: Masood Parvania, University of Utah, Salt Lake City, UT, 84112, United States, masood.parvania@utah.edu Co-Chair: Sauleh Ahmad Siddiqui, Johns Hopkins University, Baltimore, MD, 21218, United States, siddiqui@jhu.edu 1 - Optimizing Water Energy Flexibility in Water Distribution Systems Masood Parvania, Assistant Professor, University of Utah, 50 S. Central Campus Drive, Room 2110, Salt Lake City, UT, 84112, United States, masood.parvania@utah.edu, Konstantinos Oikonomou We present a model for optimizing the energy flexibility of water distribution systems (WDS). The water distribution system operators are considered as energy savvy entities, who run the proposed WDS operation model to optimize the operation of water pumps and tanks for minimizing the operation cost of the WDSs, while respecting the hydraulic operating constraints for ensuring deliverability of the WDS energy flexibility. The power system operator, then, optimizes final decisions on the contribution of WDS energy flexibility in power systems operation. Michael J. Racer, University of Memphis, 302 Fogelman College of Business, Memphis, TN, 38152, United States, mracer@memphis.edu, Palaniappa Krishnan The purpose of the website is to provide a resource for faculty members in the operations research are. This website will include several items available for faculty members- sample curriculums to which any member can submit examples, cases, projects, software, etc. MA61

summarizes the policy implications of the identified opportunities. 4 - Optimization of Marine Hydro-Kinetic Devices for Electricity Systems

Alberto J. Lamadrid, Lehigh University, 621 Taylor Street, R451, Bethlehem, PA, 18015-3120, United States, ajl259@cornell.edu In this work we formulate a proposal for wave farm owners to participate in deregulated electricity markets. Our proposal for the day ahead market allows for a closed form solution of the optimal offer. We establish a mapping between real time prices and profits considering uncertainty, and evaluate the revenue streams for wave energy producers.

MA62

370C Journal of Quality Technology Invited Session Sponsored: Quality, Statistics and Reliability Sponsored Session Chair: Fugee Tsung, HKUST, Clearwater Bay Road, Hong Kong, HK, Hong Kong, season@ust.hk 1 - Robust Multivariate Control Chart Based on Goodness-of-fit Test Nan Chen, National University of Singapore, Department of Industrial and System Eng, 1 Engineering Drive 2, Singapore, 117576, Singapore, isecn@nus.edu.sg, Chen Zhang, Changliang Zou This paper proposes a distribution-free MSPC chart to detect general distributional changes in multivariate variables. The chart is based on a multivariate goodness- of-fit test, extensible to high dimensional observations. The chart also employs data-dependent control limits to ensure robust charting performance. The proposed chart is exactly distribution-free, and able to operate with unknown in- control distribution or limited reference samples. The chart also has satisfactory OC detection power for general changes without distributional assumptions. 2 - Change Detection in a Dynamic Stream of Attributed Networks Mostafa Reisi Gahrooei, Georgia Institute of Technology, Georgia Tech, H. Milton Stewart School Of ISYE, Atlanta, GA, 30332-0205, United States, mostafa.reisi@gmail.com, Kamran Paynabar While anomaly detection in static networks has been extensively studied, only recently, the attention has been focused on dynamic networks. This paper proposes a new methodology for modeling of dynamic attributed networks and for change detection in the network structure. In this methodology, generalized linear models are used to model static attributed network. This model is then combined with a state transition model to capture the dynamic behavior of the system and Extended Kalman filter is used estimate and update network parameters over time. Prediction residuals are then monitored using EWMA. The proposed method is examined through simulations and a case study. 3 - Using Curve-registration Information for Profile Monitoring Bianca Maria Colosimo, Politecnico di Milano, Via La Masa, 1, Milan, I-20156, Italy, biancamaria.colosimo@polimi.it, Marco Grasso, Alessandra Menafoglio, Piercesare Secchi The contribution presents a novel approach for profile monitoring, which combines the Functional Principal Component Analysis and the use of parametric warping functions. The key idea is to jointly monitor the stability over time of the registered profiles and the registration coefficients. This allows improving the capability of detecting unnatural pattern modifications, thanks to a better characterization of the overall natural variability.

154