Moderator of Panel Session 3 on Big Data Research
Dagmar Niebur, Ph.D., received a Diploma in Mathematics and Physics from the technical University of Dortmund, Germany in 1984, a Diploma in Computer Science in 1987 and a Ph.D. in Electrical Engineering from the Swiss Federal Institute of Technology, Lausanne, Switzerland in 1994. Dr. Niebur joined Drexel University in March 1996, where she is now an associate professor. She served as the Program Director for Power, Control and Adaptive Networks at the National Science Foundation from 2007 to 2009.
Before joining Drexel, she held research positions at the Jet Propulsion Laboratory, Pasadena, CA, and the Swiss Federal Institute of Technology as well as a computer engineering position at the University of Lausanne and a summer visiting professor appointment at CEPEL, Brazil.
Dr. Niebur’s research has been funded by the National Science Foundation, the US Department of Energy, the Office of Naval Research, the Electric Power Research Institute and others. She is a recipient of the NSF CAREER award.
Recent professional service includes chairing of the IEEE-PES Technical Committee on Power System Analysis, Computing and Economics, founding member of the IEEE PES Pus Scholarship Initiative, Editor for the IEEE Transactions on Power Systems, Associate Editor for the American Control Conference, member of the Editorial Advisory Board of the International Journal of Engineering Intelligent Systems for Electrical Engineering and Communications, technical committee membership of the Power System Computation Conference, technical vice-chair and proceedings editor of the International Conference on Intelligent Systems for Power Systems (ISAP) 2005 and 2007, member of ISAP’s Board of Directors since 2007.
Electric Reliability Council of Texas (ERCOT)
Network Model Data Management System and Process at ERCOT
Network models of high fidelity are critical in the reliability and energy market operations of the electric system. In this talk, we will present the infrastructure and procedure around a temporal CIM-based network model management system used to securely submit, validate, track, test, notify and build high fidelity network models for reliability, real-time and forward energy markets operations at ERCOT.
Diran Obadina is Principal Engineer at ERCOT, with responsibility for strategic development of applications and systems required for reliability and energy markets operations. Before joining ERCOT in 2003 as Manager of Development of Energy and Market Management Systems, he was a Senior Staff Engineer at Siemens Energy and Automation, involved with the development and delivery of EMS and MMS. He received the BSc from the University of Ife, Nigeria, the MScE from the University of New Brunswick, Canada, and the PhD degrees from the University of Calgary, Canada, all in Electrical Engineering
Thomas J. Overbye
|TEES Distinguished Research Professor
Electrical and Computer Engineering
Texas A&M University
College Station, TX
Big Data and Synthetic Electric Grid Systems
Test cases are widely used in the power systems for research and education. Even though several small-scale test cases are available to the public, access to actual large-scale power system models is much more limited. This talk explains how large-scale synthetic electric systems can help to bridge this gap, and explains some of the big data issues associated with the use of such systems.
Thomas J. Overbye, Ph.D., is a TEES Distinguished Research Professor in Electrical and Computer Engineering at Texas A&M University (TAMU). Prior to joining TAMU in January 2017 he was the Fox Family Professor of Electrical and Computer Engineering at the University of Illinois at Urbana-Champaign (UIUC). He received his BS, MS, and Ph.D. degrees in Electrical Engineering from the University of Wisconsin-Madison.
|Deputy Associate Program Leader
Cyber & Infrastructure Resilience Program at
Lawrence Livermore National Laboratory
Integrated Multi-Scale Data Analytics and Machine Learning for the Distribution Grid
A vision of the future distribution grid and its interface to buildings is one of cohesion, an interactive reliable environment where there are consumer benefits and motivations to leverage customer owned behind-the-meter assets to provide services to the grid, energy markets, other entities within the distribution feeder, and ultimately to the larger society as a whole. This future distribution grid may be a reliable, safe, and resilient energy transport platform that supports high penetration of Distributed Energy Resources (DER). The growth of communicative DER and connected behind-the-meter power electronic devices may introduce fluctuations and uncertainty not previously seen on the distribution grid if the resources operate independently, or are driven by independent communications and controls. However, these new data generating and communicative features may also offer a vast opportunity to increase the operational efficiency of both the grid and the buildings connected to it, but only if the data collected at all the various nodes can be easily transformed into intelligible, actionable information.
This presentation will discuss an approach and set of work being developed by a multi-national laboratory team, funded through the DOE Grid Modernization Initiative which will evaluate these challenges to develop data driven solutions leveraging multi-scale machine learning based analytics. The work utilizes various data sets across the nodes within the end to end power system (e.g. generation to end use) to automatically produce accurate actionable information for the various parties and actors encompassing the power system. At the heart of the work, applied analytics are required to turn these raw data into actionable information.
Emma Stewart (M08-SM14) received her under- graduate degree in Electrical and Mechanical Engineering at the University of Strathclyde in 2004 and her PhD in Electrical Engineering in 2009. She is currently a Deputy Associate Program Leader in the Cyber & Infrastructure Resilience Program at Lawrence Livermore National Lab. Her research focuses on the distribution grid and analytics associated with high penetration of distributed resources. She was Deputy Group Leader at Lawrence Berkeley National Lab until 2017.
|Utility Solution Sales Executive
The Weather Company an IBM Business
High Resolution Weather Applied to Utility Operation
Applications of weather observation and forecasts for utilities usually involve data from the nearest reporting location, e.g. an airport location many miles away. Advancements in weather technology and data collection now allow utilities to get a very specific look at weather conditions at asset locations or other locations of interest. The internet of things and crowd sourced weather information are quickly advancing the weather industry in ways that most utilities would think impossible just a few years ago.
In my presentation I will present information regarding the latest use of crowd sourced weather data, its impact on the resolution and accuracy of weather information and how it is transforming the way weather is applied in the energy and utility sector. Relevant use cases of weather will be presented to demonstrate the high resolution capability of the latest generation of weather data.
Joe Sullivan has been connecting weather with smart decisions for nearly 2 decades. He spent the last 10 years working for renewable energy, utility and weather companies coupling the weather with electric generation and demand, customer impact and storm outages. Joe has held roles as a Product Manager, Research Project Manager, Executive Director, Account Manager and Television Broadcaster.
At The Weather Company, Joe works with utilities, smart energy companies, energy service providers, energy retailers and analytics companies providing customized weather output for analyzing weather’s impact to a customer’s business. Joe has been with The Weather Company since 2012.
Prior to TWC, Joe was Director of Operating Services at WindLogics, an indirect, wholly owned subsidiary of NextEra Energy. Joe’s team of consultants and researchers provided renewable energy and electric demand forecasts for utility clientele.
Joe holds a Bachelor of Science degree in Meteorology from St. Cloud State University in St. Cloud, Minnesota. He lives in Eden Prairie, MN with his wife and three children. He enjoys everything outdoors and all kinds of weather.
|Manager, Data Analytics
Big Data Application on the Other Side of the Meter
Customer Energy Solutions at Austin Energy is looking to leverage third party public and vendor data to create a comprehensive understanding of the electric customer. Use of appraisal district information combined with psychographic data has provided a means to focus customer outreach for conservation and alternative generation sales thus saving money over a blanket, indiscriminate marketing coverage. This data is also used to target both conservation and demand response to customers that have a higher potential to realize savings.
John. Trowbridge graduated from University of Arizona with a Bachelors degree in Aerospace Engineering and a Masters in Mechanical Engineering from the University of Texas. John began his career at Austin Energy evaluating energy conservation programs using building simulation programs but found that analysis of actual energy use is more effective, thus entering the arena of statistics and data analytics. He then sought to leverage third party data to develop a more comprehensive understanding of the diversity of customers in Austin Energy’s service territory.
Polytechnic of Porto
Agent-based Energy Resource Management Supported by Local and Remote Data
Technology and business advancements are having a huge impact on power and energy systems operation, namely on the volume of the generated data. These data have relevant value for all involved entities, from producers, consumers and aggregators to retailers, market and system operators. New techniques are required to accommodate, analyze, interpret and manage all the relevant data so that the involved parties can improve their decision-making process and gain awareness on the environment in which they are operating.
Advances in data analytics and mining require researchers and other professionals to have access to adequate data sets, which is still very difficult and is proven to be a major bottleneck in the field. The Task Force on Open Data Sets, operating in the scope of the IEEE Power & Energy Society’s Intelligent System Subcommittee of the Analytic Methods for Power Systems (AMPS) Technical Committee is supporting an initiative making public data sets permanently available in http://sites.ieee.org/pes-iss/data-sets.
This talk will share Zita Vale’s experiences on real data use for improving energy resource management. It will be based on her experience on the design and implementation of a multi-agent based infrastructure for real-time operation and simulation of smart grids and micro grids and on its use from a practical perspective with real time data from multiple international sources.
Zita Vale, Ph.D., is a professor at the Polytechnic Institute of Porto and the director of the Research Group on Intelligent Engineering and Computing for Advanced Innovation and Development (GECAD). She received her diploma in Electrical Engineering in 1986 and her PhD in 1993, both from University of Porto.
Zita Vale works in the area of Power and Energy Systems, with special interest in the application of Artificial Intelligence techniques. She has been involved in more than 50 funded projects related to the development and use of Knowledge-Based systems, Multi-Agent systems, Genetic Algorithms, Neural networks, Particle Swarm Intelligence, Constraint Logic Programming and Data Mining. The main application fields of these projects comprise:
- Smart Grids, accommodating an intensive use of Renewable Energy Sources, Distributed Energy Resources (DER) and Distributed Generation (DG). She addresses the management of energy resources, the impact of DER on electrical networks, the negotiation of DER in electricity markets, demand response, storage, energy management in buildings, and electrical vehicles, including the ones with gridable capability (V2G);
- Electricity markets, addressing contracts, prices and tariffs, decision-support for market participants, aggregation, ancillary services, and wholesale and local market simulation;
- Control Center applications, namely intelligent alarm processing, intelligent interfaces and intelligent tutors.
Zita has published over 700 works, including more than 100 papers in international scientific journals, and more than 500 papers in international scientific conferences.
|Manager of Analytics and Business Insight
Energy Supply and Market Operations
San Antonio, TX
San Antonio’s Electric Utility Making Big Data Analytics the Business of the People…for the People
Being part of a municipality-owned electric utility offers a unique opportunity to lead in the area of big data analytics. What moves the electric utility of the 7th largest city in the U.S.? The answer is, People. For years, CPS Energy has invested in development of local talent, local technology development, city growth, its employees and an asset infrastructure that is setting the stage for continued success. At CPS Energy, when such investments are topped by a data infrastructure and applications conducive to creation of business insights, we can justify and prioritize investments. For us, the biggest people-opportunities in big data analytics are around operations, customer and employee engagement, and safety. The presenter will provide examples and share how his views have evolved from those of a researcher, to global renewable energy consultant, to technology innovator, and more recently a “harvester of value” from within people, process and technology assets. Lastly, current and anticipated future states with regards to San Antonio’s electric utility big data enablement platform will be presented.
Despite the diverse landscape of technology solutions in big data analytics, such as: (1) cloud-based distributed computing (driven by economies of scale and need for optimal response of Bulk Electric System and tailored customer service), and (2) machines interchanging information with other machines in the industrial Internet-of-Things (driven by exponential growth of devices in the communication network and desire for faster optimal controllability in the Distribution Management System), technology investment decisions in electric utilities are still made by and for people with a keen eye for creating value for its customers. In addition, driven by a turning point of open-source software in recent years, machine learning has matured passed the point of academic research and inflated expectations, and has enabled faster and more transparent technology deployment, even though machine learning was first conceived in the 1950s. Computer codes that use machine learning techniques could be easily trained and deployed centrally or on distributed infrastructure to predict more optimal solutions to business problems if data inputs behave within reasonable range and with normal variability. However, field sensors, actuators or communication networks of utility-scale environments, in seeking to meet economic and customer expectations, they end up being dynamic and heterogeneous in function, quality of service, time synchronization and location and there is still significant time spent in vetting security standards are met and performing input data completeness and accuracy checks. Since electric utilities serve a large group of customers in their territory the opportunities to create value for the customers far outweighs its challenges given the inequality in human resources to data intake ratio. But until new tested principles in cyber physical systems are developed it seems that we must resort to traditional error handling processes in middleware workflows to account for known potential data inaccuracies and to close the gap between central and distributed computing resources.
Rolando Vega, Ph.D., PE, has been a renewable energy consultant and researcher for the last 10-years. He currently leads a staff of engineers, analysts and data scientists to perform analysis and provide business insights and reporting on the energy market operations of CPS Energy in ERCOT. He is responsible for the analytical skills of the team, as well as the data and associated systems required to effectively provide solid analytics.
Before his current position he led the R&D and technical performance in the subjects of renewable energy forecasting, GIS LiDAR analytics, building load forecasting and grid integration at The University of Texas at San Antonio (UTSA). Dr. Vega has led the development of 3 patent pending in the area of distributed energy forecasting and led the development of technologies for distributed IoT traffic monitoring, cyber abnormality detection and prediction for the electric utility industry.
He started and was responsible for the Renewable Energy consulting business in US, Mexico, Brazil and China for a global 1700+ employee consulting company. Dr. Vega helped develop the company’s consulting renewable energy annual revenues to about $6M in 3-years. He drives teamwork, effectively draws from the strengths of his team and focuses in innovative ideas and great communication to provide solutions. Dr. Vega’s former clients include top tier global owners, utilities and manufacturers of renewable energy assets and operations. Dr. Vega is a registered Professional Engineer and holds an active NCEES record for licensure in any U.S. state.
|Chief Industry Architect and IBM Distinguished Engineer
IBM® Global Services
Big Data Analytics Program Scaling Challenges at Energy Utilities
As utility companies roll out Big Data analytics programs beyond initial pilots, there are common challenges being faced. Charles will discuss these challenges and how utilities are successfully navigating them.
Charles Vincent is a Distinguished Engineer working in IBM’s Global Center of Competency for Energy and Utilities. He has almost thirty years of experience designing and delivering technical business solutions for Energy Utilities. He has hands on experience with most utility systems including Customer Information Systems, Complex Billing, AMR/AMI, Distribution Automation and Distributed Energy Resources. Charles is a founding member of IBM’s Intelligent Utility Network Architecture Council, and has helped drive many of IBM’s strategic initiatives in the Energy and Utilities space in particular, AMI, Smart Grid, Data Analytics, Mobility and Cloud. Charles has provided architectural and implementation leadership on numerous Smart Grid projects working with utility companies and industry groups such as EPRI. He serves as an advisor on IBM’s Distributed Generation Workgroup as part of IBM’s IUN Coalition
|Associate Professor and Eugene Webb Fellow
Department of Electrical and Computer Engineering
Texas A&M University
College Station, TX
Streaming Analytics of Dynamic Data in Power Systems: A Tale of Two Time Scales
How to conduct near real-time analytics of streaming data in the smart grid? This talk offers a dynamic systems approach to utilizing emerging data for improved monitoring of the grid. The first example of the talk presents how to leverage the underlying spatio-temporal correlations of synchrophasors for early anomaly (e.g., subsynchronous oscillations) detection and data quality outlier detection. The second example presents a dynamic systems approach to modeling price responsive demand in real-time markets. The underlying theme of the work suggests the importance of integrating data with dynamic physics-based analytics in the context of electric energy systems.
Le Xie, Ph.D., is an Associate Professor and Eugene Webb Faculty Fellow in the Department of Electrical and Computer Engineering at Texas A&M University. He received B.E. in Electrical Engineering from Tsinghua University in 2004, S.M. in Engineering Sciences from Harvard in 2005, and Ph.D. in Electrical and Computer Engineering from Carnegie Mellon in 2009. His industry experience includes ISO-New England and Edison Mission Energy Marketing and Trading. His research interest includes modeling and control in data-rich large-scale systems, grid integration of clean energy resources, and electricity markets.
Dr. Xie received the U.S. National Science Foundation CAREER Award, and DOE Oak Ridge Ralph E. Power Junior Faculty Enhancement Award. He was awarded the 2017 IEEE PES Outstanding Young Engineer Award. He was recipient of Texas A&M Dean of Engineering Excellence Award, ECE Outstanding Professor Award, and TEES Select Young Fellow. He is an Editor of IEEE Transactions on Smart Grid, and the founding chair of IEEE Power and Energy Society Subcommittee on Big Data & Analytics for Grid Operations. He and his students received the Best Paper awards at North American Power Symposium, IEEE SmartGridComm, ACM E-Energy, and the Texas Power and Energy Conference.