Teaming Partners

Submit Entry to Teaming Partner List
v
   Show Advanced Search
Keyword Search includes Investigator Name, Organization, Background, and Address. Use operators "AND" or "OR" to fine tune your search. Please use only one operator per search. For example, the search term "biofuels AND modeling" will return results that include both the words biofuels and modeling, while the search term "biofuels OR modeling" will return results that include the word biofuels, modeling, or both.
View Archived Teaming Partners

By enabling and publishing the Teaming Partner List, ARPA-E is not endorsing, sponsoring, or otherwise evaluating the qualifications of the individuals and organizations that are self-identifying themselves for placement on this Teaming Partner List.

The columns below can be sorted alphabetically by clicking on the column heading and reverse alphabetically sorted by clicking twice on the column heading. Type into the white boxes or use the dropdown options to filter within the search results.

 
Organization 
Investigator Name 
Organization Type 
Area of Expertise 
Background, Interest,
and Capabilities
 
Contact Information 
State 
 
xv
xv
 
xv
 Texas A&M UniversityYu Ding Academic Power Generation: Renewable Data science for wind energy, wind turbine and farm performance assessment, design optimization, and wind power forecasting.
Website: https://aml.engr.tamu.edu/

Email: yuding@tamu.edu

Phone: 979-458-2343

Address: ETB 4016, MS 3131, College Station, TX, 77843, United States
TX
 Argonne National LaboratoryZhengchun Liu Federally Funded Research and Development Center (FFRDC) Other Energy Technologies Expertise in computer science. Good at extracting knowledge from large-scale data, machine learning, autonomic computation (e.g., I work on a project that proposes to make the science ecosystem smart by incorporating the functions of sensing, intelligence, and control). I also work on a project that focuses on extracting information from data and future converting information to knowledge for optimization. Machine learning techniques are heavily used in my projects.
Website: https://lzhengchun.github.io

Email: zhengchun.liu@anl.gov

Phone: 6302523474

Address: 9700 S Cass Ave, Lemont, IL, 60439, United States
IL
 Tacoma PowerAhlmahz Negash State and/or Local Government Other Energy Technologies Energy storage, demand response, demand-side management, renewable integration, value of distributed energy resources, resource planning and optimization
Website: https://www.mytpu.org/tacomapower/about-tacoma-power/dams-power-sources/integrated-resource-plan.htm

Email: anegash@cityoftacoma.org

Phone: 2535028093

Address: 3628 Sourth 35th Street, Tacoma, WA, 98409, United States
WA
 BAE SystemsHema Retty Large Business Grid The BAE Systems - Electronic Systems (ES) sector group, spans the commercial and defense electronics markets with a broad portfolio of mission-critical electronic systems, including power-and energy-management systems; flight and engine controls; electronic warfare and night vision systems; surveillance and reconnaissance sensors; secure networked communications equipment; geospatial imagery intelligence products and systems; and mission management.

Under ES, the Dominance Awareness and Sharing (DASH) research group is heavily involved in advanced research concepts funded primarily from government research labs and organizations. The main areas of research are in machine learning, communications networks and signal processing. Our core technologies include detection, characterization, learning and understanding of signals in the spectrum. Research includes how technologies may be applied to a number of different RF domains, such as spectrum sharing, cognitive communications, spectrum sensing, and signals intelligence. Our diverse portfolio also includes Deep Learning to build real world power system models and creating cyber secure networks for critical infrastructure systems.
Website: https://www.baesystems.com/en-us/our-company/inc-businesses/electronic-systems/fast-labs

Email: hema.retty@baesystems.com

Phone: 7814545163

Address: 600 District Ave, Burlington, MA, 01803-5012, United States
MA
 ORNLRick Archibald Federally Funded Research and Development Center (FFRDC) Other Energy Technologies My research interests lie in data reconstruction and analysis, high order edge detection, large scale optimization, time integration, and uncertainty quantification.

I am the data analytics lead for the SciDAC DOE institute FASTMath. Additionally I have worked as the co-leader of the Environment for Quantifying Uncertainty Integrated aNd Optimized at the eXtreme scale (EQUINOX) project, where I have been able to focus on more fundamental aspects of uncertainty quantification, linking convergence and accuracy results for methods independently developed by the statistics and applied mathematics communities. I have worked as the leader of the ACcurate qUantified Mathematical mEthods for Neutron and experimental science (ACUMEN), using advances in optimization, statistical modeling, image processing, and signal analysis to merge leadership scale experimental and computational facilities at Oak Ridge National Laboratory (ORNL). This combination has proven to provide the unique computational and mathematical tools necessary for analysis of big experimental data which is essential for large scale scientific discovery.
Website: https://www.ornl.gov/staff-profile/richard-k-archibald

Email: archibaldrk@ornl.gov

Phone: 8655765761

Address: Bethel Valley Rd, Oak Ridge, TN, 37831, United States
TN
 Argonne National LaboratoryRajkumar Kettimuthu Federally Funded Research and Development Center (FFRDC) Other Energy Technologies Expertise in computer science, distributed computing, on-line analysis of large-scale data, extracting knowledge from large-scale data, machine learning, autonomic computing
Website: www.mcs.anl.gov/~kettimut

Email: kettimut@anl.gov

Phone: 630-252-0915

Address: 9700 S Cass Ave, Lemont, IL, 60439, United States
IL
 West Virginia UniversitySarika Khushalani Solanki Academic Grid NSF career Award Recipient
Expertise in Distribution Systems
Expertise in Transmission Systems
Capabilities in working on data mining, cybersecurity, neural networks.
Website: community.wvu.edu/~skhushalanisolanki/

Email: skhushalanisolanki@mail.wvu.edu

Phone: 3042415967

Address: evansdale drive, Morgantown, WV, 26508, United States
WV
 University of HoustonHarish Krishnamoorthy Academic Power Generation and Energy Production: Fossil/Nuclear I am an Assistant Professor in the ECE department of University of Houston (http://www.ee.uh.edu/faculty/krishnamoorthy). My expertise is in high density electrical power conversion, renewable energy, high temperature electronics design and data driven electronics health diagnostics. A list of our capabilities can be found here: http://pemses.ece.uh.edu/facilities/. We are also adding B1506A Keysight curve tracer, a state-of-the-art dyno system and several power supplies for our lab.
Website: http://pemses.ece.uh.edu/plublications/

Email: hskrishn@uh.edu

Phone: 7137437382

Address: 4726 Calhoun Rd., Electrical Engineering, Houston, TX, 77204, United States
TX
 Pennsylvania State UniversityXingjie Ni Academic Other Energy Technologies The prime goal of our group is to explore the frontiers of science and technology in tailoring and manipulating light-matter interactions. We strive to pursue solid experimental work in addition to theoretical study and numerical simulations. Our research focuses on the interaction of light with nanostructures and nanomaterials that leads to novel optical devices and systems, which could be applied to the field of photonics, plasmonics, quantum optics, optoelectronics, energy, sensing, and biology.

Areas of expertise:
Nanophotonics
Metamaterials and Metasurfaces
Nanophotonic device fabrication and characterization
Computational electromagnetics
Website: http://nanolight.psu.edu

Email: xingjie@psu.edu

Phone: 8148653361

Address: 209G Electrical Engineering West, University Park, PA 16802-2707, University Park, PA, 16802, United States
PA
 MICROrganic TechnologiesBrent A Solina Individual Other Energy Technologies Brent Solina is CTO of MICROrganic Technologies, an seed-stage company that is developing Microbial Fuel Cells for energy-efficient Wastewater applications. After several years of R&D and piloting, we are preparing to go to market. Our first product will be geared to small Food & Beverage processors. Microbial Fuel Cells (MFCs) use microbes to break down organic waste. Instead of energy-intensive Aeration as the core WWT process, we use microbes to break down the waste. By providing an electrochemical option for the microbes to respirate ("breathe") through a circuit, instead of requiring air, we reduce WWT energy use by about 96%.

In addition, as microrganisms respirate, they deposit electrons onto a conductive circuit; these electrons are DC power, and a signal that characterizes the treatment. This is especially critical for WWT applications; current systems lack "intelligence" and even treatment rates are unknown on a real-time basis. The state of the art in Wastewater Treatment has a set, assumed rate of treatment, which drives the retention time for wastewater systems. Machine Learning could accelerate increasing sustainability and energy efficiency of Wastewater Treatment, by creating generate intelligent WWT software systems that can increase or decrease retention times and other physical data, based on factors such as temperature, waste strength, nitrogen treatment rates, and energy generation.
Website: www.MICROrganicTech.com

Email: carol@microrganictech.com

Phone: 5186369640

Address: 1477 S. Schodack Road, Castleton on Hudson, NY, 12033, United States
NY
 Oregon State UnivertyMario Enrique Gomez Fernandez Academic Power Generation and Energy Production: Fossil/Nuclear I am PhD candidate at Oregon State University and a radiological engineer intern at NuScale Power. My research areas are related to artificial intelligence and machine learning and its application on safety, integrated decision making, design optimization and automation in nuclear and radiological sciences. I have experience with multiple machine learning algorithms, e.g. neural networks, genetic algorithms, etc. I have developed and conducted research using various neural network structures (FFBP, Convnets, LSTMs) for various nuclear related tasks including nuclear test facilities behavior prediction, gamma spectrometry, and optimization, as well as non-nuclear related such as answering question using Facebook's bAbI, exploration in partially observable territories, and fine arts classification.
Website: https://ne.oregonstate.edu/

Email: gomezfem@oregonstate.edu

Phone: 5412242298

Address: 151 Batcheller Hall, Corvallis, OR, 97331, United States
OR
 Rebellion Photonics, Inc.Bo Fu Small Business Other Energy Technologies Background, Interest, and Capabilities:

Backgound:
Rebellion Photonics has developed the Gas Cloud Imaging (GCI) camera, a hyperspectral imaging camera that monitors, quantifies, and displays gas leaks in real-time as far as 2 miles away. The camera uses infrared absorption spectroscopy and can determine what gases are present by analyzing absorption signatures. The GCI camera operates in the long-wave spectral regions, which allows it to differentiate and quantify gases present.

Interest:
-Machine learning
-Optimization
-Algorithm development

Capabilities:
-Optical devices hardware
-Algorithm development


Past successful projects with ARPA-E:
https://arpa-e.energy.gov/?q=impact-sheet/rebellion-photonics-monitor
https://arpa-e.energy.gov/?q=slick-sheet-project/portable-methane-detection-system
Website: https://rebellionphotonics.com/

Email: bo@rebellionphotonics.com

Phone: 713-218-0101

Address: 2327 Commerce St Suite 200, Houston, TX, 77002, United States
TX
 White Box Batteries, LLCDr. Arnaud Devie Small Business Other Energy Technologies White Box Batteries provides engineering services for energy storage systems.
I hold a Ph.D. in Electrical Engineering.
My thesis work explored the concept of pattern classification of power duty pulses in order to develop close-to-reality battery testing profiles.

Based on my own work experience in both academic and industry labs, the testing of energy storage systems is a painfully slow process where bottlenecks are (1) the creation of human-defined test profiles, (2) the incompressible time to conduct such test profiles and (3) the human-based processing of the test results, interpretation and iteration based on the conclusions.

My current research interest revolves around the creation of automated energy storage testing systems where the sole user input would be the safe operating envelope (min/max voltage, min/max temperature) and where the system would continuously generate testing conditions. The testing outcome would be (1) an exhaustive performance map of the device under test and (2) a coupled thermo-electrical equivalent circuit model of the device under test that can then be used in industry-standard simulation tools for complete system integration.

I believe an approach based on adversarial machine learning would considerably (1) speed-up testing speed and (2) improve the accuracy and domain of validity of the generated model.
This proposed approach would mostly fall under category 2) Hypothesis Evaluation Tools.
Website: whiteboxbatteries.com

Email: whiteboxbatteries@outlook.com

Phone: 4087096354

Address: 4710B W 131st St, Hawthorne, CA, 90250, United States
CA
 Rutgers University - New BrunswickZhimin Xi Academic Other Energy Technologies • Ph.D. in Reliability Engineering, University of Maryland – College Park in 2010.
• Research interests: reliability and safety for energy storage systems, design for resilient energy systems, prognostics and health management for engineering systems, model validation under uncertainty, and system reliability analysis.
• More than 60 papers in prestigious journals and peer-reviewed conference proceedings.
• 2016 DARPA (Defense Advanced Research Projects Agency) - Young Faculty Award: New Theory in Model-Based Design: A Design Foundation Driven by Probability of Design Errors.
• Winners of multiple (including twice Top 10) Best Paper Awards from ASME – Design Automation Conference in 2008, 2011, 2013, and 2015 respectively.
• Research funding support from National Science Foundation, DARPA, Department of Energy, Ford Motor Company, Denso North American Foundation, and The Woodbridge Group.
 Capable of handling “Detailed Design” and “Inverse Design” by proposing machine learning strategies and methods with high efficiency and accuracy.

 Related work:
1. Dahmardeh M., Xi Z., State of charge estimation for lithium-ion battery packs considering cell-to-cell variability, ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems: Part B. Mechanical Engineering, accepted, 2019, in print (invited paper).
2. Xi Z., Model-based reliability analysis with both model uncertainty and parameter uncertainty, Journal of Mechanical Design, v141(5), 051404 (11 pages), 2019.
3. Xi Z., Pan H., Yang R.J., Time dependent model bias correction for model based reliability analysis, Structural Safety, Vol. 66: 74-83, 2017.
4. Pan, H., Xi, Z., and Yang, R.J., Model Uncertainty Approximation Using a Copula-based Approach for Reliability Based Design Optimization, Structural and Multidisciplinary Optimization, doi:10.1007/s00158-016-1530-2, 2016.
5. Xi, Z., and Yang, R.J., Reliability Analysis with Model Uncertainty Coupling with Parameter and Experiment Uncertainties: A Case Study of 2014 V&V Challenge Problem, ASME Journal of Verification, Validation and Uncertainty Quantification, 1(1): 011005 (11 pages), 2016 (invited paper).
Website: https://ise.rutgers.edu/zhimin-xi

Email: zhimin.xi@rutgers.edu

Phone: 848-445-3657

Address: 96 Frelinghuysen Road, Piscataway, NJ, 08854, United States
NJ
 Julia Computing Inc.Dr. Viral B. Shah Small Business Other Energy Technologies Julia has quickly become the preferred programming language for machine learning and analytics. Julia combines the functionality of quantitative environments such as R and Python with the speed of production programming languages like Java and C++ to solve large-scale problems in science, engineering, and machine learning. Julia provides parallel and distributed computing capabilities out of the box, and scalability with minimal effort.

Julia is increasingly the language of choice for AI. Ranked highly in the Github Octoverse 2018 Machine Learning survey, Julia is the only programming language that combines the capability of mathematics, engineering and AI in a single general purpose system. Thus, one can solve differential equations, do linear algebra, solve FFTs, build neural networks, deploy on GPUs and Google TPUs, and serve it all up in a web application - all in one single language. Julia particularly shines when it comes to combining real world science and data-based AI algorithms together. These results were presented at NeurIPS 2018.

Julia Computing is a firm founded by all the creators of the Julia language. It has developed products such as JuliaPro (IDE for Julia), JuliaTeam (collaborative-development for enterprises), JuliaBox (cloud solutions) and JuliaAcademy (for training). Julia Computing has a staff of 30, and focusses on making Julia easy to use, easy to deploy, and easy to scale for its customers.
Website: http://juliacomputing.com

Email: viral@juliacomputing.com

Phone: 6174879366

Address: 45 Prospect St, Cambridge, MA, 02139, United States
MA
 Self (Retired from Columbia University)Albert Boulanger Individual Other Energy Technologies In a book I coauthored, Computer-Aided Lean Management for the Energy Industry, a group of seasoned energy pioneers in oil and gas and electric power presented the opportunities of using machine learning for Computer Aided Lean Management or CALM in the energy industry product lifecycle. A prepublication 2008 tutorial on CALM is available at http://leanenergy.org/docs/CALM-Tutorial.pdf
We showed how an Integrated Systems Model (ISM) of the energy system built and improved during conceive and design stages can be used with machine learning, especially reinforcement learning, to optimize lean processes throughout the product lifecycle.
Areas of ML application we have studied capabilities and interested in:
•CALM methods to manage risk on huge CAPEX projects – ultradeep oil and gas and large scale renewable energy;
•Simulation-based optimization using the ISM with reinforcement learning (RL);
•Parametric optimization and automated discovery using RL (dynamic treatment regimes);
•Real Options using reinforcement learning for more accurate financial valuation of flexible operation throughout the product lifecycle;
•O&M policy optimization using portfolio management and ML;
•Failure prediction based on asset attributes. ML-based survival analysis;
•Threat avoidance and mitigation (ThreatSim) using the ISM and RL;
•Grid operation optimization using Smart Grid technology incorporating RL and ML;
•Forecasting (nowcasting), sort term (days) and long term (years) using ML coupled with RL for flexible “fly-by-wire”, robust, cost efficient, optimized operations and planning.
•Smart grid, minigrid, macrogrid and microgrid optimizing controllers for large penetration renewables;
•Function approximation and dimensionality reduction using encoders/decoder networks: fast AC powerflow (DeepFlow);
•Inverse problem solutions using Generative Adversarial Networks (GANs): OPF;
•Convolutional networks for nowcasting using satellite or radar data
•Gaming-the-system detection using the ISM, ML and RL.
One point to make is that with lean energy, planning and operations become integrated.
Finally, I submitted to a foundation (with positive interest) the concept of searching and optimizing the quantum properties of biosolar materials (bacteriorhodopsin and cryptochromes) in the lab and virtually (computer simulation) using the reinforcement learning based dynamic treatment regime method to automate the parametric studies of these materials.
Website: http://smartgrid.info

Email: aboulanger@ldeo.columbia.edu

Phone: 2129329881

Address: 560 Riverside Dr APT 10G, New York, NY, 10027, United States
NY
 Texas A&M UniversityDr. Shima Hajimirza Academic Power Generation: Renewable -Assistant Professor of Mechanical Engineering and Director of Energy, Control and Optimization lab (ECOlab) at Texas A&M University
-Highly experienced in using numerical and statistical methods for micro/nano-scale energy conversion modeling and design.
- Expert in machine learning for surrogate modeling and optimization of black-box cost function in energy systems design, sensitivity analysis and design knowledge transfer.
- Successful research background in computational and experimental study of thin film solar cells including opto-electrical modeling, validation and fabrication of surface textured absorbing layers, organic, inorganic, pervoskite and plasmonic enhanced photovoltaic materials and composites.
- Expert in optics and multi-scale thermal radiation heat transfer.
-Published more than 19 Journal papers and 30 conference proceedings on modeling, optimization and fabrication of thin film solar cells, and energy systems design and control.
Website: https://www.ecolab.tamu.edu/

Email: shima.hm@tamu.edu

Phone: 9798454280

Address: 3123 Tamu, College Station, TX, 77843, United States
TX
 AVLFrederic Jacquelin Large Business Transportation Expertise in modeling and software development used for transportation and energy applications including thermodynamics, electrical and hybrid powertrain technology systems. Enhancing current optimization methods (MILP, NLP, Heuristics and Derivative Free Optimization) for design and control functions with ML/AI based technology including Neuroevolution, Reinforcement Learning.
Website: www.avl.com

Email: frederic.jacquelin@avl.com

Phone: 7343773795

Address: 47519 Halyard Drive, Plymouth, MI, 48170, United States
MI
 University of FloridaPaul Gader Individual Other Energy Technologies My background is in the area of Machine Learning. I received my PhD degree in Mathematics in 1986 and have worked in industry as well as Math, Electrical and Computer Engineering, and Computer Science departments.

I have been conducting research on Pattern Recognition/Machine Learning and Image Analysis since the mid-1980s. I have taught graduate courses in Pattern Recognition/Machine Learning about 10 times.

I have worked in many application domains involving many sensors, including Ground Penetrating Radar, Acoustic/Seismic, Wideband Electro-magnetic Induction, Dual Channel Electro-magnetic induction, hyperspectral image analysis aka imaging spectroscopy, and Underwater Acoustics.

I worked closely with colleagues Dominic Ho and Hichem Frigui to devise and implement Machine Learning algorithms that were part of a systems fielded in Afghanistan. One of the systems is the subject of a National Geographic Television program entitled "Bomb Hunters: Afghanistan" which is now available on youtube.com.

My work in Imaging Spectroscopy requires solving linear and nonlinear inverse problems to perform spectral unmixing. I have given several tutorials at international conferences on this topic.

My capabilities are:
- Any type of Machine Learning
- Inverse Problems for physical systems
- Image and Signal Processing and Analysis
Website: https://faculty.eng.ufl.edu/computing-for-life/

Email: pgader@ufl.edu

Phone: 352-262-4267

Address: 365 Weil Hall, University of Florida, Gainesville, FL, 32611, United States
FL
 Argonne National LaboratoryChukwunwike Iloeje Federally Funded Research and Development Center (FFRDC) Power Generation and Energy Production: Fossil/Nuclear Background & Capabilities:
I have a background in Mechanical Engineering with a PhD from Massachusetts Institute of Technology. My research combines thermal energy science concepts and scientific computation to develop and optimize technology systems for efficient and sustainable use of global energy and material resources. In this space, my research activity involves analytical thermodynamics, technology concept development, process simulation and optimization, model order reduction, data generation and visualization analysis for physics insights, large-scale computing for exploring the space of optimal process configurations, and uncertainty analysis. My work has covered applications in the following technology areas:
(1) Gas separations process design concept for removing nitrogen, Sulphur oxides, and other contaminants from the flue gas of oxy-coal combustion plants
(2) Multiscale modeling and techno-economic optimization of the integrated energy conversion system for chemical looping combustion technology development
(3) Multi-phase, multicomponent separations process design for the recovery of critical materials from end-of-life products.

Interests:
My current interests cut across energy conversion and process systems. In energy conversion, I am interested in integrating data and physics models for hybrid simulations that capture key multiscale interactions, while maintaining computational efficiency. Example application areas include CO2 capture and hybrid renewable energy conversion technologies. For process systems, my interests include the following:
(1) Data-enabled, large-scale exploration of system behavior and design configurations
(2) Machine learning, with particular interest in domain knowledge-informed neural networks for dimensionality reduction, uncertainty propagation and robust optimization
(3) Agent-based modeling for the automated assembly of chemical separations process configurations, which includes data-driven selection and use of machine learning and statistical inference tools to model agent-adaptive behavior.
Website: https://www.anl.gov/profile/nwike-iloeje

Email: ciloeje@anl.gov

Phone: 857-500-0928

Address: 7900 Cass Avenue, Lemont, IL, 60561, United States
IL
 Resolved AnalyticsStewart Bible Small Business Power Generation: Renewable Resolved Analytics is an experienced computational engineering consulting firm specializing in computational fluid dynamics (CFD), multi-physics simulations, FEA/FEM, Artificial Intelligence, and Prototyping. Our partners all have 15 years of experience working in the power and energy industry as well as a variety of other industries.

We help show the impacts of design choices by predicting the performance and reliability of products without setting foot in the lab. Our simulation and analytical capabilities deliver this clarity in less than half the time and at less than half the cost of traditional methods, often uncovering hidden opportunities for competitive advantages in the process. We proudly support collaborative grant opportunities with small and medium size businesses.

We have used Machine Learning in optimizing our customer s' products for many years, including Genetic Algorithms, Neural Networks, and other Heuristics.
Website: https://www.resolvedanalytics.com/

Email: stewart@resolvedanalytics.com

Phone: 704-559-9560

Address: 810 Vickers Ave, Durham, NC, 27701, United States
NC
 Argonne National LaboratorySiby Jose Plathottam Federally Funded Research and Development Center (FFRDC) Grid My PhD is in Electrical Engineering and my core expertise is in developing dynamic models of electrical systems from first principles and designing advanced control systems. Currently I work on developing models for grid connected distributed energy resources for use with large scale power system simulation. My secondary expertise and long term interest is in applying deep learning to solve problems in power system control and optimization.
I have considerable experience in applying clustering algorithms and deep generative models on large scale smart meter data from Chicagoland. Additionally, I have worked with image datasets for benchmarking deep learning architectures computer vision applications. I am proficient in developing open source software using Python (including the SciPy ecosystem). I am well versed with using TensorFlow machine learning framework on both PC and cloud computing platforms.
Website: www.anl.gov/profile/siby-jose-plathottam

Email: splathottam@anl.gov

Phone: 7012138536

Address: 9700 Cass Avenue, Lemont, IL, 60439, United States
IL
 Argonne National LaboratoryKibaek Kim Federally Funded Research and Development Center (FFRDC) Grid The investigator has expertise in modeling and parallel algorithms for large-scale stochastic (mixed-integer) optimization that arises in designing, planning, and operating energy infrastructure systems. In particular, sponsored by DOE Office of Science (MMICCS, ECP, and ECRP), he has developed an open-source parallel decomposition solver DSP for solving large-scale two-stage stochastic mixed-integer (linear/nonlinear) programming on HPC, which has been further extended and applied for solving large-scale power system planning and operations problem, funded by GMLC and other projects (e.g., Advanced Grid Modeling program in DOE Office of Electricity). Specifically, the large-scale optimization solution techniques has been successfully applied for solving stochastic unit commitment, security-constrained unit commitment, and security-constrained optimal power flow. DSP has been used by colleagues in universities and national laboratories and also deployed to the NEOS server (web-based optimization solution interface). In addition to the parallel optimization methods and solver (DSP), the investigator and coworkers are working on bilevel optimization and graph convolutional neural networks in power systems. He is the PI and co-PI of DOE projects and also leading the Argonne's ARPA-E Grid Optimization Competition team.
Website: https://kibaekkim.github.io/

Email: kimk@anl.gov

Phone: 6302524832

Address: 9700 South Cass Avenue, Naperville, IL, 60540, United States
IL
 Argonne National LaboratoryQizhi Zhang Government Owned and Operated (GOGO) Other Energy Technologies Chemical Engineering (Thermodynamics and Chemical Reaction) & Software Engineering (Database & Management Systems application development)

Multi-discipline background and experience.
Website: https://www.anl.gov/dsl

Email: qzhang@anl.gov

Phone: 630-252-8058

Address: 9700 S. Cass Ave., Lemont, IL, 60439, United States
IL
 Argonne National LaboratoryPinaki Pal Federally Funded Research and Development Center (FFRDC) Power Generation and Energy Production: Fossil/Nuclear Dr. Pinaki Pal (ES) is a postdoctoral appointee at Argonne’s Center for Transportation Research. He has eight years of experience in theoretical and computational modeling of advanced energy systems. Dr. Pal’s personal research has been focused on computational methods for reacting flows, direct numerical simulation (DNS), turbulent combustion modeling, low temperature combustion for IC engines and gas turbines, flame structure/dynamics, abnormal combustion, alternative fuels, engine design optimization and machine learning. At Argonne, Dr. Pal is involved in different projects pertaining to knock modeling in spark-ignited engines, combustion modeling of rotating detonation engines, development of reduced kinetic mechanisms for biofuels, and engine design optimization using global sensitivity analysis, genetic algorithms and machine learning techniques.

Argonne’s ML-GA software provides a unique capability for rapid design optimization by combining machine learning (ML) and genetic algorithm (GA) techniques. It employs ML (either one or multiple ML algorithms can be incorporated) to predict the quality (merit) of a design from the input parameters. Then, a stochastic global optimization genetic algorithm (GA) is used with the machine learning model as the objective function to optimize the input parameters based on the merit function. ML-GA is scalable to high-performance computing platforms such as supercomputers, enabling optimization to be performed in significantly short time frames (of the order of a few days).
Website: https://www.anl.gov/profile/pinaki-pal

Email: pal@anl.gov

Phone: 6302521361

Address: 9700 S Cass Avenue, Lemont, IL, 60439, United States
IL
Page 1 of 2 (28 items)Prev[1]2Next