Energy
Using recurrent neural networks for nonlinear component computation in advection-dominated reduced-order models
Maulik, Romit, Rao, Vishwas, Madireddy, Sandeep, Lusch, Bethany, Balaprakash, Prasanna
Rapid simulations of advection-dominated problems are vital for multiple engineering and geophysical applications. In this paper, we present a long short-term memory neural network to approximate the nonlinear component of the reduced-order model (ROM) of an advection-dominated partial differential equation. This is motivated by the fact that the nonlinear term is the most expensive component of a successful ROM. For our approach, we utilize a Galerkin projection to isolate the linear and the transient components of the dynamical system and then use discrete empirical interpolation to generate training data for supervised learning. We note that the numerical time-advancement and linear-term computation of the system ensures a greater preservation of physics than does a process that is fully modeled. Our results show that the proposed framework recovers transient dynamics accurately without nonlinear term computations in full-order space and represents a cost-effective alternative to solely equation-based ROMs.
Predicting AC Optimal Power Flows: Combining Deep Learning and Lagrangian Dual Methods
Fioretto, Ferdinando, Mak, Terrence W. K., Van Hentenryck, Pascal
The Optimal Power Flow (OPF) problem is a fundamental building block for the optimization of electrical power systems. It is nonlinear and nonconvex and computes the generator setpoints for power and voltage, given a set of load demands. It is often needed to be solved repeatedly under various conditions, either in real-time or in large-scale studies. This need is further exacerbated by the increasing stochasticity of power systems due to renewable energy sources in front and behind the meter. To address these challenges, this paper presents a deep learning approach to the OPF. The learning model exploits the information available in the prior states of the system (which is commonly available in practical applications), as well as a dual Lagrangian method to satisfy the physical and engineering constraints present in the OPF. The proposed model is evaluated on a large collection of realistic power systems. The experimental results show that its predictions are highly accurate with average errors as low as 0.2%. Additionally, the proposed approach is shown to improve the accuracy of widely adopted OPF linear DC approximation by at least two orders of magnitude.
A literature review on current approaches and applications of fuzzy expert systems
Rajabi, Mina, Hossani, Saeed, Dehghani, Fatemeh
The main purposes of this study are to distinguish the trends of research in publication exits for the utilisations of the fuzzy expert and knowledge-based systems that is done based on the classification of studies in the last decade. The present investigation covers 60 articles from related scholastic journals, International conference proceedings and some major literature review papers. Our outcomes reveal an upward trend in the up-to-date publications number, that is evidence of growing notoriety on the various applications of fuzzy expert systems. This raise in the reports is mainly in the medical neuro-fuzzy and fuzzy expert systems. Moreover, another most critical observation is that many modern industrial applications are extended, employing knowledge-based systems by extracting the experts' knowledge.
Energy Department CIO breaks down goals for IT modernization in 2020 Federal News Network
The Energy Department has a new chief information officer and a plan to bring its infrastructure into the modern age. DOE CIO Chris "Rocky" Campione outlined four primary objectives to modernize and rationalize the IT infrastructure that supports his agency's wide scope of programs. In fiscal 2020, operational visibility, delivery excellence, delivering innovation and workforce development will be the name of the game. "How do we make sure -- and that's everything from making sure we're reskilling and retraining the federal workforce," Campione said of the fourth objective, on Federal Monthly Insights -- A New Approach in IT Modernization. "But's also looking at how do we provide the information to our workforce so that we can make good decisions?"
Nikkei ends above 22,000 for first time in five months
Stocks inched up Tuesday, with the benchmark Nikkei 225 average closing above 22,000 for the first time in about five months. The Nikkei rose 13.03 points, or 0.06 percent, to end at 22,001.32, The last time the Nikkei finished above 22,000 was April 26. On Friday, the key market gauge jumped 228.68 points. The market was closed Monday for a national holiday.
TGS and Quantico Energy Solutions Announce Collaboration for Artificial Intelligence-Based Seismic Inversion
TGS, a leading provider of multi-client geoscience and engineering data for Exploration & Production companies, and Quantico Energy Solutions (Quantico), an artificial intelligence (AI) company focused on subsurface solutions for Exploration & Production companies, today announced a technology collaboration to leverage their respective offerings in seismic data, AI-based well logs, and AI-based seismic inversion. The joint solution addresses the critical challenges in earth modeling workflows; specifically, insufficient seismic and log data, lengthy time until results, and difficulties mapping advanced geomechanical and petrophysical attributes. TGS will leverage its industry leading data library of seismic and well log data in the key regions of oil and gas activity across the world. In addition, the collaboration will feature TGS's Analytics Ready LAS (ARLAS) solution. Adding to the largest commercial digital log library in the world, ARLAS utilizes machine learning algorithms to predict missing curve responses in today's digital well log data.
How Artificial Intelligence can help address climate change Packt Hub
"I don't want you to be hopeful. I want you to panic. I want you to feel the fear I feel every day. And then I want you to act on changing the climate"โ Greta Thunberg Greta Thunberg is a 16-year-old Swedish schoolgirl, who is famously called as a climate change warrior. She has started an international youth movement against climate change and has been nominated as a candidate for the Nobel Peace Prize 2019 for climate activism. According to a recent report by the Intergovernmental Panel (IPCC), climate change is seen as the top global threat by many countries.
Saudi-style drone attacks not seen as major risk to U.S., experts say
HOUSTON โ The style of attack used against oil plants in Saudi Arabia that knocked out half of the country's production on Saturday is unlikely to be a risk in the United States, energy and security experts say. "The U.S. oil industry has a lot of redundancy," said Amy Myers Jaffe, senior fellow for energy at the Council on Foreign Relations. U.S. refineries go offline often, after accidents or storms, with little impact to the market, Jaffe said. Even production in the country's biggest oil field, the Permian Basin in Texas and New Mexico, is spread across thousands of wells in a 75,000- square-mile (194,250-square-kilometer) region. The kind of gas-oil separation facility hit in the attacks in Saudi Arabia is done in smaller plants located across U.S. oil fields.
Computing a hard limit on growth
Agriculture now has much bigger yields than it did a century ago, but also requires vastly more energy input.Credit: Paulo Fridman/Bloomberg via Getty In 70,000 years, Homo sapiens has grown from thousands of hunter-gatherers teetering on the brink of extinction to a global population of 7.7 billion. In Growth, Vaclav Smil explains how we have peopled the planet through our growing capacity for harvesting energy from our environment: food from plants, labour from animals and energy from fossil fuels. Civilization has developed by dominating Earth's resources. It is high: polluted land, air and water, lost wilderness and rising levels of atmospheric carbon dioxide. He argues that most economic projections predict growth by ignoring the biophysical reality of limited resources.
Ilhan Omar rips Trump's 'locked and loaded' tweet, blames president for escalation with Iran
Democratic Congresswoman Ilhan Omar faces condemnation over her'some people did something' comments; reaction from Fox News contributor Ari Fleischer, former White House contributor. Rep. Ilhan Omar, D-Minn, blasted President Trump over his handling of Iran and suggested that his administration is to blame over the increased tensions between the two nations. Over the weekend, Iran-backed Houthi rebels claimed they launched drone attacks on the world's largest oil processing facility in Saudi Arabia and a major oil field Saturday, sparking huge fires and halting about half of the supplies from the world's largest exporter of oil. The attacks marked the latest of many drone assaults on the Kingdom's oil infrastructure in recent weeks, but easily the most damaging. They raised concerns about the global oil supply and could further escalate tensions across the Persian Gulf amid a growing crisis between the U.S. and Iran over the troubled nuclear deal.