Search NASA⌕ Search

SEARCH · Search NASA

Results for “Distributed Learning”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,531 records · Page 85
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

Deducing subnanometer cluster size and shape distributions of heterogeneous supported catalysts

Abstract Infrared (IR) spectra of adsorbate vibrational modes are sensitive to adsorbate/metal interactions, accurate, and easily obtainable in-situ or operando. While they are the gold standards for characterizing single-crystals and large nanoparticles, analogous spectra for highly dispersed heterogeneous catalysts consisting of single-atoms and ultra-small clusters are lacking. Here, we combine data-based approaches with physics-driven surrogate models to generate synthetic IR spectra from first-principles. We bypass the vast combinatorial space of clusters by determining viable, low-energy structures using machine-learned Hamiltonians, genetic algorithm optimization, and grand canonical Monte Carlo calculations. We obtain first-principles vibrations on this tractable ensemble and generate single-cluster primary spectra analogous to pure component gas-phase IR spectra. With such spectra as standards, we predict cluster size distributions from computational and experimental data, demonstrated in the case of CO adsorption on Pd/CeO 2 (111) catalysts, and quantify uncertainty using Bayesian Inference. We discuss extensions for characterizing complex materials towards closing the materials gap.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2020

Machine Learning for Neutron Resonance Evaluations [Slides]

The performance of nuclear reactors and other nuclear systems depends on a precise understanding of the neutron interaction cross sections for materials used in these systems. These cross sections exhibit a resonance structure whose shape is determined in part by the angular momentum quantum numbers of the resonances. The correct assignment of the quantum numbers of neutron resonances is therefore of paramount importance. In this presentation, we describe the application of machine learning to automate the quantum number assignments. Scikit-learn classifiers were trained on simulated resonance data whose statistical properties were chosen to mimic real data. We explored the use of several physics (and random matrix theory)-motivated features for training the classifiers, including the nearest neighbor spacing distribution, cumulative level distribution, and channel width distributions. Initial results demonstrated that we can determine resonance spin groups somewhat reliably. We are now investigating the application of our approach to 52 Cr resonance data.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗
DOE OSTI2025

RLMolLM: Reinforcement Learning-Enhanced Language Model Framework for Inverse Molecular Design

Inverse molecular design faces significant challenges due to vast chemical space and complex property requirements. While language models show promise for molecular generation, they struggle with validity, multi-property optimization, and structural constraints. This work presents RLMolLM, a reinforcement learning framework combining Proximal Policy Optimization (PPO) with genetic algorithms to address these limitations. Our approach optimizes multiple user-specified properties including quantitative estimates of drug-likeness (QED), synthetic accessibility (SA), and ADMET (absorption, distribution, metabolism, excretion, and toxicity) endpoints without requiring complete model retraining, while maintaining capability for scaffold-constrained generation where specific substructures must be preserved. We outperform state-of-the-art methods for molecular optimization, achieving best QED scores across GDB13, Moses, and Zinc datasets with up to 31% improvement over previous methods while maintaining excellent validity, uniqueness, and novelty metrics. For simultaneous multi-property optimization, our framework achieves substantial improvements in ADMET properties including 4.5-fold reduction in hERG toxicity and enhanced Caco-2 permeability compared to Moses dataset. Under structural constraints, the framework significantly improves molecular validity while preserving scaffolds and effectively optimizing properties. In conclusion, this versatile solution advances pharmaceutical and materials molecular design through effective integration of reinforcement learning and genetic algorithms with multi-property optimization and scaffold preservation.

Genetic algorithms↗
DOE OSTI2022

Quantifying subsurface parameter and transport uncertainty using surrogate modelling and environmental tracers

Here, we combine physics-based groundwater reactive transport modelling with machine-learning techniques to quantify hydrogeological model and solute transport predictive uncertainties. We train an artificial neural network (ANN) on a dataset of groundwater hydraulic heads and 3 H concentrations generated using a high-fidelity groundwater reactive transport model. Using the trained ANN as a surrogate model to reproduce the input–output response of the high-fidelity reactive transport model, we quantify the posterior distributions of hydrogeological parameters and hydraulic forcing conditions using Markov chain Monte Carlo calibration against field observations of groundwater hydraulic heads and 3 H concentrations. We demonstrate the methodology with a model application that predicts Chlorofluorocarbon-12 (CFC-12) solute transport at a contaminated field site in Wyoming, United States. Our results show that including 3 H observations in the calibration dataset reduced the uncertainty in the estimated permeability field and infiltration rates, compared to calibration against hydraulic heads alone. However, predictive uncertainty quantification shows that CFC-12 transport predictions conditioned to the parameter posterior distributions cannot reproduce the field measurements. We found that calibrating the model to hydraulic head and 3 H observations results in groundwater mean ages that are too large to explain the observed CFC-12 concentrations. The coupling of the physics-based reactive transport model with the machine-learning surrogate model allows us to efficiently quantify model parameter and predictive uncertainties, which is typically computationally intractable using reactive transport models alone.

58 GEOSCIENCES↗
DOE OSTI2020

Machine-Learning Enabled Evaluation of Probability of Piping Degradation In Secondary Systems of Nuclear Power Plants

The transition to condition-based, risk-informed automated maintenance will contribute to a significant reduction of operations and maintenance costs that account for the majority of nuclear power generation costs. Furthermore, of the operations and maintenance costs in U.S. plants, approximately 80% are labor costs. To address the issue of rising operating costs and economic viability, technologies used to perform online monitoring of piping and other secondary system structural components in commercial nuclear power plants (NPPs) are under evaluation. These online monitoring systems have the potential to identify when a more detailed inspection is needed using real time measurements, rather than at a pre-determined inspection interval thus reducing the maintenance cost. This paper describes distributed high-temperature stable fiber sensors fabricated in optical fibers through a roll-to-roll laser direct writing process using femtosecond lasers. Using phase-sensitive optical time domain reflectometry, distributed acoustic and vibration sensors can be developed and deployed to critical components and systems in NPPs to perform active measurements with spatial resolution down to 0.5-meter throughout the piping systems. Complex acoustic and vibration signatures harnessed by distributed sensors are registered and analyzed by artificial intelligence algorithms for degradation detection and flaw identification. Piping elbows with machined-in flaws were instrumented with fiber sensors. High-spatial-resolution data were used to develop and validate machine learning algorithms, including both linear and nonlinear regression, and classification. Additionally, classification and sensor analysis were also performed for data analysis. The paper concludes with recommendations and future work on applications of machine learning enabled high-resolution fiber sensors for piping degradation monitoring in current or future NPPs.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2021

Identifying schools at high-risk for elevated lead in drinking water using only publicly available data

Estimating the risk of lead contamination of schools' drinking water at the State level is a complex, important, and unexplored challenge. Variable water quality among water systems and changes in water chemistry during distribution affect lead dissolution rates from pipes and fittings. In addition, the locations of lead-bearing plumbing materials are uncertain. We tested the capability of six machine learning models to predict the likelihood of lead contamination of drinking water at the schools' taps using only publicly available datasets. The predictive features used in the models correspond to those with a proven correlation to the dominant, but commonly unavailable, factors that govern lead leaching: the presence of lead-bearing plumbing materials and water quality conducive to lead corrosion. By combining water chemistry data from public reports, socioeconomic information from the US census, and spatial features using Geographic Information Systems, we trained and tested models to estimate the likelihood of lead contaminated tap water in over 8,000 schools across California and Massachusetts. Our best-performing model was a Random Forest, with a 10-fold cross validation score of 0.88 for Massachusetts and 0.78 for California using the average Area Under the Receiver Operating Characteristic Curve (ROC AUC) metric. The model was then used to assign a lead leaching risk category to half of the schools across California (the other half was used for training). There was good agreement between the modeled risk categories and the actual lead leaching outcomes for every school; however, the model overestimated the lead leaching risk in up to 17% of the schools. This model is the first of its kind to offer a tool to predict the risk of lead leaching in schools at the State level. Further use of this model can help deploy limited resources more effectively to prevent childhood lead exposure from school drinking water.

63 RADIATION, THERMAL, AND OTHER ENVIRON. POLLUTAN↗
DOE OSTI2019

Efficient Multiscale Optoelectronic Prediction for Conjugated Polymers

Conjugated polymers represent a high-potential material class due to the tunability of their optoelectronic properties via straightforward processing protocols. However, to in silico tailor these optoelectronic properties, one must compute the conformationally dependent electronic structure over mesoscopic length and time scales. This task represents a challenging multiscale computational problem in which quantum chemistry and atomistic or coarse-grained molecular dynamics must be integrated. Recently, we introduced a methodology, called electronic coarse graining (ECG), that utilizes artificial neural networks to compute ab initio quality electronic structures using only the reduced degrees of freedom of coarse-grained models. Here, we adapt ECG to variable-molecular weight conjugated oligomers by casting the problem in the framework of sequence detection. A machine-learning (ML) architecture employing one-dimensional convolutional neural networks and long short-term memory networks is utilized to compute ground-state orbital energies, charge density distributions, and optical spectra solely from the coarse-grained model's configurational degrees of freedom. Robust molecular weight transferability for ECG is established via a A-ML approach that leverages model electronic Hamiltonians for ground and excited-state property determination. The accuracy and transferability of the ECG methodology opens the door for scalable optoelectronic property prediction in conjugated polymers directly from coarse-grained degrees of freedom.

36 MATERIALS SCIENCE↗
DOE OSTI2023

Simulated sulfur K-edge X-ray absorption spectroscopy database of lithium thiophosphate solid electrolytes

X-ray absorption spectroscopy (XAS) is a premier technique for materials characterization, providing key information about the local chemical environment of the absorber atom. In this work, we develop a database of sulfur K-edge XAS spectra of crystalline and amorphous lithium thiophosphate materials based on the atomic structures reported in Chem. Mater., 34, 6702 (2022). The XAS database is based on simulations using the excited electron and core-hole pseudopotential approach implemented in the Vienna Ab initio Simulation Package. Our database contains 2681 S K-edge XAS spectra for 66 crystalline and glassy structure models, making it the largest collection of first-principles computational XAS spectra for glass/ceramic lithium thiophosphates to date. This database can be used to correlate S spectral features with distinct S species based on their local coordination and short-range ordering in sulfide-based solid electrolytes. The data is openly distributed via the Materials Cloud, allowing researchers to access it for free and use it for further analysis, such as spectral fingerprinting, matching with experiments, and developing machine learning models.

36 MATERIALS SCIENCE↗
DOE OSTI2021

AI-based design of a nuclear reactor core

The authors developed an artificial intelligence (AI)-based algorithm for the design and optimization of a nuclear reactor core based on a flexible geometry and demonstrated a 3× improvement in the selected performance metric: temperature peaking factor. The rapid development of advanced, and specifically, additive manufacturing (3-D printing) and its introduction into advanced nuclear core design through the Transformational Challenge Reactor program have presented the opportunity to explore the arbitrary geometry design of nuclear-heated structures. The primary challenge is that the arbitrary geometry design space is vast and requires the computational evaluation of many candidate designs, and the multiphysics simulation of nuclear systems is very time-intensive. Therefore, the authors developed a machine learning-based multiphysics emulator and evaluated thousands of candidate geometries on Summit, Oak Ridge National Laboratory’s leadership class supercomputer. The results presented in this work demonstrate temperature distribution smoothing in a nuclear reactor core through the manipulation of the geometry, which is traditionally achieved in light water reactors through variable assembly loading in the axial direction and fuel shuffling during refueling in the radial direction. The conclusions discuss the future implications for nuclear systems design with arbitrary geometry and the potential for AI-based autonomous design algorithms.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2025

Machine Learning for Optimized Polarization at Jefferson Lab

Polarized cryo-targets and polarized photon beams are widely used in experiments at Jefferson Lab. Traditional methods for maintaining the optimal polarization involve manual adjustments throughout data taking by human shift takers. This may introduce some level of inconsistency simply due to the wide variety of experience and expertise of the shift takers themselves. Implementing machine learning-based control systems can improve the stability of the polarization without relying on human intervention. The cryo-target polarization is influenced by temperature, microwave energy, the distribution of paramagnetic radicals, as well as operational conditions including the radiation dose. Diamond radiators are used to generate linearly polarized photons from a primary electron beam. The energy spectrum of these photons can drift over time due to changes in the primary electron beam conditions and diamond degradation. As a first step towards automating the continuous optimization and control processes, uncertainty aware surrogate models have been developed to predict the polarization based on historical data. This talk will provide an overview of the use cases and models developed, highlighting the collaboration between data scientists and physicists at Jefferson Lab.

Jeske, Torri [Thomas Jefferson National Accelerato↗
DOE OSTI2023

Clustering High-dimensional Toxicogenomics Data with Rare Signals

Toxicogenomics studies the gene and protein activities to drug treatments or toxic exposures. As the drugs and genes are numerous, toxicogenomics data are naturally high dimensional, with dimension sizes up to millions. In addition, the distribution of toxicogenomics data is oftentimes skewed, and they contain rare but important signals representing a cell or organism’s response to toxicity. The combination of high dimension and extremely skewed distribution of toxicogenomics data makes clustering analysis extremely challenging.We present our study of clustering toxicogenomics data using classical approaches such as principal component analysis as well as deep learning approaches such as auto-encoders. Our experiments show that these approaches fail to preserve rare signals and produce high-quality clusters. We then explore augmenting matrix factorization with deep learning techniques such as attention mechanism to produce latent representations for clustering. Our technique is able to better preserve rare signals after dimensionality reduction than prior approaches. Furthermore, we combine our augmented matrix factorization with a mechanism similar to autoencoder to balance separable clusters and low regeneration errors. Our experiments demonstrate better clustering with our proposed approach.

Cong, Guojing↗
DOE OSTI2023

Regional Medium-Term Hourly Electricity Demand Forecasting Based on LSTM

This paper aims to forecast high-resolution (hourly) aggregated load for a certain region in the medium term (a few days to over a year). One region is defined as some places with similar climate characteristics because the climate influences people's daily lifestyles and hence the electric usage. We decom- pose the electric usage records into two parts: base load and seasonal load. Considering both temperature and time factors, different deep learning methods are adopted to characterize them. The first goal of our approach is to predict the peak load which is critical for power system planning. Furthermore, our proposed forecast method can provide the depiction of the hourly load profile to provide customized load curves for high- level real-time applications. The proposed method is tested on real-world historical data collected by CAISO, BPA, and PACW. The experimental results show that trained by three years of data, our method could reduce the prediction error for one-year lead hourly load below 5% MAPE, and predict the occurrence of the peak load for next year in CAISO with an error within three days. Furthermore, as a byproduct, an interesting observation on the impact of COVID-19 on human life was made and discussed based on these case studies.

deep learning↗
DOE OSTI2022

RLC4CLR (Reinforcement Learning Controller for Critical Load Restoration Problems)

RLC4CLR demonstrates using a reinforcement learning controller (RLC) to solve a critical load restoration (CLR) problem, which improves the grid resilience after a substation outage event. RLC4CLR consists of two parts. (1) RL environment: This environment encapsulates the CLR problem to be solved and provides interfacing functions to follow the standard OpenAI Gym format. A power system simulator, i.e., OpenDSS, is included to provide the power flow solution. Controller inputs and outputs (RL state and action) as well as the reward are defined in this environment as well. In summary, the RL environment is the problem formulation from which the RL agent can learn. (2) RL training script: The training script enables the RL agent to learn its control policy by interacting with the RL environment. For RL training, an open-sourced RL library, i.e., RLlib, is leveraged which is based on a distributed computing framework (Ray). The training script is designed to be able to be run on both local machine or the NREL HPC system. Other components of RLC4CLR include input data, e.g., grid model (standard IEEE test feeders), and other files used for results analysis.

Zhang, Xiangyu↗
DOE OSTI2022

Developing novel electrodes with ultralow catalyst loading for high-efficiency hydrogen production in proton exchange membrane electrolyzer cells

Hydrogen plays more crucial roles for decarbonizing the planets and meeting the climate challenges because of its high energy density and zero-emission. It can be produced with proton exchange membrane electrolyzer cells (PEMECs) driven by sustainable and renewable energy resources. Although PEMECs have a number of advantages, including high purity production, quick response, and the ability to operate at high pressure facilitating the gas delivering, their performance and cost greatly hinder their commercial-scale applications. To achieve high-efficiency and cost-reduced hydrogen production in PEMECs, we proposed thin engineered liquid/gas diffusion layers (LGDLs) and associated electrodes, i.e., catalyst-coated LGDLs (CCLGDLs), over conventional porous transport layers (PTLs) and catalyst-coated membranes (CCMs). The research approaches in this project are based on material synthesis, in-situ and ex-situ characterizations, component design and treatment, numerical modeling, and cost analysis. The thin and tunable LGDLs (TT-LGDLs) and CCLGDLs were successfully developed with great performance improvement as demonstrated in lab-scale, bench-scale, and system-scale electrolyzer tests. The electrode thickness was reduced from 370 µm to less than 100 µm with simplified fabrication processes. With the catalytically enhanced Ir-based catalyst coating, the as-developed CCLGDLs with a catalyst loading of 0.34 mg Ir /cm 2 achieved a cell performance of 1.77 V at 2 A cm -2 , exhibiting the catalyst mass activity enhanced by >20 times with significant catalyst saving over conventional catalyst cell design. In-situ PEMEC characterizations, including the current distribution mapping and high-speed and multiscale visualizations, were conducted for a deeper understanding of mass transport and electrochemical reactions within an electrolyzer with LGDLs and CCLGDLs. A 2D cell model was developed and validated for the enhanced performance on TT-LGDL through reducing ohmic losses due to nonuniform hydration and water transport. Further, the cost analysis results have shown a path to move beyond equivalency and surpass costs associated with the project baseline. In this project, the design and fabrication of TT-LGDLs and CCLGDLs will contribute to the performance enhancement, manufacturing simplification, and cost reduction for PEMECs and other energy conversion devices, thus shortening their pathways towards commercialization. This project also provides a good foundation for furthering the in-situ reaction interface research.

08 HYDROGEN↗
DOE OSTI2023

Regional Medium-Term Hourly Electricity Demand Forecasting Based on LSTM: Preprint

This paper aims to forecast high-resolution (hourly) aggregated load for a certain region in the medium term (a few days to over a year). One region is defined as some places with similar climate characteristics because the climate influences people's daily lifestyles and hence the electric usage. We decompose the electric usage records into two parts: base load and seasonal load. Considering both temperature and time factors, different deep-learning methods are adopted to characterize them. The first goal of our approach is to predict the peak load which is critical for power system planning. Furthermore, our proposed forecast method can provide the depiction of the hourly load profile to provide customized load curves for high-level real-time applications. The proposed method is tested on real-world historical data collected by CAISO, BPA, and PACW. The experimental results show that trained by three years of data, our method could reduce the prediction error for a one-year lead hourly load below 5% MAPE, and predict the occurrence of the peak load for next year in CAISO with an error within three days. Furthermore, as a byproduct, an interesting observation on the impact of COVID-19 on human life was made and discussed based on these case studies.

deep learning↗
DOE OSTI2023

Enhancement of operational Flexibility of Power Plants Using IN740

Headers are crucial components within diverse industries, especially in the energy sector, as they enable the efficient transfer of fluids. The selection of materials for headers is determined by their specific applications; for example, Grade 91 and Grade 92 steels are commonly utilized. In our research, we recommend the adoption of INCONEL alloy 740 due to its exceptional robustness and heat-resistant characteristics. One critical parameter in header systems is the heat transfer coefficient, which directly influences the efficiency of heat exchange processes and can thereby impact the structural integrity of the headers. This coefficient is closely linked with factors such as the Nusselt number, which is influenced by fluid flow characteristics and thermal properties. The flow direction within headers, whether unidirectional or multidirectional—significantly affects the overall dynamics of heat transfer. This research focuses on exploring the behavior of headers, a specific pipeline system component, using ANSYS simulation software. The study aims to predict heat transfer and mechanical behavior within headers under various conditions through steady-state and transient simulations (parts 1 and 2 of the report). Key parameters such as heat transfer coefficient, velocity, and temperature are examined with the goal of optimizing header design. Part 3 of the report addresses the critical yet underexplored relationship between pressure drop and heat transfer coefficients in the transient flow regime within headers, specifically focusing on smooth horizontal circular tubes. Limited experimental work has been conducted in this area, prompting the need for comprehensive analysis. By leveraging machine learning techniques, this research aims to establish a correlation between pressure drop and heat transfer across various flow conditions, including laminar, transient, quasi-turbulent, and turbulent regimes. The data utilized for this analysis were meticulously gathered from existing literature, capturing simultaneous measurements of pressure drops and heat transfer. Part 4: In the context of power plants, header pipes are essential components that significantly influence system performance by facilitating the collection and distribution of steam. This report highlights the critical role of header pipes in enhancing reliability, efficiency, and overall power plant performance. A key aspect of this investigation is shape optimization, which aims to maximize performance while minimizing material usage. By focusing on shape optimization, this research contributes to improved efficiency and a reduced environmental footprint for power plant installations. The methodology developed in this study emphasizes optimizing header shapes to decrease reliance on expensive alloy materials and lower maintenance costs. Furthermore, a case study was conducted using a header from an operational power plant to validate the proposed optimization techniques. Finally, part 5 addresses the challenges associated with flexible operations in boiler systems, the study outlines several strategies for enhancing the durability and reliability of steam headers. Key approaches include material selection, which involves utilizing advanced materials with superior high-temperature properties and enhanced fatigue resistance to extend the lifespan of steam headers. Design modifications are also recommended, focusing on implementing changes that mitigate thermal stress and cyclic loading to reduce the likelihood of failures under varying operating conditions. Additionally, the study emphasizes the importance of regular inspection and monitoring by establishing rigorous protocols to detect early signs of damage, allowing for timely maintenance and minimizing the risks of catastrophic failures. Furthermore, operational guidelines are developed to minimize the frequency and severity of thermal transients, ensuring stable and efficient operations. Collectively, these strategies provide a robust framework for overcoming the unique challenges posed by flexible operation in boiler systems, ultimately contributing to improved reliability and performance in power plant operations. Through this comprehensive approach, the study not only enhances the understanding of pressure drop and heat transfer relationships but also promotes advancements in design and operation that will benefit the entire power generation industry.

01 COAL, LIGNITE, AND PEAT↗
DOE OSTI2021

Approximating Nash Equilibrium in Day-ahead Electricity Market Bidding with Multi-agent Deep Reinforcement Learning

In this paper, a day-ahead electricity market bidding problem with multiple strategic generation company (GEN-CO) bidders is studied. The problem is formulated as a Markov game model, where GENCO bidders interact with each other todevelop their optimal day-ahead bidding strategies. Considering unobservable information in the problem, a model-free and data-driven approach, known as multi-agent deep deterministic policy gradient (MADDPG), is applied for approximating the Nash equilibrium (NE) in the above Markov game. The MADDPG algorithm has the advantage of generalization due to the automatic feature extraction ability of the deep neural networks. The algorithm is tested on an IEEE 30-bus system with three competitive GENCO bidders in both an uncongested caseand a congested case. Comparisons with a truthful bidding strategy and state-of-the-art deep reinforcement learning methods including deep Q network and deep deterministic policy gradient (DDPG) demonstrate that the applied MADDPG algorithm can find a superior bidding strategy for all the market participants with increased profit gains. In addition, the comparison with a conventional model-based method shows that the MADDPG algorithm has higher computational efficiency, which is feasible for real-world applications.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2020

Learning to Solve Large-Scale Security-Constrained Unit Commitment Problems

Security-constrained unit commitment (SCUC) is a fundamental problem in power systems and electricity markets. In practical settings, SCUC is repeatedly solved via mixed-integer linear programming (MIP), sometimes multiple times per day, with only minor changes in input data. In this work, we propose a number of machine learning techniques to effectively extract information from previously solved instances in order to significantly improve the computational performance of MIP solvers when solving similar instances in the future. Based on statistical data, we predict redundant constraints in the formulation, good initial feasible solutions, and affine subspaces where the optimal solution is likely to lie, leading to a significant reduction in problem size. Computational results on a diverse set of realistic and large-scale instances show that using the proposed techniques, SCUC can be solved on average 4.3 times faster with optimality guarantees and 10.2 times faster without optimality guarantees, with no observed reduction in solution quality. Out-of-distribution experiments provide evidence that the method is somewhat robust against data-set shift. Summary of Contribution. The paper describes a novel computational method, based on a combination of mixed-integer linear programming (MILP) and machine learning (ML), to solve a challenging and fundamental optimization problem in the energy sector. The method advances the state-of-the-art, not only for this particular problem, but also, more generally, in solving discrete optimization problems via ML. We expect that the techniques presented can be readily used by practitioners in the energy sector and adapted, by researchers in other fields, to other challenging operations research problems that are solved routinely.

Machine Learning↗