Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “applied statistics”

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 451 records · Page 25
All sourcesNASA NTRSDOE OSTI
DOE OSTI2020

Experimental investigation of multi-scale strain-field heterogeneity in rocks

Rocks have inherently heterogeneous micro-structures. The mechanical response of these heterogeneous micro-structures primarily governs the overall macroscopic behavior of intact rocks, as these features cause heterogeneity in the distribution of stress and strain within a rock volume. These attributes have generally been studied through numerical tools, but in this study, the stress-induced multi-scale spatial heterogeneity in the strain-field of three types of rocks was analyzed experimentally. The full-field non-contact strain measurement approach of 2D Digital Image Correlation (DIC) was employed for real-time evaluation of the progression of strain-field heterogeneity across the surface of the rock specimens when subjected to uniaxial compression. The results show that the strain-field heterogeneity is a characteristic of the inherent heterogeneity of the rock specimens, and that it amplifies with the magnitude of stress applied on the rock specimens. The changes in the strain-field heterogeneity with loading were consistent with established microcrack evolution processes in the rock specimens. The statistical fluctuation in the strain-field heterogeneity of the three rocks at varying gauge lengths (GL) was then analyzed for the determination of the Representative Volume Element (RVE) length-scale at increasing load levels. The evolution of the RVE length-scale with loading facilitates an objective way of determination of the stress at which the strain-field heterogeneity increases and begins to influence the overall global response of the material. The RVE length-scale variation with loading showed that at the RVE length-scale reaches the specimen-scale at load levels well below the peak strength.

2D-digital image correlation↗
DOE OSTI2024

Searching for parity violation in SDSS DR16 Lyman-α forest data

The four-point correlation function is the lowest order correlation function for scalar fields that can be used to probe statistical parity invariance in an isotropic universe. There are intriguing claims of detection of parity violation in the 4-point function of BOSS galaxy clustering data. We apply the same estimator to the public SDSS Data Release 16 Lyman-α forest data. Lyman-α forest data probes a different redshift range and is sensitive to a different density regime using a completely different technique. A detection would therefore be a strong indication of new physics. We identify an accurate covariance matrix as a crucial impediment to performing this measurement accurately, consistent with existing literature on galaxy 4-point function. Here, we discuss several approaches to estimating the covariance matrix, several of which produce spurious detection. Using a robust, but very suboptimal, covariance matrix derived from subsample bootstrapping, we find no evidence for parity violation.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

G-Mapper: Learning a Cover in the Mapper Construction

The Mapper algorithm is a visualization technique in topological data analysis (TDA) that outputs a graph reflecting the structure of a given dataset. However, the Mapper algorithm requires tuning several parameters in order to generate a “nice” Mapper graph. This paper focuses on selecting the cover parameter. We present an algorithm that optimizes the cover of a Mapper graph by splitting a cover repeatedly according to a statistical test for normality. Our algorithm is based on G-means clustering, which searches for the optimal number of clusters in 𝑘-means by iteratively applying the Anderson–Darling test. Our splitting procedure employs a Gaussian mixture model to carefully choose the cover according to the distribution of the given data. In conclusion, experiments for synthetic and real-world datasets demonstrate that our algorithm generates covers so that the Mapper graphs retain the essence of the datasets, while also running significantly faster than a previous iterative method.

G-means clustering↗
DOE OSTI2022

Differentiable Predictions for Large Scale Structure with SHAMNet

In simulation-based models of the galaxy-halo connection, theoretical predictions for galaxy clustering and lensing are typically made based on Monte Carlo realizations of a mock universe. In this paper, we use Subhalo Abundance Matching (SHAM) as a toy model to introduce an alternative to stochastic predictions based on mock population, demonstrating how to make simulation-based predictions for clustering and lensing that are both exact and differentiable with respect to the parameters of the model. Conventional implementations of SHAM are based on iterative algorithms such as Richardson-Lucy deconvolution; here we use the JAX library for automatic differentiation to train SHAMNet, a neural network that accurately approximates the stellar-to-halo mass relation (SMHM) defined by abundance matching. In our approach to making differentiable predictions of large-scale structure, we map parameterized PDFs onto each simulated halo, and calculate gradients of summary statistics of the galaxy distribution by using autodiff to propagate the gradients of the SMHM through the statistical estimators used to measure one- and two-point functions. Our techniques are quite general, and we conclude with an overview of how they can be applied in tandem with more complex, higher-dimensional models, creating the capability to make differentiable predictions for the multi-wavelength universe of galaxies.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

Exploring Advanced Computational Tools and Techniques with Artificial Intelligence and Machine Learning in Operating Nuclear Plants

This report presents the project Idaho National Laboratory conducted for Nuclear Regulatory Commission to explore the advanced computational tools and techniques, such as artificial intelligence (AI) and machine learning (ML), for operating nuclear plants. The report reviews the nuclear data sources, with the focus on the operating experience data, that could be applied by advanced computational tools and techniques. Plant-specific and generic (national and international) data from different sources are described. The report describes the relationships between statistics and AI/ML and then introduces the most widely used AI/ML algorithms in both supervised and unsupervised learning. The report reviews the recent applications of advanced computational tools and techniques in various fields of nuclear industry, such as reactor system design and analysis, plant operation and maintenance, and nuclear safety and risk analysis. Finally, the report presents the insights from the project on the potential applicability of AI/ML techniques in improving advanced computational capabilities, how the advanced tools and techniques could contribute to the understanding of safety and risk, and what information would be needed to provide meaningful insights to decision makers. The report also documents an NRC survey on the current state of commercial nuclear power operations relative to the use of AI and ML tools as well as the role of AI/ML tools in nuclear power operations was published by the NRC as in FRN NRC-2021-0048 in April 2021. A summary of the survey including the survey questions, survey participants, survey responses, and the conclusions and insights derived from the survey is provided in the report. Finally, the report investigates potential applications of using AI/ML in operating NPPs and advanced reactors (both advanced LWRs and advanced NLWRs) to improve nuclear plant safety and efficiency. Three main application fields are defined and discussed: (1) plant safety and security assessments; (2) plant degradation modeling, fault and accident diagnosis and prognosis; and (3) plant operation and maintenance efficiency improvement.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
DOE OSTI2023

Assessment of Baseline Monitoring Data for the Remote-Handled Low-Level Waste Disposal Facility at Idaho National Laboratory

The purpose of this document is to summarize environmental monitoring data collected at the Remote-Handled Low-Level Waste (RHLLW) Disposal Facility during the first four years of facility operations (FY 2019 through FY 2022). This summary provides a “baseline” condition for the facility, which can be used to distinguish contaminant releases from the RHLLW Disposal Facility from pre existing contamination as well as potential future releases from other sources (i.e., upgradient aquifer sources), as specified in the facility monitoring plan. Sufficient data has been collected over the first four years of operation of the RHLLW Disposal Facility to establish baseline conditions for future compliance monitoring of aquifer wells and performance monitoring of vadose zone lysimeters. Except for seven elevated tritium measurements from lysimeter HFEF-South believed to have been impacted by waste disposals, all data was deemed appropriate for establishing baseline concentrations. Monitoring of the aquifer detected indicator analytes gross alpha and gross beta and target analytes tritium and C-14. There were a few C-14 detections prior to an increase in the required detection level (RDL) after the first round of sampling. I-129 and Tc-99 were not detected above RDLs in aquifer samples. Lysimeter samples detected indicator analytes gross alpha and gross beta and target analyte tritium. Target analytes C-14, I-129, and Tc-99 were not detected above RDLs in lysimeter samples. Except for tritium, baseline concentrations of indicator and target analytes measured during the first four years of RHLLW facility operations are expected to represent conditions through the expected 20 year operating period of the facility. Elevated tritium in the aquifer, a result of past discharges of tritium at upgradient facilities, showed a decline over the first four years of operations, and levels are expected to continue to decline with time as a result of dilution and decay. Current tritium levels in lysimeter samples may be elevated due to tritium in the water applied during construction and infiltration testing of the facility. As a result, tritium concentrations in lysimeters may decline with time as a result of dilution and decay. Statistical measures (i.e., mean, standard deviation, and 99% upper confidence level [UCL]) were calculated for all detected analytes using the four years of concentration data. These measures will be used to evaluate future monitoring results and to demonstrate the facility is performing, or not performing, as established in the facility performance assessment (PA). Future monitoring results will also be combined with the baseline data in this report to further establish temporal trends and natural variability in the measurements. Based on the data collected during the baseline period, it is recommended the gross alpha action level for performance monitoring increase from 10 to 20 pCi/L due to several baseline measurements exceeding the preliminary action level of 10. An action level of 20 pCi/L is slightly greater than the 99% UCL, is protective of the aquifer, and would reduce unnecessary sampling. It is also recommended that tritium be added to the lysimeter analyte list for post-baseline period monitoring. Tritium, while not a dose concern, is a good tracer that can provide valuable information on water flow in and around the RHLLW Disposal Facility. Recommendations for a tritium action level are provided if considered necessary.

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2025

VitriEdge: Repairable & Durable Vitrimer Coatings for Wind Turbine Blade Leading Edges

The primary goal of this Level 1b incubator project was to explore the use of vitrimer coatings for repair of leading-edge erosion on end-of-life wind turbine blade surfaces, beyond coating strength of adhesion which has previously been demonstrated in the Level 1a project. Uniform vitrimer coatings (thickness: 400 µm) were applied to two end-of-life wind turbine blades for flexural, fatigue, and laminate tensile testing where the addition of the coating did not produce any statistical variation in tensile properties with minor drops in flexural strength for some laminate formulations. However, a <2% variation in storage modulus was measured for laminate structures (i.e., blade samples with vitrimer coatings) across 100,000 flexural cycles and upon laminate tensile failure, the vitrimer coatings displayed no visible signs of delamination. In addition, three methods to heal vitrimer coating damage was displayed: oven heating, addition of hot water, and a forced convection heat gun. All three heating and healing mechanisms demonstrated significant healing with scratch depths decreasing between 79-91% at healing times ranging between 1-min and 10-minutes. Finally, a water jet machine was used to simulate rain erosion for both the blade surfaces and vitrimer-coated blade surfaces where the diameter and depth of the damage was recorded as a function of exposure time, water pressure, height of exposure, and angle of exposure. Of interest, while the vitrimer coating did not significantly lessen the damage experienced during rain erosion, the addition of vitrimer composite coatings(5 wt.% mica addition) did result in a crack-resistant, durable coating capable of self-healing behavior and in all cases the angle of rain exposure was the most critical parameter explored. It is crucial to continue exploring this space where vitrimer coatings are of interest for both their self-healing properties and potential use as reversible adhesives.

17 WIND ENERGY↗
DOE OSTI2025

Data from: 'Abiotic influences on continuous conifer forest structure across a subalpine watershed'

This package archives the core data used for analysis and inference in 'Abiotic influences on continuous conifer forest structure across a subalpine watershed' (Worsham et al., 2025). All data were collected in the East River, Washington Gulch, Slate River, and Coal Creek watersheds of Colorado. In the paper, we quantified the relative influence of climate, topographic, edaphic, and geologic factors on conifer stand structure and composition, and their functional relationships, at the watershed scale. We used waveform LiDAR data to derive spatially continuous stand structure metrics. We fused these with a species-level classification map to estimate tree species abundance. We applied generalized additive and generalized boosted models to evaluate the covariability of structural and compositional metrics with abiotic variables. The package contains the essential products required for reproducing our analysis and the tables and figures reported in the publication. The products comprise four classes: (1) geospatial data, (2) tabular data used for inferential analysis, (3) tabular data describing analytical results and performance statistics, and (4) a data user guide. (1) includes discretized waveform LiDAR data, locations and attributes of individual tree crowns, sampling locations and domain boundaries, a canopy height model, and raster files of estimated forest structural and compositional metrics at 100 m grid scale. (2) includes all response and explanatory variable values applied in inferential models. Response variables include conifer forest stand density, basal area, 95th percentile height, quadratic mean diameter, and others. Explanatory variables include climatic water deficit, actual evapotranspiration, elevation, heat load, soil available water content, and others. (3) includes results of training and testing several individual tree detection (ITD) algorithms, as well as inferential modeling results. (4) is a PDF user guide for this data package, including detailed descriptions and data dictionaries for all files. The data package root contains 17 assets: 8 compressed tape archive (.tar.gz) files, 5 comma-separated values (.csv) files, 3 Geographic Tagged Image File Format (GeoTIFF) (.tif) files, and 1 Portable Document Format (.pdf) file. The compressed .tar.gz archives contain ESRI shapefiles (.shp) .tif, compressed LASer (.laz), and .csv files. The archives must first be decompressed using the widely distributed command-line software utility TAR. All other files, including constituent files within the .tar.gz archives, can be opened in the open-source R statistical computing environment. Alternatively, .csv files may also be read in any simple text editor software or Microsoft Excel. Geospatial files including .shp and .tif files can also be opened in GIS software, such as QGIS (open-source) or ESRI ArcGIS (proprietary). The .pdf Data User Guide can be read with Adobe Acrobat Reader or other compatible readers.

2018 NEON and 2025 CHESS Campaigns↗
DOE OSTI2025

Cosmology with second- and third-order shear statistics for the Dark Energy Survey: Methods and simulated analysis

We present a new pipeline designed for the robust inference of cosmological parameters using both second- and third-order shear statistics. We build a theoretical model for rapid evaluation of three-point correlations using our fastnc code and integrate it into the cosmosis framework. We measure the two-point functions 𝜉 ± and the full configuration-dependent three-point shear correlation functions across all auto- and cross-redshift bins. We compress the three-point functions into the mass aperture statistic ⟨ℳ$^{3}_{ap}$⟩ for a set of 796 simulated shear maps designed to model the Dark Energy Survey Year 3 data. We estimate from it the full covariance matrix and model the effects of intrinsic alignments, shear calibration biases and photometric redshift uncertainties. We apply scale cuts to minimize the contamination from the baryonic signal as modeled through hydrodynamical simulations. We find a significant improvement of 83% on the figure of merit in the Ω m − 𝑆 8 plane when we add the ⟨ℳ$^{3}_{ap}$⟩ data to 𝜉 ± . Here, we present our findings for all relevant cosmological and systematic uncertainty parameters and discuss the complementarity of third-order and second-order statistics.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2020

Peer-to-Peer Energy Trading and Grid Impact Studies in Smart Communities

The rise of peer-to-peer (P2P) marketplace paradigms has transformed existing marketplace models, but the extent to which this approach can be applied to the energy marketplace has yet to be considered. In this paper, we examine existing approaches taken in the application of a P2P paradigm to the energy marketplace, further presenting an approach towards facilitating an online P2P energy marketplace, implementing a prototype P2P web application named SolTrade. Furthermore, we submit initial statistics based on simulated transactions facilitated through the platform, which illustrate the physical impact of marketplace transactions on the energy grid. In particular, these results show that, as the number of users rises, the chance of overloading the grid rises, but the chance of the grid being unable to sustain itself without an external source of energy falls.

peer-to-peer economy, web development, energy shar↗
DOE OSTI2022

Global estimates of the fitness advantage of SARS-CoV-2 variant Omicron

Abstract New variants of SARS-CoV-2 show remarkable heterogeneity in their relative fitness over both time and space. In this paper we extend the tools available for estimating the selection strength for new SARS-CoV-2 variants to a hierarchical, mixed-effects, renewal equation model. This formulation allows us to estimate selection effects at the global level while incorporating both measured and unmeasured heterogeneity among countries. Applying this model to the spread of Omicron in forty countries, we find evidence for very strong but very heterogeneous selection effects. To test whether this heterogeneity is explained by differences in the immune landscape, we considered several measures of vaccination rates and recent population-level infection as covariates, finding moderately strong, statistically significant effects. We also found a significant positive correlation between the selection advantage of Delta and Omicron at the country level, suggesting that other region-specific explanatory variables of fitness differences do exist. Our method is implemented in the Stan programming language, can be run on standard consumer-grade computing resources, and will be straightforward to apply to future variants.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Identifying microbial drivers in biological phenotypes with a Bayesian network regression model

Abstract In Bayesian Network Regression models, networks are considered the predictors of continuous responses. These models have been successfully used in brain research to identify regions in the brain that are associated with specific human traits, yet their potential to elucidate microbial drivers in biological phenotypes for microbiome research remains unknown. In particular, microbial networks are challenging due to their high dimension and high sparsity compared to brain networks. Furthermore, unlike in brain connectome research, in microbiome research, it is usually expected that the presence of microbes has an effect on the response (main effects), not just the interactions. Here, we develop the first thorough investigation of whether Bayesian Network Regression models are suitable for microbial datasets on a variety of synthetic and real data under diverse biological scenarios. We test whether the Bayesian Network Regression model that accounts only for interaction effects (edges in the network) is able to identify key drivers (microbes) in phenotypic variability. We show that this model is indeed able to identify influential nodes and edges in the microbial networks that drive changes in the phenotype for most biological settings, but we also identify scenarios where this method performs poorly which allows us to provide practical advice for domain scientists aiming to apply these tools to their datasets. BNR models provide a framework for microbiome researchers to identify connections between microbes and measured phenotypes. We allow the use of this statistical model by providing an easy‐to‐use implementation which is publicly available Julia package at https://github.com/solislemuslab/BayesianNetworkRegression.jl .

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2024

Extending deterministic transport capabilities for very-high and ultra-high energy electron beams

Focused Very-High Energy Electron (VHEE, 50–300 MeV) and Ultra-High Energy Electron (UHEE, > 300 MeV) beams can accurately target both large and deeply seated human tumors with high sparing properties, while avoiding the spatial requirements and cost of proton and heavy ion facilities. Advanced testing phases are underway at the CLEAR facilities at CERN (Switzerland), NLCTA at Stanford (USA), and SPARC at INFN (Italy), aiming to accelerate the transition to clinical application. Currently, Monte Carlo (MC) transport is the sole paradigm supporting preclinical trials and imminent clinical deployment. In this paper, we propose an alternative: the first extension of the nuclear-reactor deterministic chain Njoy-Dragon for VHEE and UHEE applications. We have extended the Boltzmann-Fokker-Planck (BFP) multigroup formalism and validated it using standard radio-oncology benchmarks, complex assemblies with a wide range of atomic numbers, and comprehensive irradiation of the entire periodic table. We report that 99% of water voxels exhibit a BFP-MC deviation below 2% for electron energies under 1.5 GeV. Additionally, we demonstrate that at least 97% of voxels of bone, lung, adipose tissue, muscle, soft tissue, tumor, steel, and aluminum meet the same criterion between 50 MeV and 1.5 GeV. For water, the thorax, and the breast intra-operative benchmark, typical average BFP-MC deviations of 0.3% and 0.4% were observed at 300 MeV and 1 GeV, respectively. By irradiating the entire periodic table, we observed similar performance between lithium (Z = 3) and cerium (Z = 58). Deficiencies observed between praseodymium (Z = 59) and einsteinium (Z = 99) have been reported, analyzed, and quantified, offering critical insights for the ongoing development of the Evaluated Nuclear Data File mode in NJOY.

62 RADIOLOGY AND NUCLEAR MEDICINE↗
DOE OSTI2026

Measuring labor productivity dynamics in U.S. industrial and electric power sectors: a case study (2014–2023)

This study proposes a subsystem methodology for measuring labor productivity in the U.S. industrial and electric power sectors by leveraging public data available between 2014 and 2023. Building on Pasinetti’s framework and subsequent developments, the approach employs Vertically Integrated Sectors (VIS) to account for both direct and indirect productivity effects. The novelty of this work is twofold. First, it enables the estimation of productivity trends over time, providing a robust foundation for empirical analysis. Second, it applies the methodology to a case study of the electric generation sector, highlighting its practical relevance. Using data from the Bureau of Economic Analysis, the Bureau of Labor Statistics, and the Impact Analysis for Planning (IMPLAN) tool, the study reveals significant discrepancies between conventional productivity measures and those derived from the VIS approach. Furthermore, the proposed method aligns with the principles of Integrated Energy Systems by capturing the interrelations among generation, distribution, storage, and consumption. This alignment underscores its utility and applications for energy-related policy and planning. Overall, the findings contribute to more precise labor productivity assessments, supporting informed decision-making and future research. Additionally, the method highlights the importance of considering the whole supply chain, providing interrelated metrics for labor productivity which includes both, direct and indirect effects on the final labor productivity metric. By incorporating intersectoral dependencies, this method offers a more comprehensive and accurate measure of labor productivity compared to traditional metrics.

11 - NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2025

Evaluation of fluxon synapse device based on superconducting loops for energy efficient neuromorphic computing

With Moore’s law nearing its end due to the physical scaling limitations of CMOS technology, alternative computing approaches have gained considerable attention as ways to improve computing performance. Here, we evaluate performance prospects of a new approach based on disordered superconducting loops with Josephson-junctions for energy efficient neuromorphic computing. Synaptic weights can be stored as internal trapped fluxon states of three superconducting loops connected with multiple Josephson-junctions (JJ) and modulated by input signals applied in the form of discrete fluxons (quantized flux) in a controlled manner. The stable trapped fluxon state directs the incoming flux through different pathways with the flow statistics representing different synaptic weights. We explore implementation of matrix–vector-multiplication (MVM) operations using arrays of these fluxon synapse devices. We investigate the energy efficiency of online-learning of MNIST dataset. Our results suggest that the fluxon synapse array can provide ~100× reduction in energy consumption compared to other state-of-the-art synaptic devices. This work presents a proof-of-concept that will pave the way for development of high-speed and highly energy efficient neuromorphic computing systems based on superconducting materials.

42 ENGINEERING↗
DOE OSTI2023

An asymptotic approach for the statistical thermodynamics of certain model systems

In classical statistical thermodynamics, calculating the configuration integral is both vital and elusive. Analytic relations for configuration integrals are desirable for modeling purposes, but it is typically impossible to obtain them. Certain systems become analytically tractable after replacing steep potential energies with harmonic potentials or athermal rigid constraints, but these approximations are often inadequate, especially when modeling the stretching of molecules. It is therefore necessary to develop a systematic approach to improve upon the approximations provided by these reference systems. Here, a general asymptotic approach is introduced, where the configuration integral for the full system is obtained in terms of that of the reference system and several corrections. This asymptotic approach is first demonstrated using the simple example of a classical three-dimensional oscillator. Next, the approach is applied to modeling the stretching of single polymer chains and to modeling thermally assisted crack growth, where results are verified with respect to numerical calculations. Overall, this asymptotic approach is a valid and effective tool for statistical thermodynamics in general.

Buche, Michael Robert↗
DOE OSTI2026

Anomaly Detection for Online Monitoring of Thermocouple Sensors in the Advanced Test Reactor

This study explores data-driven anomaly detection methods to analyze sensor fail- ures in the Advanced Gas Reactor (AGR) nuclear fuel irradiation experiments. Specifically, we examine failures of thermocouples (TCs), which are critical for mon- itoring and controlling in-reactor temperatures during operation. Failures were pri- marily observed during abrupt power transitions and manifested as sensor drop-outs, drifts, or unexplained behavior. We applied three time-series analysis techniques— rolling mean smoothing, matrix profile, and vector auto-regression (VAR)—to de- tect anomalies in TC data prior to failure events. The rolling mean method effec- tively highlighted deviations aligned with reported failures, while the matrix profile provided partial early warning but sometimes flagged normal fluctuations during power-down periods. VAR shows potential in capturing multivariate dependencies but requires further calibration. A rare case of TC drift was also documented, which did not result in failure, underscoring the challenge of building predictive models with sparse positive examples. Our findings demonstrate that traditional statistical tools can aid anomaly detection but have limited predictive power without richer training data. We propose future directions including synthetic data generation, real- time surrogate modeling, and multi-modal feature integration. This work provides a foundation for applying robust anomaly detection frameworks to mission-critical sensor systems in experimental settings.

11 - NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2020

Cross-Market Price Difference Forecast Using Deep Learning for Electricity Markets

Price forecasting is in the center of decision making in electricity markets. Many researches have been done in forecasting energy prices while little research has been reported on forecasting price difference between day-ahead and realtime markets due to its high volatility, which however plays a critical role in virtual trading. To this end, this paper takes the first attempt to employ novel deep learning architecture with Bidirectional Long-Short Term Memory (LSTM) units to forecast the price difference between day-ahead and real-time markets for the same node. The raw data is collected from PJM market, processed and fed into the proposed network. The Root Mean Squared Error (RMSE) and customized performance metric are used to evaluate the performance of the proposed method. Case studies show that it outperforms the traditional statistical models like ARIMA, and machine learning models like XGBoost and SVR methods in both RMSE and the capability of forecasting the sign of price difference. Additionally, to cross-market price difference forecast, the proposed approach has the potential to be applied to solve other forecasting problems such as price spread forecast in DA market for Financial Transmission Right (FTR) trading purpose.

DA/RT price difference↗