Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “out of memory”

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 883 records · Page 49
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Short-Term Forecasting of Thermostatic and Residential Loads Using Long Short-Term Memory Recurrent Neural Networks

Internet of Things (IoT) devices in smart grids enable intelligent energy management for grid managers and personalized energy services for consumers. Investigating a smart grid with IoT devices requires a simulation framework with IoT devices modeling. However, there lack comprehensive study on the modeling of IoT devices in smart grids. This paper investigates the IoT device modeling of a thermostatic load and implements the recurrent neural networks model for short-term load forecasting in this IoT-based thermostatic load. The recurrent neural network structure is leveraged to build a load forecasting model on temporal correlation. The temporal recurrent neural network layers including long short-term memory cells are employed to learn the data from both the simulation platform and New South Wales residential datasets. The simulation results are provided for demonstration.

electric load forecasting↗
DOE OSTI2024

Variation-Resilient FeFET-Based In-Memory Computing Leveraging Probabilistic Deep Learning

Reliability issues stemming from device level nonidealities of nonvolatile emerging technologies like ferroelectric field-effect transistors (FeFETs), especially at scaled dimensions, cause substantial degradation in the accuracy of in-memory crossbar-based AI systems. Here, in this work, we present a variation-aware design technique to characterize the device level variations and to mitigate their impact on hardware accuracy employing a Bayesian neural network (BNN) approach. An effective conductance variation model is derived from the experimental measurements of cycle-to-cycle (C2C) and device-to-device (D2D) variations performed on FeFET devices fabricated using 28 nm high-k metal gate technology. The variations were found to be a function of different conductance states within the given programming range, which sharply contrasts earlier efforts where a fixed variation dispersion was considered for all conductance values. Such variation characteristics formulated for three different device sizes at different read voltages were provided as prior variation information to the BNN to yield a more exact and reliable inference. Near-ideal accuracy for shallow networks (MLP5 and LeNet models) on the MNIST dataset and limited accuracy decline by ~3.8%–16.1% for deeper AlexNet models on CIFAR10 dataset under a wide range of variations corresponding to different device sizes and read voltages, demonstrates the efficacy of our proposed device-algorithm co-design technique.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2019

Directed aging, memory, and nature’s greed

Disordered materials are often out of equilibrium and evolve very slowly in a rugged and tortuous energy landscape. This slow evolution, referred to as aging, is deemed undesirable as it often leads to material degradation. However, we show that aging also encodes a memory of the stresses imposed during preparation. Because of inhomogeneous local stresses, the material itself decides how to evolve by modifying stressed regions differently from those under less stress. Because material evolution occurs in response to stresses, aging can be “directed” to produce sought-after responses and unusual functionalities that do not inherently exist. Aging obeys a natural “greedy algorithm” as, at each instant, the material simply follows the path of most rapid and accessible relaxation. Our experiments and simulations illustrate directed aging in examples in which the material’s elasticity transforms as desired because of an imposed deformation.

75 CONDENSED MATTER PHYSICS, SUPERCONDUCTIVITY AND↗
DOE OSTI2024

Performance Study of CXL Memory Topology

This paper presents a comprehensive evaluation of the performance impact of various Compute Express Link (CXL) memory topologies, with a particular emphasis on CXL switches, in the context of High- Performance Computing (HPC) and Large Language Model (LLM) inference workloads. Our study unveils significant performance variations across different topologies, demonstrating that certain configurations yield superior performance for specific workloads. These findings underscore the critical importance of tailored topol- ogy selection in optimizing system performance. Additionally, we address the inherent challenges associated with integrating CXL switches, including overhead considerations and routing complex- ities. Our research highlights the necessity for thorough evalua- tion methodologies to fully leverage CXL technology’s potential in contemporary computing environments. These insights provide valuable guidance for system architects and data center operators in designing and optimizing CXL-based infrastructures for diverse workload requirements.

CXL, memory, Artificial Intelligence (AI), HPC↗
DOE OSTI2026

qSIEVE: Efficient qLDPC Memory via Systolic Movement in Atom Arrays

As quantum machines have scaled up in their number of qubits, significant research has turned towards increasing their fidelity with quantum error correction codes. Although promising results have been shown with the surface code, which only requires near-neighbor connections between qubits, the high qubit overhead of such local codes promises to be problematic. Consequently, recent work has explored non-local quantum LDPC (qLDPC) codes, which have good asymptotic encoding rates. Despite theoretical progress, hardware implementations of these codes have been a longstanding challenge. At the experimental level, demonstrations of movement based communication on atom arrays suggest this is a powerful new primitive to achieve non-local connectivity. Leveraging this, we present a protocol for implementing non-local qLDPC codes in hardware. Our protocol, qSIEVE, is a co-design of such codes with movement in atom arrays. qSIEVE defines a restricted family of qLDPC codes that can be implemented efficiently with systolic movement. We then quantify the utility of qSIEVE in the context of a complete fault tolerant architecture. We compare the cost of implementing benchmark programs in a standard, surface code only architecture and a mixed architecture where data is stored in qLDPC memory with qSIEVE and loaded to surface codes for computation.

Quantum error correction↗
DOE OSTI2023

Electrophysiological Signatures of Visual Recognition Memory across All Layers of Mouse V1

In mouse primary visual cortex (V1), familiar stimuli evoke significantly altered responses when compared with novel stimuli. This stimulus-selective response plasticity (SRP) was described originally as an increase in the magnitude of visual evoked potentials (VEPs) elicited in layer 4 (L4) by familiar phase-reversing grating stimuli. SRP is dependent on NMDA receptors (NMDARs) and has been hypothesized to reflect potentiation of thalamocortical (TC) synapses in L4. However, recent evidence indicates that the synaptic modifications that manifest as SRP do not occur on L4 principal cells. To shed light on where and how SRP is induced and expressed in male and female mice, the present study had three related aims: (1) to confirm that NMDAR are required specifically in glutamatergic principal neurons of V1, (2) to investigate the consequences of deleting NMDAR specifically in L6, and (3) to use translaminar electrophysiological recordings to characterize SRP expression in different layers of V1. We find that knock-out (KO) of NMDAR in L6 principal neurons disrupts SRP. Current-source density (CSD) analysis of the VEP depth profile shows augmentation of short latency current sinks in layers 3, 4, and 6 in response to phase reversals of familiar stimuli. Multiunit recordings demonstrate that increased peak firing occurs in response to phase reversals of familiar stimuli across all layers, but that activity between phase reversals is suppressed. Together, these data reveal important aspects of the underlying phenomenology of SRP and generate new hypotheses for the expression of experience-dependent plasticity in V1. SIGNIFICANCE STATEMENT Repeated exposure to stimuli that portend neither reward nor punishment leads to behavioral habituation, enabling organisms to dedicate attention to novel or otherwise significant features of the environment. The neural basis of this process, which is so often dysregulated in neurologic and psychiatric disorders, remains poorly understood. Learning and memory of stimulus familiarity can be studied in mouse visual cortex by measuring electrophysiological responses to simple phase-reversing grating stimuli. The current study advances knowledge of this process by documenting changes in visual evoked potentials (VEPs), neuronal spiking activity, and oscillations in the local field potentials (LFPs) across all layers of mouse visual cortex. In addition, we identify a key contribution of a specific population of neurons in layer 6 (L6) of visual cortex.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2022

Control of a Three-Phase Grid-Connected Voltage-Sourced Converter Using Long Short-Term Memory Networks

With the rise of inverter-based resources (IBRs) within the power system, the control of grid-connected converters (GCCs) has become pertinent due to the fact they interface IBRs to the grid. The conventional method of control for a GCC such as the voltage-sourced converter (VSC) is through a decoupled control loop in the synchronous reference frame. However, this model-based control method is sensitive to parameter changes causing deterioration in controller performance. Data-driven approaches such as machine learning can be utilized to design controllers that are capable of operating GCCs in various system conditions. This work explores a deep learning-based control method for a three-phase grid-connected VSC, specifically utilizing a long short-term memory (LSTM) network for robust control. Simulations of a conventional controlled VSC are conducted using Simulink to collect data for training the LSTM-based controller. The LSTM model is built and trained using the Keras and TensorFlow libraries in Python and tested in Simulink. The performance of the LSTM-based controller is evaluated under different case studies and compared to the conventional method of control. Simulation results demonstrate the effectiveness of this approach by outperforming the conventional controller and maintaining stability under different system parameter changes.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

Anomaly Detection in Liquid Sodium Cold Trap Operation with Multisensory Data Fusion Using Long Short-Term Memory Autoencoder

Sodium-cooled fast reactors (SFR), which use high temperature fluid near ambient pressure as coolant, are one of the most promising types of GEN IV reactors. One of the unique challenges of SFR operation is purification of high temperature liquid sodium with a cold trap to prevent corrosion and obstructing small orifices. We have developed a deep learning long short-term memory (LSTM) autoencoder for continuous monitoring of a cold trap and detection of operational anomaly. Transient data were obtained from the Mechanisms Engineering Test Loop (METL) liquid sodium facility at Argonne National Laboratory. The cold trap purification at METL is monitored with 31 variables, which are sensors measuring fluid temperatures, pressures and flow rates, and controller signals. Loss-of-coolant type anomaly in the cold trap operation was generated by temporarily choking one of the blowers, which resulted in temperature and flow rate spikes. The input layer of the autoencoder consisted of all the variables involved in monitoring the cold trap. The LSTM autoencoder was trained on the data corresponding to cold trap startup and normal operation regime, with the loss function calculated as the mean absolute error (MAE). The loss during training was determined to follow log-normal density distribution. During monitoring, we investigated a performance of the LSTM autoencoder for different loss threshold values, set at a progressively increasing number of standard deviations from the mean. The anomaly signal in the data was gradually attenuated, while preserving the noise of the original time series, so that the signal-to-noise ratio (SNR) averaged across all sensors decreased below unity. Results demonstrate detection of anomalies with sensor-averaged SNR < 1.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2021

Coexisting Multiple Martensites in Ni 57-x Mn 21+x Ga 22 Ferromagnetic Shape Memory Alloys: Crystal Structure and Phase Transition

A comprehensive study of the crystal structure and phase transition as a function of temperature and composition in Ni 57–x Mn 21+x Ga 22 (x = 0, 2, 4, 5.5, 7, 8) (at. %) magnetic shape memory alloys was performed by a temperature-dependent synchrotron X-ray diffraction technique and transmission electron microscopy. A phase diagram of this Ni 57–x Mn 21+x Ga 22 alloy system was constructed. The transition between coexisting multiple martensites with monoclinic and tetragonal structures during cooling was observed in the Ni 51.5 Mn 26.5 Ga 22 (x = 5.5) alloy, and it was found that 5M + 7M multiple martensites coexist from 300 K to 160 K and that 5M + 7M + NM multiple martensites coexist between 150 K and 100 K. The magnetic-field-induced transformation from 7M martensite to NM martensite at 140 K where 5M + 7M + NM multiple martensites coexist before applying the magnetic field was observed by in situ neutron diffraction experiments. The present study is instructive for understanding the phase transition between coexisting multiple martensites under external fields and may shed light on the design of novel functional properties based on such phase transitions.

36 MATERIALS SCIENCE↗
DOE OSTI2021

Long Short-Term Memory Networks for Pattern Recognition of Synthetical Complete Earthquake Catalog

Exploring the spatiotemporal distribution of earthquake activity, especially earthquake migration of fault systems, can greatly to understand the basic mechanics of earthquakes and the assessment of earthquake risk. By establishing a three-dimensional strike-slip fault model, to derive the stress response and fault slip along the fault under regional stress conditions. Our study helps to create a long-term, complete earthquake catalog. We modelled Long-Short Term Memory (LSTM) networks for pattern recognition of the synthetical earthquake catalog. The performance of the models was compared using the mean-square error (MSE). Our results showed clearly the application of LSTM showed a meaningful result of 0.08% in the MSE values. Our best model can predict the time and magnitude of the earthquakes with a magnitude greater than Mw = 6.5 with a similar clustering period. These results showed conclusively that applying LSTM in a spatiotemporal series prediction provides a potential application in the study of earthquake mechanics and forecasting of major earthquake events.

58 GEOSCIENCES↗