Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “data platform”

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 559 records · Page 31
All sourcesNASA NTRSDOE OSTI
DOE OSTI2013

Design of the Energy Partitioning Energy Coupling (EPEC) NIF Experiment

Using scaled experiments performed at the National Ignition Facility (NIF), the Energy Partitioning Energy Coupling (EPEC) experimental platform will provide benchmark data from scaled high energy density (HED) environments to validate codes for prompt yield determination following a near surface explosion. A set of numerical codes has been used to design the experiment and predict the experimental results. Preliminary NIF shots assessing performance of the EPEC energy source (a halfraum) have been carried out. Modeling of the EPEC experiments is discussed, with comparisons to results from the source shots.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2013

Phase II Nevada Water Resources Data, Modeling, and Visualization (DMV) Center (Final Report)

Water is unquestionably a critical resource throughout the United States. In the semi-arid west -- an area stressed by increase in human population and sprawl of the built environment -- water is the most important limiting resource. Crucially, science must understand factors that affect availability and distribution of water. To sustain growing consumptive demand, science needs to translate understanding into reliable and robust predictions of availability under weather conditions that could be average but might be extreme. These predictions are needed to support current and long-term planning. Similar to the role of weather forecast and climate prediction, water prediction over short and long temporal scales can contribute to resource strategy, governmental policy and municipal infrastructure decisions, which are arguably tied to the natural variability and unnatural change to climate. Change in seasonal and annual temperature, precipitation, snowmelt, and runoff affect the distribution of water over large temporal and spatial scales, which impact the risk of flooding and the groundwater recharge. Anthropogenic influences and impacts increase the complexity and urgency of the challenge. The goal of this project has been to develop a decision support framework of data acquisition, digital modeling, and 3D visualization. This integrated framework consists of tools for compiling, discovering and projecting our understanding of processes that control the availability and distribution of water. The framework is intended to support the analysis of the complex interactions between processes that affect water supply, from controlled availability to either scarcity or deluge. The developed framework enables DRI to promote excellence in water resource management, particularly within the Lake Tahoe basin. In principle, this framework could be replicated for other watersheds throughout the United States. Phase II of this project builds upon the research conducted during Phase I, in which the hydrologic framework was investigated and the development initiated. Phase II concentrates on practical implementation of the earlier work but emphasizes applications to the hydrology of the Lake Tahoe basin. Phase 1 efforts have been refined and extended by creating a toolset for geographic information systems (GIS) that is usable for disparate types of geospatial and geo-referenced data. The toolset is intended to serve multiple users for a variety of applications. The web portal for internet access to hydrologic and remotely sensed product data, prototyped in Phase I, has been significantly enhanced. The portal provides high performance access to LANDSAT-derived data using techniques developed during the course of the project. The portal is interactive, and supports the geo-referenced display of hydrologic information derived from remotely sensed data, such as various vegetative indices used to calculate water consumption. The platform can serve both internal and external constituencies using inter-operating infrastructure that spans both sides of the DRI firewall. The platform is intended grow its supported data assets and to serve as a template for replication to other geographic areas. An unanticipated development during the project was the use of ArcGIS software on a new computer system, called the IBM PureSytems, and the parallel use of the systems for faster, more efficient image processing. Additional data, independent of the portal, was collected within the Sagehen basin and provides detailed information regarding the processes that control hydrologic responses within mountain watersheds. The newly collected data include elevation, evapotranspiration, energy balance and remotely sensed snow-pack data. A Lake Tahoe basin hydrologic model has been developed, in part to help predict the hydrologic impacts of climate change. The model couples both the surface and subsurface hydrology, with the two components having been independently calibrated. Results from the coupled simulations involving both surface water and groundwater processes show that it is possible to fairly accurately simulate lake effects and water budget variables over a wide range of dry and wet cycles in the historical record. The Lake Tahoe basin is representative of the hydrology, topography and climate throughout the Sierra Nevada Range, and the entire model development is prototypical of the efforts required to replicate the decision support framework to other locales. The Lake Tahoe model in particular, could allow water managers to evaluate more accurately components of the water budget (ET, runoff, groundwater, etc) and to answer important questions regarding water resources in northern Nevada. This report discusses the geographic scale and the hydrologic complexity of the calibrated model developed as part of this project, as well as simulation results for historical and future climate projects To enable human-driven data exploration and discovery, de novo software for a globalized rendering module that extends the capability of our evolving custom visualization engine from Phase I (called SMEngine) has been developed. The new rendering component, called Horizon, supports terrain rendering capable of displaying and interrogating both remotely sensed and modeled data. The development of Horizon necessitated adaptation of the visualization engine to allow extensible integration of components such as the global rendering module and support for associated features. The resulting software is general in its GIS capability, but a specific Lake Tahoe visualization application suitable for immersive decision support in the DRIVE6 virtual reality facility has been developed. During the development, various features to enhance the value of the visualization experience were explored, including the use of hyperspectral image overlays. An over-arching goal of the visualization aspect of the project has been to develop and demonstrate the CAVE (CAVE Automatic Virtual Environment) as a practical tool for hydrologic research.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2016

An Extensible Sensing and Control Platform for Building Energy Management

The goal of this project is to develop Mortar.io, an open-source BAS platform designed to simplify data collection, archiving, event scheduling and coordination of cross-system interactions. Mortar.io is optimized for (1) robustness to network outages, (2) ease of installation using plug-and-play and (3) scalable support for small to large buildings and campuses.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2021

Neighborhood Keeper Program Review

Dragos provided INL access to their Neighborhood Keeper platform, which contains simulated data, sample reports given to utilities, and access to anonymized program data that is sent from utilities to the cloud. Dragos has specifically asked INL to review the available data and respond to the following questions: 1) What detections or combinations of detections are most useful? 2) What additional analysis would benefit the electricity subsector? 3) How could Neighborhood Keeper reporting be modified to benefit the electricity subsector? 4) What lessons learned from the Cybersecurity for the Operational Technology Environment (CyOTE) program could be provided? 5) Based on INL’s experience with utilities, are there lessons learned about data sharing that could be provided? 6) Are there recommendations that could benefit the electricity subsector?

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2019

Efficient partnership models for energy technology startups enabled by artificial intelligence that hyper-targets ecosystem connectivity

PartnerAI is a platform that utilizes the tools of the rapidly advancing field of Artificial Intelligence (AI) to understand and identify the connections between founders and potential partners or investors in the clean energy space. The platform makes use of data science tools, including clustering and NLP libraries, to evaluate scraped text and data, and build a real-time network of potential connections.

99 GENERAL AND MISCELLANEOUS↗
DOE OSTI2021

A Short-Term Solar Forecasting Platform Using a Physics-Based Smart Persistence Model and Data Imputation Method

Electrical energy plays vital role in our socio-economic activity and therefore ensuring the reliability of the electric grid, from the generation, transmission and distribution level is critical. In order to maintain the power system parameter viz., frequency, voltage, etc., optimally, balancing of generation and consumption is very much essential. However, solar energy is infirm power by nature this is due to cloud cover / other local phenomena. Hence, Photovoltaic (PV) power generation brings a significant challenge to the grid operator due to the variability of the solar energy. The complexity of this challenge in terms of planning and dispatch ability of PV resources, aggravates with the high penetration of solar energy into the electric grid. In this setting, reliable solar radiation forecasting models based on accurate and quality input data become essential. In order to develop a suitable model for predicting solar radiation, quality historical / real time measurement is also needed. Under this study NIWE and NREL jointly developed / tested short-term solar forecasting frameworks using a smart persistence and physics-based smart persistence models for intra-hour forecasting of solar radiation (PSPI) and benchmarked 9 different data imputation techniques in 15 Solar Radiation Resource Assessment (SRRA) stations, located at different parts of India. During any measurement campaign, due to various technical reasons, we may miss few observations. However, the missing observation often reduce the performance of any forecasting model. Therefore, suitable data imputation method would assist us to obtain continuous observation of solar radiation. A station-by-station and method-by-method analysis was carried out to understand the performance of each model. Based on our analysis, among all the data imputation methods, the Kalman data imputation method is better for Indian Weather condition. In addition, Kalman StructTS, Linear, Stine and Arima methods yield slightly inferior accuracy compared to Kalman, but outperform the other methods. The extended solar radiation data are used by solar forecasting models to provide the prediction of solar radiation at 15 SRRA stations. As far as short term forecasting model is concerned, the PSPI model outperforms the Smart Persistence model. However, the forecast error is increases with the forecasting horizon.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2023

Creating a Digital Twin for a Hydropower System through 3D Object Modeling: Alder Dam FY23

Hydropower stands as the world's leading source of renewable electricity, with hydropower plants spanning the globe. A typical hydropower plant comprises essential components including the governor, excitation system, generator, thrust bearing, hydraulic turbine, transformer, main lead, metering and control devices, tailwater depression system, and dissolved oxygen monitoring. Each of these components undergoes various measures and monitoring procedures. These measurements are collected through a diverse array of systems, encompassing standalone sensors, programmable logic controllers (PLCs), Supervisory Control and Data Acquisition (SCADA) systems, Internet of Things (IoT) devices, and data acquisition and integration platforms like OSI/PI.

13 HYDRO ENERGY↗
DOE OSTI2023

Preliminary Feasibility of Printing, Microstructure Analysis and Mechanical Performance of a Down Selected Ni Alloy

This report is submitted as completion of a Milestone 3 deliverable under work package ORNL CT-23OR1304051 in support of the Advanced Materials and Manufacturing Technologies (AMMT) program. The AMMT program is aiming at the faster incorporation of new materials and manufacturing technologies into complex nuclear-related systems. An integrated approach, combining advanced characterization, high-throughput and accelerated testing, modeling and simulation including machine learning and artificial intelligence will be employed. While 316H (Fe-16-18Cr-10-14Ni-2-3Mo-0.04-0.1C) has been identified as a key alloy to be integrated into the AMMT accelerated alloy qualification approach due its relevance for many current and future nuclear energy reactors, many other alloys could be considered for the advanced fabrication of innovate high-performance nuclear components. ANL, INL, ORNL and PNNL are collaborating on identifying the most promising alloy candidates relevant for the AMMT program. A selection criteria matrix was established to evaluate the alloys considering their relative importance and technological readiness levels for nuclear energy applications, with a focus on laser powder bed fusion (LPBF). Due to the broad range of potential candidate alloys, ORNL and INL focused on Ni-based alloys, while ANL and PNNL mainly evaluated Fe-based alloys. PNNL previously published materials scorecards reports on several key alloys and this report is providing a broader overview of Ni-based candidate alloys, expending beyond alloys well-known to the nuclear community. Of particular interest are alloys that are currently commercially available in powder form due to the growing demand from other industries that have invested heavily in additive manufacturing. Among these alloys, Haynes 282 (Fe-20Cr-20Co-8Mo) was selected due to its superior strength at high temperature compared to the code-qualified alloy 617 (Ni-20-24Cr-10-15Co-8-10Mo). To assess the integration of this new alloy into the AMMT digital manufacturing framework, we performed the rapid optimization of alloy 282 printing parameters on a Renishaw 250 machine, the fabrication of sufficient materials for extensive characterization and mechanical testing both at ORNL and INL, and added the printing data into the digital platform via the Peregrine software. A detailed analysis of the LPBF 718 alloy was also conducted, with creep specimens being tested at 600-650°C and characterized by advanced electron microscopy. The alloy superior mechanical strength and great printability associated with the extensive database that has already been generated highlight the promising potential of LPBF 718 as a candidate alloy for the AMMT program. INL, ANL and PNNL have generated similar reports and all the information will be compiled into a final M2 milestone report to provide the AMMT leadership team with clear recommendations on the down selection of reactor materials, as well as establish a roadmap for the qualification of these selected alloys.

36 MATERIALS SCIENCE↗
DOE OSTI2025

MLCommons Science Benchmarks

Benchmarks are a cornerstone of modern machine learning practice, providing standardized eval- uations that enable reproducibility, comparison, and scientific progress. Yet, as AI systems particularly deep learning models become increasingly dynamic, traditional static benchmarking approaches are losing their relevance. Models rapidly evolve in architecture, scale, and capability; datasets shift; and deployment contexts continuously change, creating a moving target for evaluation. Without adaptive benchmarking frame- works, both scientific assessment and real-world de- ployment risk becoming misaligned with actual system behavior. Drawing on our experience from MLCommons, educa- tional initiatives, and government programs such as the DOE s Million Parameter Consortium, we identify key barriers that hinder the broader adoption and utility of benchmarking in AI. These include substantial resource demands, limited access to specialized hardware, lack of expertise in benchmark design, and uncertainty among practitioners about how to relate benchmark results to their own application domains. Moreover, current benchmarks often emphasize peak performance on leadership-class hardware, offering limited guidance for more diverse, real-world deployment scenarios. We argue that benchmarking itself must become dy- namic in order to incorporate evolving models, updated data, and heterogeneous computational platforms while maintaining transparency, reproducibility, and inter- pretability. Democratizing this process requires not only technical innovation, but also systematic educational efforts spanning undergraduate to professional levels to develop sustained expertise in benchmark design and use. Finally, benchmarks should be framed and com- municated to support application-relevant comparisons, enabling both developers and users to make informed, context-sensitive decisions. Advancing dynamic and inclusive benchmarking practices will be essential to ensure that evaluation keeps pace with the evolving AI landscape and supports responsible, reproducible, and accessible AI deployment.

Hawks, Benjamin G. [Fermilab]↗
DOE OSTI2021

KBase partners with community developers from several Department of Energy Science Focus Areas to increase functionality of tools and analysis

Several SFAs were selected for training on the KBase Software Development Kit (SDK) to integrate tools and data into the KBase platform. Overall, the collaborative effort was viewed as highly successful. Every SFA project was able to achieve their proposed targets for training and functionality, while also gaining an appreciation for the role KBase plays/could play in their future science plans. Both the SFA and KBase teams felt that continued collaboration would be beneficial, especially if the programs were able to jointly prioritize scope and readiness of future projects. This poster will outline the scope of functionality added by SFA community developers, and highlight points of intersection across these efforts.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2012

Molecular beam mass spectrometry with tunable vacuum ultraviolet (VUV) synchrotron radiation

Tunable soft ionization coupled to mass spectroscopy is a powerful method to investigate isolated molecules, complexes and clusters and their spectroscopy and dynamics.[1-4] Fundamental studies of photoionization processes of biomolecules provide information about electronic structure of these systems. Furthermore determinations of ionization energies and other properties of biomolecules in the gas phase are not trivial, and these experiments provide a platform to generate these data. We have developed a thermal vaporization technique coupled with supersonic molecular beams that provides a gentle way to transport these species into the gas phase. Judicious combination of source gas and temperature allows for formation of dimers and higher clusters of the DNA bases. The focus of this particular work is on the effects of non-covalent interactions, i.e., hydrogen bonding, stacking, and electrostatic interactions, on the ionization energies and proton transfer of individual biomolecules, their complexes and upon micro-hydration by water.[1, 5-9] We have performed experimental and theoretical characterization of the photoionization dynamics of gas-phase uracil and 1,3-methyluracil dimers using molecular beams coupled with synchrotron radiation at the Chemical Dynamics Beamline[10] located at the Advanced Light Source and the experimental details are visualized here. This allowed us to observe the proton transfer in 1,3-dimethyluracil dimers, a system with pi stacking geometry and with no hydrogen bonds[1]. Molecular beams provide a very convenient and efficient way to isolate the sample of interest from environmental perturbations which in return allows accurate comparison with electronic structure calculations[11, 12]. By tuning the photon energy from the synchrotron, a photoionization efficiency (PIE) curve can be plotted which informs us about the cationic electronic states. These values can then be compared to theoretical models and calculations and in turn, explain in detail the electronic structure and dynamics of the investigated species [1, 3].

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2025

Portable Software Environment for Ultrahigh-Resolution ELM Development on GPUs

This paper presents our endeavors in developing the large-scale, ultra-high-resolution E3SM Land Model (uELM), specifically designed for exascale computers furnished with accelerators such as Nvidia GPUs. The uELM is a sophisticated code that substantially relies on High-Performance Computing (HPC) environments, necessitating particular machine and software configurations. To facilitate community-based uELM developments employing GPUs, we have created a portable, standalone software environment preconfigured with uELM input datasets, simulation cases, and source code. This environment, utilizing Docker, encompasses all essential code, libraries, and system software for uELM development on GPUs. It also features a functional unit test framework and an offline model testbed for comprehensive numerical experiments. From a technical perspective, the paper discusses GPU-ready container generations, uELM code management, and input data distribution across computational platforms. Lastly, the paper demonstrates the use of environment for functional unit testing, end-to-end simulation on CPUs and GPUs, and collaborative code development.

E3SM Land Model↗
DOE OSTI2025

RTN-045: Guidelines for User Tutorials

This document defines the guidelines, principles, and formats for user-facing tutorials that demonstrate how to use the Rubin Science Platform (RSP) to analyze data from the Legacy Survey of Space and Time (LSST). All Rubin staff and the broader science community should use these guidelines when contributing to the sets of Jupyter Notebook or documentation-based tutorials maintained by the Rubin Community Science team (CST).

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2022

Achieving American Leadership in Cybersecurity and Digital Components Factsheet

The Biden Administration’s efforts to meet 100% clean electricity by 2035 and net-zero greenhouse gas emissions by 2050 has created opportunities to rebuild American supply chains create new jobs, strengthen community engagement, and spur U.S. economic growth. DOE’s strategy for success in the transition to a clean energy economy hinges on building and maintaining technology supply chains that are advanced, secure, and resilient to cyber threats. As the energy sector grows increasingly globalized, complex, and digitized, the supply chain for digital components of energy systems – including software, virtual platforms and services, and data – is facing greater threats. Nearly all digital components of U.S. energy sector systems are vulnerable to cyber supply chain instability, stemming from a variety of causes and shared among a broad set of interdependent stakeholders. Overall, supply chain risks for digital components in energy sector systems will continue to evolve and likely increase as these systems are increasingly interconnected, digitized, and remotely operated.

CCE↗
DOE OSTI2013

Presentation of the MERC work-flow for the computation of a 2D radial reflector in a PWR

This paper presents a work-flow for computing an equivalent 2D radial reflector in a pressurized water reactor (PWR) core, in adequacy with a reference power distribution, computed with the method of characteristics (MOC) of the lattice code APOLLO2. The Multi-modelling Equivalent Reflector Computation (MERC) work-flow is a coherent association of the lattice code APOLLO2 and the core code COCAGNE, structured around the ADAO (Assimilation de Donnees et Aide a l'Optimisation) module of the SALOME platform, based on the data assimilation theory. This study leads to the computation of equivalent few-groups reflectors, that can be spatially heterogeneous, which have been compared to those obtained with the OPTEX similar methodology developed with the core code DONJON, as a first validation step. Subsequently, the MERC work-flow is used to compute the most accurate reflector in consistency with all the R and D choices made at Electricite de France (EDF) for the core modelling, in terms of number of energy groups and simplified transport solvers. We observe important reductions of the power discrepancies distribution over the core when using equivalent reflectors obtained with the MERC work-flow. (authors)

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2026

Pixel-Registered Multimodal Synchrotron XRF and FTIR Microscopies Reveal Salinity Stress Response Mechanisms in Pistachio

Background: Salinity is a major abiotic stress that negatively affects nearly all plant species at all stages of growth. Drought and poor-quality irrigation cause high soil salinity and salt accumulation via evaporation, reducing crop productivity. Despite its critical importance, the spatial localization of salt ions and associated biochemical changes within plants experiencing high salinity remains largely unknown. In this study, we developed a multimodal imaging pipeline to understand the impact of salinity on the pistachio rootstock UCB-1 (Pistacia atlantica x Pistacia integerrima). We directly link biochemical fingerprints in stem tissue architecture with salt ion localization to provide insights into the strategies pistachio uses to tolerate salinity. Results: We observed that Pistacia spp. exposed to high salt conditions accumulated Ca, Si, Cl, Al and Mg as hotspots within the pith, compared to the control (of which only Ca and Al co-locate). In contrast, there was a decrease in K between the control and salinity treatment. Hotspots of amide I and II were present in the cortex and pith of the salinity treated sample. Additionally, the salinity treatment resulted in an increased abundance of pectin and carbohydrates within the pith compared to the control, and the abundance of esters/carboxylic acid was greater in the salinity treatment. Conclusions: We determined that Cl and K, S and P, and biochemical components polysaccharide and pectin, esters and carboxylic acid, amide I and cellulose are the strongest drivers of salinity- treatment induced variability. In the cortex and phloem/xylem, a negative K-Ca correlation decreases in the salinity treatment. Several hotspots of elements and amide I (proteins) appear under salinity treatment, particularly in the cortex, suggesting an increase in the production of stress-related proteins (in response to high Cl) and/or structural proteins (i.e. Ca). Together, these results indicate that pistachio responds to salinity through ion compartmentalization coupled with a targeted biochemical adjustment, rather than a broadscale tissue-wide response. Overall, these novel, spatially resolved pixel-registered multimodal imaging data provide an enabling platform to understand the mechanisms of salinity tolerance in Pistacia spp and can be broadly applied to studying stress-related phenotype response in various plant tissues.

FTIR spectromicroscopy↗
DOE OSTI2016

Automated Work Package: Initial Wireless Communication Platform Design, Development, and Evaluation

The Department of Energy’s Light Water Reactor Sustainability Program is developing the scientific basis to ensure long-term reliability, productivity, safety, and security of the nuclear power industry in the United States. The Instrumentation, Information, and Control (II&C) pathway of the program aims to increase the role of advanced II&C technologies to achieve this objective. One of the pathway efforts at Idaho National Laboratory (INL) is to improve the work packages execution process by replacing the expensive, inefficient, bulky, complex, and error-prone paper-based work orders with automated work packages (AWPs). An AWP is an automated and dynamic presentation of the work package designed to guide the user through the work process. It is loaded on a mobile device, such as a tablet, and is capable of communicating with plant equipment and systems to acquire plant and procedure states. The AWP replaces those functions where a computer is more efficient and reliable than a human. To enable the automatic acquisition of plant data, it is necessary to design and develop a prototype platform for data exchange between the field instruments and the AWP mobile devices. The development of the platform aims to reveal issues and solutions generalizable to large-scale implementation of a similar system. Topics such as bandwidth, robustness, response time, interference, and security are usually associated with wireless communication. These concerns, along with other requirements, are listed in an earlier INL report. Specifically, the targeted issues and performance aspects in this work are relevant to the communication infrastructure from the perspective of promptness, robustness, expandability, and interoperability with different technologies.

Automated Work Packages↗
DOE OSTI2021

Hardware-Based Emulator with Deep Learning Model for Building Energy Control and Prediction Based on Occupancy Sensors’ Data

Heating, ventilation, and air conditioning (HVAC) is the largest source of residential energy consumption. Occupancy sensors’ data can be used for HVAC control since it indicates the number of people in the building. HVAC and sensors form a typical cyber-physical system (CPS). In this paper, we aim to build a hardware-based emulation platform to study the occupancy data’s features, which can be further extracted by using machine learning models. In particular, we propose two hardware-based emulators to investigate the use of wired/wireless communication interfaces for occupancy sensor-based building CPS control, and the use of deep learning to predict the building energy consumption with the sensor data. We hypothesize is that the building energy consumption may be predicted by using the occupancy data collected by the sensors, and question what type of prediction model should be used to accurately predict the energy load. Another hypothesis is that an in-lab hardware/software platform could be built to emulate the occupancy sensing process. The machine learning algorithms can then be used to analyze the energy load based on the sensing data. To test the emulator, the occupancy data from the sensors is used to predict energy consumption. The synchronization scheme between sensors and the HVAC server will be discussed. We have built two hardware/software emulation platforms to investigate the sensor/HVAC integration strategies, and used an enhanced deep learning model—which has sequence-to-sequence long short-term memory (Seq2Seq LSTM)—with an attention model to predict the building energy consumption with the preservation of the intrinsic patterns. Because the long-range temporal dependencies are captured, the Seq2Seq models may provide a higher accuracy by using LSTM architectures with encoder and decoder. Meanwhile, LSTMs can capture the temporal and spatial patterns of time series data. The attention model can highlight the most relevant input information in the energy prediction by allocating the attention weights. The communication overhead between the sensors and the HVAC control server can also be alleviated via the attention mechanism, which can automatically ignore the irrelevant information and amplify the relevant information during CNN training. Our experiments and performance analysis show that, compared with the traditional LSTM neural network, the performance of the proposed method has a 30% higher prediction accuracy.

Ye, Zhijing↗