Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Model”

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 271 records · Page 15
All sourcesNASA NTRSDOE OSTI
DOE OSTI2016

Vehicle Modeling for use in the CAFE model: Process description and modeling assumptions

The objective of this project is to develop and demonstrate a process that, at a minimum, provides more robust information that can be used to calibrate inputs applicable under the CAFE model’s existing structure. The project will be more fully successful if a process can be developed that minimizes the need for decision trees and replaces the synergy factors by inputs provided directly from a vehicle simulation tool. The report provides a description of the process that was developed by Argonne National Laboratory and implemented in Autonomie.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2022

Dynamic energy system modeling using hybrid physics-based and machine learning encoder–decoder models

Three model configurations are presented for multi-step time series predictions of the heat absorbed by the water and steam in a thermal power plant. The models predict over horizons of 2, 4, and 6 steps into the future, where each step is a 5-minute increment. The evaluated models are a pure machine learning model, a novel hybrid machine learning and physics-based model, and the hybrid model with an incomplete dataset. The hybrid model deconstructs the machine learning into individual boiler heat absorption units: economizer, water wall, superheater, and reheater. Each configuration uses a gated recurrent unit (GRU) or a GRU-based encoder–decoder as the deep learning architecture. Mean squared error is used to evaluate the models compared to target values. The encoder–decoder architecture is over 11% more accurate than the GRU only models. The hybrid model with the incomplete dataset highlights the importance of the manipulated variables to the system. The hybrid model, compared to the pure machine learning model, is over 10% more accurate on average over 20 iterations of each model. Automatic differentiation is applied to the hybrid model to perform a local sensitivity analysis to identify the most impactful of the 72 manipulated variables on the heat absorbed in the boiler. The models and sensitivity analyses are used in a discussion about optimizing the thermal power plant.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2017

On the Bayesian calibration of computer model mixtures through experimental data, and the design of predictive models

For many real systems, several computer models may exist with different physics and predictive abilities. To achieve more accurate simulations/predictions, it is desirable for these models to be properly combined and calibrated. Here, we propose the Bayesian calibration of computer model mixture method which relies on the idea of representing the real system output as a mixture of the available computer model outputs with unknown input dependent weight functions. The method builds a fully Bayesian predictive model as an emulator for the real system output by combining, weighting, and calibrating the available models in the Bayesian framework. Moreover, it fits a mixture of calibrated computer models that can be used by the domain scientist as a mean to combine the available computer models, in a flexible and principled manner, and perform reliable simulations. It can address realistic cases where one model may be more accurate than the others at different input values because the mixture weights, indicating the contribution of each model, are functions of the input. Inference on the calibration parameters can consider multiple computer models associated with different physics. The method does not require knowledge of the fidelity order of the models. We provide a technique able to mitigate the computational overhead due to the consideration of multiple computer models that is suitable to the mixture model framework. We implement the proposed method in a real-world application involving the Weather Research and Forecasting large-scale climate model.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2022

A new multi-model absolute difference-based sensitivity (MMADS) analysis method to screen non-influential processes under process model and parametric uncertainty

Process-based models have been widely used for hydrologic modeling, and it is a common practice to use sensitivity analysis methods for excluding non-influential hydrologic processes from further investigation and/or model improvement. This study develops a new method called multi-model absolute difference-based sensitivity (MMADS) analysis method to screen non-influential system processes and parameters. MMADS is conceptually similar to the Morris method for addressing parametric uncertainty, but has a unique feature to address both process model uncertainty (i.e., a process may be represented by multiple process models) and process model parameter uncertainty (i.e., parameters associated with a process model are random). MMADS first evaluates absolute differences of a quantity of interest (i.e., a system model output) by varying process models and/or process model parameter values, and then calculates the mean and variance of the differences for investigating process influence. The mean measures overall influence of the process on the quantity of interest, and the variance estimates influence of nonlinear effects of the process and/or its interactions with other processes. MMADS is an extension of the Morris method from a parameter space to a joint parameter-model space for explicitly addressing both process model uncertainty and model parameter uncertainty. The performance of MMADS is evaluated by using two numerical experiments. One experiment is based on Sobol’s G*-function with ten product elements, and has analytical solutions of the MMADS mean and variance of absolute differences. The other experiment is for groundwater flow modeling which considers three processes (i.e., recharge, geology, and snowmelt) that interact with each other. Finally, results indicate that MMADS is computationally efficient and can identify non-influential processes of complex hydrological systems.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2016

Analyzing the impact of modeling choices and assumptions in compartmental epidemiological models

In this study, computational models have become increasingly used as part of modeling, predicting, and understanding how infectious diseases spread within large populations. These models can be broadly classified into differential equation-based models (EBM) and agent-based models (ABM). Both types of models are central in aiding public health officials design intervention strategies in case of large epidemic outbreaks. We examine these models in the context of illuminating their hidden assumptions and the impact these may have on the model outcomes. Very few ABM/EBMs are evaluated for their suitability to address a particular public health concern, and drawing relevant conclusions about their suitability requires reliable and relevant information regarding the different modeling strategies and associated assumptions. Hence, there is a need to determine how the different modeling strategies, choices of various parameters, and the resolution of information for EBMs and ABMs affect outcomes, including predictions of disease spread. In this study, we present a quantitative analysis of how the selection of model types (i.e., EBM vs. ABM), the underlying assumptions that are enforced by model types to model the disease propagation process, and the choice of time advance (continuous vs. discrete) affect the overall outcomes of modeling disease spread. Our study reveals that the magnitude and velocity of the simulated epidemic depends critically on the selection of modeling principles, various assumptions of disease process, and the choice of time advance.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2014

Technical Note: On the use of nudging for aerosol–climate model intercomparison studies

Nudging as an assimilation technique has seen increased use in recent years in the development and evaluation of climate models. Constraining the simulated wind and temperature fields using global weather reanalysis facilitates more straightforward comparison between simulation and observation, and reduces uncertainties associated with natural variabilities of the large-scale circulation. On the other hand, the forcing introduced by nudging can be strong enough to change the basic characteristics of the model climate. In the paper we show that for the Community Atmosphere Model version 5 (CAM5), due to the systematic temperature bias in the standard model and the sensitivity of simulated ice formation to anthropogenic aerosol concentration, nudging towards reanalysis results in substantial reductions in the ice cloud amount and the impact of anthropogenic aerosols on long-wave cloud forcing. In order to reduce discrepancies between the nudged and unconstrained simulations, and meanwhile take the advantages of nudging, two alternative experimentation methods are evaluated. The first one constrains only the horizontal winds. The second method nudges both winds and temperature, but replaces the long-term climatology of the reanalysis by that of the model. Results show that both methods lead to substantially improved agreement with the free-running model in terms of the top-of-atmosphere radiation budget and cloud ice amount. The wind-only nudging is more convenient to apply, and provides higher correlations of the wind fields, geopotential height and specific humidity between simulation and reanalysis. Results from both CAM5 and a second aerosol–climate model ECHAM6-HAM2 also indicate that compared to the wind-and-temperature nudging, constraining only winds leads to better agreement with the free-running model in terms of the estimated shortwave cloud forcing and the simulated convective activities. This suggests nudging the horizontal winds but not temperature is a good strategy for the investigation of aerosol indirect effects since it provides well-constrained meteorology without strongly perturbing the model's mean climate.

Zhang, K.↗
DOE OSTI2015

BioEarth: Envisioning and developing a new regional earth system model to inform natural and agricultural resource management

As managers of agricultural and natural resources are confronted with uncertainties in global change impacts, the complexities associated with the interconnected cycling of nitrogen, carbon, and water present daunting management challenges. Existing models provide detailed information on specific sub-systems (land, air, water, economics, etc). An increasing awareness of the unintended consequences of management decisions resulting from interconnectedness of these sub-systems, however, necessitates coupled regional earth system models (EaSMs). Decision makers’ needs and priorities can be integrated into the model design and development processes to enhance decision-making relevance and "usability" of EaSMs. BioEarth is a current research initiative with a focus on the U.S. Pacific Northwest region that explores the coupling of multiple stand-alone EaSMs to generate usable information for resource decision-making. Direct engagement between model developers and non-academic stakeholders involved in resource and environmental management decisions throughout the model development process is a critical component of this effort. BioEarth utilizes a "bottom-up" approach, upscaling a catchment-scale model to basin and regional scales, as opposed to the "top-down" approach of downscaling global models utilized by most other EaSM efforts. This paper describes the BioEarth initiative and highlights opportunities and challenges associated with coupling multiple stand-alone models to generate usable information for agricultural and natural resource decision-making.

agricultural↗
DOE OSTI2018

Practical factors of envelope model setup and their effects on the performance of model predictive control for building heating, ventilating, and air conditioning systems

Model predictive control (MPC) for buildings is attracting significant attention in research and industry due to its potential to address a number of challenges facing the building industry, including energy cost reduction, grid integration, and occupant connectivity. However, the strategy has not yet been implemented at any scale, largely due to the significant effort required to configure and calibrate the model used in the MPC controller. While many studies have focused on methods to expedite model configuration and improve model accuracy, few have studied the impact a wide range of factors have on the accuracy of the resulting model. In addition, few have continued on to analyze these factors’ impact on MPC controller performance in terms of final operating costs. Therefore, this study first identifies the practical factors affecting model setup, specifically focusing on the thermal envelope. The seven that are identified are building design, model structure, model order, data set, data quality, identification algorithm and initial guesses, and software tool-chain. Then, through a large number of trials, it analyzes each factor's influence on model accuracy, focusing on grey-box models for a single zone building envelope. Finally, this study implements a subset of the models identified with these factor variations in heating, ventilating, and air conditioning MPC controllers, and tests them in simulation of a representative case that aims to optimally cool a single-zone building with time-varying electricity prices. It is found that a difference of up to 20%25 in cooling cost for the cases studied can occur between the best performing model and the worst performing model. The primary factors attributing to this were model structure and initial parameter guesses during parameter estimation of the model.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2023

A single-point modeling approach for the intercomparison and evaluation of ozone dry deposition across chemical transport models (Activity 2 of AQMEII4)

A primary sink of air pollutants and their precursors is dry deposition. Dry deposition estimates differ across chemical transport models, yet an understanding of the model spread is incomplete. Here, we introduce Activity 2 of the Air Quality Model Evaluation International Initiative Phase 4 (AQMEII4). We examine 18 dry deposition schemes from regional and global chemical transport models as well as standalone models used for impact assessments or process understanding. We configure the schemes as single-point models at eight Northern Hemisphere locations with observed ozone fluxes. Single-point models are driven by a common set of site-specific meteorological and environmental conditions. Five of eight sites have at least 3 years and up to 12 years of ozone fluxes. The interquartile range across models in multiyear mean ozone deposition velocities ranges from a factor of 1.2 to 1.9 annually across sites and tends to be highest during winter compared with summer. No model is within 50 % of observed multiyear averages across all sites and seasons, but some models perform well for some sites and seasons. For the first time, we demonstrate how contributions from depositional pathways vary across models. Models can disagree with respect to relative contributions from the pathways, even when they predict similar deposition velocities, or agree with respect to the relative contributions but predict different deposition velocities. Both stomatal and nonstomatal uptake contribute to the large model spread across sites. Our findings are the beginning of results from AQMEII4 Activity 2, which brings scientists who model air quality and dry deposition together with scientists who measure ozone fluxes to evaluate and improve dry deposition schemes in the chemical transport models used for research, planning, and regulatory purposes.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2018

Development and evaluation of a variably saturated flow model in the global E3SM Land Model (ELM) version 1.0

Abstract. Improving global-scale model representations of near-surface soil moisture and groundwater hydrology is important for accurately simulating terrestrial processes and predicting climate change effects on water resources. Most existing land surface models, including the default E3SM Land Model (ELMv0), which we modify here, routinely employ different formulations for water transport in the vadose and phreatic zones. Clark et al. (2015) identified a variably saturated Richards equation flow model as an important capability for improving simulation of coupled soil moisture and shallow groundwater dynamics. In this work, we developed the Variably Saturated Flow Model (VSFM) in ELMv1 to unify the treatment of soil hydrologic processes in the unsaturated and saturated zones. VSFM was tested on three benchmark problems and results were evaluated against observations and an existing benchmark model (PFLOTRAN). The ELMv1-VSFM's subsurface drainage parameter, fd, was calibrated to match an observationally constrained and spatially explicit global water table depth (WTD) product. Optimal spatially explicit fd values were obtained for 79 % of global 1.9∘ × 2.5∘ grid cells, while the remaining 21 % of global grid cells had predicted WTD deeper than the observationally constrained estimate. Comparison with predictions using the default fd value demonstrated that calibration significantly improved predictions, primarily by allowing much deeper WTDs. Model evaluation using the International Land Model Benchmarking package (ILAMB) showed that improvements in WTD predictions did not degrade model skill for any other metrics. We evaluated the computational performance of the VSFM model and found that the model is about 30 % more expensive than the default ELMv0 with an optimal processor layout. The modular software design of VSFM not only provides flexibility to configure the model for a range of problem setups but also allows for building the model independently of the ELM code, thus enabling straightforward testing of the model's physics against other models.

58 GEOSCIENCES↗
DOE OSTI2014

A Grid Intensity Map-Based Source Model for Monte Carlo Modeling of IMRT Field Irradiation - Paper 5

An accurate source model is important for TPS (Treatment Planning System) dose calculation and verification, especially for IMRT (Intensity Modulated Radiotherapy) irregular and inhomogeneous fields. Monte Carlo simulation is the most accurate way to calculate dose distributions in the heterogeneous media like human bodies. A full radiotherapy modeling generally includes Linac modeling and phantom dose calculation. Full Linac modeling is very time-consuming and requires highly detailed knowledge of the accelerator composition and structure, however, which is very difficult to obtain for commercial interests. Often all relevant parameters are not known with sufficient accuracy, and thus a time-consuming tuning of e.g. the electron beam spot size and energy must be performed. A multiple source model (MSM) regards particles coming from different parts of an accelerator as if they are coming from different virtual sources. MSM uses a set of virtual sources representing the treatment beam (e.g. primary photons, head scatter, electron contamination) by a set of analytic functions or histograms with parameters derived from dosimetric measurements or a full MC simulation. Tillikainen et al built a three sub-source model by matching with measurement data using an automatic process to optimize the free model parameters for a Varian 2100 C/D accelerator. Lin et al have built a convenient five-photon-sub-source model for Varian 2300C 6 MV-X beam based on Monte Carlo simulated Linac for ARTS (Accurate Radiotherapy System). The particle generation of MSM is very fast compared to full Linac simulation, and its sampling efficiency is not limited by the size of the phase space file (PSF). However, generally MSM is generated based on regular field PSF and needs an irregular component to form the beam shape meanwhile apt to bringing error Linac modeling and MSM producing from PSF analysis actually both are multi-freedom optimization process by adjusting several parameters (e.g. electron energy and angular divergence). Linac modeling adjusts its parameters from the beginning of electron hitting target through all components to fit the simulation to the measurement. MSM tunes its PSF-derived parameters by optimizing to minimize the deviations between the simulation and the measurement. Since the full Linac modeling and the MSM model both need to fine tune their parameters to match the simulation to the measurement, and sometimes maybe offsets the real accelerator for its multi-parameter optimization process. So, why not fine tune directly all source model parameters just behind all Linac components to fit the simulation to the measurement? A grid intensity-based surface source model was suggested here, which assumed the particle emitting from the bottom surface of Linac last beam trimmer MLC (Multi Leaf Collimator). The particle emitting position is sampled on the grid intensity map optimized by TPS, and the particle weight is adjusted by its original grid intensity. This source model not only takes advantage of the Monte Carlo method in the heterogeneous media, but also avoids effectively the transportation speed shortcoming of Monte Carlo simulation through Linac components. (authors)

61 RADIATION PROTECTION AND DOSIMETRY↗
DOE OSTI2013

Hurricanes in an Aquaplanet World: Implications of the Impacts of External Forcing and Model Horizontal Resolution

High-resolution climate models have been shown to improve the statistics of tropical storms and hurricanes compared to low-resolution models. The impact of increasing horizontal resolution in the tropical storm simulation is investigated exclusively using a series of Atmospheric Global Climate Model (AGCM) runs with idealized aquaplanet steady-state boundary conditions and a fixed operational storm-tracking algorithm. The results show that increasing horizontal resolution helps to detect more hurricanes, simulate stronger extreme rainfall, and emulate better storm structures in the models. However, increasing model resolution does not necessarily produce stronger hurricanes in terms of maximum wind speed, minimum sea level pressure, and mean precipitation, as the increased number of storms simulated by high-resolution models is mainly associated with weaker storms. The spatial scale at which the analyses are conducted appears to have more important control on these meteorological statistics compared to horizontal resolution of the model grid. When the simulations are analyzed on common low-resolution grids, the statistics of the hurricanes, particularly the hurricane counts, show reduced sensitivity to the horizontal grid resolution and signs of scale invariant.

aquaplanet↗
DOE OSTI2016

Simulation of Subsurface Multiphase Contaminant Extraction Using a Bioslurping Well Model

Subsurface simulation of multiphase extraction from wells is notoriously difficult. Explicit representation of well geometry requires small grid resolution, potentially leading to large computational demands. To reduce the problem dimensionality, multiphase extraction is mostly modeled using vertically-averaged approaches. In this paper, a multiphase well model approach is presented as an alternative to simplify the application. The well model, a multiphase extension of the classic Peaceman model, has been implemented in the STOMP simulator. The numerical solution approach accounts for local conditions and gradients in the exchange of fluids between the well and the aquifer. Advantages of this well model implementation include the option to simulate the effects of well characteristics and operation. Simulations were conducted investigating the effects of extraction location, applied vacuum pressure, and a number of hydraulic properties. The obtained results were all consistent and logical. A major outcome of the test simulations is that, in contrast with common recommendations to extract from either the gas-NAPL or the NAPL-aqueous phase interface, the optimum extraction location should be in between these two levels. Further, the new model implementation was also used to simulate extraction at a field site in Brazil. The simulation shows a good match with the field data, suggesting that the new STOMP well module may correctly represent oil removal. The field simulations depend on the quality of the site conceptual model, including the porous media and contaminant properties and the boundary and extraction conditions adopted. The new module may potentially be used to design field applications and analyze extraction data.

42 ENGINEERING↗
DOE OSTI2016

Aggregate modeling of fast-acting demand response and control under real-time pricing

This paper develops and assesses the performance of a short-term demand response (DR) model for utility load control with applications to resource planning and control design. Long term response models tend to underestimate short-term demand response when induced by prices. This has two important consequences. First, planning studies tend to undervalue DR and often overlook its benefits in utility demand management program development. Second, when DR is not overlooked, the open-loop DR control gain estimate may be too low. This can result in overuse of load resources, control instability and excessive price volatility. Our objective is therefore to develop a more accurate and better performing short-term demand response model. We construct the model from first principles about the nature of thermostatic load control and show that the resulting formulation corresponds exactly to the Random Utility Model employed in economics to study consumer choice. The model is tested against empirical data collected from field demonstration projects and is shown to perform better than alternative models commonly used to forecast demand in normal operating conditions. The results suggest that (1) existing utility tariffs appear to be inadequate to incentivize demand response, particularly in the presence of high renewables, and (2) existing load control systems run the risk of becoming unstable if utilities close the loop on real-time prices.

Aggregate Modeling↗
DOE OSTI2022

Tritium Transport Modeling at the Pore Scale in Ceramic Breeder Materials Using TMAP8

Fusion reactors depend on the blanket material to breed and release tritium at the same rate or faster than it is consumed by the fusion reaction. Cellular ceramic breeders (CCBs) are dense materials that can maintain a high tritium breeding ratio while promoting tritium release because of highly connected pores. Assessing the tritium breeding capabilities of these materials requires a combination of extensive experimental and modeling efforts. In this work, we develop and calibrate a multiphysics model of tritium transport. This novel model accounts for ceramic and pore diffusion, trapping and detrapping, and several surface reactions at the pore surface. We perform a sensitivity analysis and calibrate the model by comparing its predictions against experimental measurements of deuterium absorption. The calibrated model is then used to model tritium absorption in samples with different pore microstructures to investigate the effect of pore interconnectivity on tritium absorption. The model is part of the development of the multiscale, multiphysics framework for tritium transport [i.e., the Tritium Migration Analysis Program (TMAP8)], which is itself built on top of the finite-element multiphysics framework multiphysics object-oriented simulation environment (MOOSE). This study demonstrates some of TMAP8’s capabilities and is the first step toward assessing the tritium breeding capabilities of ceramic breeder material designs.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗
DOE OSTI2022

Delivery of Dynamic Thermal Energy Storage Models and Advanced Reactor Concept Models to the HYBRID Repository

This publication details newly created energy storage and reactor models developed within the HYBRID modeling repository as part of the Department of Energy Office of Nuclear Energy (DOE-NE) Integrated Energy Systems (IES) program, led by Idaho National Laboratory (INL). Model development to-date includes creation of dynamic systems-level models of a pebble bed high temperature gas reactor (HTGR), sodium fast reactor (SFR), compressed air energy storage (CAES), liquid air energy storage (LAES) and Modelica standard library based two-tank sensible heat storage (SHS) in the IES-based HYBRID repository. Models are developed using the latest publicly available data and incorporate the possibility of control strategy inclusion for use with the existing IES modeling, analysis, and optimization toolset. Simulations showcase the abilities of each technology to flexibly operate in ways consistent with IES operation expectations. When these models are available, they can be utilized within different integrated energy park concepts to understand optimal system operation, control, and dispatching. Moreover, given the generic nature of the models, industrial partner technologies can be quickly added to the repository using the existing models as a basis. Additional dynamic models for thermal energy storage concepts can be developed and added to the HYBRID repository as needed. Also detailed in this report are future development goals for the HYBRID repository including adding suites of steady-state models, economic costing information, and reduced-order models. By adding these models in addition to the physical transient models currently existing within HYBRID, HYBRID will be a fully integrable tool for FORCE users.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗
DOE OSTI2025

Understanding Model Inadequacy in TRISO Nuclear Fuel Fission Products Release Models: Empirical and Mechanistic Approaches

The increasing use of tristructural isotropic (TRISO) particle fuel in both advanced and existing reactors necessitates a thorough evaluation of uncertainties and shortcomings in TRISO fission product release models. These inadequacies arise from the simplifications made in computational models compared to experimental data. Utilizing the BISON fuel performance code and experimental data from the Advanced Gas Reactor (AGR) program provides a unique chance to rigorously assess these inadequacies within a Bayesian uncertainty quantification (UQ) framework. This study contrasts the standard Bayesian framework with the Kennedy-O'Hagan (KOH) framework, which explicitly accounts for modeling inadequacies, in the context of UQ for TRISO silver release models. It examines both the traditional Arrhenius equation and a more advanced lower-length-scale (LLS)-informed model that incorporates microstructure information. The inverse UQ process applied to AGR-2 and AGR-3/4 datasets identified modeling inadequacy as the primary source of uncertainty, with experimental noise also being significant, while model parameter uncertainty was minimal. Both the Arrhenius and LLS-informed models showed similar levels of modeling inadequacy. For forward predictive UQ using the AGR-1 dataset, the KOH framework enhanced the accuracy and quality of quantified uncertainties by approximately 30% and 40%, respectively, compared to the standard Bayesian framework. This improvement was observed for both the Arrhenius and LLS-informed models. At the engineering scale, both models performed similarly, but the LLS-informed model outperformed the Arrhenius equation at the mesoscale. These findings underscore the importance of explicitly considering modeling inadequacy in the UQ process and highlight the need for ongoing refinement of physics-based models to address these shortcomings.

11 - NUCLEAR FUEL CYCLE AND FUEL MATERIALS↗
DOE OSTI2020

A novel improved model for building energy consumption prediction based on model integration

Building energy consumption prediction plays an irreplaceable role in energy planning, management, and conservation. Constantly improving the performance of prediction models is the key to ensuring the efficient operation of energy systems. Moreover, accuracy is no longer the only factor in revealing model performance, it is more important to evaluate the model from multiple perspectives, considering the characteristics of engineering applications. Based on the idea of model integration, this paper proposes a novel improved integration model (stacking model) that can be used to forecast building energy consumption. The stacking model combines advantages of various base prediction algorithms and forms them into “meta-features” to ensure that the final model can observe datasets from different spatial and structural angles. Two cases are used to demonstrate practical engineering applications of the stacking model. A comparative analysis is performed to evaluate the prediction performance of the stacking model in contrast with existing well-known prediction models including Random Forest, Gradient Boosted Decision Tree, Extreme Gradient Boosting, Support Vector Machine, and K-Nearest Neighbor. The results indicate that the stacking method achieves better performance than other models, regarding accuracy (improvement of 9.5%–31.6% for Case A and 16.2%–49.4% for Case B), generalization (improvement of 6.7%–29.5% for Case A and 7.1%-34.6% for Case B), and robustness (improvement of 1.5%–34.1% for Case A and 1.8%–19.3% for Case B). The proposed model enriches the diversity of algorithm libraries of empirical models.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗