An official website of the United States government
Accurate and efficient power demand forecasting in urban settings is essential for making decisions related to planning, managing and operations in electricity supply. This task, however, is complicated due to many sources of uncertainty such as due to the variation in weather conditions and household or other needs that influence the inherent stochastic and nonlinear characteristics of electricity demand. Due to the modeling flexibility and computational efficiency afforded by it, a Gaussian process model is employed in this study for energy demand prediction as a function of temperature. A Gaussian process model is a Bayesian non-parametric regression method that models data using a joint Gaussian distribution with mean and covariance functions. The selected mean function is modeled as a polynomial function of temperature, whereas the covariance function is appropriately selected to reflect the actual data patterns. We employ real data sets of daily temperature and electricity demand from Austin, Texas, USA to assess the effectiveness of the proposed method for load forecasting. The accuracy of the model prediction is evaluated using metrics such as mean absolute error (MAE), root mean squared error (RMSE), mean absolute percentage error (MAPE) and 95% confidence interval (95% CI). A numerical study undertaken demonstrates that the proposed method has promise for energy demand prediction.
more »
« less
This content will become publicly available on September 1, 2026
Energy Demand Forecasting Using Temporal Variational Residual Network
The growing demand for efficient energy management has become essential for achieving sustainable development across social, economic, and environmental sectors. Accurate energy demand forecasting plays a pivotal role in energy management. However, energy demand data present unique challenges due to their complex characteristics, such as multi-seasonality, hidden structures, long-range dependency, irregularities, volatilities, and nonlinear patterns, making energy demand forecasting challenging. We propose a hybrid dimension reduction deep learning algorithm, Temporal Variational Residual Network (TVRN), to address these challenges and enhance forecasting performance. This model integrates variational autoencoders (VAEs), Residual Neural Networks (ResNets), and Bidirectional Long Short-Term Memory (BiLSTM) networks. TVRN employs VAEs for dimensionality reduction and noise filtering, ResNets to capture local, mid-level, and global features while tackling gradient vanishing issues in deeper networks, and BiLSTM to leverage past and future contexts for dynamic and accurate predictions. The performance of the proposed model is evaluated using energy consumption data, showing a significant improvement over traditional deep learning and hybrid models. For hourly forecasting, TVRN reduces root mean square error and mean absolute error, ranging from 19% to 86% compared to other models. Similarly, for daily energy consumption forecasting, this method outperforms existing models with an improvement in root mean square error and mean absolute error ranging from 30% to 95%. The proposed model significantly enhances the accuracy of energy demand forecasting by effectively addressing the complexities of multi-seasonality, hidden structures, and nonlinearity.
more »
« less
- Award ID(s):
- 2100729
- PAR ID:
- 10630406
- Publisher / Repository:
- MDPI
- Date Published:
- Journal Name:
- Forecasting
- Volume:
- 7
- Issue:
- 3
- ISSN:
- 2571-9394
- Page Range / eLocation ID:
- 42
- Subject(s) / Keyword(s):
- bidirectional long short-term memory energy demand forecasting residual neural network ResNet variational autoencoder
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
This paper presents a practical framework that integrates wind speed forecasting with proton exchange membrane (PEM) electrolyzer design to optimize hydrogen production. Due to wind speed fluctuations, excess electrical energy is sometimes produced and left unused. A wind-to-hydrogen system addresses this challenge by converting surplus energy into storable hydrogen using a PEM electrolyzer. The proposed approach employs a multivariate supervisory control and data acquisition (SCADA) dataset and applies a convolutional neural network with bi-directional long short-term memory (CNN-Bi-LSTM) for multivariate wind speed temporal forecasting, enabling more efficient PEM operations. Compared to standard deep learning models, the CNN-Bi-LSTM architecture reduces the root mean square error by 52.5% and the mean absolute error by 56%, thereby enhancing hydrogen production forecasting. Simulation results show that a membrane thickness of 0.0252 mm and an operating temperature of 70% achieve the highest overall PEM efficiency of 63.611%. This study demonstrates the integration of deep learning-based forecasting with electrochemical modeling and SCADA datasets as a novel approach for wind-to-hydrogen production systems.more » « less
-
Accurately predicting the performance of radiant slab systems can be challenging due to the large thermal capacitance of the radiant slab and room temperature stratification. Current methods for predicting heating and cooling energy consumption of hydronic radiant slabs include detailed first-principles (e.g., finite difference) and reduced-order (e.g., thermal Resistor-Capacitor (RC) network) models. Creating and calibrating detailed first-principles models, as well as detailed RC network models for predicting the performance of radiant slabs require substantial effort. To develop improved control, monitoring, and diagnostic methods, there is a need for simpler models that can be readily trained using in-situ measurements. In this study, we explored a novel hybrid modeling method that integrates a simple RC network model with an evolving learning-based algorithm termed the Growing Gaussian Mixture Regression (GGMR) modeling approach to predict the heating and cooling rates of a radiant slab system for a Living Laboratory office space. The RC network model predicts heating or cooling load of the radiant slab system that is provided as an input to the GGMR model. Three modeling approaches were considered in this study: 1) an RC network model; 2) a GGMR model, and 3) the proposed hybrid modeling between RC and GGMR. The three modeling methods have been compared for predicting the energy use of a radiant slab system of a Living Laboratory office space using measurement data from January 15th to March 7th, 2022. The first two weeks of data were used for training, while the remaining data was used for testing of all three modeling methods. The hybrid approach had a Normalized Root Mean Square Error (NRMSE) of 15.46 percent (8.62 percent less than the RC-Model 3 alone and 19.36 percent less than the GGMR alone), a Coefficient of Variation of RMSE (CVRMSE) of 6.43 percent (3.59 percent less than the RC-Model 3 and 8.05 percent less than the GGMR), a Mean Absolute Error (MAE) of 3.61 kW (2.13 kW and 3.87 kW less than the RC-Model 3 and GGMR, respectively), and a Mean Absolute Percentage Error (MAPE) of 5.28 percent (3.85 percent and 3.92 percent lower than the RC-Model 3 and GGMR, respectively).more » « less
-
Electric load forecasting refers to forecasting the electricity demand at aggregated levels. Utilities use the predictions of this technique to keep a balance between electricity generation and consumption at each time and make accurate decision for power system planning, operations, and maintenance, etc. Based on prediction time horizon, electric load forecasting is classified to very short-term, short-term, medium-term, and long-term. In this paper, a multiple output Gaussian processes with multiple kernel learning is proposed to predict short-term electric load forecasting (predicting 24 load values for the next day) based on load, temperature, and dew point values of previous days. Mean absolute percentage error (MAPE) is used as a measure of prediction accuracy. By comparing MAPE values of the proposed method with the persistence method, it can been seen that the proposed method improves the persistence method MAPE up to 4%.more » « less
-
We examined the effect of estimation methods, maximum likelihood (ML), unweighted least squares (ULS), and diagonally weighted least squares (DWLS), on three population SEM (structural equation modeling) fit indices: the root mean square error of approximation (RMSEA), the comparative fit index (CFI), and the standardized root mean square residual (SRMR). We considered different types and levels of misspecification in factor analysis models: misspecified dimensionality, omitting cross-loadings, and ignoring residual correlations. Estimation methods had substantial impacts on the RMSEA and CFI so that different cutoff values need to be employed for different estimators. In contrast, SRMR is robust to the method used to estimate the model parameters. The same criterion can be applied at the population level when using the SRMR to evaluate model fit, regardless of the choice of estimation method.more » « less
