More Like this

1. Electric Load Forecasting Using Multiple Output Gaussian Processes and Multiple Kernel Learning

   https://doi.org/10.1109/isiea58478.2023.10212291  

   Ghasempour, Alireza; Martínez-Ramón, Manel (July 2023, 2023 IEEE Symposium on Industrial Electronics & Applications (ISIEA))

   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
2. Energy Demand Forecasting Using Temporal Variational Residual Network

   https://doi.org/10.3390/forecast7030042  

   Ashebir, Simachew; Kim, Seongtae (September 2025, Forecasting)

   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
3. Improved Shrinkage Prediction under a Spiked Covariance Structure

   Trambak Banerjee, Gourab Mukherjee (July 2021, Journal of machine learning research)

   We develop a novel shrinkage rule for prediction in a high-dimensional non-exchangeable hierarchical Gaussian model with an unknown spiked covariance structure. We propose a family of priors for the mean parameter, governed by a power hyper-parameter, which encompasses independent to highly dependent scenarios. Corresponding to popular loss functions such as quadratic, generalized absolute, and Linex losses, these prior models induce a wide class of shrinkage predictors that involve quadratic forms of smooth functions of the unknown covariance. By using uniformly consistent estimators of these quadratic forms, we propose an efficient procedure for evaluating these predictors which outperforms factor model based direct plug-in approaches. We further improve our predictors by considering possible reduction in their variability through a novel coordinate-wise shrinkage policy that only uses covariance level information and can be adaptively tuned using the sample eigen structure. Finally, we extend our disaggregate model based methodology to prediction in aggregate models. We propose an easy-to-implement functional substitution method for predicting linearly aggregated targets and establish asymptotic optimality of our proposed procedure. We present simulation experiments as well as real data examples illustrating the efficacy of the proposed method. 

   more » « less
4. Few-shot Time-Series Forecasting with Application for Vehicular Traffic Flow

   https://doi.org/10.1109/IRI54793.2022.00018  

   Tran, Victor; Panangadan, Anand (August 2022, Information Reuse and Integration for Data Science (IRI), 2022 IEEE 23rd International Conference on)

   Few-shot machine learning attempts to predict outputs given only a very small number of training examples. The key idea behind most few-shot learning approaches is to pre-train the model with a large number of instances from a different but related class of data, classes for which a large number of instances are available for training. Few-shot learning has been most successfully demonstrated for classification problems using Siamese deep learning neural networks. Few-shot learning is less extensively applied to time-series forecasting. Few-shot forecasting is the task of predicting future values of a time-series even when only a small set of historic time-series is available. Few-shot forecasting has applications in domains where a long history of data is not available. This work describes deep neural network architectures for few-shot forecasting. All the architectures use a Siamese twin network approach to learn a difference function between pairs of time-series, rather than directly forecasting based on historical data as seen in traditional forecasting models. The networks are built using Long short-term memory units (LSTM). During forecasting, a model is able to forecast time-series types that were never seen in the training data by using the few available instances of the new time-series type as reference inputs. The proposed architectures are evaluated on Vehicular traffic data collected in California from the Caltrans Performance Measurement System (PeMS). The models were trained with traffic flow data collected at specific locations and then are evaluated by predicting traffic at different locations at different time horizons (0 to 12 hours). The Mean Absolute Error (MAE) was used as the evaluation metric and also as the loss function for training. The proposed architectures show lower prediction error than a baseline nearest neighbor forecast model. The prediction error increases at longer time horizons. 

   more » « less
5. Estimating atmospheric motion winds from satellite image data using space‐time drift models

   https://doi.org/10.1002/env.2818  

   Sahoo, Indranil; Guinness, Joseph; Reich, Brian J. (December 2023, Environmetrics)

   Abstract Geostationary weather satellites collect high‐resolution data comprising a series of images. The Derived Motion Winds (DMW) Algorithm is commonly used to process these data and estimate atmospheric winds by tracking features in the images. However, the wind estimates from the DMW Algorithm are often missing and do not come with uncertainty measures. Also, the DMW Algorithm estimates can only be half‐integers, since the algorithm requires the original and shifted data to be at the same locations, in order to calculate the displacement vector between them. This motivates us to statistically model wind motions as a spatial process drifting in time. Using a covariance function that depends on spatial and temporal lags and a drift parameter to capture the wind speed and wind direction, we estimate the parameters by local maximum likelihood. Our method allows us to compute standard errors of the local estimates, enabling spatial smoothing of the estimates using a Gaussian kernel weighted by the inverses of the estimated variances. We conduct extensive simulation studies to determine the situations where our method performs well. The proposed method is applied to the GOES‐15 brightness temperature data over Colorado and reduces prediction error of brightness temperature compared to the DMW Algorithm. 

   more » « less