skip to main content


The NSF Public Access Repository (NSF-PAR) system and access will be unavailable from 11:00 PM ET on Thursday, May 23 until 2:00 AM ET on Friday, May 24 due to maintenance. We apologize for the inconvenience.

Title: City-Scale Electricity Demand Forecasting using a Gaussian Process Model
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
Award ID(s):
Author(s) / Creator(s):
Date Published:
Journal Name:
5th International Conference on Green Technology and Sustainable Development (GTSD 2020)
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. 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. 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
  3. Abstract

    Estimating uncertainty in flood model predictions is important for many applications, including risk assessment and flood forecasting. We focus on uncertainty in physics‐based urban flooding models. We consider the effects of the model's complexity and uncertainty in key input parameters. The effect of rainfall intensity on the uncertainty in water depth predictions is also studied. As a test study, we choose the Interconnected Channel and Pond Routing (ICPR) model of a part of the city of Minneapolis. The uncertainty in the ICPR model's predictions of the floodwater depth is quantified in terms of the ensemble variance using the multilevel Monte Carlo (MC) simulation method. Our results show that uncertainties in the studied domain are highly localized. Model simplifications, such as disregarding the groundwater flow, lead to overly confident predictions, that is, predictions that are both less accurate and uncertain than those of the more complex model. We find that for the same number of uncertain parameters, increasing the model resolution reduces uncertainty in the model predictions (and increases the MC method's computational cost). We employ the multilevel MC method to reduce the cost of estimating uncertainty in a high‐resolution ICPR model. Finally, we use the ensemble estimates of the mean and covariance of the flood depth for real‐time flood depth forecasting using the physics‐informed Gaussian process regression method. We show that even with few measurements, the proposed framework results in a more accurate forecast than that provided by the mean prediction of the ICPR model.

    more » « less
  4. 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
  5. null (Ed.)
    Predicting workload behavior during execution is essential for dynamic resource optimization of processor systems. Early studies used simple prediction algorithms such as a history tables. More recently, researchers have applied advanced machine learning regression techniques. Workload prediction can be cast as a time series forecasting problem. Time series forecasting is an active research area with recent advances that have not been studied in the context of workload prediction. In this paper, we first perform a comparative study of representative time series forecasting techniques to predict the dynamic workload of applications running on a CPU. We adapt state-of-the-art matrix profile and dynamic linear models (DLMs) not previously applied to workload prediction and compare them against traditional SVM and LSTM models that have been popular for handling non-stationary data. We find that all time series forecasting models struggle to predict abrupt workload changes. These changes occur because workloads go through phases, where prior work has studied workload phase detection, classification and prediction. We propose a novel approach that combines time series forecasting with phase prediction. We process each phase as a separate time series and train one forecasting model per phase. At runtime, forecasts from phase-specific models are selected and combined based on the predicted phase behavior. We apply our approach to forecasting of SPEC workloads running on a state-of-the-art Intel machine. Our results show that an LSTM-based phase-aware predictor can forecast workload CPI with less than 8% mean absolute error while reducing CPI error by more than 12% on average compared to a non-phase-aware approach. 
    more » « less