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
Electric Load Forecasting Using Multiple Output Gaussian Processes and Multiple Kernel Learning
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
- Award ID(s):
- 1757207
- PAR ID:
- 10462093
- Date Published:
- Journal Name:
- 2023 IEEE Symposium on Industrial Electronics & Applications (ISIEA)
- Page Range / eLocation ID:
- 1 to 6
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Summary: This repository contains the datasets used in the 2025 PG&E Energy Analytics Challenge on Electricity Load Forecasting, co-organized by the IISE Energy Systems Division and the INFORMS Quality, Statistics, and Reliability Section, and graciously sponsored by the Pacific Gas & Electric Company (PG&E). The repository contains two files: Train.xlsx: Contains three years of hourly electric loads from San Diego, California (Years 2020-2022), as well as exogenous weather information at five neighboring sites within the San Diego area. Test.xlsx: Contains one year of hourly electric loads from San Diego, California (Year 2023), as as well as exogenous weather information at five neighboring sites within the San Diego area. Background: This competition aimed to predict electricity loads for a specific location within the CAISO system. Accurate load forecasting is critical for managing electricity distribution within California’s diverse and dynamic energy market. Load patterns can vary significantly due to factors such as weather conditions, local supply and demand, and the mix of nearby energy generation sources. During the competition, the specific location and the actual years were not disclosed to the participants. Participants were then asked to generate a year’s worth of load forecasts using historical load values and exogeneous weather information. Predictor data were not allowed to be taken from future time periods: When predicting the load values at a particular day, the model was allowed to only use predictor variable information from that time period or before. For example, if a team is predicting the load for Day 5 Hour 3 in Year 3, the model can only take in predictor values from Day 5 Hour 3 in Year 3, or before. Furthermore, during the competition, the load information for the test set (highlighted in yellow in the test data file) was reserved from all participants, who were asked to submit their predictions for the full year. This is the second offering of the PG&E Energy Analytics challenge, complementing the first offering in 2024 which focused on electricity price forecasting [Results of the 2024 challenge: Aziz Ezzat, A., Mansouri, M., Yildirim, M., & Fang, X. (2025). IISE PG&E Energy Analytics Challenge 2024: Forecasting day-ahead electricity prices. IISE Transactions, 1–13. https://doi.org/10.1080/24725854.2024.2447049].more » « less
-
Abstract: Load forecasting plays a very crucial role in many aspects of electric power systems including the economic and social benefits. Previously, there have been many studies involving load forecasting using time series approach, including weather-load relationships. In one such approach to predict load, this paper investigates through different structures that aim to relate various daily parameters. These parameters include temperature, humidity and solar radiation that comprises the weather data. Along with natural phenomenon as weather, physical aspects such as traffic flow are also considered. Based on the relationship, a prediction algorithm is applied to check if prediction error decreases when such external factors are considered. Electricity consumption data is collected from the City of Tallahassee utilities. Traffic count is provided by the Florida Department of Transportation. Moreover, the weather data is obtained from Tallahassee regional Airport weather station. This paper aims to study and establish a cause and effect relationship between the mentioned variables using different causality models and to forecast load based on the external variables. Based on the relationship, a prediction algorithm is applied to check if prediction error decreases when such external factors are considered.more » « less
-
Accurate long-term electricity load forecasting is critical for energy planning, infrastructure development, and risk management, especially under increasing uncertainty from climate and economic shifts. This study proposes a multi-resolution probabilistic load forecasting framework that leverages temporal hierarchies to generate coherent forecasts at hourly, daily, monthly, and yearly levels. The model integrates climate and economic indicators and employs tailored forecasting techniques at each resolution, including XGBoost and ARIMAX. Initially incoherent forecasts across time scales are reconciled using advanced methods such as Ordinary Least Squares (OLS), Weighted Least Squares with Series Variance Scaling (WLS_V), and Structural Scaling (WLS_S) to ensure consistency. Using historical data from Alberta, Canada, the proposed approach improves the accuracy of deterministic forecasts and enhances the reliability of probabilistic forecasts, particularly when using the OLS reconciliation method. These results highlight the value of temporal hierarchy structures in producing high-resolution long-horizon load forecasts, providing actionable insights for utilities and policymakers involved in long-term energy planning and system optimization.more » « less
-
The ever-increasing demand for energy is resulting in considerable carbon emissions from the electricity grid. In recent years, there has been growing attention on demand-side optimizations to reduce carbon emissions from electricity usage. A vital component of these optimizations is short-term forecasting of the carbon intensity of the grid-supplied electricity. Many recent forecasting techniques focus on day-ahead forecasts, but obtaining such forecasts for longer periods, such as multiple days, while useful, has not gotten much attention. In this paper, we present CarbonCast, a machine-learning-based hierarchical approach that provides multi-day forecasts of the grid's carbon intensity. CarbonCast uses neural networks to first generate production forecasts for all the electricity-generating sources. It then uses a hybrid CNN-LSTM approach to combine these first-tier forecasts with historical carbon intensity data and weather forecasts to generate a carbon intensity forecast for up to four days. Our results show that such a hierarchical design improves the robustness of the predictions against the uncertainty associated with a longer multi-day forecasting period. We analyze which factors most influence the carbon intensity forecasts of any region with a specific mixture of electricity-generating sources and also show that accurate source production forecasts are vital in obtaining precise carbon intensity forecasts. CarbonCast's 4-day forecasts have a MAPE of 3.42--19.95% across 13 geographically distributed regions while outperforming state-of-the-art methods. Importantly, CarbonCast is the first open-sourced tool for multi-day carbon intensity forecasts where the code and data are freely available to the research community.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/isiea58478.2023.10212291
