Search NASA⌕ Search

SEARCH · Search NASA

Results for “Load forecasting”

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 55 records · Page 3

BuildingsBench: A Benchmark for Universal Building Load Forecasting [SWR-23-51]

The residential and commercial building stock in the United States is responsible for a significant percentage of energy consumption and greenhouse gas emissions. Electrification of end-uses, as well as decarbonizing the electrical grid through renewable energy sources such as solar and wind, constitutes the pathway to zero-emission buildings. Forecasting day-ahead building energy consumption is an integral part of this solution. Currently, specialized forecasting models are hand-made for each individual building, which is time-consuming, expensive, and leads to duplicated efforts. BuildingsBench is a Python software framework for training and comparing generalized machine learning models for universal building load forecasting. This challenge tasks a single foundational model to generalize its forecasts for a wide variety of buildings, across geographic regions, building types, weather patterns, and more. This software provide code for pre-training such models and subsequently evaluating their performance on a suite of hundreds of diverse real and synthetic buildings. BuildingsBench is a platform for: - Large-scale pretraining with the synthetic Buildings-900K dataset for short-term load forecasting (STLF). Buildings-900K is statistically representative of the entire U.S. building stock and is extracted from the NREL End-Use Load Profiles database. - Benchmarking on two tasks evaluating generalization: zero-shot STLF and transfer learning for STLF. We provide an index-based PyTorch Dataset for large-scale pretraining, easy data loading for multiple real building energy consumption datasets as PyTorch Tensors or Pandas DataFrames, simple (persistence) to advanced (transformer) baselines, metrics management, and more.

Emami, Patrick↗

Short-term electricity load forecasting: Application-driven evaluation of machine learning models across spatial and temporal scales

As we transition towards a decarbonized economy, the integration of variable renewable energy resources and new demands (e.g., electric vehicles, heat pumps) into the electricity grid places unprecedented pressure on grid operators to effectively anticipate and manage peak load. In this context, machine learning algorithms are proving to be indispensable for accurate short-term load forecasting, a crucial task to address these challenges. This study benchmarks 6 machine learning algorithms, including three neural networks and three tree-based algorithms, across various levels of spatial aggregation and time horizons (1, 4, 8, 24, and 48 h). The central contribution of this work is the comparison and analysis of load forecasting models not only based on statistical metrics, but also based on a novel error metric, which evaluates the cost implications of forecast errors for power system stakeholders. Results show that tree-based models outperform neural networks, based on statistical metrics, and yield less skewed error distributions for most spatial scales. However, through the lens of the novel error metric, neural networks are the more competitive choice, especially for forecast horizons that exceed 8 h. The study concludes with actionable recommendations to grid operators and highlights the need for the development of error metrics that link forecasting accuracy to operational costs. To promote transparency and open science, the datasets and Python code are open-sourced via a supplementary repository.

Houben, Nikolaus↗

Robust Deep Gaussian Process-Based Probabilistic Electrical Load Forecasting Against Anomalous Events

The abnormal events, such as the unprecedented COVID-19 pandemic, can significantly change the load behaviors, leading to huge challenges for traditional short-term forecasting methods. This article proposes a robust deep Gaussian processes (DGP)-based probabilistic load forecasting method using a limited number of data. Since the proposed method only requires a limited number of training samples for load forecasting, it allows us to deal with extreme scenarios that cause short-term load behavior changes. In particular, the load forecasting at the beginning of abnormal event is cast as a regression problem with limited training samples and solved by double stochastic variational inference DGP. The mobility data are also utilized to deal with the uncertainties and pattern changes and enhance the flexibility of the forecasting model. The proposed method can quantify the uncertainties of load forecasting outcomes, which would be essential under uncertain inputs. Extensive comparison results with other state-of-the-art point and probabilistic forecasting methods show that our proposed approach can achieve high forecasting accuracies with only a limited number of data while maintaining the excellent performance of capturing the forecasting uncertainties.

anomalous events↗

Comparison of Wind Power and Load Forecasting Error Distributions: Preprint

The introduction of large amounts of variable and uncertain power sources, such as wind power, into the electricity grid presents a number of challenges for system operations. One issue involves the uncertainty associated with scheduling power that wind will supply in future timeframes. However, this is not an entirely new challenge; load is also variable and uncertain, and is strongly influencedby weather patterns. In this work we make a comparison between the day-ahead forecasting errors encountered in wind power forecasting and load forecasting. The study examines the distribution of errors from operational forecasting systems in two different Independent System Operator (ISO) regions for both wind power and load forecasts at the day-ahead timeframe. The day-ahead timescale iscritical in power system operations because it serves the unit commitment function for slow-starting conventional generators.

17 WIND ENERGY↗

BuildingsBench: A Large-Scale Dataset of 900K Buildings and Benchmark for Short-Term Load Forecasting

The BuildingsBench datasets consist of: - Buildings-900K: A large-scale dataset of 900K buildings for pretraining models on the task of short-term load forecasting (STLF). Buildings-900K is statistically representative of the entire U.S. building stock. - 7 real residential and commercial building datasets for benchmarking two downstream tasks evaluating generalization: zero-shot STLF and transfer learning for STLF. Buildings-900K can be used for pretraining models on day-ahead STLF for residential and commercial buildings. The specific gap it fills is the lack of large-scale and diverse time series datasets of sufficient size for studying pretraining and finetuning with scalable machine learning models. Buildings-900K consists of synthetically generated energy consumption time series. It is derived from the NREL End-Use Load Profiles (EULP) dataset (see link to this database in the links further below). However, the EULP was not originally developed for the purpose of STLF. Rather, it was developed to "...help electric utilities, grid operators, manufacturers, government entities, and research organizations make critical decisions about prioritizing research and development, utility resource and distribution system planning, and state and local energy planning and regulation." Similar to the EULP, Buildings-900K is a collection of Parquet files and it follows nearly the same Parquet dataset organization as the EULP. As it only contains a single energy consumption time series per building, it is much smaller (~110 GB). BuildingsBench also provides an evaluation benchmark that is a collection of various open source residential and commercial real building energy consumption datasets. The evaluation datasets, which are provided alongside Buildings-900K below, are collections of CSV files which contain annual energy consumption. The size of the evaluation datasets altogether is less than 1GB, and they are listed out below: 1. ElectricityLoadDiagrams20112014 2. Building Data Genome Project-2 3. Individual household electric power consumption (Sceaux) 4. Borealis 5. SMART 6. IDEAL 7. Low Carbon London A README file providing details about how the data is stored and describing the organization of the datasets can be found within each data lake version under BuildingsBench.

Array↗

Solar, Wind, and Load Forecasting Dataset for MISO, NYISO, and SPP Balancing Areas

The Performance-based Energy Resource Feedback, Optimization, and Risk Management (PERFORM) program is an initiative intended to foster "a fundamental shift in grid management rooted in an understanding of asset risk and system risk" (ARPA-E 2020). Launched by the Advanced Research Projects Agency-Energy (ARPA-E), the program supports efforts to incorporate uncertainty in electric power decision making. In support of PERFORM, the National Renewable Energy Laboratory (NREL) has produced a set of time-coincident forecasts of solar, wind, and load profiles. As part of Phase I of the PERFORM effort, NREL created a dataset that consists of one year of time-coincident load, wind, and solar actuals and probabilistic forecasts based on data from the Electric Reliability Council of Texas (ERCOT) (Bryce et al. 2023). In Phase II, NREL developed similar datasets for three other U.S. Independent System Operators (ISO): the Midcontinent Independent System Operator (MISO), the New York Independent System Operator (NYISO), and the Southwest Power Pool (SPP).

24 POWER TRANSMISSION AND DISTRIBUTION↗

Considerations for Short-Term Load Forecasting of Morocco

There are many factors that determine how demand for electricity may change over time. The analysis described in this report is focused on using auto-regressive models and neural networks to examine load-forecasting techniques for the next 24 hours.

54 ENVIRONMENTAL SCIENCES↗

Joint Seasonal ARMA Approach for Modeling of Load Forecast Errors in Planning Studies

To make informed and robust decisions in the probabilistic power system operation and planning process, it is critical to conduct multiple simulations of the generated combinations of wind and load parameters and their forecast errors to handle the variability and uncertainty of these time series. In order for the simulation results to be trustworthy, the simulated series must preserve the salient statistical characteristics of the real series. In this paper, we analyze day-ahead load forecast error data from multiple balancing authority locations and characterize statistical properties such as mean, standard deviation, autocorrelation, correlation between series, time-of-day bias, and time-of-day autocorrelation. We then construct and validate a seasonal autoregressive moving average (ARMA) model to model these characteristics, and use the model to jointly simulate day-ahead load forecast error series for all BAs.

Power system planning, Operations, Probabilistic m↗

PV Generation and Load Forecasting for Adjuntas PR Community Microgrids

Existing frameworks to forecast time-series photovoltaic (PV) output power and consumer load for microgrid operations and controls assume a near-continuous availability of real-time input features from the field assets such as PV inverters, energy meters, and weather station. These incoming data points are used to periodically retrain models and update forecast snapshots over a moving horizon window, be it one hour-ahead, one-day ahead, or one-week ahead. However, such frameworks are not resilient to disruptions in data availability caused by losses in communications between the field sensors and data loggers. Hence, there is a need for programs that assume no availability of real-time microgrid asset data and still make reliable forecasts that can be used for decision-making. Such programs would be apt to function in extreme weather events such as hurricanes and would use lightweight recursive time-series models to independently forecast solar irradiance and ambient temperature, then compute PV power from those forecasts, as well as independently forecast consumer load. The codebase performs forecasting for the scenario of when the microgrid does not have a reliable access to forecasts or real-time observations of solar irradiance (I) and ambient temperature (AT) and load (Load) to be able to adequately forecast, in real-time, the PV power production or a business' load. In this case, using historical values of PV power and load, a univariate forecasting of generation and consumption are respectively made. The use-case in particular has two sub-scenarios: one, a normal 7-day ahead forecast where the unavailability of real-time data is assumed due to infrastructure issues such as loss of communication or sensor maintenance or service downtimes. Whereas a hurricane-caused unavailability of real-time data requires a second model trained specifically on historical hurricane days to be able to capture the extreme day behavior of generation in particular, and load if applicable. A gradient boosted regression tree comprises an ensemble of additive models that map between the input of historical values (be it irradiance, temperature, or load) and their corresponding output forecasts of a given horizon such that the individual learner predictions are summed up over the total number of such learners in the ensemble to produce an aggregate forecast. A weighting mechanism is applied to the training data in each iteration, where actual and forecast values are compared to penalize incorrect forecasts by increasing the weight and reducing it to reward correct forecasts. The code's benefits are that it: (a) accounts for a contingency where communication loss renders newly measured real-time data unavailable for model tuning and snapshot updates; (b) presents blind forecasting that recursively determines the next time-step value in a horizon using the forecast of the same attribute from a prior step; and (c) employs lightweight models that, once trained, can reliably generalize for different horizons, which make them suitable for enhancing the resilience of field microgrids prone to extreme events that encounter disruptions to data availability.

Sundararajan, Aditya [Oak Ridge National Laborator↗

Roadmap and Benchmarking: Privacy in Federated Load Forecasting

Data-driven techniques for energy demand forecasting continue to emerge with promising impacts on distribution grid planning. However, the development of robust and generalizable machine learning models requires that representative high quality training data are available. Distributed energy resources have begun to embed intelligence, gathering large amounts of data on customer demand, behavior, and household devices that are connected to the grid. Though utilities aggregate meter-level demand data for load shaping, demand response, outage management, reliability planning, and billing applications, there lies an inherent privacy concern in sharing consumption data that may identify individual consumer behavioral patterns. Hence, while sharing the data is crucial, the private sensitive customer data must be safeguarded from being exposed or manipulated. In this study, we propose a roadmap for implementing a based privacy preserving framework to support the advancement of data-driven analytics in data-sensitive distributed energy resources environments. The roadmap incorporates federated learning–a distributed training framework, differential privacy–a statistical framework that provides guarantees to safeguard the leakage of sensitive data, secure multiparty computation and homomorphic encryption– techniques for encrypting model gradients and applying secure aggregation on the server. Moreover, we perform baseline experiments on the federated short-term load forecasting (STLF) task using open-source residential load profile datasets, offering insights into the challenges of integrating differential privacy into federated learning.

Abebe, Waqwoya [Oak Ridge National Laboratory (ORN↗

Air compressor load forecasting using artificial neural network

Air compressor systems are responsible for approximately 10% of the electricity consumed in United States and European Union industry. As many researches have proven the effectiveness of using Artificial Neural Network inair compressor performance prediction, there is still a need to forecast the air compressor electrical load profile. The objective of this study is to predict compressed air systems’ electrical load profile, which is valuable to industry practitioners as well as software providers in developing better practice and tools for load managementand look-ahead scheduling programs. Two artificial neural networks, Two-Layer Feed-Forward Neural Networkand Long Short-Term Memory were used to predict an air compressors electrical load. Compressors with three different control mechanisms are evaluated with a total number of 11,874 observations. Here, the forecasts were validated using out-of-sample datasets with 5-fold cross-validation. Models produced average coefficient ofdetermination values from 0.24 to 0.94, average root-mean-square errors from 0.05 kW - 5.83 kW, and meanabsolute scaled errors from 0.20 to 1.33. The results indicate that both artificial neural networks yield goodresults for compressors using variable speed drive (average R 2 = 0.8 and no naïve forecasting), only the longshort-term memory model gives acceptable results for compressors using on/off control (average R 2 = 0.82 and no naïve forecasting), and no satisfactory results are obtained for load/unload type air compressors (models constituting active forecasting).

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Sequence-to-sequence neural networks for short-term electrical load forecasting in commercial office buildings

The U.S. power grid is transforming to become smarter, cleaner, and more effi- cient. This is leading to the addition of significant distributed variable renew- able generation. Due to the variable nature of renewable generation, the short- and long-term supply-demand imbalances are less predictable, and conventional approaches to mitigating the imbalance will not be efficient or cost-effective. To address this challenge, transactive control technologies have been proposed which balance energy generation and consumption with market activity and in- frastructural limitations. Transactive control requires the ability of individual end-use loads to express flexibility as a function of a transactive signal (e.g., price). Empirical gray- and black-box models have been widely used to express flexibility, and although these approaches are generally easy to construct and simple to use, they do not capture the non-linear behavior that some end-use loads represent . Machine learning approaches have been proposed to address this limitation. Although deep learning approaches for forecasting end-use loads have been explored, certain aspects of the application of deep models to load forecasting are not well understood. These aspects include how much training data is required, and how models should be structured and trained. To that end, this work explores how to approach applying deep recurrent neural networks to short-term electrical load forecasting with a case study of four commercial office buildings. We identify data requirements for training accurate models of whole building electricity use conditioned on outdoor temperature, provide insight into model hyperparameter sensitivity, and demonstrate how readily models can be generalized to unseen buildings.

Skomski, Elliott↗

A Data-Driven Method for Adaptive Reserve Requirement Estimation via Probabilistic Net Load Forecasting

The University of Colorado Boulder Boulder, CO, 80309, USA With the increasing penetration of renewable energy, power systems are subject to more uncertainty. This makes power system reserve scheduling more challenging. Most of the current reserve requirement determination methods calculate reserve requirements based on historical data, which does not consider the real-time or future system uncertainty. In this paper, a data-driven method is developed to determine the non-spinning reserve requirement (NSRR) in the Electric Reliability Council of Texas (ERCOT) system. The method follows the procedure of the current ERCOT method while adaptively determining the NSRR based on probabilistic net load forecasts. Case studies with two years of ERCOT data show that the developed method significantly reduces the NSRR by introducing an adaptive temporal resolution and update rate. Sensitivity analysis with different forecasting and percentile thresholds indicates the flexibility of the developed method.

non-spinning reserve↗

Wind Energy Management System Integration Project Incorporating Wind Generation and Load Forecast Uncertainties into Power Grid Operations

The power system balancing process, which includes the scheduling, real time dispatch (load following) and regulation processes, is traditionally based on deterministic models. Since the conventional generation needs time to be committed and dispatched to a desired megawatt level, the scheduling and load following processes use load and wind power production forecasts to achieve future balance between the conventional generation and energy storage on the one side, and system load, intermittent resources (such as wind and solar generation) and scheduled interchange on the other side. Although in real life the forecasting procedures imply some uncertainty around the load and wind forecasts (caused by forecast errors), only their mean values are actually used in the generation dispatch and commitment procedures. Since the actual load and intermittent generation can deviate from their forecasts, it becomes increasingly unclear (especially, with the increasing penetration of renewable resources) whether the system would be actually able to meet the conventional generation requirements within the look-ahead horizon, what the additional balancing efforts would be needed as we get closer to the real time, and what additional costs would be incurred by those needs. In order to improve the system control performance characteristics, maintain system reliability, and minimize expenses related to the system balancing functions, it becomes necessary to incorporate the predicted uncertainty ranges into the scheduling, load following, and, in some extent, into the regulation processes. It is also important to address the uncertainty problem comprehensively, by including all sources of uncertainty (load, intermittent generation, generators’ forced outages, etc.) into consideration. All aspects of uncertainty such as the imbalance size (which is the same as capacity needed to mitigate the imbalance) and generation ramping requirement must be taken into account. The latter unique features make this work a significant step forward toward the objective of incorporating of wind, solar, load, and other uncertainties into power system operations. In this report, a new methodology to predict the uncertainty ranges for the required balancing capacity, ramping capability and ramp duration is presented. Uncertainties created by system load forecast errors, wind and solar forecast errors, generation forced outages are taken into account. The uncertainty ranges are evaluated for different confidence levels of having the actual generation requirements within the corresponding limits. The methodology helps to identify system balancing reserve requirement based on a desired system performance levels, identify system “breaking points”, where the generation system becomes unable to follow the generation requirement curve with the user-specified probability level, and determine the time remaining to these potential events. The approach includes three stages: statistical and actual data acquisition, statistical analysis of retrospective information, and prediction of future grid balancing requirements for specified time horizons and confidence intervals. Assessment of the capacity and ramping requirements is performed using a specially developed probabilistic algorithm based on a histogram analysis incorporating all sources of uncertainty and parameters of a continuous (wind forecast and load forecast errors) and discrete (forced generator outages and failures to start up) nature. Preliminary simulations using California Independent System Operator (California ISO) real life data have shown the effectiveness of the proposed approach. A tool developed based on the new methodology described in this report will be integrated with the California ISO systems. Contractual work is currently in place to integrate the tool with the AREVA EMS system.

17 WIND ENERGY↗

Wind Energy Management System EMS Integration Project: Incorporating Wind Generation and Load Forecast Uncertainties into Power Grid Operations

The power system balancing process, which includes the scheduling, real time dispatch (load following) and regulation processes, is traditionally based on deterministic models. Since the conventional generation needs time to be committed and dispatched to a desired megawatt level, the scheduling and load following processes use load and wind and solar power production forecasts to achieve future balance between the conventional generation and energy storage on the one side, and system load, intermittent resources (such as wind and solar generation), and scheduled interchange on the other side. Although in real life the forecasting procedures imply some uncertainty around the load and wind/solar forecasts (caused by forecast errors), only their mean values are actually used in the generation dispatch and commitment procedures. Since the actual load and intermittent generation can deviate from their forecasts, it becomes increasingly unclear (especially, with the increasing penetration of renewable resources) whether the system would be actually able to meet the conventional generation requirements within the look-ahead horizon, what the additional balancing efforts would be needed as we get closer to the real time, and what additional costs would be incurred by those needs. To improve the system control performance characteristics, maintain system reliability, and minimize expenses related to the system balancing functions, it becomes necessary to incorporate the predicted uncertainty ranges into the scheduling, load following, and, in some extent, into the regulation processes. It is also important to address the uncertainty problem comprehensively by including all sources of uncertainty (load, intermittent generation, generators’ forced outages, etc.) into consideration. All aspects of uncertainty such as the imbalance size (which is the same as capacity needed to mitigate the imbalance) and generation ramping requirement must be taken into account. The latter unique features make this work a significant step forward toward the objective of incorporating of wind, solar, load, and other uncertainties into power system operations. Currently, uncertainties associated with wind and load forecasts, as well as uncertainties associated with random generator outages and unexpected disconnection of supply lines, are not taken into account in power grid operation. Thus, operators have little means to weigh the likelihood and magnitude of upcoming events of power imbalance. In this project, funded by the U.S. Department of Energy (DOE), a framework has been developed for incorporating uncertainties associated with wind and load forecast errors, unpredicted ramps, and forced generation disconnections into the energy management system (EMS) as well as generation dispatch and commitment applications. A new approach to evaluate the uncertainty ranges for the required generation performance envelope including balancing capacity, ramping capability, and ramp duration has been proposed. The approach includes three stages: forecast and actual data acquisition, statistical analysis of retrospective information, and prediction of future grid balancing requirements for specified time horizons and confidence levels. Assessment of the capacity and ramping requirements is performed using a specially developed probabilistic algorithm based on a histogram analysis, incorporating all sources of uncertainties of both continuous (wind and load forecast errors) and discrete (forced generator outages and start-up failures) nature. A new method called the “flying brick” technique has been developed to evaluate the look-ahead required generation performance envelope for the worst case scenario within a user-specified confidence level. A self-validation algorithm has been developed to validate the accuracy of the confidence intervals.

24 POWER TRANSMISSION AND DISTRIBUTION↗

Considerations for Long-Term Load Forecasting in Morocco

There are many factors that determine how demand for electricity may change over time. These factors include GDP, population size, and technology diffusion and adoption. We employ a simple extrapolation of current trends in Morocco GDP to estimate how the peak demand and annual consumption may change through the year 2030. We discuss the many factors that this approach does not take into account (such as adoption of air conditioning, electric vehicles, and distributed generation).

54 ENVIRONMENTAL SCIENCES↗

Machine learning surrogate of physics-based building-stock simulator for end-use load forecasting

Building energy models are used to simulate heat and mass transfer and estimate end-use load in buildings. With the proliferation of solar photovoltaics on residential and commercial buildings, increasingly, buildings are expected to provide grid services, for which accurate and computationally efficient building energy simulations and end-use load prediction are imperative. Existing building energy simulation tools, however, have significant computational overhead that make them less practical in real-time deployment for optimization, design, uncertainty quantification and control in building energy management systems. Here this article presents a data-driven machine learning model based on light gradient boosting method (LightGBM) as a surrogate for a physics-based simulator for residential buildings to predict end-use load. The machine learning based surrogate model accounts for time-series related variables, seasonality and trend component of end-use load, and history of end-use load. The accuracy of the surrogate model is assessed on the prediction of the load profiles of 100 different houses in Cook County, Illinois, USA. The LightGBM surrogate model is shown to reduce the root-mean-squared error by 53% relative to a reference decision tree (DT) based model reported previously in the literature. Moreover, the model predicts the load spikes and high-ramp rate events throughout the year which are often the Achilles heel of other models in the literature. The machine learning based surrogate model is demonstrated to be computationally efficient, with a ten-fold reduction in the computational time compared to a physics-based building energy simulation, and suitable for uncertainty analysis and real-time control of building characteristics in response to uncertainty.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Solar PV, Wind Generation, and Load Forecasting Dataset for ERCOT 2018: Performance-Based Energy Resource Feedback, Optimization, and Risk Management (P.E.R.F.O.R.M.)

This report describes the Advanced Research Projects Agency-Energy Performance-Based Energy Resource Feedback, Optimization, and Risk Management (PERFORM) Electric Reliability Council of Texas (ERCOT) dataset consisting of load, solar, and wind deterministic and probabilistic forecasts at three timescales. This dataset consists of 1 year of time-coincident load, wind, and solar actuals and probabilistic forecasts for a region similar to ERCOT. All the data are stored in Hierarchical Data Format 5 (HDF5) files and have been uploaded to an Amazon Web Services repository. The ERCOT data set has 2 years (2017, 2018) of actuals and 1 year (2018) of probabilistic forecasts. These data are provided at various spatial (i.e., site-level, zone-level, and system-level) and temporal scales (i.e., day-ahead, intraday, and intra-hour). Specifically, data are provided for 125 existing wind sites, 22 existing solar sites, 139 proposed wind sites, and 204 proposed solar sites.

14 SOLAR ENERGY↗