Pursuing the impossible (?) dream: Incorporating attitudes into practice-ready travel demand forecasting models
Not Available
Mokhtarian, Patricia L. (ORCID:000000017104499X)↗
SEARCH · Search NASA
Results for “demand 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.
Impact of Building Characteristics on Energy Demand Profile Forecasting: An Evaluation of Predictive Accuracy and Methods
Explore the source record for details and available documents.
Chowdhury, Shovan [ORNL]↗
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↗
Artificial Intelligence and Machine Learning Applications in Modern Power Systems
Machine learning (ML) and artificial intelligence (AI) algorithms offer valuable tools for the analysis and interpretation of large datasets. These tools have the capability to uncover insights that may not be readily apparent within these datasets. In recent years, the integration of ML and AI has become increasingly prevalent in various applications within the power system domain. One of the earliest instances of machine learning in power systems can be traced back to demand forecasting, where artificial neural networks were employed for short-term load forecasting. In contemporary power systems, an abundance of high-resolution geospatial and temporal data is generated at various time intervals, ranging from sub-seconds (Phasor Measurement Units or PMUs) to seconds (Supervisory Control and Data Acquisition or SCADA), minutes (Process Information or PI), and extending to days, months, and years. These datasets contain valuable information concerning system reliability and performance. This information holds the potential to offer critical insights into system operations, as well as solutions for predicting and mitigating contingencies to prevent cascading outages. Despite the immense power of machine learning tools, system operators, planners, and utilities often exhibit hesitancy in fully embracing AI-enabled system operations and planning. This cautious approach persists, even as numerous diverse applications of machine learning continue to emerge in the realm of power systems. In this chapter, our focus will delve deep into ML and AI applications tailored for power systems. These applications aim to furnish system operators with enhanced situational awareness and augment their decision-making capabilities, especially during challenging operating conditions. Specific areas of interest encompass root cause analyses of electricity market datasets and the strategic selection of representative samples from vast power system databases for training ML/AI models. Finally, the chapter will conclude with a short discussion on the future of ML/AI in power systems and possible directions that the industry is moving towards.
power system applications, machine learning (ML), ↗
Data efficiency assessment of generative adversarial networks in energy applications
This study investigates the data requirements of generative artificial intelligence (AI), particularly generative adversarial networks (GANs), for reliable data augmentation in energy applications. Generative AI, though seen as a solution to data limitations, requires substantial data to learn meaningful distributions—a challenge often overlooked. This study addresses the challenge through synthetic data generation for critical heat flux (CHF) and power grid demand, focusing on renewable and nuclear energy. Two variants of GAN employed are conditional GAN (cGAN) and Wasserstein GAN (wGAN). Our findings include the strong dependency of GAN on data size, with performance declining on smaller datasets and varying performance when generalizing to unseen experiments. Mass flux and heated length significantly influence CHF predictions. wGAN is more robust to feature exclusion, making it suitable for constrained synthetic data generation. In energy demand forecasting, wGAN performed well for solar, wind, and load predictions. Longer lookback hours and larger datasets improved predictions, especially for load power. Seasonal variations posed challenges, with wGAN achieving a relatively high error of Root Mean Squared Error (RMSE) of 0.32 for load power prediction, compared to RMSE of 0.07 under same-season conditions. Feature exclusions impacted cGAN the most, while wGAN showed greater robustness. This study concludes that, while generative AI is effective for data augmentation, it requires substantial data and careful training to generate realistic synthetic data and generalize to new experiments in engineering applications.
22 - GENERAL STUDIES OF NUCLEAR REACTORS↗
Work from Home Patterns across COVID-19 Waves: Implications for Future Transportation
The unprecedented rise in work from home (WFH) during COVID-19 poses challenges for the transportation engineers and planners with the travel demand forecasting. If WFH persists post-pandemic, it could influence traffic patterns, reducing peak-hour congestion. However, the evolution of WFH decisions across pandemic phases and varying socio-economic contexts remains unclear. This study examines factors influencing WFH choices using data from the US Census Bureau’s Household Pulse Survey. Findings reveal a decline in WFH participation from 60% during the first wave to 38% by the third wave of the COVID-19 pandemic. A Geographically Weighted Regression model highlights the influence of socio-economic, household, and COVID-19-related variables, with notable spatial variability. Results show that younger individuals, females, and households with children are consistently more likely to WFH, while non-white and higher income individuals have an increasing likelihood for WFH as the pandemic progresses. These insights inform future transportation planning, emphasizing equity and decentralization strategies for post-pandemic commuting.
Patwary, Latif [ORNL] (ORCID:0000000189174928)↗
2011 Atlanta, Georgia, Regional Travel Survey
The 2011 Regional Travel Survey collected trip data from households across 20 counties in and around Atlanta, Georgia, to improve regional travel demand forecasts. The survey was conducted by PTV NuStats, GeoStats, and PG Americas Inc. on behalf of the Atlanta Regional Commission. The goal was to collect trip data from a minimum of 10,000 households with a subsample of 1,000 households providing global positioning system (GPS) data. The GPS add-on consisted of two sample groups. The first sample group was provided with GPS devices to install in their personal vehicles (797 vehicles) to collect the speed and location of a vehicle during an assigned study period. The second sample group (1,653 participants) was provided with a wearable GPS device to collect the speed and location of an individual during an assigned study period. People participating in the wearable add-on part of the study were chosen because their travel diaries reported use of public transit in day-to-day travel. Each GPS participant was grouped into either the spring phase (March to May 2011) or the fall phase (July to September 2011), and data were recorded for a maximum of seven days for vehicle units and three days for wearable units.
1Hz data↗
2007 Chicago Regional Household Travel Inventory
To provide data for developing and refining travel demand forecast models, the 2007 Regional Household Travel Inventory studied the demographic and travel behavior characteristics of residents in the greater Chicago area. It included households in eight counties in Illinois and three in Indiana. The Chicago Metropolitan Agency for Planning conducted the study in coordination with the Illinois Department of Transportation, the Northwestern Indiana Regional Planning Commission, and the Indiana Department of Transportation. Travel and activity information for all household members (regardless of age) was collected during a randomly assigned 24- or 48-hour period. It relied on the willingness of households to provide detailed information about their members and vehicles, and to record all travel and associated activity during the collection period. This study also featured a subsample of households collecting data via in-vehicle and wearable global positioning system devices.
1Hz data↗
2010-2012 Minneapolis - St. Paul Travel Behavior Inventory
The 2010-2012 Travel Behavior Inventory (TBI) provided Minnesota policymakers and researchers with data about travel in the Minneapolis - St. Paul region. It also updated the region's travel demand forecasting, including transit ridership for major transportation projects. The Metropolitan Council in the Minneapolis-St. Paul area conducted the survey. The TBI consists of a paper-based survey and a wearable global positioning system survey. The data collection process for these two surveys was independent, and the results are not intended to function together.
1Hz data↗
2008 NIRPC Household Travel Inventory
The Northwestern Indiana Regional Planning Commission (NIRPC) Household Travel Inventory, also sponsored by the Indiana Department of Transportation, is a comprehensive study of the demographic and travel of residents of Lake, Porter, and La Porte counties in northwest Indiana. The primary objective of the study was to provide data for the continued development and refinement of the Indiana regional travel demand forecast models. 3,838 households from northwest Indiana participated in the survey, which entailed the collection of activity and travel information for all household members regardless of age during a randomly assigned 24- or 48-hour period. NIRPC travel survey data provided the information required on base-year daily trips made by study area residents to the Chicago CBD. This travel market is treated separately because of the importance of transit for its travelers.
1Hz data↗
1995 OMPO Model Development Project
The 1995 Oahu Metropolitan Planning Organization (OMPO) Model Development Project for Oahu Island was intended to document how Oahu residents use the streets, highways, and transit services in the region. These data were used to develop the Travel Demand Forecasting Model, which is used to forecast the traffic impacts of various land use changes. The survey collected complete travel information of 4,060 Oahu households for a 24-hour period, including demographic and socioeconomic data.
1Hz data↗
1988/1989 Maricopa Household Travel Study
This study was commissioned by the Maricopa Association of Governments (MAG) Transportation and Planning Office. The primary objectives of this study were to update the trip generation rates used in the MAG travel demand forecasting process and to provide data to validate the MAG trip distribution model. Demographic, socioeconomic, and travel data was collected for 2,992 households residing within the MAG Urban Planning Area. Respondents were asked to record their travel and activities for a 24-hour period. A total of 26,733 trips were recorded by 6,463 people.
1Hz data↗
1999 Puget Sound Household Travel Survey
The 1999 Puget Sound Household Travel Survey was conducted between July and November. NuStats Research and Consulting conducted the survey on behalf of the Puget Sound Regional Council. The purpose of the study was to provide data to continue developing and refining the Regional Travel Demand Forecasting Model, as well as to provide a better understanding of travel behavior in the Puget Sound region. The study area consists of King, Kitsap, Pierce, and Snohomish counties. The resultant dataset will be used to fulfill the model's functions of estimating trip generation and distribution, mode choice, and assignments. The study had household members 16 years old or older keep track of travel for a 48-hour period. A total of 9,028 households were recruited to participate in the study. Of these, 6,000 households (66.5%) completed travel diaries, and the information was retrieved from all household members regardless of age. An “attitude” survey about transportation and land use issues was also mailed to household members 16 years old or older.
1Hz data↗
1994 Household Travel Survey
The Metropolitan Washington Council of Governments/National Capital Region Transportation Planning Board (COG/TPB) periodically conducts regional household travel surveys to monitor changes in daily travel and to gather information on the demographic, socioeconomic, and trip-making characteristics of Washington, D.C.-area residents. Information collected in the 1994 Household Travel Survey was an important component in the development of regional travel demand forecasting models used to predict changes in daily travel in response to current development trends and changes in regional transportation policies and programs. In two waves during the spring and fall of 1994, consultants for COG/TPB conducted a survey of daily travel by persons living in area households. The survey file contains travel information associated with 4,863 households residing in 13 jurisdictions comprising the greater Washington, D.C., region (approximately a 1-in-300 sample). The survey file contains 39,800 internal trip records with respect to the expanded cordon.
1Hz data↗
1998/99 Thurston County Household Travel Study
The survey was conducted under the auspices of the Thurston Regional Planning Council, and it was funded through a state grant awarded to Intercity Transit of Olympia, Washington. Data collection was from September 1998 through March 1999. The purpose of the study was to provide data for the continuing development and refinement of the Regional Travel Demand Forecasting Model, as well as to provide a better understanding of travel behavior in the southern Puget Sound region of Washington. The resultant data set will be used to fulfill the model's functions of estimating trip generation and distribution, mode choice, and assignments. Participating households were assigned specific “travel days” to record their travel over a 48-hour period. A total of 2,465 households were recruited to participate in the study. Of these, 1,537 households completed travel diaries, and the information was retrieved from 3,653 household members regardless of age. Households member made 25,278 total trips during their 48-hour diary period.
1Hz data↗
1968 Metropolitan Washington Council of Governments/National Capital Region Transportation Planning Board Home Interview Survey
The Metropolitan Washington Council of Governments/National Capital Region Transportation Planning Board periodically conducts regional household travel surveys to monitor changes in daily travel and to gather information on the demographic, socioeconomic, and trip-making characteristics of Washington, D.C.-area residents. Information collected in the 1968 Home Interview Survey was an important component in the development of regional travel demand forecasting models used to predict changes in daily travel in response to current development trends and changes in regional transportation policies and programs. The survey sampled 26,000 households residing in six jurisdictions comprising the greater Washington, D.C. region (an approximately 1-in-20 sample).
1Hz data↗
1987/88 Metropolitan Washington Council of Governments/National Capital Region Transportation Planning Board Home Interview Survey
The Metropolitan Washington Council of Governments/National Capital Region Transportation Planning Board periodically conducts regional household travel surveys to monitor changes in daily travel and to gather information on the demographic, socioeconomic, and trip-making characteristics of Washington, D.C.-area residents. Information collected in the 1987/88 Home Interview Survey was an important component in the development of regional travel demand forecasting models used to predict changes in daily travel in response to current development trends and changes in regional transportation policies and programs. The survey sampled 8,000 households residing in eight jurisdictions comprising the greater Washington, D.C. region (an approximately 1-in-166 sample).
1Hz data↗
Hourly Load Profile Dataset for Electric Transit Bus Depots in the United States
Transit buses operate primarily in dense urban areas, where nearby populations face increased exposure to fine particulates, nitrogen oxides, and other harmful pollutants. Electrifying transit buses presents a clear opportunity to reduce greenhouse gas emissions and improve urban air quality. However, widespread adoption may pose significant energy and infrastructure challenges, which can be mitigated through proactive planning and investment. This report presents a robust modeling framework and an initial estimation of the hourly electricity demand at transit bus depots across the United States. The resulting depot-level dataset, available at data.nrel.gov/submissions/282, provides valuable insights for infrastructure planning and electricity demand forecasting, supporting the scalable electrification of transit bus fleets nationwide.
33 ADVANCED PROPULSION SYSTEMS↗