Hierarchical Scheduling of Aggregated TCL Flexibility for Transactive Energy in Power Systems
Not provided.
SEARCH · Search NASA
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.
Not provided.
For effective engagement of residential demand-side resources and to ensure efficient operation of distribution networks, we must overcome the challenges of controlling and coordinating residential components and devices at scale. To overcome this challenge, we present a distributed and scalable algorithm with a three-level hierarchical information exchange architecture for managing the residential demand response programs. First, a centralized optimization model is formulated to maximize community social welfare. Then, this centralized model is solved in a distributed manner with alternating direction method of multipliers (ADMM) by decomposing the original problem to utility-level and house-level problems. The information exchange between the different layers is limited to the primary residual (i.e., supply-demand mismatch), Lagrangian multipliers, and the total load of each house to protect each customer’s privacy. Simulation studies are performed on the IEEE 33 bus test system with 605 residential customers. The results demonstrate that the proposed approach can save customers’ electricity bills and reduce the peak load at the utility level without much affecting customers’ comfort and privacy. Finally, a quantitative comparison of the distributed and centralized algorithms shows the scalability advantage of the proposed ADMM-based approach, and it gives benchmarking results with achievable value for future research works.
As the sporting industry continues to increase dependence on new and often massive data sets, they also risk exposing themselves, as well as the leagues, teams, venues, players, and fans, to risks posed by not protecting the confidentiality and integrity of this data. The industry, especially true for professional sports, demands an ever increasing supply of new forms of data to achieve their goals of enticing new fans; enhancing experience; expanding the fan experience from venues and television to the internet and mobile devices; measuring and evaluating the performance and safety of players; and increasing revenue. New methods have emerged to collect data about a variety of aspects of sports ranging from players to fans to teams to venues. Data collected during sporting events is combined with historical data to also help teams analyze and predict performance. To synthesize these predictive analytical and historical memories, sports teams and organizations mix a variety of computer technologies. System integration tends to focus on ensuring the availability of the data and reliability of the technologies but might introduce risks to the confidentiality (privacy) and integrity of the data. Recognizing the potential risks requires review and evaluation. Much of the data is collected for publicly providing information to the fans, so threats to confidentiality pose fewer risks. The greatest risk is violating the privacy of players, such a private performance test, or using technology to gain a competitive advantage.
Demand flexibility is increasingly important for power grids. Careful coordination of thermostatically controlled loads (TCLs) can modulate energy demand, decrease operating costs, and increase grid resiliency. We propose a novel distributed control framework for the Coordination Of HeterOgeneous Residential Thermostatically controlled loads (COHORT). COHORT is a practical, scalable, and versatile solution that coordinates a population of TCLs to jointly optimize a grid-level objective, while satisfying each TCL’s end-use requirements and operational constraints. To achieve that, we decompose the grid-scale problem into subproblems and coordi- nate their solutions to find the global optimum using the alternating direction method of multipliers (ADMM). The TCLs’ local problems are distributed to and computed in parallel at each TCL, making COHORT highly scalable and privacy-preserving. While each TCL poses combinatorial and non-convex constraints, we characterize these constraints as a convex set through relaxation, thereby making COHORT computationally viable over long planning horizons. After coordination, each TCL is responsible for its own control and tracks the agreed-upon power trajectory with its preferred strategy. In this work, we translate continuous power back to discrete on/off actuation, using pulse width modulation. COHORT is generalizable to a wide range of grid objectives, which we demonstrate through three distinct use cases: generation following, minimizing ramping, and peak load curtailment. In a notable experiment, we validated our approach through a hardware-in-the-loop simulation, including a real-world air conditioner (AC) controlled via a smart thermostat, and simulated instances of ACs modeled after real-world data traces. During the 15-day experimental period, COHORT reduced daily peak loads by an average of 12.5% and maintained comfortable temperatures.
Demand response (DR) of building HVAC load can provide crucial demand-side flexibility for the future smart grid. Compared to direct load control, price-based control can respect the customers’ autonomy and privacy. However, it is challenging for price-based control to attain provable performance guarantees under future uncertainty. In this paper, we propose a framework for a utility to perform price-based control of flexible building load within the utility’s service area, in order to attain competitive performance guarantees in terms of controlling the system peak demand under future uncertainty. By adopting a two-step approach, our online price-based control solution can attain a provable competitive ratio for all possible realizations within a given uncertainty set. Simulation experiments demonstrate that, with a robustification procedure, our solution can perform well not only for worst-case inputs, but also for average-case inputs.
Human mobility data science using trajectories or check-ins of individuals has many applications. Recently, we have seen a plethora of research efforts that tackle these applications. However, research progress in this field is limited by a lack of large and representative datasets. The largest and most commonly used dataset of individual human trajectories captures fewer than 200 individuals, while datasets of individual human check-ins capture fewer than 100 check-ins per city per day. Thus, it is not clear if findings from the human mobility data science community would generalize to large populations. Since obtaining massive, representative, and individual-level human mobility data is hard to come by due to privacy considerations, the vision of this work is to embrace the use of data generated by large-scale socially realistic microsimulations. Informed by both real data and leveraging social and behavioral theories, massive spatially explicit microsimulations may allow us to simulate entire megacities at the person level. The simulated worlds, which do not capture any identifiable personal information, allow us to perform “in silico” experiments using the simulated world as a sandbox in which we have perfect information and perfect control without jeopardizing the privacy of any actual individual. In silico experiments have become commonplace in other scientific domains such as chemistry and biology, permitting experiments that foster the understanding of concepts without any harm to individuals. This work describes challenges and opportunities for leveraging massive and realistic simulated alternate worlds for in silico human mobility data science.
Federated finetuning is crucial for unlocking the knowledge embedded in pretrained Large Language Models (LLMs) when data are geographically distributed across clients. Unlike finetuning with data from a single institution, federated finetuning allows collaboration across multiple institutions, enabling the utilization of diverse and decentralized datasets while preserving data privacy. Given the high computing costs of LLM training and the emphasis on energy efficiency in Federated Learning (FL), Low-Rank Adaptation (LoRA) has emerged as a widely adopted algorithm due to its significantly reduced number of trainable parameters. However, this assumes that all data silos have the necessary computing resources to compute local updates of LLMs. Nevertheless, in practice, the computing resources across clients are highly heterogeneous: while some may have access to hundreds of GPUs, others might have limited or no GPU access. Recently, federated finetuning using synthetic data has been proposed, allowing clients to participate in a collaborative training run without training LLMs locally. However, our experimental results reveal a performance gap between models trained using synthetic data and those trained using local updates. Motivated by the observed heterogeneity in computing resources and the performance gap, we propose a novel two-stage algorithm that leverages the storage and computing capabilities of a strong server. In the first stage, under the coordination of the strong server, clients with limited computing resources collaborate to generate synthetic data, which is transferred to and stored on the strong server. In the second stage, the strong server uses this synthetic data on behalf of the resource-constrained clients to perform federated LoRA finetuning alongside clients with sufficient computing resources. This approach ensures that all clients can participate in the finetuning process. Experimental results demonstrate that incorporating local updates from even a small fraction of clients improves performance compared to using synthetic data for all clients. Furthermore, we incorporate the Gaussian mechanism in both stages to guarantee client-level differential privacy.
Federated learning (FL) at leadership-class HPC systems remains largely unexplored, despite growing interest in deploying federated workflows on modern HPC systems. This paper provides the first system-level empirical characterization of federated fine-tuning of pretrained foundation models on an exascale supercomputer under a multi-node deployment. Using up to 96 concurrent FL clients deployed across Frontier nodes, we study the impact of client scale, model size, data heterogeneity, partial participation, and differential privacy on runtime, communication overhead, and convergence stability. Our results show that pretrained transformer models remain robust to heterogeneity, client dropout, and privacy noise, while system efficiency degrades rapidly with scale as synchronizat and orchestration dominate runtime. We further demonstrate that system-aware execution strategies, including intra-node aggregation and early aggregation, significantly reduce wall-clock time without degrading model quality. These findings establish a practical performance baseline and inform the design of communication-efficient FL systems on leadership-class HPC platforms.
Rideshare use has grown significantly, beginning with solo riders and evolving to pooled rideshare. Pooled rideshare involves sharing a ride with stranger(s). Despite the growth in rideshare services worldwide, the use of pooled rideshare in the U.S. is relatively low within all rideshare trips and compared to other forms of transportation, e.g., driving one's personal vehicle. A national survey of 5,385 individuals was conducted to identify factors influencing riders' willingness to consider pooled rideshare. Exploratory and confirmatory factor analyses were performed. The survey results indicated five factors: service experience, time/cost, traffic/environment, privacy, and safety. Understanding these factors is crucial for the future of dynamic ridesharing services in the U.S.
Abstract Privacy protection is a growing concern in the digital era, with machine vision techniques widely used throughout public and private settings. Existing methods address this growing problem by, e.g., encrypting camera images or obscuring/blurring the imaged information through digital algorithms. Here, we demonstrate a camera design that performs class-specific imaging of target objects with instantaneous all-optical erasure of other classes of objects. This diffractive camera consists of transmissive surfaces structured using deep learning to perform selective imaging of target classes of objects positioned at its input field-of-view. After their fabrication, the thin diffractive layers collectively perform optical mode filtering to accurately form images of the objects that belong to a target data class or group of classes, while instantaneously erasing objects of the other data classes at the output field-of-view. Using the same framework, we also demonstrate the design of class-specific permutation and class-specific linear transformation cameras, where the objects of a target data class are pixel-wise permuted or linearly transformed following an arbitrarily selected transformation matrix for all-optical class-specific encryption, while the other classes of objects are irreversibly erased from the output image. The success of class-specific diffractive cameras was experimentally demonstrated using terahertz (THz) waves and 3D-printed diffractive layers that selectively imaged only one class of the MNIST handwritten digit dataset, all-optically erasing the other handwritten digits. This diffractive camera design can be scaled to different parts of the electromagnetic spectrum, including, e.g., the visible and infrared wavelengths, to provide transformative opportunities for privacy-preserving digital cameras and task-specific data-efficient imaging.
Congress enacted the Health Insurance Portability and Accountability Act of 1996 (HIPAA) without including specific provisions for protecting the privacy of healthrelated information. The law gave Congress three years to enact such requirements and provided that if it failed to do so the Secretary of the Department of Health and Human Services (DHHS) was obligated to promulgate regulations to implement the statutory standards. When Congress failed to meet the deadline, the obligation to issue privacy regulations passed to DHHS. DHHS received over 52,000 comments on the proposed regulations. Responses to the comments and the final rule were published in the Federal Register on December 28, 2000. The cost of implementing the regulations over a ten-year period was estimated at $17.6 billion by DHHS. Industry estimates the cost at five times that amount.
The Systems Analysis & Decision Support (02150) group completed a review of the research literature on workspace and office design in 2016 for the Asset Management Department (04853). The goal was to characterize results and lessons learned from existing research to understand the effectiveness of current workspaces at Sandia National Laboratories and inform guidance for future workspace design. The study team reviewed 96 documents, published primarily since the year 2000, covering a range of factors associated with workspace design - workspace costs, acoustics, collaboration and privacy, generational preferences, employee health, performance and productivity, organizational retention, and workspace satisfaction. The research literature consistently highlighted the relative deficiencies of open-plan office spaces as compared to traditional private enclosed offices for knowledge workers. While open-plan offices can provide some cost savings, they may not be cost effective in the long term due to future hidden costs incurred by degradations in employee productivity, increased attrition, and increased sickness absences as well as any post-construction modifications needed to resolve emerging workspace issues. The chief deficiencies of open-plan offices include lower levels of employee satisfaction due to reduced visual and auditory privacy, increased interruptions, distractions from irrelevant background speech, less physical space, and more ambient noise. The drawbacks reported in the literature tend to outweigh any benefits associated with potential facilitation of coworker interactions and collaboration. Key suggestions identified in the literature to guide and optimize workspace and office design are provided.
A key issue for saving energy in buildings is to assure that delivery of energy services matches building occupancy as closely as possible, to assure that energy is not wasted providing the services to empty rooms or buildings, and to assure that needed services are provided during all times when desired. Accomplishing this to date has been significantly hampered by a lack of inexpensive mechanisms to obtain and use building-wide and more granular data about occupancy. In recent years, the concept of inferential (or implicit) sensing has been proposed and explored to use data from IT systems that already exists in most buildings, to obtain data that are not perfect, but are nearly free to obtain. Past work by LBNL and others has primarily demonstrated the principle and potential for this, with a primary focus on data from Wi-Fi networks as the best near-term opportunity for inferential sensing from IT networks. This is due to its near-ubiquity, ease of explanation to many audiences, relative uniformness in deployment, low latency of detection, clear ways to mitigate privacy and security, and other benefits (Price et al., 2015). While the potential and value are clear, researchers or building managers who want to obtain the data lack a source of information to understand what data might exist, what devices may have it, and what mechanisms are available to obtain the data. The purpose of this report is to fill that gap. The report begins with a review of institutional issues in collecting such data, including very real concerns about privacy and IT security. It then describes the various system architectures used in Wi-Fi systems in commercial buildings today, and a variety of mechanisms that can be used to obtain information from them, including examples of how to use them, and sample output. Next is a summary of how to use such data for several different purposes, from retrospective analysis to dynamic building operation, and a conclusion. An appendix provides additional detail on specific mechanisms available from major equipment manufacturers. The mechanisms specified in this report can be used by building owners and operators to confirm proper operation and uncover any issues or unexpected conditions as a resource for building owners and researchers interesting in utilizing inferential sensing data.
This documentation focuses on a single end-use savings shape measure - window film. The window film studied in this analysis, called solar control film, is a passive retrofit solution for windows that does not involve window replacement. This type of film is composed of transparent, tinted, or metalized laminated polyester layers and can be attached to an existing window surface (either on the exterior or interior side of the window). The properties of the window film are designed to shift the thermal and optical performances of the overall glazing system in order to serve various needs the customer would have (e.g., heat, glare). While the practical goal of purchasing and installing a window film varies widely in the real market, this study only focuses on the goal of energy savings, and highlighting the corresponding emissions. Other important aspects that customers typically consider include visual comfort, privacy, aesthetics, ultraviolet protection, etc. Thus, in practice, customers often choose a window film product not only to save energy (or cost) but also to mitigate issues around glare, excessive light, daytime privacy, or inconsistent appearance of the building. Window film products that were modeled in this analysis significantly reduced the solar heat gain coefficient of the overall glazing system, resulting in better energy savings for buildings in hot climate regions. However, significantly reducing the solar heat gain coefficient that can block unfavorable heat during the summer can actually harm blocking favorable heat during the winter. By applying window films on a stock of buildings covering various load and weather conditions, this analysis highlights when (e.g., time of day) and where (e.g., geospacial location) we can save energy with window films.
The Ohio State University and Idaho National Laboratory organized the 4 th Big Data for Nuclear Power Plants Workshop in November, 2023 in Columbus, Ohio. Workshop topics were chosen to understand the challenges and gaps that need to be addressed to maximize the impact of data on the nuclear industry, as well as the associated applications and risks. Discussions were focused around six specific application areas: Operation and Maintenance; Machine Learning in Nuclear Materials and Advanced Manufacturing; Cybersecurity; High-Performance Computing and Massive Computation; Big Data and Digital Twins; and Nuclear Non-Proliferation. The opportunities, challenges, and risks identified in the six focus areas explored in this workshop are diverse, but some common themes emerge, such as the importance of data integrity, quality, coverage, privacy, and traceability. Big data and AI/ML tools can be leveraged to reduce costs, optimize human tasking, and reduce human error across various application areas. In order for the nuclear industry to benefit from big data and advanced analytic capabilities, it is essential to address challenges and risks, such as data privacy, model reliability, and computational resource availability. Learning from other industries that have successfully implemented big data and AI/ML technologies, like the aerospace industry, can help the nuclear industry successfully integrate these technologies.
Recent advancements in AI models, like ChatGPT, are structured to retain user interactions, which could inadvertently include sensitive healthcare data. In the healthcare field, particularly when radiologists use AI-driven diagnostic tools hosted on online platforms, there is a risk that medical imaging data may be repurposed for future AI training without explicit consent, spotlighting critical privacy and intellectual property concerns around healthcare data usage. Addressing these privacy challenges, a novel approach known as Unlearnable Examples (UEs) has been introduced, aiming to make data unlearnable to deep learning models. A prominent method within this area, called Unlearnable Clustering (UC), has shown improved UE performance with larger batch sizes but was previously limited by computational resources (e.g., a single workstation). To push the boundaries of UE performance with theoretically unlimited resources, we scaled up UC learning across various datasets using Distributed Data Parallel (DDP) training on the Summit supercomputer. Our goal was to examine UE efficacy at high-performance computing (HPC) levels to prevent unauthorized learning and enhance data security, particularly exploring the impact of batch size on UE’s unlearnability. Utilizing the robust computational capabilities of the Summit, extensive experiments were conducted on diverse datasets such as Pets, MedMNist, Flowers, and Flowers102. Our findings reveal that both overly large and overly small batch sizes can lead to performance instability and affect accuracy. However, the relationship between batch size and unlearnability varied across datasets, highlighting the necessity for tailored batch size strategies to achieve optimal data protection. The use of Summit’s high-performance GPUs, along with the efficiency of the DDP framework, facilitated rapid updates of model parameters and consistent training across nodes. Our results underscore the critical role of selecting appropriate batch sizes based on the specific characteristics of each dataset to prevent learning and ensure data security in deep learning applications. The source code is publicly available at https: // github. com/ hrlblab/ UE_ HPC .
This dissertation explores the development and deployment of machine learning approaches to address critical challenges in anomaly detection across two distinct domains: neural network security in federated learning settings and cavity behavior analysis in particle accelerator operations at Jefferson Lab in Newport News, Virginia. Anomaly detection identifies deviations from expected patterns, safeguarding systems in cybersecurity, industry, and research against malicious activities and failures. This dissertation demonstrates how our machine learning approaches enhance detection accuracy and efficiency in both neural network security and industrial applications. First, we investigate vulnerabilities in deep neural networks deployed in federated learning. Although federated learning preserves user privacy by training models locally, it remains vulnerable to backdoor attacks, in which malicious participants embed hidden triggers that induce targeted misbehavior. We propose a self-supervised contrastive learning framework to detect and mitigate such backdoor attacks. In our experiments, this method achieves higher detection accuracy and lower false positive rates than existing defenses, while operating without access to local model updates or original training data and thus preserving the privacy guarantees of the federated setting. Second, we address the operational reliability of superconducting radio-frequency (SRF) cavities at the Continuous Electron Beam Accelerator Facility (CEBAF). Our research leverages an unsupervised learning approach, combined with Principal Component Analysis (PCA) and k-means clustering, to identify anomalous behaviors in SRF cavities. Our method detects subtle anomalous behavior by analyzing SRF signal data. This knowledge allows for the early detection and resolution of potential faults, significantly improving the efficiency and reliability of operations. Third, we extend these insights to time-series anomaly detection more broadly. We design a contrastive-learning based model tailored to increasingly dynamic environments and academic research. This model improves detection accuracy in settings that require real-time monitoring and predictive maintenance. Our research underscores the broader applicability and impact of advanced machine learning techniques in anomaly detection. By extracting meaningful patterns from complex data, machine learning can significantly enhance security in distributed neural networks and improve the efficiency of particle accelerator operations. This dissertation serves as a stepping stone for future investigations into the vast possibilities of anomaly detection, inspiring further exploration and development of machine learning techniques in this field.
Bias in medical image segmentation can lead to unequal performance across demographic subgroups, raising concerns about fairness and reliability in clinical AI systems. While deep learning models have achieved high segmentation accuracy, ensuring equitable performance across race and gender remains a significant challenge, particularly in privacy-sensitive healthcare environments. This study investigates fairness-aware medical image segmentation for hip and knee radiographs using deep learning models evaluated in both centralized and Federated Learning (FL) settings. We introduce Curriculum Learning (CL) strategies and Progressive Loss (PL) functions to regulate sample difficulty during training. In addition, we propose two novel fairness-oriented federated learning algorithms, Federated Intersection over Union (FedIoU) and Federated Intersection over Union with Outlier Analysis (FedIoUoutlier). Experiments are conducted using multiple segmentation backbones and simulated multi-site data partitions derived from the Osteoarthritis Initiative dataset. Model performance is evaluated using Intersection over Union (IoU), IoU standard deviation, Skewed Error Ratio (SER), and Min-Max Disparity across race and gender subgroups. Statistical significance was verified using paired t-tests to compare per-sample IoU performance against baseline configurations. Across both hip and knee segmentation tasks, curriculum learning and progressive loss strategies consistently improved segmentation accuracy and reduced demographic performance disparities in centralized training. In federated settings, fairness-aware aggregation further enhanced performance. Notably, FedIoUoutlier combined with balanced curriculum learning and tiered progressive loss achieved the highest mean IoU while yielding the lowest SER and Min-Max Disparity, indicating improved fairness without sacrificing accuracy. In several configurations, federated models matched or exceeded the performance of optimized centralized models, with statistically significant improvements in per-sample IoU over baseline configurations. The results demonstrate that structured training strategies and fairness-aware federated aggregation can jointly improve accuracy, stability, and demographic fairness in medical image segmentation. By integrating curriculum learning, progressive loss, and novel FL algorithms, this work provides a practical pathway toward equitable and privacy-preserving AI systems for medical imaging.