Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “decentralized learning”

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
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Decentralized Microgrid Protection Through Relative Fault Direction Classification: Preprint

Protection in inverter-based resources (IBRs) dominated microgrids generally face significant challenges due to the low fault current and inconsistent fault behaviors from IBRs. Recently, machine learning-based approaches have attracted considerable attention to address these challenges. This paper introduces a novel decentralized protection strategy for microgrids. The proposed method decomposes the protection challenge into several distributed learning tasks, enabling individual relays to autonomously determine the direction of faults using a binary classification framework based on support vector machine (SVM) algorithms. Following the distributed fault direction estimation, classifier outcomes are shared among neighboring relays, facilitating a local decision-making process to ascertain the presence of faults within the neighborhood. Finally, a tripping signal is generated based on the classifier results of each relay to operate the circuit breaker. To test and validate this approach, a 100% renewable microgrid model is simulated in MATLAB/Simulink. In the numerical analysis, the application of SVM classifiers in our approach yields impressive results: an average relay classification accuracy of 98%, and a 96% accuracy in circuit breaker control. These findings highlight the potential of machine-learning-based approaches in enhancing the efficiency and reliability of microgrid protection systems.

decentralized algorithm↗
DOE OSTI2025

Performance Evaluation of Vertical Federated Machine Learning Against Adversarial Threats on Wide-Area Control System: Preprint

Federated machine learning (FL) is gaining significant popularity to develop cybersecurity solutions in power grids because of its advanced capability to support decentralized data handing at local devices, its privacy preservation, and its low-bandwidth requirement. However, the evolving adversarial machine learning (AML) threats raise significant concerns for the cybersecurity of FL architectures. The FL-based split neural network (SplitNN) achieves high performance through the decentralized training of local neural network models while preserving data privacy across multiple entities. In this paper, we propose a methodology for evaluating the performance of a vertical FLbased anomaly detector against different types of AML attacks, including denial-of-service attacks, adversarial data injection attacks, and replay attacks on the trained local models deployed in the grid network. For a case study, we consider the modified IEEE 13-bus system, and we develop SplitNN-based binary and multiclass classification models to detect, locate, and identify different types of data integrity attacks on the volt-watt control with two pooling layers: maximum pooling and AvgPool. Our experimental results, computed through performance metrics, reveal that the severity of these AML attacks varies with the integrated pooling mechanism, the type of classification model, and the nature of the cyberattack. Further, the AML attacks negatively impacted the prediction time per sample for the pretrained SplitNN during the online testing.

adversarial threats↗
DOE OSTI2024

Multi-agent voltage control in distribution systems using GAN-DRL-based approach

Active distribution grids can experience voltage fluctuations and violations due to the high penetration of variable distributed energy resources (DERs). These problems might occur because of the uncertain and variable generation natures of these resources, especially solar photovoltaic resources, during panel shadowing scenarios. Volt-VAR control (VVC) is an efficient method that controls the reactive power set-points of the inverters to regulate the voltage of distribution grids. Although several VVC approaches have been proposed recently, the performance of these approaches degrades significantly if behind-the-meter solar generation data are unobservable/missing. Therefore, it is necessary to impute missing/unobservable PV data accurately to be utilized in VVC approaches. Further, this paper proposes a model-free, data-driven, centrally trained, and decentrally executed multi-agent deep reinforcement learning-based VVC architecture to regulate the voltage of distribution networks. A generative adversarial network (GAN) is incorporated to impute the unobservable PV data accurately, which improves the performance of the proposed control architecture. The proposed multi-agent-soft-actor–critic algorithm (MASAC)-based VVC technique utilizes the actual PV dataset as well as the imputed dataset from the GAN framework to learn the optimal coordinated control policy for controlling the optimal reactive power set-points of PV inverters. The effectiveness of the proposed approach is analyzed on a modified IEEE 34-bus test case with added PV inverters. The results are compared and analyzed with a base case model with no VVC and VVC with a local droop control approach, genetic algorithm optimization, and a centralized soft actor–critic-based approach. Moreover, the performance of the proposed approach is compared with that of a multi-agent VVC framework without using the PV generation data and load information as the system state. The results illustrate that the proposed method with more state input improves the voltage profile and reduces the power loss of the network across various loading and PV generation scenarios.

14 SOLAR ENERGY↗
DOE OSTI2024

RuralAI in Tomato Farming: Integrated Sensor System, Distributed Computing, and Hierarchical Federated Learning for Crop Health Monitoring

Precision horticulture is evolving due to scalable sensor deployment and machine learning (ML) integration. These advancements boost the operational efficiency of individual farms, balancing the benefits of analytics with autonomy requirements. However, given concerns that affect wide geographic regions (e.g., climate change), there is a need to apply models that span farms. Federated learning (FL) has emerged as a potential solution. FL enables decentralized ML across different farms without sharing private data. Traditional FL assumes simple two-tier network topologies and, thus, falls short of operating on more complex networks found in real-world agricultural scenarios. Networks vary across crops and farms and encompass various sensor data modes, extending across jurisdictions. New hierarchical FL (HFL) approaches are needed for more efficient and context-sensitive model sharing, accommodating regulations across multiple jurisdictions. Here, we present the RuralAI architecture deployment for tomato crop monitoring, featuring sensor field units for soil, crop, and weather data collection. HFL with personalization is used to offer localized and adaptive insights. Model management, aggregation, and transfers are facilitated via a flexible approach, enabling seamless communication between local devices, edge nodes, and the cloud.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2025

Machine Learning for Scalable and Optimal Load Shedding Under Power System Contingency

Prompt and effective corrective actions in response to unexpected contingencies are crucial for improving power system resilience and preventing cascading blackouts. The optimal load shedding (OLS) accounting for network limits has the potential to address the diverse system-wide impacts of contingency scenarios as compared to traditional local schemes. However, due to the fast cascading propagation of initial contingencies, real-time OLS solutions are challenging to attain in large systems with high computation and communication needs. In this paper, we propose a decentralized design that leverages offline training of a neural network (NN) model for individual load centers to autonomously construct the OLS solutions from locally available measurements. Our learning-for-OLS approach can greatly reduce the computation and communication needs during online emergency responses, thus preventing the cascading propagation of contingencies for enhanced power grid resilience. Numerical studies on both the IEEE 118-bus system and a synthetic Texas 2000-bus system have demonstrated the efficiency and effectiveness of our scalable OLS learning design for timely power system emergency operations.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

A Hybrid Optimization and Deep Learning Algorithm for Cyber-Resilient DER Control

With the proliferation of distributed energy resources (DERs) in the distribution grid, it is a challenge to effectively control a large number of DERs resilient to the communication and security disruptions, as well as to provide the online grid services, such as voltage regulation and virtual power plant (VPP) dispatch. To this end, a hybrid feedback-based optimization algorithm along with deep learning forecasting technique is proposed to specifically address the cyber-related issues. The online decentralized feedback-based DER optimization control requires timely, accurate voltage measurement from the grid. However, in practice such information may not be received by the control center or even be corrupted. Therefore, the long short-term memory (LSTM) deep learning algorithm is employed to forecast delayed/missed/attacked messages with high accuracy. The IEEE 37-node feeder with high penetration of PV systems is used to validate the efficiency of the proposed hybrid algorithm. The results show that 1) the LSTM-forecasted lost voltage can effectively improve the performance of the DER control algorithm in the practical cyber-physical architecture; and 2) the LSTM forecasting strategy outperforms other strategies of using previous message and skipping dual parameter update.

cyber-resilient algorithm↗
DOE OSTI2024

Machine learning without a processor: Emergent learning in a nonlinear analog network

Standard deep learning algorithms require differentiating large nonlinear networks, a process that is slow and power-hungry. Electronic contrastive local learning networks (CLLNs) offer potentially fast, efficient, and fault-tolerant hardware for analog machine learning, but existing implementations are linear, severely limiting their capabilities. These systems differ significantly from artificial neural networks as well as the brain, so the feasibility and utility of incorporating nonlinear elements have not been explored. Here, we introduce a nonlinear CLLN—an analog electronic network made of self-adjusting nonlinear resistive elements based on transistors. We demonstrate that the system learns tasks unachievable in linear systems, including XOR (exclusive or) and nonlinear regression, without a computer. We find our decentralized system reduces modes of training error in order (mean, slope, curvature), similar to spectral bias in artificial neural networks. The circuitry is robust to damage, retrainable in seconds, and performs learned tasks in microseconds while dissipating only picojoules of energy across each transistor. This suggests enormous potential for fast, low-power computing in edge systems like sensors, robotic controllers, and medical devices, as well as manufacturability at scale for performing and studying emergent learning.

Science & Technology - Other Topics↗
NASA NTRSDate not supplied

DRF: A Software Architecture for a Data Marketplace to Support Advanced Air Mobility

Advanced Air Mobility is a new aviation vision, where unmanned aerial systems will trans- port passengers and cargo across urban and rural areas. Critical to the realization of this vision is the development of a digital marketplace, which allows service providers and consumers operating in the airspace ecosystem to securely exchange data and reasoning insights. In this paper, we present the architecture of a decentralized data marketplace that connects data and reasoning service providers to vehicles and other service consumers along the cloud-to-edge continuum. We also present two example use cases to demonstrate the value of our approach.

Autonomy↗
DOE OSTI2022

Roadmap for Deployment of Modularized Hydrothermal Liquefaction: Understanding the Impacts of Industry Learning, Optimal Plant Scale, and Delivery Costs on Biofuel Pricing

Hydrothermal liquefaction (HTL) is a promising technology for converting abundant organic wastes into fuels. Previous techno-economic analyses (TEAs) of HTL have been used to estimate the minimum fuel selling price (MFSP) of biofuel products, but these analyses often assume a bespoke plant design where each plant operates under unique process conditions and neglect transportation costs. However, transportation costs must be included in realistic TEAs, and further, a mass-produced fixed-scale modular plant design approach may be more effective than case-by-case plant design, provided that there is sufficient market capacity to benefit from modularization. This study estimates fuel price behavior in the presence of transportation costs and benefits stemming from modular plant design. This analysis indicates that a modular process capable of handling 60 dry tons per day (DTPD) is optimal, resulting in a ~25% reduction in MFSP (from $4.70/GGE, fully upgraded) at complete market feedstock utilization compared with case-by-case design. The associated cost reductions are attributable to learning benefits and modularization. Several HTL deployment “roadmaps” are then explored, with each roadmap consisting of different periods of case-by-case design followed by adoption of a modularized approach. A period of nonmodular industry growth up to market saturation of ~7% followed by implementation of modular plant design strikes a balance between the investment risk and learned cost reductions associated with modular plant design. However, if bespoke plants built during this period of nonmodular growth saturate more than 23% of available feedstock, learned cost reductions are significantly diminished. Here, this study points to the potential benefits of modularized and decentralized waste-to-energy processes when the modularization follows an optimal deployment strategy.

09 BIOMASS FUELS↗
NASA NTRS1992

Neural joint control for Space Shuttle Remote Manipulator System

Neural networks are being used to control a robot arm in a telerobotic operation. The concept uses neural networks for both joint and inverse kinematics in a robotic control application. An upper level neural network is trained to learn inverse kinematic mappings. The output, a trajectory, is then fed to the Decentralized Adaptive Joint Controllers. This neural network implementation has shown that the controlled arm recovers from unexpected payload changes while following the reference trajectory. The neural network-based decentralized joint controller is faster, more robust and efficient than conventional approaches. Implementations of this architecture are discussed that would relax assumptions about dynamics, obstacles, and heavy loads. This system is being developed to use with the Space Shuttle Remote Manipulator System.

Atkins, Mark A.↗
DOE OSTI2023

Decentralized digital twins of complex dynamical systems

Abstract In this article, we introduce a decentralized digital twin (DDT) modeling framework and its potential applications in computational science and engineering. The DDT methodology is based on the idea of federated learning, a subfield of machine learning that promotes knowledge exchange without disclosing actual data. Clients can learn an aggregated model cooperatively using this method while maintaining complete client-specific training data. We use a variety of dynamical systems, which are frequently used as prototypes for simulating complex transport processes in spatiotemporal systems, to show the viability of the DDT framework. Our findings suggest that constructing highly accurate decentralized digital twins in complex nonlinear spatiotemporal systems may be made possible by federated machine learning.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Randomized Federated Learning Methods for Nonsmooth, Nonconvex, and Hierarchical Optimization (Final Technical Report)

This final technical report summarizes the outcomes of a DOE-funded project on federated scientific machine learning (FL) under nonsmooth, nonconvex, and hierarchical optimization settings. The project develops new mathematical models, algorithms, and theoretical guarantees for decentralized stochastic, bilevel, and minimax optimization problems arising in DOE mission-relevant applications. A unified framework of randomized and zeroth-order federated optimization methods is introduced, providing provable convergence, communication efficiency, and sample-complexity guarantees. The report documents algorithmic design, theoretical analysis, and empirical validation of the proposed federated learning methods. The project also contributes to workforce development through graduate training and dissemination of results via publications and seminars.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

End-To-End Decentralized Transmission Line Protection in IBR-Dominated Weak Grids Using Interpretable Data-Driven Methods

Traditional transmission line protection relies on predictable synchronous-based fault signatures, which frequently fail under the non-standard, current-limited fault characteristics of Inverter-Based Resources (IBRs). This study investigates how to achieve secure, communication-free fault isolation in IBR-dominated weak grids without relying on opaque, computationally heavy "black-box" machine learning algorithms. To address this, we propose a novel, standalone, and inherently interpretable data-driven protection framework. Unlike centralized methods requiring multi-terminal communication, this decentralized approach relies solely on local measurements using a hierarchical linear-kernel Support Vector Machine (SVM). The methodology decomposes the protection task into four sequential stages that mimic traditional protection elements: fault detection and fault direction identification, fault type classification, zone classification, and location estimation. This multi-stage architecture allows for specialized feature engineering at each stage, combining high computational efficiency with logic traceability. The framework's end-to-end performance was validated via C-code and PSCAD/EMTDC co-simulation, utilizing a real-world utility network and an OEM black-box IBR model. The proposed relay achieves 97.2% overall accuracy and provides a reliable trip decision within a 2.5-cycle window. The results confirm 100% accuracy in fundamental fault detection, reliable zone selectivity across low to moderate fault resistances, and robust security against non-fault transients, proving its immediate viability for integration into commercial numerical relays.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2025

CAFE AU LAIT: Compute-Aware Federated Augmented Low-Rank AI Training

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.

Wang, Jiayi [ORNL]↗
DOE OSTI2023

Reinforcement Learning-based Output Structured Feedback for Distributed Multi-Area Power System Frequency Control

Load frequency control (LFC) is a key factor to maintain the stable frequency in multi-area power systems. As the modern power systems evolve from centralized to decentralized paradigm, LFC needs to consider the decentralized scheme that considers limited information from the information-exchange graph for the generator control of each interconnected area. This paper aims to solve a data-driven constrained LQR problem with mean-variance risk constraints and output structured feedback, and applies this framework to solve the LFC problem in multi-area power systems. By reformulating the constrained optimization problem into a minimax problem, the stochastic gradient descent max-oracle (SGDmax) algorithm with zero-order policy gradient (ZOPG) is adopted to find the optimal feedback gain from the learning, while guaranteeing the convergence. In addition, to improve the adaptation of the proposed learning method to new or varying models, we construct an emulator grid that approximates the dynamics of a physical grid and performs training based on this model. Once the feedback gain is obtained from the emulator grid, it is applied to the physical grid with a robustness test to check whether the controller from the approximated emulator applies to the actual system. Numerical tests show that the obtained feedback controller can successfully control the frequency of each area, while mitigating the uncertainty from the loads, with reliable robustness that ensures the adaptability of the obtained feedback gain to the actual physical grid.

Kwon, Kyung-bin↗
DOE OSTI2026

Signal Whisperers: Enhancing Wireless Reception Using DRL-Guided Reflector Arrays

This paper presents a multi-agent reinforcement learning (MARL) approach for controlling adjustable metallic reflector arrays to enhance wireless signal reception in non-line-of-sight (NLOS) scenarios. Unlike conventional reconfigurable intelligent surfaces (RIS) that require complex channel estimation, our system employs a centralized training with decentralized execution (CTDE) paradigm where individual agents corresponding to reflector segments autonomously optimize reflector element orientation in three-dimensional space using spatial intelligence based on user location information. Through extensive ray-tracing simulations with dynamic user mobility, the proposed multi-agent beam-focusing framework demonstrates substantial performance improvements over single-agent reinforcement learning baselines, while maintaining rapid adaptation to user movement within one simulation step. Comprehensive evaluation across varying user densities and reflector configurations validates system scalability and robustness. The results demonstrate the potential of learning-based approaches for adaptive wireless propagation control.

deep reinforcement learning↗
DOE OSTI2022

Vulnerability and resilience of urban energy ecosystems to extreme climate events: A systematic review and perspectives

We reviewed the present studies on the vulnerability and resilience of the energy ecosystem (most parts of the energy ecosystem), considering extreme climate events. This study revealed that the increased interactions formed during the transformation of the energy landscape into an ecosystem could notably increase the vulnerability of the energy infrastructure. Such complex ecosystem cannot be assessed using the present state of the art models used by the energy system modelers. Therefore, this study introduces a novel analogy known as the COVID analogy to understand the propagation of disruption within and beyond the energy ecosystem and organized the present state of the art based on the COVID analogy. The analogy helps to categorize the vulnerability of the energy infrastructure into three stages. The study revealed that although there are many publications covering the vulnerability and resilience of the energy infrastructure, considering extreme climate events, the majority are focused on the direct impact of extreme climate on the energy ecosystem. In addition, most of the studies do not consider the impact of future climate variations during this assessment. The propagation of disruptions was assessed mainly for wildfires and hurricanes. Further, there is a clear research gap in considering vulnerability assessment for interconnected energy infrastructure. Here, the transformation of energy systems into a complex ecosystem notably increases the complexity, making it difficult to assess vulnerability and resilience. A shift from a centralized to decentralized modeling architecture could be beneficial when considering the complexities brought by that transformation. Hybrid models consisting of both physical and data-driven machine learning techniques could also be beneficial in this context.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2025

Network Slicing for Federated Learning in Operational Technology Environment

Industrial Control Systems (ICS) and Supervisory Control and Data Acquisition (SCADA) environments are essential to modern infrastructure, facing challenges in ensuring low-latency, high-throughput communication while mitigating cyber threats. This paper presents a framework integrating Federated Learning (FL) and network slicing with Quality of Service (QoS) to enable real-time monitoring without disrupting OT operations. Leveraging digital twin technology and Network Function Virtualization (NFV), the architecture supports predictive analytics and Industry 4.0 requirements. FL facilitates decentralized model training, preserving data privacy and scalability, though it introduces potential throughput constraints. Network slicing addresses this by creating dedicated virtualized segments optimized for performance and security. Advanced fault tolerance at the container and instance levels enhances system reliability. The proposed architecture ensures high throughput, low latency, and secure orchestration for real-time anomaly detection in OT networks. Performance evaluations validate its efficiency in throughput, deployment, and learning accuracy, providing a robust foundation for future ICS automation and data-driven decision-making.

Delgado, Brian G. Rodiles [University of Texas at ↗