Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “online adaptivity”

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 OSTI2023

Online evolutionary neural architecture search for multivariate non-stationary time series forecasting

Time series forecasting (TSF) is one of the most important tasks in data science. TSF models are usually pre-trained with historical data and then applied on future unseen datapoints. However, real-world time series data is usually non-stationary and models trained offline usually face problems from data drift. Models trained and designed in an offline fashion can not quickly adapt to changes quickly or be deployed in real-time. To address these issues, this work presents the Online NeuroEvolution-based Neural Architecture Search (ONE-NAS) algorithm, which is a novel neural architecture search method capable of automatically designing and dynamically training recurrent neural networks (RNNs) for online forecasting tasks. Without any pre-training, ONE-NAS utilizes populations of RNNs that are continuously updated with new network structures and weights in response to new multivariate input data. ONE-NAS is tested on real-world, large-scale multivariate wind turbine data as well as the univariate Dow Jones Industrial Average (DJIA) dataset. These results demonstrate that ONE-NAS outperforms traditional statistical time series forecasting methods, including online linear regression, fixed long short-term memory (LSTM) and gated recurrent unit (GRU) models trained online, as well as state-of-the-art, online ARIMA strategies. Additionally, results show that utilizing multiple populations of RNNs which are periodically repopulated provide significant performance improvements, allowing this online neural network architecture design and training to be successful.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Digital twin framework for PIP-II linac: AI-driven multi-scale modeling from ion source to 800 MeV

The PIP-II superconducting linac at Fermilab is designed to deliver multi-megawatt proton beams for neutrino physics and other high-intensity applications. To expedite commissioning and enhance operational reliability, we have developed an EPICS-based data flow framework that seamlessly integrates digital twins (DT) with physical twins (PT). These digital twins comprise high-fidelity beam dynamics models or data-driven surrogate models connected to their physical counterparts through real-time diagnostics and advanced machine-learning algorithms.Central to this framework is Linac_Gen, an accelerated simulation tool that incorporates convolutional neural networks, random forests, and genetic algorithms to provide up to a tenfold speedup in optimizing the accelerator geometry model. An EPICS translator layer ensures interoperability by efficiently mapping lattice parameters across diverse simulation platforms.Our EPICS-based framework supports multiple operational modes—monitoring, passive learning, closed-loop control, and online learning—covering the entire machine lifecycle. By leveraging HPC resources and multi-objective optimization techniques, the digital twin enables adaptive trajectory correction, real-time fault detection, and predictive modeling of beam stability. This comprehensive approach paves the way for robust, high-intensity operation and data-driven accelerator R&D at Fermilab.

Pathak, Abhishek [Fermilab]↗
DOE OSTI2023

A Hardware and Software Co-design Framework for Energy Efficient Neuromorphic Systems

Neuromorphic systems can be realized by a variety of algorithms and architectures. A common understanding is that spiking neuromorphic designs, which encode information into spatio-temporal spiking events, are both a biologically-accurate and efficient way of processing information. However, representing the information through timing relationships induces sophisticated circuit designs in traditional CMOS-based implementations. In recent years, high-capacity resistive memory (RRAM, aka, memristor) has demonstrated great potential in mimicking synaptic behaviors. Several RRAM-based spiking neuromorphic designs exist, most of which focus on rate coding schemes. These designs simplify circuit implementations of neuron models and explore challenges such as unsatisfactory speed, resolution, and performance. As an alternative, we will explore temporal coding spiking neuromorphic systems that encode information as the relative timing of neuron activations (spikes), which have been proven to be more adaptive and energy-efficient. Developing a neuromorphic system for spiking neural network (SNN) inference and online training, however, faces some major technical challenges: (1) It lacks circuit implementation support for temporal-coding SNN to achieve satisfying power efficiency and accuracy; (2) Although existing research works have investigated memristive synapse and neuron designs for spike-timing-dependent plasticity, the non-ideal conditions in implementation, such as device variations and signal degradation, degrade online learning accuracy of large scale systems; and (3) Non-optimized, inter-layer data traffic in SNNs, leads to unnecessary data communication costs. In this project, we plan to address these challenges by a hardware and software co-design framework that incorporates solutions at the circuit, architecture, and algorithm levels. At the circuit-level, we will elaborate on the in-situ SNN processing element designs for supporting both inference and online training modes. Variation-aware schemes will be studied to improve reliability. At the architecture level, we propose a pipelined, asynchronous architecture to retain the timing resolution of spikes. At the algorithm level, we will investigate an innovative SNN training algorithm for enabling activation sparsification and reducing unnecessary data communication costs. This neuromorphic system will provide an effective solution to real-life energy-constrained applications and significantly contribute to the exploration of next-generation high-performance computing systems under the DOE context.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

Safely Exploring Solar: A Guide for Austin Energy Customers

It's easy to get overwhelmed as you start to explore your solar options. There is a wealth of information available out there, particularly online, and it can be hard to know who to trust. This informational guide has been adapted from Austin Energy's Solar Education Course and other national best practice resources, as of May 1, 2023. It will help you understand some of the key concepts and resources available to help you on your solar journey if you have a home in Austin Energy's service territory and are considering installing solar. This document includes: (1) Austin Energy Programs and Services Related to Solar; (2) Tips for Spotting a Solar Scam; (3) Things to Know When Designing Your System; (4) Key Considerations When Shopping for a Solar Contractor; and (5) Final Takeaways.

14 SOLAR ENERGY↗
DOE OSTI2023

Enabling Floating Solar Photovoltaic (FPV) Deployment: FPV Technical Potential Assessment for Southeast Asia

Southeast Asia (SE Asia) is a region with growing energy demand and increasing development of floating solar photovoltaic (FPV) systems, which can help meet countries' renewable energy and energy security goals. This study uses a high-level geospatial assessment methodology to estimate the technical potential for monofacial and bifacial FPV on reservoirs and natural waterbodies in the ten countries within the Association of Southeast Asian Nations (ASEAN). Technical potential consists of the suitable waterbody area for FPV development (km2), the capacity of FPV that could be installed on this suitable area (MW), and the annual energy that could be generated from these installations (GWh/year). This first-of-its-kind FPV technical potential assessment for SE Asia can help policymakers and planners better understand the role that FPV could play in meeting regional energy demand and can ultimately guide investment decisions. Although this work focuses on SE Asia, the methodology may also be applicable for countries in other regions, with adaptations. The FPV technical potential results are also integrated into the Renewable Energy (RE) Data Explorer online tool (https://www.re-explorer.org/).

bifacial↗
DOE OSTI2025

Aggregated DER_A Model Parameterization via Online Moving Horizon Estimation

Here, this paper introduces a methodology for parameterizing the DER_A model using a novel smooth mathematical representation, simplifying the process and preserving accuracy in modeling inverter-based generator (IBG). The methodology employs an online parameterization process that can operate in real-time. The model parameterization process is structured into five sequential steps, each targeting a specific aspect of the DER_A model through moving horizon estimation. This approach adapts to systems with varying voltage and frequency support requirements by selectively applying each step. Simulation results on systems with both known and unknown parameters validate the methodology’s effectiveness. The online moving horizon estimation technique accurately captures the dynamics of the overall system and ensures that the parameterized DER_A model closely mirrors the real system’s voltage, current, and power dynamics. The findings highlight the potential of this methodology to substantially improve and simplify the dynamic modeling of power systems, paving the way for more reliable and robust IBG and grid integration.

42 ENGINEERING↗
DOE OSTI2025

Radio Frequency Field Programable Gate Array Implementation of Reflectometry Cable Monitoring

This document describes the development of a field programable gate array (FPGA) radio frequency system on a chip (RF SoC) adaptation and evaluation of the single-board device to perform both Frequency Domain Reflectometry (FDR) and Spread Spectrum Time Domain Reflectometry (SSTDR) for offline and online cable testing. The work builds on and leverages the work of Pacific Northwest National Laboratory (PNNL) in airport millimeter wave technology by using the same development hardware employed in that program. The work is performed under sponsorship from the U.S. Department of Energy (DOE) Light Water Reactor Sustainability (LWRS) program and the task objective is to confirm and demonstrate feasibility to adapt FPGA technology for a cost-effective multiplexed single-board electronic module to perform cable tests that are equivalent to commercial and laboratory test instruments for FDR and SSTDR cable tests. The developed 2-channel (extendable to 7 channels) system was compared to dedicated and proven test instruments and shown to produce equivalent results on a range of cables and with a range of damage types. The FPGA reflectometry test board is one of several technologies that could facilitate implementation of online monitoring of safety critical cable systems.

42 ENGINEERING↗
DOE OSTI2023

Robust Power System Stability Assessment Against Adversarial Machine Learning-Based Cyberattacks via Online Purification

The increasing complexity associated with renewable generation brings more challenges to power system stability assessment (SA). Data-driven approaches based on machine learning (ML) techniques for stability assessment have received significant research interest and shown their promising performance. However, ML-based models are recognized to be vulnerable to adversarial disturbances, where a slight perturbation to power system measurements could lead to unacceptable errors. To address this issue, this paper develops a novel lightweight mitigation strategy, i.e., robust online stability assessment (ROSA), to enhance the ML-based assessment model against both white-box and the black-box adversarial disturbances (i.e., purification) in the online implementation. The ROSA involves a supervised learning-based module for the primary stability assessment and a self-supervised learning-based module. Further, the two modules are trained jointly with different objective (loss) functions and implemented in sequence. A suitable purification objective and various time-series data augmentation methods are designed for SA applications to tackle adversarial disturbances adaptively. Case studies are performed, and the comparative results have clearly illustrated the competitive, robust accuracy against various adversarial scenarios and verified the effectiveness of the proposed online purification strategy.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2023

A Barrier-Certificated Reinforcement Learning Approach for Enhancing Power System Transient Stability

Increasing integration of renewable resources brings more flexibility and poses new challenges to modern power systems, leading to highly nonlinear and complex dynamics. Here, this paper aims to provide a general solution framework to traditional control problems, such as frequency control and voltage control, which attempt to maintain the stability of either synchronous generators-governed or inverter-governed systems when subjected to a disturbance and simultaneously guarantee operational constraints, providing a complete complement to existing works on control design. Building on reinforcement learning (RL) and control barrier functions, the framework includes two subsystems, i.e., a model-free controller and a barrier-certification system, which discover RL-based control actions and sequentially filter them using a barrier certificate to satisfy operational constraints. Calculating a barrier function is generally challenging for a complex power system. This is addressed by representing the barrier function using neural networks (NNs) and data-based approaches. An adaptive method is introduced to certify the neural barrier function that perseveres barrier conditions, which is more compatible with online implementation. The proposed framework synthesizes a stabilizing controller that satisfies predefined safety regions. The effectiveness of the proposed framework is demonstrated via several comparative case studies.

24 POWER TRANSMISSION AND DISTRIBUTION↗
DOE OSTI2022

Online Learning and Pricing for Service Systems with Reusable Resources

We consider a price-based revenue management problem with finite reusable resources over a finite time horizon T. Customers arrive following a price-dependent Poisson process, and each customer requests one unit of c homogeneous reusable resources. If there is an available unit, the customer gets served within a price-dependent exponentially distributed service time; otherwise, the customer waits in a queue until the next available unit. In this paper, we assume that the firm does not know how the arrival and service rates depend on posted prices, and thus it makes adaptive pricing decisions in each period based only on past observations to maximize the cumulative revenue. Given a discrete price set with cardinality P, we propose two online learning algorithms, termed batch upper confidence bound (BUCB) and batch Thompson sampling (BTS), and prove that the cumulative regret upper bound is O˜(√PT) , which matches the regret lower bound. In establishing the regret, we bound the transient system performance upon price changes via a novel coupling argument, and also generalize bandits to accommodate subexponential rewards. Here, we also extend our approach to models with balking and reneging customers and discuss a continuous price setting. Our numerical experiments demonstrate the efficacy of the proposed BUCB and BTS algorithms.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2025

Online Bayesian State Estimation for Real-Time Monitoring of Growth Kinetics in Thin Film Synthesis

Rapid validation of newly predicted materials through autonomous synthesis requires real-time adaptive control methods that exploit physics knowledge, a capability that is lacking in most systems. Here, in this study, we demonstrate an approach to enable real-time control of thin film synthesis by combining in situ optical diagnostics with a Bayesian state estimation method. We developed a physical model for film growth and applied the direct filter (DF) method for real-time estimation of nucleation and growth rates during pulsed laser deposition (PLD). We validated the approach using simulated and experimental reflectivity data for WSe 2 growth and ultimately deployed the algorithm on an autonomous PLD system during the growth of 1T'-MoTe 2 . The DF robustly estimates growth parameters in real time at early stages of growth, down to 15% monolayer area coverage. This fusion of in situ diagnostics, data assimilation, and physical modeling opens new opportunities in adaptive control of synthesis trajectories toward desired material states.

36 MATERIALS SCIENCE↗
DOE OSTI2025

Online energy consumption forecast for battery electric buses using a learning-free algebraic method

Accurately predicting the energy consumption plays a vital role in battery electric buses (BEBs) route planning and deployment. Based on the algebraic derivative estimation, we present a novel method to forecast the energy consumption in real time. In contrast to the mainstream machine-learning-based methods, the proposed method does not require access to the historical energy consumption data. It eliminates the time-consuming and computationally expensive offline training. Consequently, its prediction performance is not constrained by the quantity and quality of the training data. Moreover, the method can swiftly adapt to new situations not included in the previous driving cycles, which makes it especially suitable for emerging transport modes, e.g., on-demand transit services. In addition, its online execution only involves algebraic calculations, yielding superior calculation efficiency. Using real-world data, we comprehensively compare the performance of the proposed learning-free algebraic method with multiple representative machine-learning-based methods. Finally, the advantages and limitations of the proposed method are discussed in detail.

33 ADVANCED PROPULSION SYSTEMS↗
DOE OSTI2025

Virtual to Physical: Reinforcement Learning to Optimize SNS Particle Accelerator Controls

Complex accelerators must have control systems that can handle dynamic nonlinear environments. This makes traditional control methods unsuitable as they can struggle to adapt to these uncertainties. This provides an ideal environment for reinforcement learning algorithms as they are adaptable and generalizable. We present a reinforcement learning pipeline that can effectively handle the dynamics of a complex accelerator. We test and prove our pipelines capabilities on multiple environments including the Spallation Neutron Source (SNS) and the Beam Test Facility (BTF) at Oakridge National Lab (ORNL). Due to the limited time available to train an online algorithm like reinforcement learning on a real accelerator, we utilize a virtual twin accelerator (VIRAC) developed by ORNL to pretrain the policy and show its ability to converge in the virtual environment. We then test the adaptability of the pretrained RL model by applying it on the real accelerator and comparing the results. Utilizing our Scientific Optimization and Controls Toolkit (SOCT) and open-source standards such as Gymnasium we create and solve for a MEBT orbit correction problem in the SNS and an emittance maximization problem in the BTF. We show how Twin Delayed Deep Deterministic Policy Gradient (TD3) can solve this optimization environment in the virtual accelerator and transfer this policy onto the real accelerator for inference and model retraining. We show how reinforcement learning can be utilized as a control system for complex accelerators and provide a model pipeline for how an implementation performs and can be adapted to new accelerator control problems.

Kasparian, Armen [Thomas Jefferson National Accele↗
DOE OSTI2023

An Online Prototype Toolset for Predicting and Optimizing P&T Performance (FY23 Status Report)

A new web-based toolset is being developed to support ongoing remediation optimization efforts and implementation of an adaptive site management strategy for the 200 West Area Pump-and-Treat (P&T) system at the Hanford Site. This toolset, comprising the well performance index tool and the well optimization pre-screening tool, will offer a user-friendly interface to predict and optimize the P&T well network’s performance at a preliminary level. Efforts in fiscal year (FY) 2023 focused on three main components: updating the existing deep learning model for predicting P&T performance, designing and developing a prototype of a web-based performance index tool, and initiating the conceptual design of the well optimization pre-screening tool. The well performance index tool is based on a pre-trained deep learning model that allows users to select a target contaminant and well screen length, then visualize the predicted performance of potential new wells across the site. The well optimization pre-screening tool includes two separate modules: the pre-computed scenario viewer, which organizes and visualizes offline optimization simulation results, and the quick analysis module, which provides real-time model prediction using user-specified well locations. In FY24, the plan is to add web-based applications to SOCRATES for both the well performance prediction tool and the optimization prescreening tool, with accompanying user and theory guides. These tools are intended to enable an accessible, easily applied, and transparent approach to remedy planning and decision-making.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Online transfer learning strategy for enhancing the scalability and deployment of deep reinforcement learning control in smart buildings

In recent years, advanced control strategies based on Deep Reinforcement Learning (DRL) proved to be effective in optimizing the management of integrated energy systems in buildings, reducing energy costs and improving indoor comfort conditions when compared to traditional reactive controllers. However, the scalability and implementation of DRL controllers are still limited since they require a considerable amount of time before converging to a near-optimal solution. This issue is currently addressed in literature through the offline pre-training of the DRL agent. However this solution results in two main critical issues: (1) the need to develop a building surrogate model to perform the training task, and (2) the need to perform a fine-tuning process over several training episodes to obtain a near-optimal control policy. In this context, this paper introduces an Online Transfer Learning (OTL) strategy that exploits two knowledge-sharing techniques, weight-initialization and imitation learning, to transfer a DRL control policy from a source office building to various target buildings in a simulation environment coupling EnergyPlus and Python. A DRL controller based on discrete Soft Actor–Critic (SAC) is trained on the source building to manage the operation of a cooling system consisting of a chiller and a thermal storage. Several target buildings are defined to benchmark the performance of the OTL strategy with that of a Rule-Based Controller (RBC) and two DRL-based control strategies, deployed in offline and online fashion. The strategy adopted for OTL emulates the real world implementation with a simulation process by implementing the transferred DRL agent for a single episode in the target buildings. Target buildings have the same geometrical features and are served by the same energy system as the source building, but differ in terms of weather conditions, electricity price schedules, occupancy patterns, and building envelope efficiency levels. The results show that the OTL strategy can reduce the cumulated sum of temperature violations on average by 50% and 80% respectively when compared to RBC and online DRL while enhancing the energy system operation with electricity cost savings ranging between 20% and 40%. Furthermore, the OTL agent performs slightly worse than the offline DRL controller but it does not require any modeling effort and can be implemented directly on target buildings emulating a real-world implementation.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
DOE OSTI2026

FLYING SERVING: On-the-Fly Parallelism Switching for Large Language Model Serving

Production LLM serving must simultaneously deliver high throughput, low latency, and sufficient context capacity under non-stationary traffic and mixed request requirements. Data parallelism (DP) maximizes throughput by running independent replicas, while tensor parallelism (TP) reduces per-request latency and pools memory for long-context inference. However, existing serving stacks typically commit to a static parallelism configuration at deployment; adapting to bursts, priorities, or long-context requests is often disruptive and slow. We present Flying Serving, a vLLM-based system that enables online DP-TP switching without restarting engine workers. Flying Serving makes reconfiguration practical by virtualizing the state that would otherwise force data movement: (i) a zero-copy Model Weights Manager that exposes TP shard views on demand, (ii) a KV Cache Adaptor that preserves request KV state across DP/TP layouts, (iii) an eagerly initialized Communicator Pool to amortize collective setup, and (iv) a deadlock-free scheduler that coordinates safe transitions under execution skew. Across three popular LLMs and realistic serving scenarios, Flying Serving improves performance by up to 4.79 × under high load and 3.47 × under low load while supporting latency- and memory-driven requests.

Gao, Shouwei [ORNL]↗
DOE OSTI2026

Microsecond-latency feedback at a particle accelerator by online reinforcement learning on hardware

The commissioning and operation of future large-scale scientific experiments will challenge current tuning and control methods. Reinforcement learning (RL) algorithms are a promising solution due to their ability to dynamically adapt to changing environments and consider delayed consequences. In many real-world applications, RL policies must produce actions in real time, often within microseconds to milliseconds, imposing significant constraints on system latency and computational overhead that conventional machine learning libraries are not designed to handle. To control phenomena in real time at these timescales, RL needs to be deployed on-the-edge, namely on dedicated hardware located near the system it controls, without relying on a host CPU or cloud-based inference. In this work we present the design and deployment of an experience accumulator system in a particle accelerator. In this system, deep-RL algorithms run using hardware acceleration and act within a few microseconds, enabling the use of RL for control of phenomena like beam instabilities. The training uses the collected data offline to reduce the number of operations carried out on the acceleration hardware. The proposed architecture was tested in real experimental conditions at the Karlsruhe research accelerator, a synchrotron light source, where the system was used to control artificially induced horizontal betatron oscillations in real-time, with a control loop period of just 2.7 μs. The results showed a performance comparable to the commercial feedback system available at the accelerator, demonstrating the viability and potential of this approach. Due to the self-learning and reconfiguration capability of this implementation, a seamless application to other control problems is possible. Applications range from particle accelerators to large-scale research and industrial facilities.

FPGA↗
DOE OSTI2025

Three-dimensional modeling of hyphal fusion, branching, and nutrient transport in filamentous fungi

Fungi exhibit behaviors distinct from other microbes. Filamentous fungi grow by extending complex networks of branched filaments collectively referred to as the mycelium. These networks can expand over large distances and traverse low-nutrient areas by translocating nutrients through the filament network. This spatial characteristic makes filamentous fungi crucial for soil ecosystems, supporting stable microbial communities and promoting plant growth. However, simulating these behaviors is complex. The elongated nature of fungal compartments results in different mechanical interactions compared to the commonly modeled spherical bacteria. These detailed hyphal mechanics require specialized consideration and are often excluded from conventional fungal simulation packages. Additionally, the extensive fungal networks in nature demand computationally intensive simulations, necessitating high-performance algorithms. Therefore, realistic fungi simulations require specialized software. Here, we introduce a fungal modeling expansion to the high-performance biological modelling and interface exchange (bmx) software suite. bmx leverages adaptive mesh refinement in AMReX for chemical diffusion and incorporates a full mechanical model for bacterial cells, accelerated by GPUs. By extending bmx to model filamentous particles, we demonstrate the formation of complex filament networks through interactions like hyphal branching and fusion (anastomosis). We show that the networks produced match real-world fungal structures through various metrics. This work supports computational studies of fungal growth dynamics and can be adapted to investigate the growth of other filamentous structures in biology or materials science. The expanded-BMX package is open-sourced and is available online.

Cell mechanics↗