SEARCH · Engineering Papers

Results for “network baseline”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 217 records · Page 12

All sources NASA NTRS DOE OSTI

DOE OSTI2020

In situ compression artifact removal in scientific data using deep transfer learning and experience replay

The massive amount of data produced during simulation on high-performance computers has grown exponentially over the past decade, exacerbating the need for streaming compression and decompression methods for efficient storage and transfer of this data---key to realizing the full potential of large-scale computational science. Lossy compression approaches such as JPEG when applied to scientific simulation data realized as a stream of images can achieve good compression rates but at the cost of introducing compression artifacts and loss of information. This paper develops a unified framework for in situ compression artifact removal in which the fully convolutional neural network architectures are combined with scalable training, transfer learning, and experience replay to achieve superior accuracy and efficiency while significantly decreasing the storage footprint as compared with the traditional optimization-based approaches. We demonstrate the proposed approach and compare it with compressed sensing postprocessing and other baseline deep learning models using climate simulations and nuclear reactor simulations, both of which are driven by hyperbolic partial differential equations. Our approach when applied to remove the compression artifacts on the JPEG-compressed nuclear reactor simulation data (using a transfer-trained model that was pretrained on the climate simulation data and updated incrementally as the nuclear reactor simulation progressed), achieved a significant improvement---mean peak signal-to-noise ratio of 42.438 as compared with 27.725 obtained with the compressed sensing approach.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2026

Adaptation of virtual synchronous generators to dynamic conditions in power grids

Virtual synchronous generators (VSGs) are widely adopted as grid-forming controls for inverter-based resources. However, when grid conditions vary significantly as characterized by changes in short-circuit ratio (SCR) and the reactance-to-resistance (X/R) ratio, fixed-gain designs and the commonly used P–Q decoupling assumption can become inaccurate. Such conditions can degrade transient power performance, leading to oscillations, prolonged settling, and overshoot, particularly in stiff-grid operating points. This paper quantifies how grid strength and impedance-dependent coupling affect the active–reactive power dynamics of a conventional VSG over a broad range of SCR and X/R values. An adaptive VSG tuning framework is then developed by combining (i) a coupling-explicit, impedance-parameterized state-space model to enable systematic controller synthesis, (ii) a full-state-feedback law designed via pole placement to meet prescribed damping and settling-time specifications, and (iii) a physics-informed neural network (PINN)–based online grid-impedance estimator that updates controller gains in real time as grid conditions vary. Offline simulations in MATLAB/Simulink and real-time validation on an OPAL-RT platform show that the proposed method preserves consistent damping and settling behavior with reduced overshoot across wide SCR and X/R ranges, compared with fixed-gain VSG baselines.

Adaptive control↗

DOE OSTI2024

On Building Predictive Digital Twin Incorporating Wave Predicting Capabilities: Case Study on UMaine Experimental Campaign - FOCAL

The response of floating wind turbines (FWT) are susceptible to stochastic wave variations. For the optimal operation of FWT, a comprehensive understanding of the phaseresolved wave dynamics and the consequential system response is crucial for real-time monitoring and control. A multi-variate, multi-step, long short term memory (MLSTM), a type of recurrent neural network (RNN) is used to capture complex system dynamics for real-time application. Results indicate that the integration of a wave prediction-reconstruction (WRP) model substantially enhances prediction accuracy by 50% on average relative to the baseline model. The improvement is consistent across various wave extremity and prediction horizons, thereby significantly broadening the scope for timely and precise predictive capabilities.

17 WIND ENERGY↗

DOE OSTI2022

Longitudinal Trajectories of Memory Performance in Patients with Early-Stage Breast Cancer

Background. While breast cancer and its treatments may affect cognition, the longitudinal trajectories of cognition among those receiving differing cancer treatment types remain poorly understood. Prior research suggests hippocampal-prefrontal cortex network integrity may influence cognition, although how this network predicts performance over time remains unclear. Methods. We conducted a prospective trial including 69 patients with early-stage breast cancer receiving adjuvant therapy and 12 controls. Longitudinal cognitive testing was conducted at four visits: pretreatment-baseline, 6-7 months, 14-15 months, and 23-24 months. Cognitive composite scores of episodic memory, executive functioning, and processing speed were assessed at each timepoint. Baseline structural MRI was obtained in a subset of these participants, and hippocampal and prefrontal cortex regional volumes were extracted. Results. Longitudinal linear mixed modeling revealed significant group by time interactions on memory performance, controlling for age and education. Post hoc analyses revealed this effect was driven by patients treated with chemotherapy or chemotherapy plus hormone therapy, who demonstrated the least improvement in memory scores over time. Treatment group did not significantly influence the relationship between time and processing speed or executive functioning. Neither pretreatment hippocampal nor prefrontal volume differed between groups, and there were no significant group by time by baseline regional volume effects on cognition. Conclusion. Patients with early-stage breast cancer treated with chemotherapy or chemotherapy plus hormone therapy benefit less from practice effects seen in healthy controls on memory tests. Loss of longitudinal practice effect may be a new and clinically relevant measure for capturing patients’ experience of cognitive difficulties after treatment.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2022

Estimating Fast Charging Infrastructure Requirements to Fully Electrify Ride-Hailing Fleets Across the United States

Ride-hailing electrification is made challenging by a variety of factors, including limited driver access to overnight charging and a nascent network of public direct-current fast charging (DCFC). This article projects the DCFC infrastructure needed to electrify ride-hailing across 384 cities in the United States. Research leveraging a novel infrastructure projection tool, Electric Vehicle Infrastructure Tool for On-Demand Mobility Services model (EVI-OnDemand), estimates that 25,400 DCFC ports capable of charging vehicles at a mean power of 150 kW are required to electrify 1.45 million ride-hailing vehicles in the baseline scenario. Results show that ride-hailing vehicles require 17.5 DCFC ports per 1000 vehicles, three times that of personal electric vehicles (EVs). Infrastructure demand is also shown to vary across cities; 63% more DCFC ports are needed to support 1000 battery EVs in Chicago versus Miami. The analysis also includes sensitivity studies that explore variation in charging demand across input assumptions, finding that charging power, vehicle class, overnight charging access rates, and port utilization influence the network size needed. Projections vary from 18,600 to 41,300 DCFC ports across sensitivity scenarios, indicating that ride-hailing electrification will require significant expansion of access to fast charging even in the most optimistic scenarios, and investments into supporting assets can reduce the scale of the public charging expansion needed.

33 ADVANCED PROPULSION SYSTEMS↗

DOE OSTI2025

Anomaly Detection in Seismic Data with Deep Learning: Application for Instrument Failure Detection and Forecasting

Seismic data quality assessment (QA) is the first and one of the most important steps before conducting any further data analysis. Traditional methods involve checking various metrics, such as spike detection and power spectral density, by setting strict thresholds or comparing data against synthetic benchmarks. However, these approaches often rely on pre-existing knowledge and assumptions about data anomalies, leading to potential misclassification of unusual cases. Here, in this study, we propose a deep autoencoder model, an unsupervised learning approach that evaluates data quality without making assumptions about normal and anomalous data, which can be used to identify deviations in recorded data that may indicate nascent instrument failure. We test the model with the U.S. International Monitoring System (IMS) seismic stations and demonstrate the capability of detecting anomalies on a monthly scale. This could prompt station operators to examine potential problems early, allowing sufficient time for instrument maintenance to prevent data outages. In addition, we use a new manually selected testing dataset to compare our model performance against two supervised machine learning (ML) approaches and a standard QA package, as baseline models. When applied to the dataset containing known data anomalies, performance of the supervised and unsupervised ML approaches is similar, with an accuracy of 88.1% for our model compared to ∼90% for the supervised ML approach and 78.2% for the standard QA package. Our model outperforms the baseline models when applied to new stations, where new types of data anomalies can be station-specific and not included in the training dataset. Finally, we show model transferability by training the model with data from the Global Seismograph Network only and applying it to the IMS network data. The results suggest that our model is generalizable and can be applied to new stations with good accuracy.

Lin, Jiun-Ting [Lawrence Livermore National Labora↗

DOE OSTI2025

Voucher Opportunity 5-15: Independent Assessment of Monitoring, Reporting, and Verification (MRV) Technologies and Practices for Enhanced Rock Weathering (CRADA 718) Abstract

Development of robust, transparent, and precise monitoring, reporting, and verification (MRV) technologies and practices is critical for carbon dioxide removal (CDR) project developers to comply with regulatory and permitting requirements, voluntary carbon market (VCM) protocols, and to ensure safety while reducing environmental impacts. Enhanced rock weathering (ERW)-based CDR technologies focus on removing atmospheric carbon through conversion into thermodynamically stable solid or aqueous carbonate forms for permanent storage (i.e., mineralization). This highly durable form of CDR enhances naturally occurring silicate rock weathering cycles by optimizing application of finely-ground silicate rock particles (i.e., from basalt) on terrestrial agricultural lands to accelerate natural silicate rock weathering and mineralization. Enhanced rock weathering may also provide improved crop yields and enhance soil health. A critical aspect for commercialization of these technologies is the development of MRV to quantify the net removal and durable storage of atmospheric CO 2 . For ERW systems, it is essential to accurately characterize the mineral feedstock selected for application to establish the baseline geochemical composition, mineral dissolution rates, and carbon removal potential of the feedstocks to estimate overall net removal. Given the difficulty with conducting MRV for ERW in diverse soil/environment types, over large application areas, and due to complex chemical reaction networks, this project will accelerate understanding towards consensus on best practices for MRV. The overall objectives of the proposed voucher project are to: 1) Characterize and analyze feedstock(s) intended for ERW field application by Lithos Carbon (“Voucher Recipient”/ “CRADA Participant”) to determine overall mineralization potential; 2) Facilitate knowledge transfer and documentation of experimental protocols, instrumentation, and other relevant best practices; and 3) Support the Voucher Recipient’s broader technology commercialization and ERW Research Facility development plans. This work will align with the Voucher Recipient’s MRV plans for field sites and build upon complementary efforts conducted by PNNL on mineralization MRV.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2024

SUBTASK 1.6 – BASIN ELECTRIC CARBON STORAGE RESEARCH PROJECT: NOVEL MONITORING TECHNIQUES

The Energy & Environmental Research Center (EERC) conducted baseline activities associated with an applied research project at Basin Electric Power Cooperative’s (Basin’s) carbon capture and storage (CCS) site in Beulah, North Dakota, to establish novel carbon storage-monitoring techniques as commercial methods under Cooperative Agreement No. DE-FE0024233, Subtask 1.6. The following report summarizes the baseline activities performed and briefly describes the subsequent (operational monitoring) activities that have been proposed to the U.S. Department of Energy (DOE) as part of the overall project to develop and demonstrate novel monitoring techniques at North America’s largest permitted CCS operation. Dakota Gasification Company (DGC), a wholly owned subsidiary of Basin, owns and operates the Great Plains Synfuels Plant (GPSP) approximately 5 miles northwest of the town of Beulah, North Dakota (Figure 1). In 2023, DGC received approval from the North Dakota Industrial Commission (NDIC) to develop a storage facility on-site for injecting a stream of carbon dioxide (CO2) captured from GPSP. DGC will transport the captured CO2 stream with approximately 6.8 miles of transmission lines that extend north of GPSP and inject >1 million tonnes (MMt) of CO2 annually (>1 MMt/yr) over a 12-year period with up to six underground injection control (UIC) Class VI-compliant injection wells completed in the Broom Creek Formation, a predominantly sandstone reservoir and saline aquifer underlying GPSP. The Broom Creek Formation lies approximately 5900 feet (ft) below ground surface (bgs) at GPSP. The commercial scale (i.e., >1 MMt/yr) of DGC’s permitted carbon storage project is ideal for developing and testing the novel monitoring techniques included within Subtask 1.6. The goals of this project are to demonstrate 1) the cost-effectiveness of novel monitoring technologies included as part of this research, 2) technology capability for tracking the CO2 plume and/or associated pressure response in the subsurface and monitoring out-of-zone migration, and 3) compliance with UIC Class VI program requirements. The research activities proposed for the overall project include 1) design of an automated, integrated, modular (AIM) monitoring station; 2) time-lapse electromagnetic (EM) field surveys; 3) drone-based surveillance studies; 4) time-lapse monitoring with seismic methods; 5) advanced wellbore-monitoring methods; 6) deployment of an AIM monitoring network; 7) EM monitoring of CO2 with real-time data processing; 8) continued seasonal drone-based surveillance studies; 9) seismic monitoring with passive and active surveys; and 10) wellbore monitoring with nuclear magnetic resonance (NMR) for near-surface characterization. Completion of Activities 1.0–5.0 (baseline activities) are described in this report. Upon authorization of funding by DOE, the EERC will initiate Activities 6.0– 10.0 (operational monitoring activities). Current state-of-the-art (SOA) carbon storage-monitoring techniques require countless labor hours dedicated to the acquisition of data. Once data are gathered, these SOA techniques often rely on commercial facilities to process raw data from the field. However, it is anticipated that next-generation monitoring techniques, such as those being demonstrated, will lower acquisition footprints, be less operationally intensive, and improve data acquisition efficiencies. These new techniques are more conducive to the application of machine learning, artificial intelligence, and automation, thus providing a pathway for integration into active control systems, informing site operability, and improving the integration of data for future CCS projects across the United States. Additionally, reclaimed and active mining lands are present within the project site, creating a unique opportunity to demonstrate the effectiveness of remote sensing and surface-based geophysics monitoring techniques at similar project sites that may include disturbed, unconsolidated, or actively excavated near-surface environments. The efforts included in the overall project will produce necessary designs, learnings, and data acquired during the baseline and operational monitoring periods that are necessary for time-lapse demonstration and validation of the described monitoring techniques. In addition, it is anticipated that the monitoring technologies included in this study will be compliant with UIC Class VI requirements to enable the potential for implementation at other CCS sites across the United States.

42 ENGINEERING↗

DOE OSTI2024

Anticipating Technical Expertise and Capability Evolution in Research Communities Using Dynamic Graph Transformers

The ability to anticipate global technical expertise and capability evolution trends is essential for national and global security, especially in safety-critical domains such as nuclear nonproliferation (NN) and rapidly emerging fields like artificial intelligence (AI). Here, in this work, we extend traditional statistical relational learning approaches (e.g., link prediction in collaboration networks) and formulate a problem of anticipating technical expertise and capability evolution using dynamic heterogeneous graph representations. We develop novel capabilities to forecast collaboration patterns, authorship behavior, and technical capability evolution at different granularities (e.g., scientist and institution levels) in two distinct research fields. We implement a dynamic graph transformer (DGT) neural architecture, which pushes the state-of-the-art graph neural network models by: 1) forecasting heterogeneous (rather than homogeneous) nodes and edges; and 2) relying on both discrete- and continuous-time inputs. We demonstrate that our DGT models predict collaboration, partnership, and expertise patterns with 0.26, 0.73, and 0.53 mean reciprocal rank values for AI and 0.48, 0.93, and 0.22 for NN domains. DGT model performance exceeds the best-performing static graph baseline models by 30%–80% across AI and NN domains. Our findings demonstrate that DGT models boost inductive task performance when previously unseen nodes appear in the test data for the domains with emerging collaboration patterns (e.g., AI). Specifically, models accurately predict which established scientists will collaborate with early career scientists and vice versa in the AI domain.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2023

Physical Insights From the Multidecadal Prediction of North Atlantic Sea Surface Temperature Variability Using Explainable Neural Networks

Abstract North Atlantic sea surface temperatures (NASST), particularly in the subpolar region, are among the most predictable in the world's oceans. However, the relative importance of atmospheric and oceanic controls on their variability at multidecadal timescales remain uncertain. Neural networks (NNs) are trained to examine the relative importance of oceanic and atmospheric predictors in predicting the NASST state in the Community Earth System Model 1 (CESM1). In the presence of external forcings, oceanic predictors outperform atmospheric predictors, persistence, and random chance baselines out to 25‐year leadtimes. Layer‐wise relevance propagation is used to unveil the sources of predictability, and reveal that NNs consistently rely upon the Gulf Stream‐North Atlantic Current region for accurate predictions. Additionally, CESM1‐trained NNs successfully predict the phasing of multidecadal variability in an observational data set, suggesting consistency in physical processes driving NASST variability between CESM1 and observations.

Geology↗

DOE OSTI2021

InversionNet3D: Efficient and Scalable Learning for 3-D Full-Waveform Inversion

Seismic full-waveform inversion (FWI) techniques aim to find a high-resolution subsurface geophysical model provided with waveform data. Some recent effort in data-driven FWI has shown some encouraging results in obtaining 2-D velocity maps. However, due to high computational complexity and large memory consumption, the reconstruction of 3-D high-resolution velocity maps via deep networks is still a great challenge. Here, in this article, we present InversionNet3D (InvNet3D), an efficient and scalable encoder–decoder network for 3-D FWI. The proposed method employs group convolution in the encoder to establish an effective hierarchy for learning information from multiple sources while cutting down unnecessary parameters and operations at the same time. The introduction of invertible layers further reduces the memory consumption of intermediate features during training and, thus, enables the development of deeper networks with more layers and higher capacity as required by different application scenarios. Experiments on the 3-D Kimberlina dataset demonstrate that InvNet3D achieves state-of-the-art reconstruction performance with lower computational cost and lower memory footprint compared to the baseline.

58 GEOSCIENCES↗

DOE OSTI2020

Influence of Process Parameters and Alloy Composition on Crack Mitigation in Selective Laser Melting

Microcracking and residual stresses are key limitations of laser powder bed fusion (LPBF), an additive manufacturing (AM) technique that uses a high power laser to consolidate successive layers of metal powder. For tungsten, these microcracks find their origin in the combination of a ductile-to-brittle transition (DBT) between 200°C and 400°C and high residual stresses. This work utilized in situ high speed video to capture the cracking mechanisms, and combined the experimental results with thermomechanical modeling to unveil correlations between crack network morphology and process parameter-related variables, such as the local temperature and residual stress distributions. Consequently, preheating and alloying with rare earth oxides were adopted as possible crack mitigation strategies, the efficacy of which was tested against the initial fundamental baseline results. Preheating temperatures above 500°C eliminated all cracking, though this threshold is expected to be higher when tungsten powder (higher oxygen content) is introduced. Alloying can serve as an active oxygen getter in the system, but the rare earth oxides in this work were too large to have significant contributions to crack-mitigation.

36 MATERIALS SCIENCE↗

DOE OSTI2025

DNN-based Signal Processing for Liquid Argon Time Projection Chambers

We investigate a deep learning-based signal processing for liquid argon time projection chambers (LArTPCs), a leading detector technology in neutrino physics. Identifying regions of interest (ROIs) in LArTPCs is challenging due to signal cancellation from bipolar responses and various detector effects observed in real data. We approach ROI identification as an image segmentation task, and employ a U-ResNet architecture. The network is trained on samples that incorporate detector geometry information and include a range of detector variations. Our approach significantly outperforms traditional methods while maintaining robustness across diverse detector conditions. This method has been adopted for signal processing in the Short-Baseline Neutrino program and provides a valuable foundation for future experiments such as the Deep Underground Neutrino Experiment.

Bhat, Avinay [Chicago U.]↗

DOE OSTI2025

Informing Plant Asset Reliability and Availability Through AI-Driven Analysis of Operator Logs

The availability and reliability of nuclear power plant (NPP) structures, systems, and components (SSCs) are critical parameters for NPP safety. Tracking these parameters is necessary but costly and labor-intensive, requiring the collection and evaluation of SSC event data such as shutdowns, startups, and failures. To show how these events are needed for the parameters an example is given: one measure of reliability is based on the number of equipment failure events and the number of run hours (i.e., the time from a startup event to a shutdown event). Here, this work investigates using artificial intelligence (AI) to mine NPP operator log entry texts for SSC event data. Four AI approaches were explored for identifying these events, including natural language processing (NLP) methods, generative AI, generative AI combined with NLP, and topic modeling. A key challenge addressed with all four approaches is the brevity of operator log entries. Among these four a neural network–based NLP method was shown to be the most promising for this application, achieving F1 scores of 86.0% for shutdowns, 92.2% for startups, and 80.4% for failures on a subject-matter-expert-curated dataset from NPP operator logs, compared to a baseline of 66.6% for a random classifier. This shows that NLP methods can perform better than generative AI. Additionally, the NLP methods combined with generative AI were shown to perform better than generative AI alone. Generative AI was most successful at providing the background information for the NLP methods to use. This work demonstrates the potential to use AI to automate parameter collection from NPP operator log entries and other records.

97 - MATHEMATICS AND COMPUTING↗

DOE OSTI2022

A machine learning approach to water quality forecasts and sensor network expansion: Case study in the Wabash River Basin, United States

Abstract Midwestern cities require forecasts of surface nitrate loads to bring additional treatment processes online or activate alternative water supplies. Concurrently, networks of nitrate monitoring stations are being deployed in river basins, co‐locating water quality observations with established stream gauges. However, tools to evaluate the future value of expanded networks to improve water quality forecasts remains challenging. Here, we construct a synthetic data set of stream discharge and nitrate for the Wabash River Basin—one of the United States’ most nutrient polluted basins—using the established Agro‐IBIS and THMB models. Synthetic data enables rapid, unbiased and low‐cost assessment of potential sensor placements to support management objectives, such as near‐term forecasting. Using the synthetic data, we established baseline 1‐day forecasts for surface water nitrate at 12 cities in the basin using support vector machine regression (SVMR; RMSE 0.48–3.3 ppm). Next, we used the SVMRs to evaluate the improvement in forecast performance associated with deployment of additional nitrate sensors. We identified the optimal sensor placement to improve forecasts at each city, and the relative value of sensors at each candidate location. Finally, we assessed the co‐benefit realized by other cities when a sensor is deployed to optimize a forecast at one city, finding significant positive externalities in all cases. Ultimately, our study explores the potential for machine learning to make near‐term predictions and critically evaluate the improvement realized by expanding a monitoring network. While we use nitrate pollution in the Wabash River Basin as a case study, this approach could be readily applied to any problem where the future value of sensors and network design are being evaluated.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2026

Estimating CO 2 fluxes through integrating spatial and temporal input layers via deep learning algorithms

Background Accurate estimation of net ecosystem exchange of CO 2 fluxes (Fc) is essential for understanding carbon cycle processes and assessing ecosystem carbon budgets. However, conventional modeling approaches often emphasize temporal dynamics while overlooking the pronounced spatial heterogeneity within the footprint of eddy covariance (EC) towers, potentially limiting predictive accuracy and interpretability of Fc estimates. To address this challenge, we developed a spatiotemporal model that integrates high-resolution footprint-weighted spatial information with sequential environmental drivers. Results The integrated model combines a deeper graph convolutional network to characterize fine-scale spatial variability within EC footprints and a gated recurrent unit network to capture temporal dependencies in biophysical conditions. Using multi-year flux tower observations, remote sensing vegetation indices and footprint modeling, we evaluate the proposed method across three land cover types. This spatiotemporal model consistently outperforms temporal-only and spatial-only baselines, achieving the highest overall accuracy (R 2 = 0.9569) and the lowest RMSE (1.8128 μmol m −2 s −1 ) and MAE (1.1939 μmol m −2 s −1 ). Performance gains are particularly evident in ecosystems with strong vegetation heterogeneity, where spatial structure substantially modulates Fc variability. Conclusions This study demonstrates the importance of joint modeling spatial heterogeneity and temporal dynamics for improving Fc estimation and provides a robust method for advancing footprint-based Fc estimates across diverse ecosystems, supporting refined assessments of terrestrial carbon fluxes, and enhancing scientific foundations for carbon studies.

CO2 flux estimate↗

DOE OSTI2024

Integration of Decentralized Graph-Based Multi-Agent Reinforcement Learning with Digital Twin for Traffic Signal Optimization

Machine learning (ML) methods, particularly Reinforcement Learning (RL), have gained widespread attention for optimizing traffic signal control in intelligent transportation systems. However, existing ML approaches often exhibit limitations in scalability and adaptability, particularly within large traffic networks. This paper introduces an innovative solution by integrating decentralized graph-based multi-agent reinforcement learning (DGMARL) with a Digital Twin to enhance traffic signal optimization, targeting the reduction of traffic congestion and network-wide fuel consumption associated with vehicle stops and stop delays. In this approach, DGMARL agents are employed to learn traffic state patterns and make informed decisions regarding traffic signal control. The integration with a Digital Twin module further facilitates this process by simulating and replicating the real-time asymmetric traffic behaviors of a complex traffic network. The evaluation of this proposed methodology utilized PTV-Vissim, a traffic simulation software, which also serves as the simulation engine for the Digital Twin. The study focused on the Martin Luther King (MLK) Smart Corridor in Chattanooga, Tennessee, USA, by considering symmetric and asymmetric road layouts and traffic conditions. Comparative analysis against an actuated signal control baseline approach revealed significant improvements. Experiment results demonstrate a remarkable 55.38% reduction in Eco_PI, a developed performance measure capturing the cumulative impact of stops and penalized stop delays on fuel consumption, over a 24 h scenario. In a PM-peak-hour scenario, the average reduction in Eco_PI reached 38.94%, indicating the substantial improvement achieved in optimizing traffic flow and reducing fuel consumption during high-demand periods. These findings underscore the effectiveness of the integrated DGMARL and Digital Twin approach in optimizing traffic signals, contributing to a more sustainable and efficient traffic management system.

actuated signal control↗

DOE OSTI2024

Integration of Decentralized Graph-Based Multi-Agent Reinforcement Learning with Digital Twin for Traffic Signal Optimization

42 ENGINEERING↗