skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


This content will become publicly available on December 19, 2026

Title: A Data-driven Action Recommender System for Power System Operations using Deep Convolutional Neural Networks
The paper proposes an approach for data generation and action recommender system development when small-signal stability assessment is performed using deep learning algorithms. These algorithms are trained on labeled time-series data solving a classification task. In this paper we propose an approach that includes automatically generated labeled data for the action recommender and the deep learning methodology to implement the recommender framework. The deep learning methodology is based on convolutional neural networks (ResNet, Encoder, Time-LeNet) that are tuned for time-series input data and shown the best performance in comparison to other architectures. The proposed approach is validated on synthetic but realistic measurement data from the IEEE 9-bus system as a reference and further applied to a 769-bus system representing a region in the U. S. Eastern Interconnection. The performance of the method is evaluated using accuracy as a most common machine learning metric, as well as precision and recall. We show that the evaluation of the methodology on the generated imbalanced data has to be treated with additional metrics other than accuracy. The training time and the classification performance time is evaluated.  more » « less
Award ID(s):
2231677
PAR ID:
10655336
Author(s) / Creator(s):
; ;
Publisher / Repository:
ResearchGate, DOI: 10.13140/RG.2.2.33102.52802
Date Published:
Subject(s) / Keyword(s):
Convolutional neural networks, deep learning, recommender system, remedial actions, security assessment
Format(s):
Medium: X
Institution:
ResearchGate
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; (, Electric Power Systems Research)
    Golpira, Hemin (Ed.)
    The paper proposes an approach for fast small signal stability assessment on a short data window using deep learning algorithms. This paper shows that the proposed deep convolutional neural networks (CNNs)-based assessment approach is faster than traditional methods (i.e. Prony’s method). The evaluated CNNs are fully convolutional network (FCN), CNN with sub-sampling steps performed through max pooling (Time LeNet), time CNN, fully convolutional network with attention mechanism (Encoder), and CNN with a shortcut residual connection (ResNet). The proposed approach is validated on different synthetic measurement data sets generated from the IEEE 9-bus system that is used as a reference, and further applied to a 769-bus system representing a region in the U. S. Eastern Interconnection. We show that precision and recall are more informative metrics than accuracy for the reliability of the stability assessment process using the proposed methodology. In addition, the method’s efficiency is compared to classical Prony method. 
    more » « less
  2. ; ; ; ; ; ; (, Laser & Photonics Reviews)
    Abstract The incorporation of high‐performance optoelectronic devices into photonic neuromorphic processors can substantially accelerate computationally intensive matrix multiplication operations in machine learning (ML) algorithms. However, the conventional designs of individual devices and system are largely disconnected, and the system optimization is limited to the manual exploration of a small design space. Here, a device‐system end‐to‐end design methodology is reported to optimize a free‐space optical general matrix multiplication (GEMM) hardware accelerator by engineering a spatially reconfigurable array made from chalcogenide phase change materials. With a highly parallelized integrated hardware emulator with experimental information, the design of unit device to directly optimize GEMM calculation accuracy is achieved by exploring a large parameter space through reinforcement learning algorithms, including deep Q‐learning neural network, Bayesian optimization, and their cascaded approach. The algorithm‐generated physical quantities show a clear correlation between system performance metrics and device specifications. Furthermore, physics‐aware training approaches are employed to deploy optimized hardware to the tasks of image classification, materials discovery, and a closed‐loop design of optical ML accelerators. The demonstrated framework offers insights into the end‐to‐end and co‐design of optoelectronic devices and systems with reduced human supervision and domain knowledge barriers. 
    more » « less
  3. ; ; (, IEEE)
    Recent studies have demonstrated significant success in detecting attacks on the Controller Area Network (CAN) bus network using machine learning and deep learning models, including convolutional neural networks and transformer-based architectures. Building on this foundation, our work investigates the use of large language models (LLMs) not only for intrusion detection but also for providing interpretable explanations of their decisions. We fine-tuned three LLMs, i.e., SecureBERT, LLaMA-2, and LLaMA-3, for intrusion detection on CAN bus data. Among them, LLaMA-3 delivered the best results, achieving SOTA performance on the Car-Hacking dataset. Beyond attack classification, we evaluated LLaMA-3’s ability to generate reasoning for its decisions through zero-shot prompting. The model successfully articulated its rationale, particularly for Denial-of- Service (DoS) attacks, demonstrating strong potential for explainability in intrusion detection systems. These findings highlight the potential of LLMs to serve as a highly accurate intrusion detection system while simultaneously providing interpretable explanations, thereby enhancing the investigative capabilities of cybersecurity professionals. 
    more » « less
  4. ; ; (, Springer Nature Switzerland)
    Hei, X; Garcia, L; Kim, T; Kim, K (Ed.)
    The Controller Area Network (CAN) is widely used in the automotive industry for its ability to create inexpensive and fast networks. However, it lacks an authentication scheme, making vehicles vulnerable to spoofing attacks. Evidence shows that attackers can remotely control vehicles, posing serious risks to passengers and pedestrians. Several strategies have been proposed to ensure CAN data integrity by identifying senders based on physical layer characteristics, but high computational costs limit their practical use. This paper presents a framework to efficiently identify CAN bus system senders by fingerprinting them. By modeling the CAN sender identification problem as an image classification task, the need for expensive handcrafted feature engineering is eliminated, improving accuracy using deep neural networks. Experimental results show the proposed methodology achieves a maximum identification accuracy of 98.34%, surpassing the state-of-the-art method’s 97.13%. The approach also significantly reduces computational costs, cutting data processing time by a factor of 27, making it feasible for real-time application in vehicles. When tested on an actual vehicle, the proposed methodology achieved a no-attack detection rate of 97.78% and an attack detection rate of 100%, resulting in a combined accuracy of 98.89%. These results highlight the framework’s potential to enhance vehicle cybersecurity by reliably and efficiently identifying CAN bus senders. 
    more » « less
  5. ; ; ; (, IEEE Transactions on Power Systems)
    null (Ed.)
    Ensuring reliable operation of large power systems subjected to multiple outages is a challenging task because of the combinatorial nature of the problem. Traditional approaches for security assessment are often limited by their scope and/or speed, resulting in missing of critical contingencies that could lead to cascading failures. This paper proposes a two-component methodology to enhance power system security. The first component combines an efficient algorithm to detect cut-set saturation (called the feasibility test (FT) algorithm) with real-time contingency analysis (RTCA) to create an integrated corrective action (iCA), whose goal is to secure the system against cut-set saturation as well as critical branch overloads. The second component employs the only results of the FT to create a relaxed corrective action (rCA) to secure the system against post-contingency cut-set saturation. The first component is more comprehensive, but the latter is computationally more efficient. The effectiveness of the two components is evaluated based upon the number of cascade triggering contingencies alleviated, and the computation time. The results obtained by analyzing different case-studies on the IEEE 118-bus and 2000-bus synthetic Texas systems indicate that the proposed two-component methodology successfully enhances the scope and speed of power system security assessment during multiple outages. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email