检索结果-内蒙古大学图书馆

Harnessing Machine Learning in Dynamic Thermal Management in Embedded CPU-GPU Platforms

ACM Transactions on Design Automation of Electronic Systems 2025年第2期30卷 1-32页

作者： Maity, Srijeeta Majumder, Anirban Roy, Rudrajyoti Hota, Ashish Dey, Soumyajit Computer Science and Engineering Indian Institute of Technology Kharagpur Kharagpur India Electrical Engineering Indian Institute of Technology Kharagpur Kharagpur India Electronics And Communication Engineering Indian Institute of Technology Kharagpur Kharagpur India

With increasing transistor density, modern heterogeneous embedded processors often exhibit high temperature gradients due to complex application scheduling scenarios which may have missed design considerations. In many use cases, off-chip "active"cooling solutions are considered prohibitive in such reduced form factors. Core frequency throttling by existing dynamic thermal management techniques often compromises the Quality-of-Service (QoS) and violates real-time deadlines. This necessitates the adoption of intelligent resource management that simultaneously manages both thermal and latency performance. Coupled with the complexity of modern heterogeneous multi-cores, the periodic application updates that cater to ever-changing user requirements often render model-driven thermal-aware resource allocation approaches unsuitable for heterogeneous multi-core systems. For such application-architecture scenarios, we propose a novel self-learning based resource manager using Reinforcement Learning that intelligently manipulates core frequencies and task set mappings to fulfill thermal and latency objectives. Our framework employs a data-driven system modeling technique using Gaussian Process Regression to enable efficient offline training of this learning-based resource manager to avoid challenges associated with initial online training. We evaluate the approach on a heterogeneous embedded CPU-GPU platform with real workloads and observe a significant reduction in peak operating temperature when compared to the default onboard frequency governor as well as other learning-based state-of-the-art approaches. © 2025 Copyright held by the owner/author(s).

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Islanding Protection scheme based on IEC61850 GOOSE application for 11kV network with distributed energy resources 33

Islanding Protection scheme based on IEC61850 GOOSE applicat...

引用

33rd Southern African Universities Power engineering Conference, SAUPEC 2025

作者： Mpaka, Abuyile Krishnamurthy, Senthil Department of Electrical Electronics and Computer Engineering PO BOX 1906 Bellville7535 South Africa

ISBN: (纸本)9798331535162

This study focuses on islanding protection for a microgrid operating at 11kV. The literature provides novel algorithms developed for islanding protection schemes. However, there is a lack of validation and test the IEC61850 GOOSE message application for the islanding protection scheme. The paper's significant contribution is to address the literature gap by comparing legacy islanding protection with the IEC 61850 GOOSE message application. The research utilizes simulation techniques in the DigSilent and Hardware-in-the-Loop (HIL) simulations using RTDS to assess the performance of the Islanding protection scheme. Four test scenarios were conducted, which include undervoltage, overvoltage, underfrequency, and overfrequency protection functionalities. The simulation validation results from these four scenarios confirm that the modeled distribution system meets the required protection criteria for both legacy (hardwired) and modern IEC61850 GOOSE message applications. The simulation results show that the GOOSE message application for the Islanding protection scheme operates faster than the legacy scheme. © 2025 IEEE.

关键词： Islanding

来源：评论

学校读者我要写书评

暂无评论

IEC61850 GOOSE message application for a power transformer voltage control 33

IEC61850 GOOSE message application for a power transformer v...

引用

33rd Southern African Universities Power engineering Conference, SAUPEC 2025

作者： Wellen, Joniff Krishnamurthy, Senthil Ratshitanga, Mukovhe Department of Electrical Electronics and Computer Engineering PO BOX 1906 Bellville7535 South Africa

ISBN: (纸本)9798331535162

Voltage regulation of power transformers is critical to controlling and maintaining system voltage levels in the electrical transmission and distribution network system. It is vital to keep the transmission and distribution network's voltage levels within a specified range and to avoid voltage levels from fluctuating outside of the predetermined range of allowed tolerance levels. Two SEL-2414 IEDs were employed in this study to perform the voltage control function of the parallel power transformers using a master-follower control scheme. The automatic tap changers that execute this voltage regulating function incorporate the IEC61850 GOOSE message application as the communication protocol. The paper demonstrates the control function, a hardware-in-the-loop simulation in a closed-loop simulation using Real Time Digital Simulator (RTDS), and the two transformer tap changer IEDs SEL-2414 were utilized for lab-scale implementation and validating the simulation results. © 2025 IEEE.

关键词： Hardware-in-the-loop simulation

来源：评论

学校读者我要写书评

暂无评论

Lumped Parameter Modelling of Internal Temperature Dynamics in Multichip Power Modules 41

Lumped Parameter Modelling of Internal Temperature Dynamics ...

引用

41st UIT International Heat Transfer Conference

作者： Alì, Giovanni Cavallaro, Daniela Fichera, Alberto Lo Faro, Marta Orlando, Stefano Pagano, Arturo Volpe, Rosaria Department of Electrical Electronics and Computer Engineering University of Catania Catania Italy STMicroelectronics Catania Italy

This study assesses a lumped parameter modelling strategy for the fast response, layer-resolved prediction of the thermal field within the die of a selected power module device. A benchmark 1D lumped parameter model was initially defined, providing a simple description of the thermal field through the identification of a low number of lumped parameters but retaining information only on the junction temperature. A refined analytical model was therefore developed by adding the internal temperature nodes at the interfaces between the device layers. Thus, with a moderate increase of the lumped parameters, the model was able to predict the thermal behaviour of the inner layers of the die, which is the fundamental information required by reliability analysis. The set of model parameters were determined from the step-response thermal impedances of the power module, simulated by means of a numerical model purposely assessed under a boundary condition of forced liquid cooling. The lumped parameter identification consisted in a curve fitting procedure calculating the couples of thermal resistance and conductance. Both models were implemented in Matlab-Simulink, and simulated in order to predict the thermal response of the device to conditions of both step-wise and alternating current power inputs. © 2025 Institute of Physics Publishing. All rights reserved.

关键词： Thermal modeling

来源：评论

学校读者我要写书评

暂无评论

Distance Protection Application for 33kV Traction Network 33

Distance Protection Application for 33kV Traction Network

引用

33rd Southern African Universities Power engineering Conference, SAUPEC 2025

作者： Nkalitshana, Luthando Krishnamurthy, Senthil Mataifa, Haltor Department of Electrical Electronics and Computer Engineering PO BOX 1906 Bellville7535 South Africa

ISBN: (纸本)9798331535162

The research investigates the laboratory-scale setup and functional testing of distance protection techniques for the Transnet traction system. The Transnet network, which powers South Africa's railway system, requires a strong protection mechanism to assure the safety and dependability of the electrical systems that power locomotives. Distance protection, essential in securing high-voltage transmission networks, is critical to detecting faults, isolating affected portions, and minimizing system interruptions. In this study, a simulation environment was created to simulate the features of the Transnet traction system, including traction substations, overhead power lines, and associated equipment. A lab-scale model was developed utilizing protection functional simulation to simulate real-time fault situations and evaluate the distance protection relay's response under different fault conditions. The performance and efficacy of the protection mechanism were assessed by varying key factors such as fault impedance, fault location, and fault types. © 2025 IEEE.

关键词： Distribution protection Mho characteristics Traction network and Locomotives

来源：评论

学校读者我要写书评

暂无评论

A Data-Driven Approach to Dataflow-Aware Online Scheduling for Graph Neural Network Inference 25

A Data-Driven Approach to Dataflow-Aware Online Scheduling f...

引用

30th Asia and South Pacific Design Automation Conference, ASP-DAC 2025

作者： Puigdemont, Pol Russo, Enrico Wassington, Axel Das, Abhijit Abadal, Sergi Palesi, Maurizio Barcelona Spain Department of Electrical Electronics and Computer Engineering Univ. of Catania Catania Italy

ISBN: (纸本)9798400706356

Graph Neural Networks (GNNs) have shown significant promise in various domains, such as recommendation systems, bioinformatics, and network analysis. However, the irregularity of graph data poses unique challenges for efficient computation, leading to the development of specialized GNN accelerator architectures that surpass traditional CPU and GPU performance. Despite this, the structural diversity of input graphs results in varying performance across different GNN accelerators, depending on their dataflows. This variability in performance due to differing dataflows and graph properties remains largely unexplored, limiting the adaptability of GNN accelerators. To address this, we propose a data-driven framework for dataflow-aware latency prediction in GNN inference. Our approach involves training regressors to predict the latency of executing specific graphs on particular dataflows, using simulations on synthetic graphs. Experimental results indicate that our regressors can predict the optimal dataflow for a given graph with up to 91.28% accuracy and a Mean Absolute Percentage Error (MAPE) of 3.78%. Additionally, we introduce an online scheduling algorithm that uses these regressors to enhance scheduling decisions. Our experiments demonstrate that this algorithm achieves up to 3.17× speedup in mean completion time and 6.26× speedup in mean execution time compared to the best feasible baseline across all datasets. © 2025 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Data flow graphs

来源：评论

学校读者我要写书评

暂无评论

A practical evaluation of an IEC 61499 standard-based Low-Cost Gateway for photovoltaic power plants 33

A practical evaluation of an IEC 61499 standard-based Low-Co...

引用

33rd Southern African Universities Power engineering Conference, SAUPEC 2025

作者： Luwaca, Emmanuel Krishnamurthy, Senthil Department of Electrical Electronics and Computer Engineering PO BOX 1906 Bellville7535 South Africa

ISBN: (纸本)9798331535162

Communication plays a significant role in an electrical grid that includes Distributed Energy Resources (DERs). Modern control and automation systems used by these systems are predominantly distributed using domain standards such as IEC 61131-3. However, the IEC 61131-3 standard does not address communication. The IEC 61499 standard, in contrast, introduces the use of the Service Interface Function Block (SIFB) concept and high-level communication patterns to achieve hardware-independent access to communication services. This paper recommends the application of the IEC 61499 standard for DER control and automation and the application of SIFB to facilitate the ease of system integration in a DER plant. A low-cost gateway application using open-source IEC61499 tools is implemented, and its simulation results are presented. © 2025 IEEE.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

A Framework for Flood Disaster Detection From Remote Sensing Images Using Spatiotemporal Fusion With Digital Twin Technology

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年 18卷 11547-11560页

作者： Lim, Se-Jung Sankaran, K. Sakthidasan Haldorai, Anandakumar Chonnam National University School of Electrical and Computer Engineering Yeosu Campus Yeosu-si59626 Korea Republic of Hindustan Institute of Technology and Science Department of Electronics and Communication Engineering Chennai603103 India Sri Eshwar College of Engineering Department of Computer Science and Engineering Coimbatore641202 India

Flood is regarded as common disaster which could cause serious devastation in any country. Typically, it is caused due to precipitation & river runoffs, specifically at the time of excessive rainfall season. The technology of sensor network has been used to monitor changes in landcovers and water level fluctuations. Moreover, effective disaster monitoring & notification system in real-time becomes a crucial part which needs to be overcome. For this reason, the proposed methodology is designed aiming at developing natural disaster prediction and monitoring system for alerting that aids in offering right decision at right time. At first, remote sensing image data are collected and preprocessed using Frequency Ratio and Multi-collinearity test (MCT) to ensure noise removal and image augmentation by enhancing their quality. A feature extraction process is carried with the use of Deep Convolution VGGNet-16 from which optimal features are selected using Improved Harris Hawks Optimization algorithm (IHHOA). Then, a Flexible Spatio-temporal image fusion (F-SPTF) approach is employed to fuse images. After this, Deep cascaded RNN classifier is employed for predicting flood occurrence and to map flood susceptibility areas. This, in turn, classifies the normal and abnormal condition of flood occurrence thus giving alerts in case of natural disaster occurrences which could be visualized through digital twin technologies. The suggested scheme offers an accuracy rate of about (99.89%), precision (99.37%), recall (99.82%), and F1-score (99.74%). The error rates estimated like RMSE (0.784), MAE (0.764), and MAPE (0.102) also seems to be lower than other existing models compared. © 2008-2012 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Oversampling-Enhanced Feature Fusion-Based Hybrid ViT-1DCNN Model for Ransomware Cyber Attack Detection

引用

computer Modeling in engineering & Sciences 2025年第2期142卷 1667-1695页

作者： Muhammad Armghan Latif Zohaib Mushtaq Saifur Rahman Saad Arif Salim Nasar Faraj Mursal Muhammad Irfan Haris Aziz Department of Computer and Information System Cleveland State UniversityOhio44115USA Department of Electrical Electronics and Computer SystemsCollege of Engineering and TechnologyUniversity of SargodhaSargodha40100Pakistan Electrical Engineering Department College of EngineeringNajran UniversityNajran61441Saudi Arabia Department of Mechanical Engineering College of EngineeringKing Faisal UniversityAl Ahsa31982Saudi Arabia Department of Mechanical Industrial and Energy System EngineeringUniversity of SargodhaSargodha40100Pakistan

Ransomware attacks pose a significant threat to critical infrastructures,demanding robust detection *** study introduces a hybrid model that combines vision transformer(ViT)and one-dimensional convolutional neural network(1DCNN)architectures to enhance ransomware detection *** common challenges in ransomware detection,particularly dataset class imbalance,the synthetic minority oversampling technique(SMOTE)is employed to generate synthetic samples for minority class,thereby improving detection *** integration of ViT and 1DCNN through feature fusion enables the model to capture both global contextual and local sequential features,resulting in comprehensive ransomware *** on the UNSW-NB15 dataset,the proposed ViT-1DCNN model achieved 98%detection accuracy with precision,recall,and F1-score metrics surpassing conventional *** approach not only reduces false positives and negatives but also offers scalability and robustness for real-world cybersecurity *** results demonstrate the model’s potential as an effective tool for proactive ransomware detection,especially in environments where evolving threats require adaptable and high-accuracy solutions.

关键词： Ransomware attacks cybersecurity vision transformer convolutional neural network feature fusion encryption threat detection

来源：评论

学校读者我要写书评

暂无评论

Monitoring COVID-19 environment: a real-time facial mask detection using YOLO models

引用

Research on Biomedical engineering 2025年第1期41卷 1-18页

作者： Pandiyan, P. Thangaraj, Rajasekaran V, Balasubramanian V. K, Manavalasundaram S, Balakrishnan Department of Electrical and Electronics Engineering KPR Institute of Engineering and Technology Coimbatore India Department of Computer Science and Engineering Nandha Engineering College Erode India Department of Information Technology Velalar College of Engineering and Technology Erode India Department of Computer Science and Engineering Aarupadai Veedu Institute of Technology Chennai India Department of Computer Science and Engineering Sri Ramakrishna Institute of Technology Coimbatore India

Purpose: The rapid spread of COVID-19 has resulted in significant harm and impacted tens of millions of people globally. In order to prevent the transmission of the virus, individuals often wear masks as a protective measure for themselves and others. Coronavirus protection guidelines have been published by the World Health Organization (WHO). According to WHO standards, COVID-19 can be prevented by wearing a mask in public places and congested regions. In these places, it is very difficult to personally check to see if people are wearing face masks or not. Methods: The objective of this research work is to build a powerful, efficient, and real-time approach for detecting people not wearing masks. Three cutting-edge object identification models, namely YOLOv4, Tiny-YOLOv4, and YOLOv5, are employed in this study for the identification of masked faces. Result: The proposed YOLOv5 model is evaluated using real-time images captured using a smartphone or tablet. The test images include both single and multiple people with and without masks. The YOLOv5 model achieved recognition accuracy of 88.90% with an average detection speed of 0.0316 s per image, whereas the YOLOv4 and Tiny-YOLOv4 produced recognition accuracy of 82.24% and 74.80% with an average detection speed of 0.0530 s and 0.0541 s per image, respectively. Conclusion: The comparative performance suggests that the YOLOv5 model has a maximum recognition accuracy of 88.90% in face mask identification tasks compared to other models such as the YOLOv4 and Tiny-YOLOv4. © The Author(s), under exclusive licence to The Brazilian Society of Biomedical engineering 2025.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：