检索结果-内蒙古大学图书馆

CMD: A Cache-Assisted GPU Memory Deduplication Architecture

IEEE Transactions on computer-Aided Design of Integrated Circuits and systems 2025年

作者： Zhao, Wei Feng, Dan Tong, Wei Wei, Xueliang Wu, Bing Ministry of Education of China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of data storage systems and Technology China

Massive off-chip accesses in GPUs are the main performance bottleneck. We find that many writes are duplicate, and the duplication can be inter-dup and intra-dup. While inter-dup means different memory blocks are identical, and intra-dup means all the 4B elements in a line are the same. In this work, we propose a cache-assisted GPU memory deduplication architecture named CMD to reduce the off-chip accesses via utilizing the data duplication in GPU applications. CMD includes three key design contributions which aim to reduce the three kinds of accesses: (1) A novel GPU memory deduplication architecture that removes the intra-dup and inter-dup lines. We design several techniques to manage duplicate blocks, reducing massive off-chip writes. (2) We propose a cache-assisted read scheme to reduce the reads to duplicate data. When an L2 cache miss wants to read the duplicate block, if the reference block has been fetched to L2 and it is clean, we can copy it to the L2 missed block without accessing off-chip DRAM. As for the reads to intra-dup data, CMD uses the on-chip metadata cache to get the data. (3) When a cache line is evicted, the clean sectors in the line are invalidated while the dirty sectors are written back. However, most read-only victims are re-referenced from DRAM more than twice. Therefore, we add a full-associate FIFO to accommodate the read-only (it is also clean) victims to reduce the re-reference counts. Experiments show that CMD can decrease the off-chip accesses by 31.01%, reduce the energy by 32.78% and improve performance by 42.53%. Besides, CMD can improve the performance of memory-intensive workloads by 57.56%. © 2025 IEEE.

关键词： Cache memory

来源：评论

学校读者我要写书评

暂无评论

Energy-efficient and Privacy-preserving Edge Intelligence for 6G-Empowered Intelligent Transportation systems

引用

IEEE Network 2025年

作者： Zhu, Chenlu Fan, Xiaoxuan Deng, Xianjun Xiao, Ziheng Guo, Tingting Liu, Shenghao Sun, Jiaqi Park, Jong Hyuk Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Wuhan Kedao Geographic Information Engineering Co. Wuhan China Department of Computer Science and Engineering Seoul National University of Science and Technology Seoul Korea Republic of

6G-empowered Intelligent Transportation systems (ITS) generate large amounts of data through millions of devices and sensors at the terminal and network edge. Edge intelligence advances the frontier of data-driven artificial intelligence (AI) to the network edge, which enables AI applications to better utilize edge data. Broader connectivity, higher device density, and stronger data exchange present challenges for reliable device communication and privacy data protection in 6G-empowered ITS. To address these challenges, this paper proposes an energy-efficient and privacy-preserving edge intelligence framework named EP-EI. EP-EI deploys a deep reinforcement learning-based cluster head selection model at the edge to ensure energy-efficient communication for terminal devices. Meanwhile, EP-EI designs a privacy-aware hierarchical computing framework for terminal-edge-cloud to prevent privacy leakage. Furthermore, the application scenarios, challenges, and future directions of EP-EI are discussed. Finally, simulation experiments in a specific intelligent transportation case study demonstrate that EP-EI can provide energy-efficient and privacy-protecting services. © 2025 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approaches for Battery Capacity and State of Charge Estimation with the NASA B0005 Dataset

引用

computers, Materials and Continua 2025年第3期83卷 4795-4813页

作者： Zeyang Zhou Zachary James Ryan Utkarsh Sharma Tran Tien Anh Shashi Mehrotra Angelo Greco Jason West Mukesh Prasad School of Computer Science Faculty of Engineering and Information Technology University of Technology Sydney Ultimo NSW 2007 Australia School of Data Science and Engineering Indian Institute of Science Education and Research Bhopal 462066 India Research Institute of Marine Systems Engineering Seoul National University Seoul 08826 Republic of Korea Department of Computer Science and Engineering Faculty of Engineering and Technology SRM Institute of Science and Technology Delhi NCR Campus Ghaziabad 201204 India Battery System Modelling Department CLARIOS VARTA Hannover GmbH Hanover 30419 Germany Science and Innovation Group Bureau of Meteorology Brisbane 4000 Australia

Accurate capacity and State of Charge (SOC) estimation are crucial for ensuring the safety and longevity of lithium-ion batteries in electric vehicles. This study examines ten machine learning architectures, Including Deep Belief Network (DBN), Bidirectional Recurrent Neural Network (BiDirRNN), Gated Recurrent Unit (GRU), and others using the NASA B0005 dataset of 591,458 instances. Results indicate that DBN excels in capacity estimation, achieving orders-of-magnitude lower error values and explaining over 99.97% of the predicted variable’s variance. When computational efficiency is paramount, the Deep Neural Network (DNN) offers a strong alternative, delivering near-competitive accuracy with significantly reduced prediction times. The GRU achieves the best overall performance for SOC estimation, attaining an R 2 of 0.9999, while the BiDirRNN provides a marginally lower error at a slightly higher computational speed. In contrast, Convolutional Neural Networks (CNN) and Radial Basis Function Networks (RBFN) exhibit relatively high error rates, making them less viable for real-world battery management. Analyses of error distributions reveal that the top-performing models cluster most predictions within tight bounds, limiting the risk of overcharging or deep discharging. These findings highlight the trade-off between accuracy and computational overhead, offering valuable guidance for battery management system (BMS) designers seeking optimal performance under constrained resources. Future work may further explore advanced data augmentation and domain adaptation techniques to enhance these models’ robustness in diverse operating conditions.

关键词： Battery capacity estimation state of charge deep learning prediction efficiency energy storage systems

来源：评论

学校读者我要写书评

暂无评论

A third-party platoon coordination service: Pricing under government subsidies

A third-party platoon coordination service: Pricing under go...

引用

作者： Bai, Ting Johansson, Alexander Li, Shaoyuan Johansson, Karl Henrik Mårtensson, Jonas School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden KTH Royal Institute of Technology Stockholm Sweden Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Shanghai Jiao Tong University Shanghai China Digital Futures Stockholm Sweden

This paper models a platooning system consisting of trucks and a third-party service provider (TPSP), which performs platoon coordination, distributes the platooning profit in platoons, and charges trucks in exchange for the services. Government subsidies used to incentivize platooning are also considered. We propose a pricing rule for the TPSP, which keeps part of the platooning profit including the subsidy each time a platoon is formed. In addition, a platoon coordination solution based on the distributed model predictive control (MPC) is proposed, in which the pricing rule under government subsidies is integrated. We perform a realistic simulation over the Swedish road network to evaluate the impact of the pricing rule and subsidies on the achieved profits and fuel savings. Our results show that subsidies are an effective mean to boost fuel savings from platooning. Moreover, the simulation study indicates that high pricing corresponds to a low platooning rate of the system, as trucks' incentives for platooning decrease. © 2023 The Authors. Asian Journal of Control published by John Wiley & Sons Australia, Ltd on behalf of Chinese Automatic Control Society.

关键词： Trucks

来源：评论

学校读者我要写书评

暂无评论

Mobility-Aware User Association and Computation Offloading in Ultra-Dense Networks

IEEE Transactions on Green Communications and Networking

引用

IEEE Transactions on Green Communications and Networking 2025年

作者： Qiu, Bin Feng, Ke Li, Xian Xiao, Hailin Zhang, Zhongshan Guilin University of Technology School of Computer Science and Engineering Guilin541004 China Guilin University of Technology Guangxi Key Laboratory of Embedded Technology and Intelligent System Guilin541004 China Guangxi Modern Polytechnic College Hechi530700 China Shenzhen University College of Electronics and Information Engineering Shenzhen518060 China Hubei University School of Computer Science and Information Engineering Wuhan430062 China Wuhan430062 China School of Cyberspace Science and Technology Guangdong519088 China

The integration of mobile edge computing (MEC) into ultra-dense network (UDN) has emerged as a promising solution for providing uninterrupted task offloading services to computation-demanding mobile devices (MDs), leveraging densely deployed MEC servers. However, the mobility of MDs can significantly affect the computation offloading decision and system performance in UDN-MEC. To address this issue, we develop a joint optimization algorithm for mobility-aware user association and computation offloading to minimizize the total system cost, including delay and energy consumption in UDN-MEC. Specifically, a polynomial fitting algorithm based on an extended Kalman filter (PFA-EKF) is designed to predict the nonlinear moving trajectories of the MDs. Furthermore, we present a mobility-aware user-association rule based on a breadth-first search (UAR-BFS) that can realize balanced matching offloading in the overlapping coverage area of densely deployed small base stations. Accordingly, we propose an improved deep deterministic policy gradient-based greedy algorithm (IDDPG-GA) to address the joint optimization problem of multiuser dynamic offloading and resource allocation, in which an intelligently adjusted bias factor is proposed to enhance collaborative behavior among MDs. Extensive numerical results and comparisons demonstrate the promising performance improvements of the proposed scheme compared with existing benchmark schemes in various scenarios. © 2025 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Leveraging Predictive Maintenance for Photovoltaic systems 9th

Leveraging Predictive Maintenance for Photovoltaic Systems

引用

9th International Conference on Smart City Applications, SCA 2024

作者： Ledmaoui, Younes Raif, Mourad El Aroussi, Mohamed Saadane, Rachid Jakimi, Abdeslam Chehri, Abdellah Laboratory Engineering System Hassania School of Public Works Casablanca Morocco Software Engineering and Information Systems Engineering Team FST of Errachidia Moulay Ismail University Meknes Morocco Department of Mathematics and Computer Science Royal Military College of Canada Kingston K7K 7B4 ON Canada

ISBN: (纸本)9783031886522

This paper introduces a novel edge device architecture designed to optimize solar energy management systems. It integrates cutting-edge functionalities such as generation prediction, maintenance alerts, and anomaly detection into a unified framework. Through the utilization of edge computing, the system enables real-time analysis and decision-making at the network’s edge. Leveraging machine learning algorithms and predictive models, these edge devices provide highly accurate energy generation forecasts, facilitating efficient energy utilization and strategic planning. Additionally, the architecture incorporates anomaly detection techniques to proactively identify deviations from normal operation, minimizing downtime and enabling timely maintenance interventions. The seamless integration of these features within the edge devices significantly enhances the overall efficiency, reliability, and performance of energy monitoring systems. By adopting this advanced edge device architecture, energy stakeholders can reap benefits such as improved energy management, reduced operational costs, and enhanced system reliability. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Edge device Energy management system Energy monitoring Predictive maintenance Renewable energy Solar energy

来源：评论

学校读者我要写书评

暂无评论

Unknown Task Selection and Worker Recruitment Using Two-Stage Multi-Armed Bandit in Crowdsensing

引用

IEEE Internet of Things Journal 2025年

作者： Song, Haoyuan Li, Peng Du, Rui Yu, Hai Huang, Weiyi Nie, Lei Bao, Haizhou Liu, Qin Wuhan University of Science and Technology School of Computer Science and Technology Wuhan430065 China Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan430065 China Hubei Polytechnic University School of Computer Huangshi435003 China Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Changchun130012 China Wuhan University School of Cyber Science and Engineering Wuhan430072 China

Mobile Crowdsensing (MCS) faces significant challenges in selecting tasks with expected high revenue and recruiting workers with expected high qualities to maximize overall utility. Existing approaches often assume the revenue of posting tasks or the quality of workers is determined, which limits their practical applicability. This paper tackles these challenges by modeling the long-term multi-task, multi-worker selection problem as a Two-Stage Multi-Armed Bandit (TS-MAB) problem under uncertainty. In each round, the MCS platform selects a long-term task from a pool and recruits the necessary workers, determining payments accordingly. We model the task selection phase as a MAB problem, and the worker recruitment phase, influenced by the task selection, as a Combinatorial MAB (CMAB) problem. We propose an extended Upper Confidence Bound (UCB)-based strategy and develop an incentive mechanism based on Auction theory, combined with TS-MAB (i.e., ATS-MAB), for unknown task selection and worker recruitment. Our mechanism theoretically guarantees truthfulness and individual rationality, with a theoretical analysis of its regret bounds. Furthermore, we introduce an adaptive incentive mechanism called AATS-MAB, which improves worker recruitment and quality updates, achieving higher total sensing quality and lower regret. Extensive simulations demonstrate the effectiveness and scalability of the proposed methods. © 2014 IEEE.

关键词： Personnel selection

来源：评论

学校读者我要写书评

暂无评论

Testing Facility Location with Constrained Queue Time Problem: A Case Study in Florida, USA 24

Testing Facility Location with Constrained Queue Time Proble...

引用

Proceedings of the Winter Simulation Conference

作者： Almir Antonio Monteiro Junior Rafael Schneider Vanessa de Almeida Guimarães Pedro Henrique González System Engineering and Computer Science Program Federal University of Rio de Janeiro BRAZIL COPPEAD Graduate School of Business Federal University of Rio de Janeiro BRAZIL

ISBN: (纸本)9798331534202

This study addresses the Testing Facility Location with Constrained Queue Time Problem. This optimization problem focuses on determining the best places to deploy testing sites and their available testers for infectious diseases, while constraining the maximum time in the queue with a given probability. An integer programming model is introduced and applied to the three biggest counties, in terms of population, of Florida, United States. Moreover, the Monte Carlo method is used to evaluate the model's output, aiming to check if the queueing time constraint is being satisfied. Through the experiments, a testing facility deployment plan can be determined for each county and further validated by the simulation. The results show that the solutions returned by the model behaved successfully when submitted to the Monte Carlo method, not exceeding the time in the queue in more than the predefined probability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High-resolution waveguide array-based astronomical spectrograph with cascaded phase modulation

引用

Chinese Optics Letters 2025年第03期 62-66页

作者：仲韵贤林栋徐彪朱壮壮童雪钟晴冯吉军何晋平 Laboratory of Solar and Space Instruments Nanjing Institute of Astronomical Optics&TechnologyChinese Academy of Sciences CAS Key Laboratory of Astronomical Optics&Technology Nanjing Institute of Astronomical Optics&TechnologyChinese Academy of Sciences University of Chinese Academy of Sciences Shanghai Key Laboratory of Modern Optical System Engineering Research Center of Optical Instrument and SystemMinistry of EducationSchool of Optical-Electrical and Computer EngineeringUniversity of Shanghai for Science and Technology

Integrated photonic spectrographs could provide a new generation of low-cost,highly integrated,high-performance optical terminal instruments for astronomical ***,these spectrographs still face the challenge of high spectral *** this Letter,we demonstrate a cascaded phase-modulated waveguide array (CPMWA) spectrograph,with designed and measured spectral resolutions of 100,000 and 68,000,respectively.A spectral reconstruction method is proposed to minimize the influence of the phase error induced during the chip fabrication process and increase the spectral contrast to 20 d *** type of spectrograph demonstrates promising potential for high-resolution spectrum observations in astronomy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FedEAT: A Robustness Optimization Framework for Federated LLMs

arXiv

引用

arXiv 2025年

作者： Pang, Yahao Wu, Xingyuan Zhang, Xiaojin Chen, Wei Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Huazhong University of Science and Technology Wuhan China

Significant advancements have been made by Large Language Models (LLMs) in the domains of natural language understanding and automated content creation. However, they still face persistent problems, including substantial computational costs and inadequate availability of training data. The combination of Federated Learning (FL) and LLMs (federated LLMs) offers a solution by leveraging distributed data while protecting privacy, which positions it as an ideal choice for sensitive domains. However, Federated LLMs still suffer from robustness challenges, including data heterogeneity, malicious clients, and adversarial attacks, which greatly hinder their applications. We first introduce the robustness problems in federated LLMs, to address these challenges, we propose FedEAT (Federated Embedding space Adversarial Training), a novel framework that applies adversarial training in the embedding space of client LLM and employs a robust aggregation approach, specifically geometric median aggregation, to enhance the robustness of Federated LLMs. Our experiments demonstrate that FedEAT effectively improves the robustness of Federated LLMs with minimal performance loss. © 2025, CC BY.

关键词： Federated learning

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：