检索结果-内蒙古大学图书馆

funcX: Federated Function as a Service for science

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Zhuozhao Chard, Ryan Babuji, Yadu Galewsky, Ben Skluzacek, Tyler J. Nagaitsev, Kirill Woodard, Anna Blaiszik, Ben Bryan, Josh Katz, Daniel S. Foster, Ian T. Chard, Kyle Department of Computer Science and Engineering Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China The University of Chicago ChicagoIL60637 United States Argonne National Laboratory LemontIL60439 United States NCSA CS ECE and the iSchool University of Illinois UrbanaIL61801 United States NCSA University of Illinois UrbanaIL61801 United States Northwestern University EvanstonIL60208 United States

funcX is a distributed function as a service (FaaS) platform that enables flexible, scalable, and high performance remote function execution. Unlike centralized FaaS systems, funcX decouples the cloud-hosted management functionality from the edge-hosted execution functionality. funcX’s endpoint software can be deployed, by users or administrators, on arbitrary laptops, clouds, clusters, and supercomputers, in effect turning them into function serving systems. funcX’s cloud-hosted service provides a single location for registering, sharing, and managing both functions and endpoints. It allows for transparent, secure, and reliable function execution across the federated ecosystem of endpoints—enabling users to route functions to endpoints based on specific needs. funcX uses containers (e.g., Docker, Singularity, and Shifter) to provide common execution environments across endpoints. funcX implements various container management strategies to execute functions with high performance and efficiency on diverse funcX endpoints. funcX also integrates with an in-memory data store and Globus for managing data that may span endpoints. We motivate the need for funcX, present our prototype design and implementation, and demonstrate, via experiments on two supercomputers, that funcX can scale to more than 130 000 concurrent workers. We show that funcX’s container warming-aware routing algorithm can reduce the completion time for 3000 functions by up to 61% compared to a randomized algorithm and the in-memory data store can speed up data transfers by up to 3x compared to a shared file system. Copyright © 2022, The Authors. All rights reserved.

关键词： Supercomputers

Robust multimodal federated learning for non-IID multimodal data with incompleteness

学校读者我要写书评

暂无评论

Future Generation computer systems 2026年 174卷

作者： Songcan Yu Kaiming Zhu Feiyuan Liang Junbo Wang Krishna Kant Ling Yin Department of Computer Science and Technology Sichuan Police College Luzhou 646000 PR China Police Integration Computing Key Laboratory of Sichuan Province Chengdu 610206 PR China School of Intelligent Systems Engineering Sun Yat-Sen University Shenzhen 518107 PR China Department of Computer and Information Sciences Temple University Philadelphia USA Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen 518055 PR China

Federated learning (FL) provides a privacy-aware distributed learning framework using private data belonging to multiple users (or clients). Often the data is generated continuously by the sensors deployed by different clients and is increasingly multimodal. However, the data is invariably imbalanced across different modalities, and certain modalities may even be missing from some clients for certain periods due to sensor failure or unavailability. Furthermore, the available data across clients may not be identically distributed (non-IID). Non-IID data is already known to be a problem with FL, and incomplete modalities could worsen the results even further. Effectively fusing multimodal data with incompleteness and training a high-accuracy global model is still a challenging problem. To tackle this problem, we propose a novel framework called MFedNI that extracts cross-modal temporal features and adaptively adjusts the weights of each modality to mitigate the effect of modal incompleteness. The prototype contrastive learning (PCL)-based feature alignment method further improves the consistency of feature representations across clients. We evaluated MFedNI using two multimodal datasets, HAR and DEAP with different levels of incompleteness. The results demonstrate that MFedNI outperforms other approaches and can train highly accurate models on datasets comprising non-IID multimodal data with incompleteness.

关键词：

Improving unsupervised domain adaptation by reducing bi-level feature redundancy

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wang, Mengzhu Zhang, Xiang Lan, Long Wang, Wei Tan, Huibin Luo, Zhigang Science and Technology on Parallel and Distributed Laboratory College of Computer National University of Defense Technology Changsha China Institute for Quantum State Key Laboratory of High Performance Computing National University of Defense Technology Changsha China DUT-RU International School of Information Science & Engineering Dalian University of Technology DalianLiaoning116000 China Department of Science and Technology on Parallel and Distributed Processing National University of Defense Technology Changsha China

Reducing feature redundancy has shown beneficial effects for improving the accuracy of deep learning models, thus it is also indispensable for the models of unsupervised domain adaptation (UDA). Nevertheless, most recent efforts in the field of UDA ignore this point. Moreover, main schemes realizing this in general independent of UDA purely involve a single domain, thus might not be effective for cross-domain tasks. In this paper, we emphasize the significance of reducing feature redundancy for improving UDA in a bi-level way. For the first level, we try to ensure compact domain-specific features with a transferable decorrelated normalization module, which preserves specific domain information whilst easing the side effect of feature redundancy on the sequel domain-invariance. In the second level, domain-invariant feature redundancy caused by domain-shared representation is further mitigated via an alternative brand orthogonality for better generalization. These two novel aspects can be easily plugged into any BN-based backbone neural networks. Specifically, simply applying them to ResNet50 has achieved competitive performance to the state-of-the-arts on five popular benchmarks. Our code will be available at https://***/dreamkily/gUDA. © 2020, CC BY.

关键词： Deep learning

System Level Synthesis for Affine Control Policies: Model Based and Data-Driven Settings

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Schüepp, Lukas De Pasquale, Giulia Dörfler, Florian Alonso, Carmen Amo Automatic Control Laboratory Department of Electrical Engineering and Information Technology ETH Zurich Physikstrasse 3 Zurich8092 Switzerland Computer Science Department of Stanford University Palo AltoCA United States Control Systems Group Department of Electrical Engineering TU Eindhoven Flux Groene Loper 19 Eindhoven5612AP Netherlands

There is an increasing need for effective control of systems with complex dynamics, particularly through data-driven approaches. System Level Synthesis (SLS) has emerged as a powerful framework that facilitates the control of large-scale systems while accounting for model uncertainties. SLS approaches are currently limited to linear systems and time-varying linear control policies, thus limiting the class of achievable control strategies. We introduce a novel closed-loop parameterization for time-varying affine control policies, extending the SLS framework to a broader class of systems and policies. We show that the closed-loop behavior under affine policies can be equivalently characterized using past system trajectories, enabling a fully data-driven formulation. This parameterization seamlessly integrates affine policies into optimal control problems, allowing for a closed-loop formulation of general Model Predictive Control (MPC) problems. To the best of our knowledge, this is the first work to extend SLS to affine policies in both model-based and data-driven settings, enabling an equivalent formulation of MPC problems using closed-loop maps. We validate our approach through numerical experiments, demonstrating that our model-based and data-driven affine SLS formulations achieve performance on par with traditional model-based MPC. © 2025, CC BY.

关键词： distributed parameter control systems

Thermosim: Deep learning based framework for modeling and simulation of thermal-aware resource management for cloud computing environments

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Gill, Sukhpal Singh Tuli, Shreshth Toosi, Adel Nadjaran Cuadrado, Felix Garraghan, Peter Bahsoon, Rami Lutfiyya, Hanan Sakellariou, Rizos Rana, Omer Dustdar, Schahram Buyya, Rajkumar School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom Delhi India Faculty of Information Technology Monash University ClaytonVIC Australia Spain School of Computing and Communications Lancaster University United Kingdom School of Computer Science University of Birmingham Birmingham United Kingdom Department of Computer Science University of Western Ontario LondonON Canada School of Computer Science University of Manchester Oxford Road ManchesterUK United Kingdom School of Computer Science and Informatics Cardiff University CardiffUK United Kingdom Distributed Systems Group Vienna University of Technology Vienna Austria Laboratory School of Computing and Information Systems University of Melbourne Australia

Current cloud computing frameworks host millions of physical servers that utilize cloud computing resources in the form of different virtual machines. Cloud Data Center (CDC) infrastructures require significant amounts of energy to deliver large scale computational services. Moreover, computing nodes generate large volumes of heat, requiring cooling units in turn to eliminate the effect of this heat. Thus, overall energy consumption of the CDC increases tremendously for servers as well as for cooling units. However, current workload allocation policies do not take into account effect on temperature and it is challenging to simulate the thermal behaviour of CDCs. There is a need for a thermal-aware framework to simulate and model the behaviour of nodes and measure the important performance parameters which can be affected by its temperature. In this paper, we propose a lightweight framework, ThermoSim, for modelling and simulation of thermal-aware resource management for cloud computing environments. This work presents a Recurrent Neural Network based deep learning temperature predictor for CDCs which is utilized by ThermoSim for lightweight resource management in constrained cloud environments. ThermoSim extends the CloudSim toolkit helping to analyse the performance of various key parameters such as energy consumption, service level agreement violation rate, number of virtual machine migrations and temperature during the management of cloud resources for execution of workloads. Further, different energy-aware and thermal-aware resource management techniques are tested using the proposed ThermoSim framework in order to validate it against the existing framework (Thas). The experimental results demonstrate the proposed framework is capable of modelling and simulating the thermal behaviour of a CDC and ThermoSim framework is better than Thas in terms of energy consumption, cost, time, memory usage and prediction accuracy. Copyright © 2020, The Authors. All rights rese

关键词： Cloud computing

Enhancing data harvesting systems: Performance quantification of Cloud–Edge-sensor networks using queueing theory

学校读者我要写书评

暂无评论

ICT Express 2025年

作者： Rocha, Jose Wanderlei Gomes, Eder Barbosa, Vandirleya Sabino, Arthur Lima, Luiz Nelson Callou, Gustavo Silva, Francisco Airton Choi, Eunmi Nguyen, Tuan Anh Min, Dugki Lee, Jae-Woo Laboratory of Applied Research to Distributed Systems (PASID) Federal University of Piaui (UFPI) Picos Piaui R. Cicero Duarte No. 905 - Junco 64607-670 Brazil School of Software College of Computer Science Kookmin University Seoul 02707 South Korea Department of Software Engineering Faculty of Information Technology Ho Chi Minh City University of Industry and Trade (HUIT) Ho Chi Minh City 700000 Viet Nam Department of Artificial Intelligence Graduate School Konkuk University Seoul 05029 South Korea Department of Computer Science and Engineering College of Engineering Konkuk University Seoul 05029 South Korea Department of Aerospace Engineering Konkuk University Seoul 05029 South Korea

This study investigates a Cloud–Edge-sensors infrastructure using M/M/c/K queuing theory to analyze agricultural data systems’ performance. It focuses on optimizing data handling and evaluates the system configuration impacts on performance. The model significantly enhances efficiency and scalability, minimizing the need for extensive physical infrastructure. Analysis shows over 90% utilization in both layers, highlighting the model's applicability to various IoT applications. The M/M/c/K queuing model addresses scalability and real-time data processing challenges in agricultural cloud–edge-sensor networks, improving over traditional methods lacking dynamic scalability. Designed for optimized resource use and reduced data handling delays, this model proves crucial in precision agriculture, where timely data is essential for decision-making. Its versatility extends to various agricultural applications requiring efficient real-time analysis and resource management. © 2025 The Authors

关键词： Agricultural monitoring system Data harvesting Performance Queuing model Sensors

Interdependence between transportation system and power distribution system: a comprehensive review on models and applications

学校读者我要写书评

暂无评论

Journal of Modern Power systems and Clean Energy 2019年第3期7卷 433-448页

作者： Wei WEI Danman WU Qiuwei WU Miadreza SHAFIE-KHAH Joao PSCATALAO State Key Laboratory of Power System Department ofElectrical EngineeringTsinghua UniversityBeijingChina Department of Electrical Engineering Technical Universityof DenmarkCopenhagenDenmark School of Technology and Innovations University of VaasaVaasaFinland Institute for Systems and Computer Engineering Technologyand Science(INESC TEC)PortoPortugal Faculty of Engineering University of PortoPortoPortugal

The rapidly increasing penetration of electric vehicles(EVs) in modern metropolises has been witnessed during the past decade, inspired by financial subsidies as well as public awareness of climate change and environment pro-tection. Integrating charging facilities, especially highpower chargers in fast charging stations, into power distribution systems remarkably alters the traditional load flow pattern, and thus imposes great challenges on the operation of distribution network in which controllable resources are rare. On the other hand, provided with appropriate incentives, the energy storage capability of electric vehicle offers a unique opportunity to facilitate the integration of distributed wind and solar power generation into power distribution system. The above trends call for thorough investigation and research on the interdependence between transportation system and power distribution system. This paper conducts a comprehensive survey on this line of research. The basic models of transportation system and power distribution system are introduced,especially the user equilibrium model, which describes the vehicular flow on each road segment and is not familiar to the readers in power system community. The modelling of interdependence across the two systems is *** into account such interdependence, applications ranging from long-term planning to short-term operation are reviewed with emphasis on comparing the description of traffic-power interdependence. Finally, an outlook of prospective directions and key technologies in future research is summarized.

关键词： Charging station Electric vehicle(EV) Interdependence Power flow Power distribution system Transportation system User equilibrium

distributed Attack-Robust Submodular Maximization for Multi-Robot Planning

学校读者我要写书评

暂无评论

Distributed Attack-Robust Submodular Maximization for Multi-...

IEEE International Conference on Robotics and Automation (ICRA)

作者： Lifeng Zhou Vasileios Tzoumas George J. Pappas Pratap Tokekar Department of Electrical and Computer Engineering Virginia Tech Blacksburg VA USA Laboratory of Information and Decision Systems Massachusetts Institute of Technology Cambridge MA USA Department of Electrical and Systems Engineering University of Pennsylvania Philadelphia PA USA Department of Computer Science University of Maryland College Park MD USA

ISBN: (数字)9781728173955

ISBN: (纸本)9781728173962

We aim to guard swarm-robotics applications against denial-of-service (DoS) attacks that result in withdrawals of robots. We focus on applications requiring the selection of actions for each robot, among a set of available ones, e.g., which trajectory to follow. Such applications are central in large-scale robotic applications, e.g., multi-robot motion planning for target tracking. But the current attack-robust algorithms are centralized, and scale quadratically with the problem size (e.g., number of robots). In this paper, we propose a general-purpose distributed algorithm towards robust optimization at scale, with local communications only. We name it distributed robust maximization (DRM). DRM proposes a divide-and-conquer approach that distributively partitions the problem among K cliques of robots. The cliques optimize in parallel, independently of each other. That way, DRM also offers computational speed-ups up to 1/K 2 the running time of its centralized counterparts. K depends on the robots' communication range, which is given as input to DRM. DRM also achieves a close-to-optimal performance. We demonstrate DRM's performance in Gazebo and MATLAB simulations, in scenarios of active target tracking with multiple robots. We observe DRM achieves significant computational speed-ups (it is 3 to 4 orders faster) and, yet, nearly matches the tracking performance of its centralized counterparts.

关键词： Planning Target tracking Robot kinematics Partitioning algorithms Robot sensing systems Robustness

BAT: A Versatile Bipartite Attention-based Approach for Comprehensive Truth Inference in Mobile Crowdsourcing

学校读者我要写书评

暂无评论

IEEE Transactions on Mobile Computing 2025年

作者： Liu, Jiacheng Tang, Feilong Liu, Hao Chen, Long Yu, Yichuan Zhu, Yanmin Yu, Jiadi Hou, Xiaofeng Heng, Pheng-Ann The Chinese University of Hong Kong Department of Computer Science and Engineering 999077 Hong Kong Shanghai Jiao Tong University School of Computer Science Shanghai200240 China East China Normal University School of Data Science and Engineering China Simon Fraser University School of Computing Science Canada Huawei Technologies Co. Ltd China Chinese Academy of Sciences Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Shenzhen518055 China

The proliferation of smart mobile devices has catalyzed the growth of Mobile CrowdSourcing (MCS) as a distributed problem-solving paradigm. MCS platforms heavily rely on advanced truth inference techniques to extract reliable information from diverse and potentially noisy crowd-contributed data. Existing truth inference models often made simplified assumptions about workers or tasks, employing complex Bayesian models or stringent data aggregation methods. These approaches tend to be task-specific, primarily limited to categorical labeling, making adaptations to other mobile computing scenarios labor-intensive. To address these limitations, we introduce the Bipartite Attention-driven Truth (BAT), a versatile approach tailored for mobile computing environments. BAT utilizes an Attributed Bipartite Graph (ABG) to holistically model the MCS process, with workers and tasks as nodes connected by edges representing answer-specific attributes. The approach employs a bipartite graph neural network with an innovative attention mechanism to assess the importance of different answers. BAT extends beyond categorical tasks to support numerical ones by incorporating novel feature representations and model extensions. Theoretical analyses clarify the link between answer similarity and worker expertise. Extensive experiments using diverse real-world datasets demonstrate BAT's superior performance compared to state-of-the-art categorical and numerical truth inference models, highlighting its effectiveness in mobile computing scenarios. © 2002-2012 IEEE.

关键词： Graph neural networks