检索结果-内蒙古大学图书馆

IEEE International Conference on Communications (ICC)

作者： Geetha Chandrasekaran Gustavo de Veciana Dept. of ECE University of Texas at Austin

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

Future wireless applications, such as online gaming, live video streaming, augmented/virtual reality need high fidelity data transfer with reliable control information exchange to provide an immersive user experience. Developing wireless scheduling algorithms that can guarantee a minimum data rate for users over a few hundred milliseconds with possibly heterogeneous requirements and/or channel quality is crucial. We propose a class of measurement based wireless schedulers that are able to trade off between opportunistically scheduling users with good channels and prioritizing users with service deficits. The proposed algorithms continuously track the QoS provided to each user and switch between conservative or greedy resource allocation depending on user channel strength, QoS deadline, and past channel realizations. We also formulate an oracle-aided linear optimization of the minimum rate QoS constrained scheduling problem to derive a spectral efficiency bound. Through extensive simulations, we show that our proposed algorithms provide a much higher user rate than popular scheduling algorithms such as QoS-PF, EXP-QoS, and weighted MaxQuantile with better reliability when the network is critically loaded. We observe at least a two-fold increase in the mean rate for each user in the network when compared to the EXP-QoS algorithm.

关键词： Wireless communication scheduling algorithms Spectral efficiency Quality of service Switches Streaming media User experience

来源：评论

学校读者我要写书评

暂无评论

Multi-Scope Spectral Graph Neural Network for Link scheduling

Multi-Scope Spectral Graph Neural Network for Link Schedulin...

引用

Power System and New Energy Technology Innovation Forum (NPSIF), Boao New Power System International Forum -

作者： Chenghai Mai Jiayi Lin Wei Zhang Marketing Department Guangdong Provincial Key Laboratory of Digital Grid Technology Southern Power Grid Digital Grid Research Institute Co. Ltd Guang Zhou China Hardware R&D Department Guangdong Provincial Key Laboratory of Digital Grid Technology(Southern Power Grid Digital Grid Research Institute Co. Ltd) Guang Zhou China Digital Metering Business Department Guangdong Provincial Key Laboratory of Digital Grid Technology(Southern Power Grid Digital Grid Research Institute Co. Ltd) GuangZhou China

ISBN: (数字)9798331504557

ISBN: (纸本)9798331504564

Effective link scheduling is crucial for optimizing energy utilization and efficiency. In power systems and wireless networks, efficient link scheduling approaches commonly rely on deep reinforcement learning or greedy algorithms designed for maximum weighted independent set (MWIS) to solve scheduling conflicts. Greedy algorithms offer lower computational complexity, making them well-suited for our link scheduling tasks. However, these methods often analyze network topologies within a single scope, which could over-look configurations and conflicts across various regional and business scopes within link scheduling systems. In these systems, the neighborhoods of links across different scopes play varying roles in conflict relationships. To address this gap, this paper proposes a link scheduling algorithm: Multi-scope Spectral Graph Neural Network based MWIS solver (MSGNN-based MWIS solver). This approach integrates multi-scope spectral graph feature embedding to capture diverse network structures and conflict relationships across various neighborhood scopes. Moreover, MSGNN-based MWIS solver leverages reinforcement-based principles alongside greedy algorithms by introducing a reinforcement-based utility function to the MWIS solver. Specifically, the MSGNN-based MWIS solver operates by constructing a spectral space that transforms conflict relations across different scopes into correlation patterns among conflict graphs at various frequencies within a designed spectral graph neural network framework. This spectral graph neural network framework then utilizes spectral filters in different frequencies to extract link features and optimize conflict graph relationships. To keep the multi-scope spectral graph feature embedding effective, this MSGNN-based MWIS solver is optimized by a tailored loss function emphasizing consistency and the introduced utility function, thereby enhancing the overall effectiveness of the link scheduling. Experimental results validate the superi

关键词： Greedy algorithms Technological innovation Filters scheduling algorithms Wireless networks Power system dynamics Transforms Feature extraction Dynamic scheduling Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing parking efficiency: An innovative vehicle scheduling algorithm

Enhancing parking efficiency: An innovative vehicle scheduli...

引用

IEEE International Conference on Information Reuse and Integration (IRI)

作者： Noman Gul Asad Masood Khattak Muhammad Imran Taj Nagarajan Chandrashekaran Bashir Hayat Awais Ahmad Centre for Excellence in IT Institute of Management Sciences Hayatabad Peshawar Pakistan College of Technological Innovation Zayed University UAE College of Interdisciplinary Studies Zayed University UAE

ISBN: (数字)9798350351187

ISBN: (纸本)9798350351194

Vehicle Parking queues in smart cities are typically managed in a first come, first serve manner. These queues are sorted on the basis of vehicle arrival time and neglect crucial vehicle information and the size of the parking area. Vehicle information consists of the vehicle’s nature, size, type, etc. Established parking systems allow any vehicles with reservation, and hence different heavyweight and unsuitable vehicles, to enter into congested roads, causing unnecessary traffic jams and inconvenience for the public. To overcome the above-mentioned issues, this research study proposes an efficient and robust vehicle scheduling algorithm known as Priority Vehicle Scheduler (PVS). The scheduler arranges vehicles based on their nature, size, and other properties. The proposed algorithm is compared with the traditional algorithm First Come First Serve (FCFS) and Shortest Job First (SJF) in terms of three parameters using a detailed simulation. These parameters are the degree of congestion, environmental pollution and throughput. The simulation results show that the proposed algorithm performs better in all three parameters, thus keeping heavy and loaded vehicles outside the congested roads and prioritising emergency vehicles.

关键词： Pollution scheduling algorithms Smart cities Roads Simulation Data science Throughput Rough surfaces

来源：评论

学校读者我要写书评

暂无评论

Cross-Period Joint scheduling of Task and Network in IEEE 802.1Qbv Time-Sensitive Networks

Cross-Period Joint Scheduling of Task and Network in IEEE 80...

引用

International Conference on Communication Technology (ICCT)

作者： Pengyu Wang Hailong Zhu Huayu Zhang Tao Huang Beijing University of Posts and Telecommunications Beijing China Purple Mountain Laboratories NanJing China

ISBN: (数字)9798350363760

ISBN: (纸本)9798350363777

Time-sensitive networking introduces deterministic latency and low jitter to Ethernet through traffic shaping mechanisms. The IEEE 802.1Qbv standard ensures deterministic transmission of critical flows via the time-aware shaper, where synthesizing the Gate Control List (GCL) schedule is a core challenge. Most SMT-based schedule synthesis algorithms consider only single-period scheduling under a unified timeline, leading to low schedulability. In this paper, we propose a cross-period scheduling algorithm that jointly schedules task and network, ensuring the correctness of cross-period scheduling constraints under a unified timeline through reasonable period mapping. In our defined task tree model, we introduce an optimization objective to minimize the end-to-end latency of task trees. Finally, we evaluate the performance of our algorithm. The results demonstrate that our algorithm significantly improves schedulability and achieves lower end-to-end latency compared to existing algorithms. Moreover, our algorithm can complete the computation within a reasonable time, even in large-scale networks.

关键词： Schedules Runtime scheduling algorithms Spread spectrum communication Ethernet Logic gates Jitter scheduling Standards Optimization

来源：评论

学校读者我要写书评

暂无评论

FlexMRS: Multi-Objective Optimization for Diverse Application Requirements in MPTCP scheduling

FlexMRS: Multi-Objective Optimization for Diverse Applicatio...

引用

IEEE International Conference on Performance, Computing and Communications (IPCCC)

作者： Zekun Zhang Lujie Zhong Xiang Ji Information Engineering College Capital Normal University Beijing China School of Computer Science Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9798350367942

ISBN: (纸本)9798350367959

Multipath TCP (MPTCP) technology efficiently leverages multiple paths for data transmission, achieving commendable throughput performance. However, existing MPTCP scheduling algorithms fail to meet the diverse and evolving demands of modern applications, which often extend beyond throughput to include preferences for low latency or stability. To address this gap, we introduce FlexMRS, an intelligent multi-objective MPTCP scheduling algorithm. Unlike prevailing algorithms that rely on black-box machine learning models, FlexMRS innovatively utilizes the Lagrangian relaxation method to overcome the traditional limitations of balancing multiple objectives in machine ***, we introduce the Krylov subspace iteration to obtain obtain the local Pareto optimal solution set, thus make FlexMRS could effectively address the switching convergence problem of different application requirement models.

关键词： scheduling algorithms Switches Reinforcement learning Pareto optimization Throughput Dynamic scheduling Stability analysis Relaxation methods MPTCP Optimization

来源：评论

学校读者我要写书评

暂无评论

Dynamic Batch Scheduler for Efficient Neural Networks Training 9

Dynamic Batch Scheduler for Efficient Neural Networks Traini...

引用

9th International Conference on Big Data and Information Analytics, BigDIA 2023

作者： Waheed, Mutayyba Li, Jinlong University of Science and Technology China School of Computer Science and Technology Anhui China

ISBN: (纸本)9798350330076

The widespread utilization of neural networks (NNs) in recent years has been driven by their remarkable ability to discern complex data patterns. However, training NN models on vast datasets can be computationally expensive. To address this challenge, we investigate the art of data batch scheduling, which involves strategically organizing extensive datasets into smaller, manageable batches for training. This paper presents a novel dynamic batch scheduling algorithm explicitly designed for training deep neural networks. It dynamically constructs batches based on a combination of training loss and batch utilization, leading to optimized training efficiency. The experiments conducted on MNIST, CIFAR-10, and CIFAR-100 datasets demonstrate the superiority of our approach over recognized methods. Our dynamic batch scheduler, when combined with different, models, optimizers, batch sizes, numbers of batches per epoch, and time complexity, consistently improves training and testing accuracy while maintaining algorithmic efficiency. © 2023 IEEE.

关键词： scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

HIDG-based PSO Algorithm: Suspicious Sensor Selection for Power Grid Monitoring System Under Data Integrity Attack 5

HIDG-based PSO Algorithm: Suspicious Sensor Selection for Po...

引用

5th International Conference on Electrical Engineering and Control Technologies, CEECT 2023

作者： Li, Pandeng Liang, Zhihong Yang, Yiwei Dong, Liangyu Suo, Yuhan Hao, Yi Electric Power Research Institute Csg Guangdong Provincial Key Laboratory of Power System Network Security Guangdong Guangzhou China China Industrial Control Systems Cyber Emergency Response Team Beijing China Beijing Institute of Technology School of Automation Beijing China

ISBN: (纸本)9798350342253

With the development of communication and sensing technology, it has become possible to monitor the operating status of the power grid system through a series of sensors. However, malicious adversaries may launch data integrity attacks to compromise the measurements of certain sensors, causing the grid monitoring system to fail to grasp the correct system operating status. To solve the NP-hard suspicious sensor selection problem, this paper proposes an efficient attack detection scheduling algorithm, the Particle Swarm Optimization algorithm based on historical information directional guidance (HIDG-based PSO algorithm). The proposed algorithm is utilized with its unique evolutionary mechanism, which reduces the computational power requirements for sensor selection. For the problem of uncertainty in evolutionary algorithms, this paper uses historical information to guide the selection of suspicious sensors at the current moment. The simulation results show that the proposed algorithm can efficiently select suspicious sensors, which will greatly improve the efficiency of attack detection and ensure the security of information fusion of the power grid monitoring system. © 2023 IEEE.

关键词： scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Running Virtual Services for the Intelligent Edge: A Review

Running Virtual Services for the Intelligent Edge: A Review

引用

2023 IEEE World AI IoT Congress, AIIoT 2023

作者： Afachao, Kevin Abu-Mahfouz, Adnan M. University of Pretoria Department of Electrical Electronic and Computer Engineering Pretoria0028 South Africa Pretoria0083 South Africa

ISBN: (纸本)9798350337617

In the world of technology, there are several emerging technologies that are driving research towards making the Intelligent Edge suitable for various application growth. Some of these technologies include Artificial Intelligence, the Internet of Things, Virtualization, and Edge Computing. Virtualization is a popular choice as it provides adaptable development of services. Meanwhile, Artificial Intelligence offers promising data manipulation opportunities, and Edge Computing provides lower latency and higher data privacy to users. This paper focuses on the architecture for virtual service deployment in the Intelligent Edge, with a particular emphasis on significant concepts such as Virtualization, Network Function Virtualization, Artificial Intelligence, and the Intelligent Edge. The paper also discusses various modifications for virtual services, such as the Round Robin Algorithm, Minimum-Minimum algorithm, Multiheuristic Algorithm, and Particle Swarm Optimization Algorithm. These algorithms are compared based on performance indicators such as makespan, standard deviation, degree of imbalance, and processing speed. While the results vary from one algorithm to another, they suggest that there is always room for improvement. Furthermore, the paper presents future opportunities for virtual service deployment in Intelligent Edge Computing. © 2023 IEEE.

关键词： scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

DeFT: Mitigating Data Dependencies for Flexible Communication scheduling in Distributed Training

arXiv

引用

arXiv 2025年

作者： Meng, Lin Sun, Yuzhong Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China

Communication scheduling aims to reduce communication bottlenecks in data parallel training (DP) by maximizing the overlap between computation and communication. However, existing schemes fall short due to three main issues: (1) hard data dependencies break some overlapping between communication and computation;(2) high coverage rates impair further improvement on performance;(3) imbalanced communication/computation times of tensors caused by partitioning/fusion strategies cause more bubbles. To address these drawbacks, we propose a new communication scheduling scheme DeFT, whose key insight is to mitigate data dependencies and support flexible scheduling in distributed training. DeFT uncovers new overlapping chances in training by transforming the scheduling problem into multiple knapsack problems. Specifically, DeFT eliminates hard dependencies with delayed updates, reducing the coverage rate by adjusting update frequency and utilizing heterogeneous communication links, merging the computation times of backward or forward as the knapsack capacity to avoid the negative impact of unbalanced tensors. Additionally, DeFT preserves training accuracy by adjusting its scheduling strategy via convergence loss quantification. Extensive experiments with 16 A100 GPUs showed that DeFT achieved speedups of 29% to 115% on three representative benchmarks compared to US-Byte and Bytescheduler with no loss of accuracy. Copyright © 2025, The Authors. All rights reserved.

关键词： scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Performance Comparison on Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) in Fog-Cloud Workflow Task scheduling

Performance Comparison on Genetic Algorithm (GA) and Particl...

引用

Computer Applications (ICCA), IEEE Conference on

作者： Zun Myat Myat Soe Tin Zar Thaw Yu Mon Zaw Faculty of Computer Science University of Computer Studies Yangon (UCSY) Yangon Myanmar

ISBN: (数字)9798331534592

ISBN: (纸本)9798331534608

In future, most of the electronic devices will be smart or Internet-of-Things (IoT) devices. These devices will be applicable and occupied in organizations, offices and homes, etc. A huge amount of data (big data) from their sensors needs to process real-time data or in a specified time with low latency. Fog computing was a solution to process these data faster because it is processed at fog nodes which are nearer the users rather than cloud nodes in spite of limited computing resources. To complete the tasks in few times and reduce the delay time, effective task scheduling is also required in Fog-Cloud environment. This paper presents and analyzes the performance of workflow task scheduling algorithms: Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) with different workflow settings (Montage, Cybershake, Epigenomics, Inspiral, and Sipht). As the Quality of Service (QoS) parameters in terms of makespan, cost, execution time, energy consumption and so on will be shown in terms of experimental results.

关键词： Energy consumption Costs Processor scheduling scheduling algorithms Quality of service scheduling Servers Particle swarm optimization Genetic algorithms Edge computing

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：