检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Keshtiarast, Navid Bishoyi, Pradyumna Kumar Petrova, Marina Mobile Communications and Computing RWTH Aachen University Aachen Germany

In this paper, we address the problem of scheduling sensing and communication functionality in an integrated sensing and communication (ISAC) enabled base station (BS) operating in an indoor factory (InF) environment. The BS is performing the task of detecting an AGV while managing downlink transmission of ultra-reliable low-latency communication (URLLC) data in a time-sharing manner. scheduling fixed time slots for both sensing and communication is inefficient for the InF environment, as the instantaneous environmental changes necessitate a higher frequency of sensing operations to accurately detect the AGV. To address this issue, we propose an environment-aware scheduling scheme, in which we first formulate an optimization problem to maximize the probability of detection of AGV while considering the survival time constraint of URLLC data. Subsequently, utilizing the Nash bargaining theory, we propose an adaptive time-sharing scheme that assigns sensing duration in accordance with the environmental clutter density and distributes time to URLLC depending on the incoming traffic rate. Using our own Python-based discrete-event link-level simulator, we demonstrate the effectiveness of our proposed scheme over the baseline scheme in terms of probability of detection and downlink latency. 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

Task scheduling in Server Farms with Reinforcement Learning

Task Scheduling in Server Farms with Reinforcement Learning

引用

Computer Information Science and Application Technology (CISAT), International Conference on

作者： Chao Deng Jianxiong Wan Chuyi Liu Leixiao Li Inner Mongolia University of Technology Huhhot China Inner Mongolia Autonomous Region Engineering & Technology Research Center of Big Data Based Software Service Huhhot China

ISBN: (数字)9798350375107

ISBN: (纸本)9798350375114

Multi-task concurrent scheduling is crucial to improving system performance. Commonly used traditional scheduling algorithms (random, greedy, etc.) are usually difficult to cope with dynamic tasks and resource requirements, resulting in unsatisfactory results. This paper proposes a deep reinforcement learning (DRL) method to solve the scheduling problem by modeling it as a Markov decision process (MDP). The Deep Q Network (DQN) algorithm uses experience replay to enhance learning stability and performance through training strategies and value networks. The training reward results show that it is 40.1 7% higher than the random scheduling strategy, proving its effectiveness.

关键词： Training Greedy algorithms scheduling algorithms Heuristic algorithms System performance Multitasking Stability analysis Resource management Servers Optimization

来源：评论

学校读者我要写书评

暂无评论

Weight-ETL: A Multi-Stage Cluster scheduling Method for Medical Data Governance

Weight-ETL: A Multi-Stage Cluster Scheduling Method for Medi...

引用

Big Data, Information and Computer Network (BDICN), International Conference on

作者： Kefan Wu Dapeng Tao Linfei Wang Jun Ni Da Zhu School of Information Yunnan University Kunming China

ISBN: (数字)9798350363821

ISBN: (纸本)9798350374612

ETL cluster scheduling technology plays a crucial role, which unveils the latent value of medical data and improve the medical digitization. However, in real-world scheduling scenarios, variations in the performance configurations of cluster nodes can significantly impact scheduling times. In addition, most mainstream ETL tools often neglect hospital business requirements in the governance process, leading to meaningless time consumption for important *** solve these problems, we propose the Weight-ETL, a multi-stage cluster scheduling algorithm specifically tailored for medical data governance. This algorithm takes into account the task importance and node performance comprehensively throughout the ETL governance process, thus enhancing data governance efficiency and aligning with hospital requirements. Quantitative experiments demonstrate that our proposed algorithm effectively prioritizes the tasks with high demand relevance and improves the efficiency of cluster scheduling compared with previous methods.

关键词： Industries Job shop scheduling Hospitals scheduling algorithms Heuristic algorithms System performance Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Optimal scheduling of AC/DC Hybrid Microgrids Based on Objective Cascade Method

Optimal Scheduling of AC/DC Hybrid Microgrids Based on Objec...

引用

Frontiers of Power and Energy (ACFPE), Asian Conference on

作者： Pengcheng Zhang Jie Wang Fei Zheng Ning Luo Yan Zhang Tao You Power Grid Planning and Research Center Guizhou Power Grid Co. Ltd Guiyang China Electrical Engineering College Guizhou University Guiyang China

ISBN: (数字)9798350367676

ISBN: (纸本)9798350378467

Microgrids are key network structures for promoting distributed power generation and renewable energy integration, and for achieving the intelligentization of traditional power grids. Faced with microgrid clusters with multiple operators, the regional distribution network energy management center needs to optimize the system to coordinate the interests of all parties. This paper aims for optimal economic benefits, considers the randomness of distributed power sources, uses box uncertainty sets to handle uncertainty, and introduces the Analytical Target Cascading (ATC) method to build a two-layer optimization scheduling model. The upper layer model is responsible for regional scheduling optimization, and the lower layer model optimizes AC/DC microgrids, achieving independent optimization. Case studies have verified the algorithm's rapidity and good convergence.

关键词： Analytical models Uncertainty scheduling algorithms Optimal scheduling Microgrids scheduling Security Energy management Convergence Load modeling

来源：评论

学校读者我要写书评

暂无评论

Resource scheduling for Cloud Computing in Space Information Networks Using Deep Reinforcement Learning

Resource Scheduling for Cloud Computing in Space Information...

引用

Sustainable Computing and Integrated Communication in Changing Landscape of AI (ICSCAI), International Conference on

作者： RenukaJyothi. S Shweta Loonkar Raman Batra Department of Biotechnology and Genetics School of Sciences JAIN (Deemed to be University) Bangalore Karnataka India Department of ISME ATLAS SkillTech University Mumbai Maharashtra India Department of Mechanical Engineering Noida Institute of Engineering & Technology Greater Noida Uttar Pradesh India

ISBN: (数字)9798350355338

ISBN: (纸本)9798350355345

The introduction of Space Communication Networks (SIN. SIN) has become critical in several sectors of satellite technological advancement. Because of the complicated interactions between resources and activities, these networks-which are built to provide ever-more-complex services and handle an ever-widening range of tasks-present a challenge to current resource scheduling algorithms. Our suggested resource allocation plan makes use of reinforcement learning to overcome this. First, acknowledging the special qualities of SIN resources, that we have developed an architecture of cloud computing designed for SINs, guaranteeing consistent resource management. Lastly, we address the complex problem of joint planning of resources by modelling the process using a reinforcement learning approach. Practically speaking, the outcomes of our simulation confirm that the suggested plan is effective. It shows a significant decrease in resource usage, a reduction in task execution time, and a significant increase in SINs' total resource utilisation efficiency.

关键词： Cloud computing Technological innovation Schedules scheduling algorithms Space communications Ecosystems Computer architecture Resource management Internet of Things Information systems

来源：评论

学校读者我要写书评

暂无评论

Deterministic scheduling Algorithm Based on Proportional Conflict and Deadline in Industrial Wireless Networks

引用

Journal of Computers (Taiwan) 2024年第1期35卷 195-206页

作者： Zhao, Xuan Shen, Bo Zhang, Maojie Liu, Ying Shi, Guohua Zhao, Peng Zhang, Zhiyuan School of Electronic and Information Engineering Beijing Jiaotong University Beijing100044 China Key Laboratory of Communication and Information Systems Beijing Jiaotong University Beijing100044 China Xincheng Information Technology Co. Ltd China

Deterministic scheduling technology is of great significance for the real-time and deterministic transmission of industrial wireless network data. In view of the fact that the industrial wireless network data stream itself has priority classification attribute, this paper, based on multi-channel time-division multiple access (TDMA) technology, analyzes link conflict delay and channel contention delay caused by high priority data stream to low priority data stream, and performs scheduling preprocessing on the network, so as to eliminate the network with unreasonable parameters, and feedback to the network manager. For preprocessed networks, the scheduling algorithm prioritizes the allocation of time slots and channel resources for links of high priority data streams, while for data streams belonging to the same priority class, a scheduling scheme based on Maximum Proportional Conflict and Deadline First (MPC-D) is proposed. Under the premise of meeting schedulability conditions, time slots and channel resources are allocated sequentially according to the proportional conflict deadline values of each link, from largest to smallest. The experimental results show that the proposed scheduling algorithm can achieve a high network scheduling success rate. © 2024 Codon Publications. 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

Adaptive Multi-Core Real- Time scheduling Based on Reinforcement Learning

Adaptive Multi-Core Real- Time Scheduling Based on Reinforce...

引用

International Conference on Control and Automation (ICCA)

作者： Yonghui Liang Hui Li Fei Shen Qimin Xu Shuna Hua Shanying Zhu Department of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Re-search Center of Intelligent Control and Management Shanghai China Key Laboratory of Wireless Sensor Network and Communications Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences Shanghai China North Information Control Research Academy Group Company Ltd. Nanjing China

ISBN: (数字)9798350354409

ISBN: (纸本)9798350354416

With the transformation towards industrial intel-ligence, multi-core processors are increasingly being applied in real-time networked control systems to ensure secure exe-cution of sensing, computing and actuating tasks under time constraints. However, existing scheduling methods result in either low CPU utilization or many missed task deadlines in dynamic systems. In this paper, we propose a two-layer scheduling architecture to address this issue by fully exploring the complex dependency between real-time tasks. To be specific, the local layer determines task execution priorities considering both dependency between tasks and deadline constraints by utilizing a reinforcement learning approach. Moreover, to better utilize the parallel capabilities of multi-core processors and reduce temporal collisions, this paper minimizes the requested core count for the task set based on a greedy strategy. The global layer designs a scheduling algorithm based on the pre-empt method and provides schedulability analysis of multiple task sets. Experimental results validate the correctness of the proposed scheduling approach, and efficiency is demonstrated through comparisons with baseline method.

关键词： Job shop scheduling Multicore processing scheduling algorithms Networked control systems Reinforcement learning Real-time systems Sensors

来源：评论

学校读者我要写书评

暂无评论

Non-clairvoyant scheduling with Partial Predictions

arXiv

引用

arXiv 2024年

作者： Benomar, Ziyad Perchet, Vianney ENSAE FAIRPLAY joint team CREST Palaiseau France Ecole polytechnique Palaiseau France Criteo AI Lab FAIRPLAY joint team Paris France

The non-clairvoyant scheduling problem has gained new interest within learning-augmented algorithms, where the decision-maker is equipped with predictions without any quality guarantees. In practical settings, access to predictions may be reduced to specific instances, due to cost or data limitations. Our investigation focuses on scenarios where predictions for only B job sizes out of n are available to the algorithm. We first establish near-optimal lower bounds and algorithms in the case of perfect predictions. Subsequently, we present a learning-augmented algorithm satisfying the robustness, consistency, and smoothness criteria, and revealing a novel tradeoff between consistency and smoothness inherent in the scenario with a restricted number of predictions. © 2024, CC BY.

关键词： scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

LoFi USER scheduling FOR MULTIUSER MIMO WIRELESS SYSTEMS

arXiv

引用

arXiv 2024年

作者： Gallyas-Sanhueza, Alexandra Marti, Gian Palhares, Victoria Wiesmayr, Reinhard Studer, Christoph Cornell University United States ETH Zurich Switzerland

We propose new low-fidelity (LoFi) user equipment (UE) scheduling algorithms for multiuser multiple-input multiple-output (MIMO) wireless communication systems. The proposed methods rely on an efficient guess-and-check procedure that, given an objective function, performs paired comparisons between random subsets of UEs that should be scheduled in certain time slots. The proposed LoFi scheduling methods are computationally efficient, highly parallelizable, and gradient-free, which enables the use of almost arbitrary, non-differentiable objective functions. System simulations in a millimeter-wave (mmWave) multiuser MIMO scenario demonstrate that the proposed LoFi schedulers outperform a range of state-of-the-art user scheduling algorithms in terms of bit error-rate and/or computational complexity. Copyright © 2024, 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

Intelligent Elastic scheduling Algorithm for Multi-Resource Low Earth Orbit Satellite Networks

Intelligent Elastic Scheduling Algorithm for Multi-Resource ...

引用

Computing, Communication, Perception and Quantum Technology (CCPQT), International Conference on

作者： Xinxin Yang Rui Huang Junyi Wu Jiahao Li Ying Wang Weihong Wu Jiang Liu China Satellite Network Application Co. Ltd Beijing China Beijing University of Posts and Telecommunications Beijing China Purple Mountain Laboratories Nanjing China University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798331528386

ISBN: (纸本)9798331528393

With the rapid development of satellite technology, satellite systems have gradually evolved into complex networks integrating multiple resources, such as bandwidth, storage, and energy. Modern low earth orbit (LEO) satellite networks are playing an increasingly important role in global communication, navigation, and the Internet of things (IoT). However, as the number of satellites grows and the diversity of resources increases, the complexity of satellite resource scheduling has also intensified. Existing single-resource scheduling methods are insufficient to meet the demands of such complex networks. To address this issue, this paper proposes a multi-resource intelligent elastic scheduling (MRIES) algorithm, aimed at optimizing task allocation and scheduling, improving resource utilization, and maximizing task completion efficiency. Simulation results demonstrate the effectiveness of the proposed algorithm in multi-resource scheduling scenarios.

关键词： Satellites scheduling algorithms Simulation Low earth orbit satellites Complex networks Satellite navigation systems scheduling Resource management Internet of Things Sorting

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：