检索结果-内蒙古大学图书馆

Quantum Computing and Engineering (QCE), IEEE International Conference on

作者： Albert Williams Nitish K. Panigrahy Andrew McGregor Don Towsley University of Massachusetts Amherst MA USA Binghamton University Binghamton NY USA

ISBN: (数字)9798331541378

ISBN: (纸本)9798331541385

As Low Earth Orbit (LEO) satellite mega constellations continue to be deployed for satellite internet and recent successful experiments in satellite-based quantum entanglement distribution emerge, a natural question arises: How should we coordinate transmissions and design scalable scheduling policies for a quantum satellite internet? In this work, we consider the problem of transmission scheduling in quantum satellite networks subject to resource constraints at the satellites and ground stations. We show that the most general problem of assigning satellites to ground station pairs for entanglement distribution is NP-hard. We then propose four heuristic algorithms and evaluate their performance for Starlink mega constellation under various amount of resources and placements of the ground stations. We find that the maximum number of receivers necessary per ground station grows very slowly with the total number of deployed ground stations. Our proposed algorithms, leveraging optimal weighted b-matching and the global greedy heuristic, outperform others in entanglement distribution rate, entanglement fidelity, and handover cost metrics. While we develop these scheduling algorithms, we have also designed a software system to simulate, visualize, and evaluate satellite mega-constellations for entanglement distribution.

关键词： Visualization Satellites Quantum computing Quantum entanglement scheduling algorithms Heuristic algorithms Software algorithms Low earth orbit satellites Receivers Software systems

来源：评论

学校读者我要写书评

暂无评论

Performance Comparison of Deep Reinforcement Learning and Genetic Algorithm for Workflow scheduling

Performance Comparison of Deep Reinforcement Learning and Ge...

引用

International Conference on Applied System Innovation (ICASI)

作者： Wei-Cheng Tseng Kuo-Chan Huang Dong-Sheng Zhan Department of Computer Science National Taichung University of Education Taichung Taiwan

ISBN: (数字)9798350394924

ISBN: (纸本)9798350394931

Traditionally, heuristic-based methods and guided random search are two major categories of workflow scheduling algorithms. Genetic Algorithm (GA) is a well-known guided random search method and has demonstrated effectiveness in previous research. In our previous work, the recently emerging Deep Reinforcement Learning (DRL) approach outperformed the state-of-the-art heuristic-based method, IPPTS. In this paper, we aim to further explore the advantages and effectiveness of DRL, and compare its performance in workflow scheduling to the well-known GA approach.

关键词： Technological innovation scheduling algorithms Search methods Deep reinforcement learning scheduling Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

EdgeTimer: Adaptive Multi-Timescale scheduling in Mobile Edge Computing with Deep Reinforcement Learning

EdgeTimer: Adaptive Multi-Timescale Scheduling in Mobile Edg...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE Computer and Communications Societies

作者： Yijun Hao Shusen Yang Fang Li Yifan Zhang Shibo Wang Xuebin Ren Xi’an Jiaotong University China

ISBN: (数字)9798350383508

ISBN: (纸本)9798350383515

In mobile edge computing (MEC), resource scheduling is crucial to task requests’ performance and service providers’ cost, involving multi-layer heterogeneous scheduling decisions. Existing schedulers typically adopt static timescales to regularly update scheduling decisions of each layer, without adaptive adjustment of timescales for different layers, resulting in potentially poor performance in *** notice that the adaptive timescales would significantly improve the trade-off between the operation cost and delay performance. Based on this insight, we propose EdgeTimer, the first work to automatically generate adaptive timescales to update multi-layer scheduling decisions using deep reinforcement learning (DRL). First, EdgeTimer uses a three-layer hierarchical DRL framework to decouple the multi-layer decision-making task into a hierarchy of independent sub-tasks for improving learning efficiency. Second, to cope with each sub-task, EdgeTimer adopts a safe multi-agent DRL algorithm for decentralized scheduling while ensuring system reliability. We apply EdgeTimer to a wide range of Kubernetes scheduling rules, and evaluate it using production traces with different workload patterns. Extensive trace-driven experiments demonstrate that EdgeTimer can learn adaptive timescales, irrespective of workload patterns and built-in scheduling rules. It obtains up to 9:1 more profit than existing approaches without sacrificing the delay performance.

关键词： Multi-access edge computing Costs Processor scheduling scheduling algorithms Production Deep reinforcement learning Reliability engineering

来源：评论

学校读者我要写书评

暂无评论

A Programmable Packet scheduling Method Based on Traffic Rate

A Programmable Packet Scheduling Method Based on Traffic Rat...

引用

Control, Electronics and Computer Technology (ICCECT), IEEE International Conference on

作者： Liangliang Kang Le Tian Yuxiang Hu Zhengzhou University Zhengzhou China PLA Strategic Support Force Information Engineering University Zhengzhou China

ISBN: (数字)9798350380958

ISBN: (纸本)9798350380965

Network congestion results in high queuing delays and increased flow completion time, significantly deteriorating the quality of network services. To mitigate network congestion, this paper proposes an active queue management scheme based on traffic rate control (Traffic Rate Control based AQM, TRC-AQM), operating entirely on the modern programmable switch. TRC-AQM monitors packets' enqueuing time to predict the congestion status of a switch and uses a sliding window to calculate the relative rank of the arrival packet. Based on the congestion status and relative rank, the arrival packet is either dropped or enqueued, mitigating network congestion while providing differentiated quality of service. Experimental results show that, for flows sharing a single queue, TRC-AQM can effectively alleviate congestion, and stabilize the queue length to a very low level while maintaining high link utilization, leading to a highly reduced flow completion time for flows with high priority.

关键词： scheduling algorithms Switches Quality of service Control systems Delays Monitoring

来源：评论

学校读者我要写书评

暂无评论

Research on the Resource Allocation Optimization Model of Automobile Based on Cloud Computing Resource scheduling Algorithm

Research on the Resource Allocation Optimization Model of Au...

引用

Signal Processing, Communications and Engineering Management Conference (ISPCEM), International

作者： Kang Kai Zhu Peipei Zhang Fan China Automotive Technology and Research Center Co. Ltd. Tianjin China China Auto Information Technology (Tianjin) Co. Ltd. Tianjin China

ISBN: (数字)9798331528676

ISBN: (纸本)9798331528683

This paper proposes a global resource allocation optimization model based on cloud computing, aiming to improve the global resource management efficiency of automobile enterprises through cloud computing resource scheduling algorithm. The system makes full use of the flexibility and scalability of cloud computing, and designs a set of advanced resource scheduling algorithms, which can dynamically adjust the allocation of computing resources according to the changes in demand in different markets and regions around the world, ensuring that resources can be optimally configured at different times and regions. The simulation results show that the model has significantly improved the resource allocation efficiency compared with traditional methods, which not only greatly improves the resource utilization rate, but also effectively reduces the operating costs of enterprises. The cloud computing resource scheduling algorithm shows higher computing efficiency and economic benefits when dealing with complex resource allocation problems. Compared with the traditional static scheduling method, the algorithm proposed in this paper shows its excellent adaptability when dealing with fluctuations in global resource demand, and provides a new technical path and practical basis for the resource allocation optimization of automobile enterprises in the context of globalization.

关键词： Cloud computing scheduling algorithms Optimization models Simulation Globalization Signal processing algorithms scheduling Resource management Automobiles Optimization

来源：评论

学校读者我要写书评

暂无评论

Online scheduling in Virtualized TSN Networks via Joint Admission Control and VNF Embedding

Online Scheduling in Virtualized TSN Networks via Joint Admi...

引用

IEEE International Conference on Communications in China (ICCC)

作者： Yajing Zhang Cailian Chen Chaoqun You Mingyan Li Xinping Guan Tony Q. S. Quek Department of Automation Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Jiao Tong University Shanghai P. R. China School of Computer Science Fudan University College of Computer Science Chongqing University Chongqing P. R. China Information Systems Technology and Design Singapore University of Technology and Design Singapore

ISBN: (数字)9798350378412

ISBN: (纸本)9798350378429

Introducing virtualization enhances the flexibility of time-sensitive networking (TSN), wherein applications manifest as service function chains comprising a series of virtual network functions (VNFs). However, such virtualized TSN realizes determinacy through global configuration, being too complicated to serve dynamic applications in time. To address this issue, we innovatively propose to achieve TSN scheduling by distributively executing admission control (AC), whereby the scheduling complexity is radically reduced. Specifically, we first build a two-way AC model that captures TSN multi-queue characteristics. Then, we define admissible regions of nodes and links, working as metrics for AC decision-making and enabling feasible TSN scheduling. Built upon this, we propose a joint AC and VNF embedding mechanism, Rapid Admission Control (RapidAC), which consists of two algorithms. The first algorithm responds to dynamic applications rapidly and derives node-mapping solutions by judging nodes’ admissible regions. Based on this, the second algorithm augments the detailed VNF embedding solution according to admissible regions of links. Simulation results show that RapidAC reduces runtime by 90% compared with existing TSN scheduling algorithms.

关键词： Measurement Runtime scheduling algorithms Service function chaining Heuristic algorithms Simulation Admission control

来源：评论

学校读者我要写书评

暂无评论

Opportunistic Energy-Aware scheduling for Container Orchestration Platforms Using Graph Neural Networks

Opportunistic Energy-Aware Scheduling for Container Orchestr...

引用

IEEE/ACM International Symposium on Cluster Computing and the Grid (CCGRID)

作者： Philipp Raith Gourav Rattihalli Aditya Dhakal Sai Rahul Chalamalasetti Dejan Milojicic Eitan Frachtenberg Stefan Nastic Schahram Dustdar TU Wien Vienna Austria Hewlett Packard Labs Milpitas USA

ISBN: (数字)9798350395662

ISBN: (纸本)9798350395679

Reducing the energy consumption of data centers is critical to meeting international climate goals and lowering operation costs. Container orchestration platforms can help counteract this trend by optimally placing applications across the infrastructure to increase resource utilization and reduce energy consumption. But platforms in use today are still energy-agnostic and do not offer any insights into energy consumption. In this paper, we present a monitoring framework and a new modeling approach for resource usage in data centers. The model captures heterogeneous hardware and software and acts as input for a Graph Neural Network (GNN) to predict power consumption. Based on this model, we derive a set of container scheduling algorithms that opportunistically schedule applications based on the estimated energy impact of incoming containers. Our results show that the GNN-based prediction model is very accurate and achieves an average RMSE (Root Mean Square Error) of 7.5%. We have implemented a custom scheduler to demonstrate the benefits of using our prediction, and our scheduler can decrease energy consumption on average by 6.2% without any code changes for the application and without increasing workload completion time compared to the default Kubernetes scheduler.

关键词： Energy consumption Data centers Schedules Power demand scheduling algorithms Containers Predictive models Graph neural networks Data models Software

来源：评论

学校读者我要写书评

暂无评论

Research on Task scheduling Methods in 5G Mobile Edge Computing Environments

Research on Task Scheduling Methods in 5G Mobile Edge Comput...

引用

Energy, Power and Grid (ICEPG), International Conference on

作者： Guangping Zhu Tianji Liu Yongshan Guo Danlei Xia Dongdong Lv Xiaohui Zhang Research and Development Center State Grid Information and Telecommunication Group Co Ltd. Beijing China Research Development Center State Grid Information and Telecommunication Group Co. Ltd Beijing China

ISBN: (数字)9798350377798

ISBN: (纸本)9798350377804

With the development of smart grids, power data presents characteristics of massive volume, high speed, and high heterogeneity, posing higher requirements for data processing and transmission capabilities. The innovation of 5G technology has made edge computing more widely applied in smart grids, helping to solve data transmission bottlenecks, reduce latency, and enhance real-time monitoring capabilities. This paper combines the FCFS, EDF, and SJF algorithms to propose a new comprehensive scheduling algorithm, DWECS (Dynamic Weighted Edge Computing Scheduler). By setting task priorities and resource allocation strategies, DWECS effectively improves task completion efficiency and controls system operating costs. This research provides a new method for edge computing task scheduling in smart grids and supports the intelligent and economic management of distribution networks.

关键词： Energy consumption Technological innovation scheduling algorithms 5G mobile communication Heuristic algorithms System performance Power system dynamics Dynamic scheduling Smart grids Edge computing

来源：评论

学校读者我要写书评

暂无评论

PROACTIVE AND REACTIVE CONSTRAINT PROGRAMMING FOR STOCHASTIC PROJECT scheduling WITH MAXIMAL TIME-LAGS

arXiv

引用

arXiv 2024年

作者： van den Houten, Kim Planken, Léon Freydell, Esteban Tax, David M.J. de Weerdt, Mathijs Delft University of Technology Delft Netherlands DSM-Firmenich Delft Netherlands

This study investigates scheduling strategies for the stochastic resource-constrained project scheduling problem with maximal time lags (SRCPSP/max)). Recent advances in Constraint Programming (CP) and Temporal Networks have re-invoked interest in evaluating the advantages and drawbacks of various proactive and reactive scheduling methods. First, we present a new, CP-based fully proactive method. Second, we show how a reactive approach can be constructed using an online rescheduling procedure. A third contribution is based on partial order schedules and uses Simple Temporal Networks with Uncertainty (STNUs). Our analysis shows that the STNU-based algorithm performs best in terms of solution quality, while also showing good relative computation time. © 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

FTTA: Optimizing Resource Utilization in Cloud Environment using Meta-Heuristic scheduling Algorithm

FTTA: Optimizing Resource Utilization in Cloud Environment u...

引用

Self Sustainable Artificial Intelligence Systems (ICSSAS), International Conference on

作者： Corbin Reginald Bennett Rohan Reddy Oduru Dominick McLaughlin Lokesh Parvathaneni Noah Bryan Riquelme Santhosh Kumar Medishetti George Mason University USA Nalla Narasimha Reddy Education Society’s Group of Institution India VIT-AP University Amaravathi India

ISBN: (数字)9798350368413

ISBN: (纸本)9798350368420

In Cloud Computing (CC) environment, optimizing resource utilization is critical for enhancing performance, reducing energy consumption, and minimizing operational costs. This paper introduces a novel Football Team Training Algorithm (FTTA) designed to improve resource allocation and utilization in dynamic cloud environments. Inspired by the collaborative and strategic dynamics of football team training, FTTA models tasks as players, assigning them to available cloud resources based on real-time workload and performance metrics. The algorithm effectively balances exploration and exploitation, ensuring that resources are allocated optimally while minimizing underutilization or overloading. Simulation results demonstrate that FTTA improves resource utilization by 20.6%, reduces task completion time by 16%, and enhances throughput by 18.4% when compared to traditional algorithms. These improvements make FTTA a promising approach for cloud service providers aiming to optimize resource management and deliver superior quality of service (QoS).

关键词： Training Cloud computing scheduling algorithms Heuristic algorithms Simulation Quality of service Dynamic scheduling Throughput Resource management Sports

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：