检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Deng, Xuanliang Sifat, Ashrarul H. Huang, Shaoyu Wang, Sen Huang, Jiabin Jung, Changhee Williams, Ryan Zeng, Haibo Purdue University United States University of Maryland United States

This paper is motivated by robotic systems that solve difficult real-world problems such as search and rescue (SAR). These applications require robots to operate in uncertain environments while maintaining safe interactions with human. We study the scheduling of real-time applications on heterogeneous hardware platforms inspired by such contexts. To capture the stochasticity due to unpredictable environments, we propose the stochastic heterogeneous parallel conditional DAG (SHPC-DAG) model, which extends the most recent HPC-DAG model in two regards. First, it uses conditional DAG nodes to model the execution of computational pipelines based on context, while the stochasticity of DAG edges captures the uncertain nature of a system’s environment or the reliability of its hardware. Second, considering the pessimism of deterministic worst-case execution time (WCET), it uses probability distributions to model the execution times of subtasks (DAG nodes). We propose a new partitioning algorithm Least Latency Partitioned (LLP), which considers precedence constraints among nodes during the allocation process. Coupled with a scheduling algorithm that accounts for varying subtask criticality and constraints, the end-to-end latencies of safety-critical paths/nodes are then minimized. We use tasksets inspired by real robotics to demonstrate that our framework allows for more flexible representation of timing constraints, and safety-performance tradeoffs. © 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

Research on scheduling algorithm for unmanned trucks in open-pit coal mines

Research on scheduling algorithm for unmanned trucks in open...

引用

Information Technology,Big Data and Artificial Intelligence (ICIBA), International Conference on IEEE International Conference on

作者： Kejie Wu Chongqing Research Institute of China Coal Science and Industry Group China State Key Laboratory of Gas Disaster Monitoring and Emergency Technology China

ISBN: (数字)9798350363609

ISBN: (纸本)9798350363616

Aiming at the multi-objective traffic flow allocation and scheduling problem of unmanned trucks in open-pit mines, a traditional multi-objective traffic flow allocation and scheduling model for open-pit mine trucks was established from three aspects: revenue, cost, and ore quality, with the objective functions of minimizing transportation costs, minimizing total queue time of unmanned trucks, and minimizing grade deviation. Combining multi-objective genetic algorithm and decomposition based multi-objective optimization algorithm adaptability and characteristics, a new decomposition based constrained dominance principle NSGA-II (DBCDP-NSGA-II) optimization algorithm based on decomposition constrained dominance was proposed, which combines Pareto dominance and decomposition with constraint dominance. And the algorithm was applied to solve the multi-objective traffic flow allocation and scheduling model of unmanned trucks in open-pit mines. The results showed that the traffic flow allocation and scheduling algorithm reduced the transportation cost in open-pit mining, reduced the queuing time of unmanned trucks, and effectively controlled the fluctuation of grade.

关键词： Adaptation models Costs Fluctuations scheduling algorithms Ores Transportation scheduling Resource management Optimization Testing

来源：评论

学校读者我要写书评

暂无评论

MJSCHED: A Moldable Job scheduling Algorithm in Heterogeneous Resource Environment

MJSCHED: A Moldable Job Scheduling Algorithm in Heterogeneou...

引用

International Conference on Computer and Communications (ICCC)

作者： Tianhai Zhao Zichen Yang Yunlan Wang Jianhua Gu Zhengxiong Hou School of Computer Science Northwestern Polytechnical University Xi'an China

ISBN: (数字)9798331507077

ISBN: (纸本)9798331507084

Moldable jobs have the ability to dynamically adjust their resource requirements before execution, offering greater flexibility compared to rigid jobs that allocate fixed resources. Currently, most resource management systems do not fully consider the resource requirements of moldable jobs, and few scheduling algorithms address the scheduling of such jobs, especially those requiring both CPU and GPU resources. In this paper, we propose a moldable job backfill algorithm(MJSched) that dynamically adjusts job resource allocation to reduce turnaround time. First, a resource allocation strategy that minimizes turnaround time is applied to jobs at the head of the waiting queue. We utilize a greedy algorithm and a genetic algorithm to construct the set of backfill jobs, determine the computational nodes, and allocate the number of tasks for these jobs. Furthermore, a profit-first remaining resource scheduling strategy is proposed. We implement the Slurm scheduling plug-in based on our moldable job scheduling algorithm to support moldable job scheduling in heterogeneous resource environments. Simulation experiments demonstrate that our MJSched-GA algorithm effectively reduces both average job turnaround time and average job waiting time by 15.7%-22% and 18.8%-26.2% respectively, while improving cluster resource utilization by 8%-14 %.

关键词： Greedy algorithms scheduling algorithms Heuristic algorithms High performance computing Clustering algorithms Graphics processing units Dynamic scheduling Genetics Resource management Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Assessment of Real time scheduling Strategies on RTOS

Assessment of Real time Scheduling Strategies on RTOS

引用

Intelligent Systems and Machine Learning Conference (ISML)

作者： Dhruva R. Rinku M. AshaRani Dept. of ECE CVR College of Engineering Hyderabad India Dept. of ECE JNTUH Hyderabad India

ISBN: (数字)9798350343878

ISBN: (纸本)9798350343885

This paper presents a comparative study of well-known real time schedulers, Earliest Deadline First (EDF) and the Rate Monotonic (RM) schedulers with the objective to evaluate their performance and suitability for real-time embedded applications on FreeRTOS. Synthetic tasks were developed to simulate real-world scenarios. Performance metrics, including average wait time, number of context switches, and CPU utilization, are then employed to assess the effectiveness of the schedulers. Results demonstrate that EDF outperforms RM in terms of deadline miss ratio, particularly under high system load. EDF also tends to minimize average wait time; however, it may result in a higher number of context switches. In contrast, RM exhibits higher average wait time but generally has fewer context switches. It is noteworthy that the difference between EDF and RM becomes less significant for periodic tasks with deadlines equal to their period, thereby increasing the performance dependability on the total number of tasks that are to be scheduled. The findings aim to assist system designers in making informed decisions when selecting a suitable scheduling algorithm for their real-time applications.

关键词： Embedded systems scheduling algorithms Switches Machine learning Dynamic scheduling Real-time systems Synchronization Resource management Kernel Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Hybrid Time-Triggered and Event-Triggered Flow scheduling for Time-Sensitive Networking (TSN)

Hybrid Time-Triggered and Event-Triggered Flow Scheduling fo...

引用

International Conference on Computer and Communications (ICCC)

作者： Yiming Xu Kaixuan Kang Qianyi Tan Suzhi Cao Peng Liu University of Chinese Academy of Sciences Beijing China Key Laboratory of Space Utilization Chinese Academy of Sciences Beijing China Technology and Engineering Center for Space Utilization Chinese Academy of Sciences Beijing China

ISBN: (数字)9798331507077

ISBN: (纸本)9798331507084

Time-sensitive Networking (TSN) is an emerging technology that aims to solve the problem of precise network latency control in next generation industrial networks. In addition to conventional best-effort flows, TSN needs to deliver time critical flows, which are of high-priority. To ensure deterministic latency for time-critical flows, various scheduling models have been developed. However, those models are primarily designed for time-triggered (TT) critical flows, which are predictable and periodic. In realistic industrial scenarios, often there exist event-triggered (ET) critical flows, which are bursty and may have higher priority than time-triggered flows. In this paper, we design an enhanced TACQ model to meet the requirements of managing event-triggered flows, without affecting the deterministic transmission of time-triggered flows. On top of this model, we propose a corresponding event-triggered flows scheduling algorithm. Furthermore, to reduce the computation time of time-triggered flows scheduling, we propose a weighted sorting algorithm based on path optimization (WSPO). Simulations are conducted to evaluate the performance of our model and algorithms. Compared to traditional models and algorithms, the proposed methods can better handle hybrid critical flows.

关键词： Job shop scheduling Event detection scheduling algorithms Computational modeling Interference Predictive models Time factors Optimization Next generation networking Sorting

来源：评论

学校读者我要写书评

暂无评论

BachLedger: Orchestrating Parallel Execution with Dynamic Dependency Detection and Seamless scheduling

BachLedger: Orchestrating Parallel Execution with Dynamic De...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Yi Yang Guangyong Shang Guangpeng Qi Zhen Ma Yaxiong Liu Jiazhou Tian Aocheng Duan Meng Zhang Jingying Li Xuan Ding School of Software Tsinghua University Beijing China Inspur Yunzhou Industrial Internet Co. Ltd Jinan Shandong China School of Cyber Engineering Xidian University Xi’an Shaanxi China

ISBN: (数字)9798331515966

ISBN: (纸本)9798331515973

Blockchain technology inherently necessitates redundant computation to achieve consensus among untrusted parties because of its fundamental threat model. This requirement, however, compromises system performance and impedes the widespread adoption of blockchain. To leverage existing physical resources, current research on high-performance consortium blockchain algorithms and architectures frequently employs cluster-node architectures to expand the parallel processing capability of traditional single physical nodes. Our investigation reveals a significant trend as the parallel capability of individual nodes improves. The idle time caused by synchronization of all transactions within each block, previously considered negligible, has become increasingly significant. To address this, we present BachLedger, which implements Seamless scheduling to fully utilize inter-block thread idle time, thereby augmenting system resource utilization and achieving overall performance improvements. Our experimental results demonstrate that our algorithm surpasses current state-of-the-art (SOTA) performance levels in high-performance consortium blockchains and effectively resolves the aforementioned synchronization issue. Furthermore, this scheduling algorithm offers enhanced scalability for BachLedger, positioning it as a promising solution for future blockchain implementations.

关键词： Threat modeling scheduling algorithms System performance Scalability Computer architecture Parallel processing Dynamic scheduling Blockchains Synchronization Resource management

来源：评论

学校读者我要写书评

暂无评论

Research on the verification method of the Event-B model for the heterogeneous multi-core scheduling algorithm

Research on the verification method of the Event-B model for...

引用

Communication Technology and Information Technology (ICCTIT), International Conference on

作者： Junjie Zuo Yahui Han Feng Xiao Shujuan Huang School of Computer Science and Engineering Xi’an Technological University Xi’an China

ISBN: (数字)9798331528973

ISBN: (纸本)9798331528980

It is well known that the logical verification for the operating system is very essential. Event-B, as a formal verification tool, is one of the most widely used methods for verifying programs at the operating system level. However, it lacks the precise time semantics expression that will make the representation of the behavioral logic complicated for verified scheduling process. To address this limitation, we proposes an EMPT (Event-B Multi-core Processor Time) model in rodin platform, which can represent the time semantics by using set mappings and operations. After that we apply it to the logical verification for the heterogeneous multicore scheduling algorithm (HEFT), and the results show that it can verify the accuracy of this algorithm.

关键词： scheduling algorithms Multicore processing Operating systems EMTP Semantics Communications technology Timing Logic Information technology Formal verification

来源：评论

学校读者我要写书评

暂无评论

An Improved Grey Wolf Optimizer with Flexible Crossover and Mutation for Cluster Task scheduling

SSRN

引用

SSRN 2024年

作者： Wang, Hongbo Zhang, Jinyu Fan, Jingkun School of Computer and Communication Engineering University of Science and Technology Beijing Beijing100083 China USTB-CERIS Joint Innovation Centre of Big Data Science for Intelligent Construction and Smart Operation University of Science and Technology Beijing Beijing100083 China

Recently, with the rapid development of cloud computing, task scheduling algorithms inspired by nature have become a research hotspot. The Grey Wolf Optimizer (GWO) have garnered increasing followers due to its strong convergence ability, and ease of implementation. To broaden the application scope of GWO, this paper proposes an improved GWO model with flexible crossover and mutation (GWO_C/M), which can adaptively adjust their strategy coefficients of action for different problem-solving stages. Essentially, GWO_C/M provides a quantifiable basis for striking a balance between exploration and exploration, improve the algorithm's robustness, and enhance overall performance. After extensive comparisons with eight state-of-the-art models in five typical scenarios explore the adaptability of GWO_C/M with different combinations of crossover and mutation strategies in various problems have conducted, the results demonstrate the proposed GWO_C/M performs well on 24 representative benchmarks among 38 different typical problems, achieving a success rate of 63%. Furthermore, CloudSim simulations reveal exciting improvements in three well-known performance evaluation metrics: total system execution time, completion time, and load balancing degree. Finally, practical experiments on the Alibaba Cluster Trace V2018 confirm that GWO_C/M can enhance resource utilization and reduce the maximum completion time of tasks, thereby bringing substantial benefits to the overall system performance. © 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

A System Utility Optimization-based Task Offloading and Computing scheduling Algorithm for Low Earth Orbit Satellite Networks

A System Utility Optimization-based Task Offloading and Comp...

引用

IEEE International Conference on Communications (ICC)

作者： Yin Wang Kang'An Gui Rong Chai School of Communications and Information Engineering Chongqing University of Posts and Telecommunications China

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

In this paper, we investigate the joint task offloading and computing scheduling in low earth orbit (LEO) satellite networks, which consists of a number of ground terminals (GTs) and multiple LEO satellites. Considering the characteristics of tasks and the energy consumption of task execution, we define a system utility function, and formulate the problem of task offloading and computing scheduling as a constrained system utility function maximization problem. The formulated optimization problem is a mixed integer non-linear programming problem which cannot be solved conveniently. To solve the formulated optimization problem, we first propose local computing scheduling algorithm to determine the task local partition strategy. And then priority-based offloading and computing scheduling algorithm is proposed to determine the task offloading strategy. The effectiveness of the proposed algorithm is verified through simulations in satellite tool kit (STK) and MATLAB.

关键词： Satellites scheduling algorithms Simulation Low earth orbit satellites Programming scheduling Partitioning algorithms

来源：评论

学校读者我要写书评

暂无评论

Channel-Aware Rotating Priority Queue scheduling with Delay Deadline over Wireless Links

Channel-Aware Rotating Priority Queue Scheduling with Delay ...

引用

International Conference on Wireless Communications and Signal Processing (WCSP)

作者： Yankai Zhang Wei Wang Xinglin Yang Yitu Wang Wenkai Zhang Zhaoyang Zhang College of Information Science and Electronic Engineering Zhejiang University Hangzhou China School of Electrical and Information Engineering North Minzu University Yinchuan China

ISBN: (数字)9798350390643

ISBN: (纸本)9798350390650

Conventional Rotating Priority Queues (RPQ) scheduling adopted in Time-Sensitive Networks (TSN) fails to achieve desired performance over time-varying wireless channel. In this paper, we propose a channel-aware RPQ scheduling algorithm to meet explicit delay deadlines in wireless context. Specifically, we first construct an improved channel-aware RPQ framework. Different to the classic RPQ scheduler, we allocate the transmission opportunity to various devices before adopting RPQ scheduling for each device. For the scheduling of device transmission time, we establish a weighted queue for each device by learning their effects to the violation of delay deadlines, and propose a low-complexity scheduling algorithm by stabilizing the virtual outage queue via Lyapunov optimization. As the mapping to the weighted queue is non-smooth, we enhance the soft threshold function by employing momentum to accelerate the convergence rate. Simulation results verify the performance improvements of the proposed scheduling algorithm,

关键词： Performance evaluation Q-learning scheduling algorithms Heuristic algorithms Wireless networks Simulation Signal processing algorithms Signal processing Delays Resource management

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：