检索结果-内蒙古大学图书馆

Delay and Load Fairness Optimization With Queuing Model in Multi-AAV Assisted MEC: A Deep Reinforcement Learning Approach

引用

IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT 2025年第2期22卷 1247-1258页

作者： Tang, Qiang Li, Bao Yang, Halvin H. Li, Yan He, Shiming Yang, Kun Changsha Univ Sci & Technol Sch Comp Sci & Commun Engn Changsha 410114 Hunan Peoples R China UCL Dept Elect & Elect Engn London WC1E 7JE England Changchun Inst Technol Sch Comp Technol & Engn Changchun 130012 Peoples R China Univ Essex Sch Comp Sci & Elect Engn Colchester CO4 3SQ England

Autonomous aerial vehicles (AAV) can alleviate the computational burden on edge devices through assisted computing. However, with the increase in the number of Internet of Things Devices (IoTDs), it is essential to establish a task queue on the AAV to schedule computing tasks from IoTDs. In addition, the load fairness of AAVs should be optimized to fully utilize the computing resources. Therefore, a multi-AAV-assisted mobile edge computing (MEC) network framework based on the queuing model is proposed, which aims at optimizing the average delay of all user devices and the load fairness of AAVs. Firstly, we prove that the arrangement of tasks with different computing delays on the AAV queue can affect the user's average delay, so a short-job-first (SJF) queuing model is proposed to minimize the average delay of users. On this basis, a joint optimization problem related to the AAV's three-dimensional trajectory and user connection scheduling is formulated. A SJF based low-complexity connection scheduling algorithm is proposed and combined in a deep reinforcement learning (DRL) to solve this NP-hard problem. To evaluate the performance of the proposed algorithm, we compare it with deep deterministic policy gradient (DDPG), particle swarm optimization (PSO), random moving (RM), and local computing (LC). Simulation results show that our algorithm effectively reduces user average delay and enhances AAV load fairness. Finally, SJF is compared with the traditional first-come-first-served (FCFS) queuing model on different algorithms. The results indicate that the average delay of SJF is significantly lower than that of FCFS.

关键词： Autonomous aerial vehicles Delays Computational modeling Trajectory Load modeling Optimization Internet of Things Heuristic algorithms Energy consumption scheduling algorithms Multi-AAV mobile edge computing (MEC) Internet of Things Devices (IoTDs) short-job-first (SJF) deep reinforcement learning (DRL)

来源：评论

学校读者我要写书评

暂无评论

Learning-Based Deadlock-Free Multi-Objective Task Offloading in Satellite Edge Computing With Data-Dependent Constraints and Limited Buffers

引用

IEEE TRANSACTIONS ON NETWORK SCIENCE AND ENGINEERING 2025年第1期12卷 356-368页

作者： Zhang, Ruipeng Feng, Yanxiang Yang, Yikang Li, Xiaoling Li, Hengnian Xi An Jiao Tong Univ Syst Engn Inst Sch Automat Sci & Engn Xian 710049 Peoples R China Changan Univ Sch Elect & Control Engn Xian 710064 Peoples R China Xian Satellite Control Ctr State Key Lab Astronaut Dynam Xian 710043 Peoples R China

Satellite edge computing (SEC) is important for future network deployments because of its global coverage and low-latency computing services. Nevertheless, due to data dependencies among tasks and limited buffers in satellites, a coupling exists between transmission and computation, and undesired deadlocks may arise. This paper addresses task offloading in SEC and aims to minimize service latency, energy consumption, and time window violations simultaneously. First, a mixed-integer nonlinear programming model is presented. To resolve potential deadlocks, a deadlock amending algorithm (DAA) based on Petri net with polynomial time complexity is proposed. Deadlocks in solutions are amended by finding a transition sequence that corresponding transmission and computation can be performed sequentially. By embedding DAA, we develop a learning-based deadlock-free multi-objective scheduling algorithm (LDMOSA) that combines the exploration of evolutionary algorithms with the perception of reinforcement learning. To enhance the convergence and diversity of solutions, an initialization strategy employing problem-specific constructive heuristics is designed. Then, a learning-based mechanism is used to leverage real-time information to perform adaptive operator selection during the search process. Finally, extensive experiments demonstrate the effectiveness of DAA in resolving deadlocks, and the LDMOSA outperforms state-of-the-art algorithms for task offloading in SEC.

关键词： Satellites System recovery Internet of Things Couplings Petri nets scheduling algorithms Energy resolution Costs Vectors Traffic control Satellite-terrestrial integrated networks satellite edge computing computation offloading multi-task offloading

来源：评论

学校读者我要写书评

暂无评论

Online Busy Time scheduling with Untrusted Prediction 50th

Online Busy Time Scheduling with Untrusted Prediction

引用

50th International Conference on Current Trends in Theory and Practice of Computer Science, SOFSEM 2025

作者： van de Bovenkamp, Rick Liu, Alison Hsiang-Hsuan Utrecht University Utrecht Netherlands

ISBN: (纸本)9783031826962

In this work, we study the online busy time scheduling problem with infinite processors, where each job j has a release time rj, a processing time pj, and a deadline dj. Busy time scheduling aims to use multiple processors to schedule jobs concurrently to minimize the time a machine has to process jobs. We consider the case proposed by Koehler and Khuller [20], where a single machine has unlimited processors. Moreover, we consider the case where the online algorithm can access prediction, which might be imperfect, on when the machine should be active. We present an algorithm, Multiplier, that dynamically adjusts its strategy for reserving time windows for potential future jobs according to the prediction it receives and how much it trusts the prediction. We show that Multiplier is (1+41+λ)-consistent and (1+41-λ)-robust with a trust parameter λ∈[0,1). © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Improved Genetic Algorithm for Optimizing Flexible Workshop scheduling

Improved Genetic Algorithm for Optimizing Flexible Workshop ...

引用

2024 International Conference on Mechatronics and Intelligent Control, ICMIC 2024

作者： Wang, Dinghua Peng, Xiaolin Qin, Hengfeng China Railway SunWard Engineering Equipment Co. Ltd. Guangzhou511468 China School of Mechanical Engineering Xiangtan University Hunan Xiangtan411105 China

ISBN: (数字)9781510686847

ISBN: (纸本)9781510686830

In automated production lines, flexible workshop scheduling is essential for optimizing resource allocation and ensuring efficient production. This study develops an efficient scheduling strategy to enhance the distribution of processing and handling tasks. Addressing the issues of local optima and slow convergence in traditional Genetic search algorithms, we introduce an improved Genetic algorithm (GA) that dynamically adjusts the crossover and mutation rates. Additionally, it sorts individuals based on their fitness during the crossover process, significantly improving the quality and efficiency of solutions. Simulation results demonstrate that the improved algorithm significantly outperforms traditional methods in task completion, reducing the time from 198 to 146 unit times, a decrease of 26%. Furthermore, the algorithm exhibits faster convergence and superior optimization capabilities. © 2025 SPIE.

关键词： scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Bi-objective Workflow scheduling in the Cloud: What is the Real State-of-the-Art? 10th

Bi-objective Workflow Scheduling in the Cloud: What is the...

引用

10th Russian Supercomputing Days Conference, RuSCDays 2024

作者： Semenov, Yury Sukhoroslov, Oleg HSE University Moscow Russia Institute for Information Transmission Problems of the Russian Academy of Sciences Moscow Russia

ISBN: (纸本)9783031784613

Workflow scheduling in the cloud is a challenging multi-objective optimization problem where an efficient scheduling algorithm is required to optimize both performance and cost. Despite the huge body of work on designing workflow scheduling algorithms, the differences in the experiment settings, VM instances, sets of baseline algorithms, and the choice of reference point for hypervolume calculation make it hard to determine the best-performing methods. In this work, we aim to determine the current state-of-the-art approach by implementing and benchmarking recently published algorithms on a unified benchmark consisting of a large set of real-world DAGs and Amazon EC2 instance types. The experiments show that VMALS and CMSWC are the current state-of-the-art algorithms demonstrating superior quality of Pareto front in terms of hypervolume on all tested DAGs. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

scheduling Policies in Edge Computing for Real-Time Video Analytics 3

Scheduling Policies in Edge Computing for Real-Time Video An...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Shreevatsan, S.S. Annambhotla, Yasasree Lasya Reji, Anaswara Rajagopal, Shinu M. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798331527549

This study compares different scheduling algorithms used in edge computing for real-time video processing. Instead of sending video data to cloud servers, the video is processed directly at the edge, reducing delays and saving bandwidth. The focus is on how different scheduling methods manage resources, prioritize tasks, and reduce the time it takes to analyze video. The algorithms are tested in simulated environments to understand how they impact system efficiency and performance. The goal of this work is to find the best scheduling policies for real-time video processing at the edge, improving overall system performance and scalability. © 2025 IEEE.

关键词： scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Optimization of Flexible Job Shop scheduling Driven by Renewable Energy Based on Deep Learning 24

Optimization of Flexible Job Shop Scheduling Driven by Renew...

引用

5th International Conference on Artificial Intelligence and Computer Engineering, ICAICE 2024

作者： Wang, Xin Chen, Qi School of Management Shanghai University Shanghai China

ISBN: (纸本)9798400718007

The application of renewable energy generation systems in production workshop benefits enterprises by reducing production cost and energy dependence. A mathematical model of a flexible job shop with a renewable energy supply system is constructed to address the scheduling problem of integrated microgrids. A meta-heuristic algorithm framework combining deep learning algorithms is designed to optimize production scheduling and energy allocation in the job shop. In the deep learning module, the uncertainty of renewable energy generation is considered, and a convolutional neural network is built for rapid approximation of expected electricity cost. The accuracy and effectiveness of the neural network predictions are validated through comparisons with other forecasting models. Numerical experiments further demonstrate that the proposed algorithm effectively reduces runtime while ensuring accuracy, enhancing the exploration efficiency compared to Monte Carlo simulation. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Cooperative scheduling of RMG, Quay Crane and AGV

Hierarchical Cooperative Scheduling of RMG, Quay Crane and A...

引用

作者： Geng, Zengtao Ding, Xiangqian Li, Quanxi Yu, Shusong Faculty of Information Science and Engineering Ocean University of China Shandong Qingdao266100 China Shandong Port Technology Group Qingdao Co. Ltd. Shandong Qingdao266011 China

To solve the loading and unloading problems of RMG (Rail Mounted Gantry), quay crane and AGV (Automated Guided Vehicle), this paper proposes a hierarchical cooperative scheduling algorithm. Firstly, the operation task is converted into 2 parts: the vertical equipment and the horizontal one, which can be regarded as the passenger and the taxi, i.e., named as the ride-hailing problem. We introduce the Hungarian algorithm to accomplish the matching of the task and the AGV. Secondly, the overall tasks of the equipment are transformed into planning paths, and then each equipment can execute it respectively. Here the global optimization should be considered. Finally, after the planning paths are truncated, we design a novel Markov random field model for the global optimization, aiming at the efficiency and safety of all equipment. In experiments, the effectiveness of our algorithm is verified by the simulation and real tests. The performance of safety and efficiency has strong promotion significance in new terminals and old reconstructed ones. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

DocQueue: A scheduling Algorithm for Optimizing Healthcare Resources

DocQueue: A Scheduling Algorithm for Optimizing Healthcare R...

引用

2025 IEEE International Students' Conference on Electrical, Electronics and Computer Science, SCEECS 2025

作者： Joji, Jeff Johnson, Sobin Angayarkanni, V. Rama, P. Kalaivani, J. Srm Institute of Science & Technology Department of Computing Technologies Chennai India

ISBN: (纸本)9798331529833

DocQueue is a cloud-based system that optimizes patient scheduling in order to maximize the delivery of healthcare by prioritizing cases (dynamically) based on real-time information and availability of resources. It uses a decision-tree algorithm to analyze symptoms in real time, and then flags high-priority cases immediately, but uses a round-robin scheduling mechanism to manage low-priority cases so things are fair. And the AWS based architecture of the system allows for scalable deployment throughout the healthcare continuum. In simulations, these changes have shown to drastically cut down patient waiting time and make better use of resources, and therefore provide better patient care and more efficient operations. DocQueue is different from the usual scheduling systems because it is flexible and data-driven, it can change its schedule based on the real time needs of health care. © 2025 IEEE.

关键词： scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Information System Resource scheduling and Optimization Methods in Cloud Computing Environment 1

Information System Resource Scheduling and Optimization Meth...

引用

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Zhao, Yichu Anyang Institute of Technology Henan Anyang China

ISBN: (纸本)9798331529246

In the cloud computing environment, existing research has mostly focused on improving traditional scheduling algorithms, lacking effective strategies for dealing with dynamic loads and complex workflows, resulting in resource waste and increased response time. Firstly, by conducting in-depth analysis of resource characteristics and task requirements in cloud computing environments, the study aims to clarify scheduling optimization objectives;secondly, the study adopts a multi-objective optimization model to maximize resource utilization and minimize response time;in terms of implementation strategy, the study adopts hierarchical scheduling and adaptive adjustment mechanism to optimize configuration for different task types and resource situations. As the complexity of the workflow decreases from low to very high, the task response time increases from 1.8 seconds to 4.9 seconds, reflecting the increased difficulty of task processing in complex workflows, and the resource utilization rate increases from 78% to 95%. Research has shown that the designed resource scheduling and optimization methods exhibit significant advantages in cloud computing environments. © 2025 IEEE.

关键词： scheduling algorithms

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：