检索结果-内蒙古大学图书馆

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Rui He Bangbang Ren Junjie Xie Deke Guo Laiping Zhao College of Intelligence and Computing Tianjin University Tianjin China Science and Technology on Information Systems Engineering Laboratory National University of Defense Technology Changsha Hunan China Institute of Systems Engineering AMS Beijing China

The modern network is equipped with many service functions to acquire high-quality service. The emergence of network function virtualization (NFV) provides a convenient way to accomplish the network services in the form of virtual network function (VNF) and also makes the scheduling solution of VNFs flexible. The VNFs can be deployed on commodity servers as software processes. Besides, multiple VNFs are chained in a specified order as a service function chain (SFC) to serve a given flow, increasing the scheduling difficulty to minimize the average flow completion time. In this paper, we study the problem of scheduling multiple SFCs with the constraint of different resource limitations in various commodity servers. This problem is typically formulated as an Integer Linear Programming (ILP) problem, which is NP-hard. To well tackle this problem, we propose a deep reinforcement learning (DRL) approach. It involves multi-step decision making, which can be naturally transformed into a DRL problem. We design specific reward and state representations for such a multi-resource scheduling problem. We also consider how to use DRL to handle online requests of SFCs. The experiment results demonstrate that the DRL approach can significantly reduce the average completion time of a set of SFC and achieves a cost saving of 39.94% against the benchmark method.

关键词： Deep learning Service function chaining scheduling algorithms NP-hard problem Reinforcement learning Benchmark testing Software

来源：评论

学校读者我要写书评

暂无评论

Distributed scheduling of Home Appliances to Flatten Peak Demand in Microgrids and Enhancements

Distributed Scheduling of Home Appliances to Flatten Peak De...

引用

International Conference on Computer and Automation Engineering, ICCAE

作者： Devendra Dahiphale Vijay Dahiphale University of Maryland Baltimore County USA Pune Institute of Computer Technology India

The primary power grids provide electricity to cities, businesses, and industries. In addition to the primary power grids, there exist smaller, independent grids called microgrids or remote grids that provide electricity to islands, rural areas, remote areas, or small communities. Because micro-grids limited capacity for power generation, flattening the peak power demand is one of the significant challenges. We focus on peak demand flattening using the power-voltage relationship approach out of the available solutions. Specifically, we observe that the existing algorithms for flattening peak demand using a distributed water heater scheduling algorithm suffer from the following drawbacks, 1. It generates short-term ON/OFF events, which are unsuitable for electrical appliances 2. It does not guarantee performance in distributed scheduling 3. Finally, it has severe consequences if water usage prediction goes wrong. Therefore, we propose a new algorithm that overcomes the problem of short-term ON/OFF events. In addition, we verified that at any given instance in time, fewer homes keep their water heater ON simultaneously without affecting the hot water usage of targeted users.

关键词： Job shop scheduling Power demand scheduling algorithms Urban areas Water heating Microgrids Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

RIFO: Pushing the Efficiency of Programmable Packet Schedulers

IEEE TRANSACTIONS ON NETWORKING

引用

IEEE TRANSACTIONS ON NETWORKING 2025年第03期33卷 1295-1308页

作者： Mostafaei, Habib Pacut, Maciej Schmid, Stefan Eindhoven Univ Technol Dept Math & Comp Sci NL-5612 AZ Eindhoven Netherlands Tech Univ Berlin TU Berlin Dept Elect Engn & Comp Sci D-10623 Berlin Germany Fraunhofer SIT D-64295 Darmstadt Germany

Packet scheduling is a fundamental networking task that recently received renewed attention in the context of programmable data planes. Programmable packet scheduling systems such as those based on Push-In First-Out (PIFO) abstraction enabled flexible scheduling policies, but are too resource-expensive for large-scale line rate operation. This prompted research into practical programmable schedulers (e.g., SP-PIFO, AIFO) approximating PIFO behavior on regular hardware. Yet, their scalability remains limited due to extensive number of memory operations. To address this, we design an effective yet resource-efficient packet scheduler, Range-In First-Out (RIFO), which uses only three mutable memory cells and one FIFO queue per PIFO queue. RIFO is based on multi-criteria decision-making principles and uses small guaranteed admission buffers. Our large-scale simulations in Netbench demonstrate that despite using fewer resources, RIFO generally achieves competitive flow completion times across all studied workloads, and is especially effective in workloads with a significant share of large flows, reducing flow completion time up to 4.91x in datamining workload compared to state-of-the-art solutions. Our prototype implementation using P4 on Tofino switches requires only 600 lines of code, is scalable, and runs at line rate.

关键词： scheduling algorithms scheduling Registers Memory management Decision making Hardware Throughput Robustness Filtering Electrical engineering Programmable networks packet scheduling resource efficiency P4 min-max normalization

来源：评论

学校读者我要写书评

暂无评论

Inter-Slice Radio Resource Allocation: An Online Convex Optimization Approach

引用

IEEE WIRELESS COMMUNICATIONS 2021年第5期28卷 171-177页

作者： Wang, Tianyu Wang, Shaowei Nanjing Univ Sch Elect Sci & Engn Nanjing Peoples R China

Inter-slice radio resource allocation (IS-RRA) is a new layer of radio resource management introduced by network slicing in 5G and beyond mobile communication systems. Instead of focusing on the per-user service quality as in conventional packet schedulers, IS-RRA is required to ensure the service-level agreements on a per-slice basis, which is particularly challenging due to the diverse requirements and behaviors of network slices. In this article, we analyze the inherent limitations of the existing model-based and data-based approaches and propose a novel framework based on online convex optimization (OCO). Specifically, the proposed OCO approach is able to incorporate the offline knowledge and the online data into a general online learning framework, which overcomes the modeling difficulty and high computational complexity of the model-based approach, and avoids the blind exploration of the data-driven approach. At last, we provide the simulation results of an example scenario, which shows that the proposed OCO approach can adapt to diverse service requirements and provide comparable performance to the optimal solutions given in hindsight.

关键词： Resource management scheduling algorithms Network slicing Computational modeling Solid modeling Data models Wireless communication

来源：评论

学校读者我要写书评

暂无评论

Distortion-Oblivious algorithms for Minimizing Flow Time 33

Distortion-Oblivious Algorithms for Minimizing Flow Time

引用

Annual ACM-SIAM Symposium on Discrete algorithms (SODA)

作者： Azar, Yossi Leonardi, Stefano Touitou, Noam Tel Aviv Univ Tel Aviv Israel Sapienza Univ Rome Rome Italy

ISBN: (纸本)9781611977073

We consider the classic online problem of scheduling on a single machine to minimize total flow time. In STOC 2021, the concept of robustness to distortion in processing times was introduced: for every distortion factor mu, an O-1(mu(2))-competitive algorithm ALG(mu) which handles distortions up to mu was presented. However, using that result requires one to know the distortion of the input in advance, which is impractical. We present the first distortion-oblivious algorithms: algorithms which are competitive for every input of every distortion, and thus do not require knowledge of the distortion in advance. Moreover, the competitive ratios of our algorithms are (O) over tilde(mu), which is a quadratic improvement over the algorithm from STOC 2021, and is nearly optimal (we show a randomized lower bound of Omega(mu) on competitiveness).

关键词： scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Entropy-based scheduling performance in real-time multiprocessor systems

Entropy-based scheduling performance in real-time multiproce...

引用

Annual Conference on Information Sciences and Systems (CISS)

作者： Carlos A. Rincon Daniel Rivas Albert M. K. Cheng Computer Science Department University of Houston Houston Texas USA

In this paper, we present the performance analysis of the entropy-based scheduling approach in real-time multiprocessor systems. We analyze the effect of using the entropy-based scheduling layer in deadline-based (global Earliest Deadline First (EDF)), laxity-based (Least Laxity First (LLF)), and PFair-based (PD2) scheduling algorithms by measuring the number of preemptions, the number of job migrations, and the number of task migrations. The performance comparison results between the selected scheduling algorithms with their entropy-enabled versions showed that the entropy layer reduces the number of task migrations for all studied algorithms and reduces the number of job migrations for LLF and PD2.

关键词： scheduling algorithms Real-time systems scheduling Entropy Performance analysis Task analysis Multiprocessing systems

来源：评论

学校读者我要写书评

暂无评论

Dynamic Demand-Aware Link scheduling for Reconfigurable Datacenters

arXiv

引用

arXiv 2023年

作者： Hanauer, Kathrin Henzinger, Monika Ost, Lara Schmid, Stefan Faculty of Computer Science University of Vienna Vienna Austria TU Berlin Berlin Germany

Emerging reconfigurable datacenters allow to dynamically adjust the network topology in a demand-aware manner. These datacenters rely on optical switches which can be reconfigured to provide direct connectivity between racks, in the form of edge-disjoint matchings. While state-of-the-art optical switches in principle support microsecond reconfigurations, the demand-aware topology optimization constitutes a bottleneck. This paper proposes a dynamic algorithms approach to improve the performance of reconfigurable datacenter networks, by supporting faster reactions to changes in the traffic demand. This approach leverages the temporal locality of traffic patterns in order to update the interconnecting matchings incrementally, rather than recomputing them from scratch. In particular, we present six (batch-)dynamic algorithms and compare them to static ones. We conduct an extensive empirical evaluation on 176 synthetic and 39 real-world traces, and find that dynamic algorithms can both significantly improve the running time and reduce the number of changes to the configuration, especially in networks with high temporal locality, while retaining matching weight. Copyright © 2023, 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

Optimal Incentive Design for One-Way EV Car Sharing System

Optimal Incentive Design for One-Way EV Car Sharing System

引用

IEEE Conference on Control Technology and Applications (CCTA)

作者： Sasaki, Shun Namerikawa, Toru Keio Univ Dept Syst Design Engn 3-14-1 HiyoshiKohoku Ku Yokohama Kanagawa 2238522 Japan

ISBN: (数字)9781665473385

ISBN: (纸本)9781665473385

This paper deals with an optimal control and scheduling algorithm for one-way car sharing systems. One of the most critical problems of one-way car sharing system is that the parking lots, which tends to be the origins and the destinations, are biased due to the traffic demand of the users, and the cost of relocating the vehicles is becoming high. In order to solve this cost problem, we propose a novel mechanism to give incentives to users in the form of discounts and propose changes to parking lots and departure times to prevent bias in the number of vehicles in parking lots. The optimal parking lot is determined by using a queue information in order to consider the traffic demand distribution of users. Furthermore, an incentive is designed so as to satisfy desirable properties based on VCG mechanism. Finally, the effectiveness of the proposed method is confirmed via several numerical simulations.

关键词： Costs scheduling algorithms Optimal control Numerical simulation Discrete-event systems Automobiles Proposals

来源：评论

学校读者我要写书评

暂无评论

Medium Access Control scheduling Policy Performance Evaluation in Wireless Networks

Medium Access Control Scheduling Policy Performance Evaluati...

引用

Artificial Intelligence and Knowledge Discovery in Concurrent Engineering (ICECONF), International Conference on

作者： N. Banupriya P. Jyothi K Malathy R Sureshkumar D Dhanush G Sajiv Department of Computer Science and Engineering R.M.K. Engineering College Chennai Departmpnt of Management Studies Saveetha Engineering college Chennai Department of Master of Computer Applications S.A Engineering College Chennai Department of Electronics and Communication Engineering Vel Tech Multitech Dr. Rangarajan Dr. Sakunthala Engineering College Chennai Department of Electronics and Communication Engineering R.MK. Engineering College Chennai Department of Electronics and Communication Engineering Saveetha School of Engineering Chennai

According to the implementation model, MAC scheduling techniques may be broken down into two distinct categories centralized and distributed scheduling. These categories apply to wireless networks. Both centralized and distributed schedulers have the ability to assure a dependable throughput capacity region, also known as achieving throughput-guaranteed, by establishing MAC scheduling criteria in a reasonable manner. However, it has been shown that some throughput-guaranteed scheduling systems that are already in use are unable to further provide constrained end-to-end mean latency, as well as the explanation for these phenomena has not been well investigated. Both throughput and latency are regarded as critically significant in operational communication networks. In this study, we build on this concept by thoroughly examining the current MAC scheduling algorithms from the perspectives of throughput and latency, and by comparing their respective performances using theoretical analysis and simulation tests. The goal of this investigation is to provide a conceptual basis for the development of MAC routing technique in next-generation cellular networks.

关键词： Cellular networks scheduling algorithms Wireless networks Throughput Routing Media Access Protocol Knowledge discovery

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-Based scheduling Algorithm for Service Differentiation in Cloud Business Process Management System 17th

Deep Reinforcement Learning-Based Scheduling Algorithm for ...

引用

17th CCF Conference on Computer Supported Cooperative Work and Social Computing, ChineseCSCW 2022

作者： Wu, Yunzhi Yu, Yang Pan, Maolin School of Computer Science and Engineering Sun Yat-sen University Guangzhou China School of Software Engineering Sun Yat-sen University Guangzhou China

ISBN: (纸本)9789819923847

Business process management system in cloud is increasingly used in enterprise organizations for its advantages of flexibility, affordability, and usability. The service differentiation problem for cloud business process management system has not been thoroughly investigated, nevertheless. Service differentiation requires corresponding service quality for different service level agreements. To address this problem, this paper designs a scheduling system in cloud business process management system by combining characteristics of the workflow engine, models the request scheduling process as the Markov decision process, and proposes a request scheduling algorithm for service differentiation in cloud business process management system based on deep reinforcement learning. The algorithm effectively reduces the over-provisioning of service quality while maintaining a low service level agreement violation rate, thus enhancing the service differentiation effect and conserving system resources. Experiments illustrate that the algorithm achieves a better service differentiation effect with a 74.4% drop rate in service quality over-provisioning compared to the heuristic algorithm while maintaining the service level agreement violation rate within 5%. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

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：