检索结果-内蒙古大学图书馆

GamePlan: Game-Theoretic Multi-Agent Planning With Human Drivers at Intersections, Roundabouts, and Merging

IEEE ROBOTICS AND AUTOMATION LETTERS 2022年第2期7卷 2676-2683页

作者： Chandra, Rohan Manocha, Dinesh Univ Maryland Dept Comp Sci College Pk MD 20742 USA

We present a new method for multi-agent planning involving human drivers and autonomous vehicles (AVs) in unsignaled intersections, roundabouts, and during merging. In multi-agent planning, the main challenge is to predict the actions of other agents, especially human drivers, as their intentions are hidden from other agents. Our algorithm uses game theory to develop a new auction, milled GAMEPLAN, that directly determines the optimal action for each agent based on their driving style (which is observable via commonly available sensors). GAMEPLAN assigns a higher priority to more aggressive or impatient drivers and a lower priority to more conservative or patient drivers;we theoretically prove that such an approach is game-theoretically optimal prevents collisions and deadlocks. We compare our approach with prior state-of-the-art auction techniques including economic auctions, time-based auctions (first-in first-out), and random bidding and show that each of these methods result in collisions among agents when taking into account driver behavior. We compare with methods based on DRL, deep learning, and game theory and present our benefits over these approaches. Finally, we show that our approach can be implemented in the real-world with human drivers.

关键词： Multi-robot systems multi-agent systems scheduling algorithms autonomous systems intelligent transportation systems intelligent vehicles traffic control vehicular and wireless technologies

来源：评论

学校读者我要写书评

暂无评论

Providing quality of service in omni-path networks

引用

JOURNAL OF SUPERCOMPUTING 2022年第10期78卷 12310-12343页

作者： Cano-Cano, Javier Andujar, Francisco J. Alfaro-Cortes, Francisco J. Sanchez, Jose L. Mora, Gaspar Univ Castilla La Mancha Comp Syst Dept Campus Univ S-N Albacete 02071 Spain Univ Valladolid Comp Syst Dept Campus Miguel DelibesPaseo Belen 15 Valladolid 47011 Castilla & Leon Spain Intel Corp Comp Syst Dept Santa Clara CA USA

New hierarchical crossbar switch architectures, such as Omni-Path (OPA) and Cray X2, have appeared to improve packet latency, reduce overall cost and increase fault tolerance of the high-performance interconnection networks in supercomputing and data center systems. These and other interconnect technologies (Infiniband or 40/100 Gigabit Ethernet) include support to provide quality of service (QoS) to the applications. In this paper, we show how this QoS support can be enabled to achieve bandwidth and/or latency differentiation in Omni-Path interconnection networks, as a representative case of hierarchical switches. To do that, three different table-based schedulers are used. We include the description of these schedulers and a comparative study by using the results obtained when we evaluate them with Hiperion, a simulation tool that implements an OPA model.

关键词： Quality of Service (QoS) scheduling algorithms Interconnection networks Omni-Path (OPA) Simulation Hierarchical-crossbar-switch architecture

来源：评论

学校读者我要写书评

暂无评论

Value of Information in Wireless Sensor Network Applications and the IoT: A Review

引用

IEEE SENSORS JOURNAL 2022年第10期22卷 9228-9245页

作者： Alawad, Faiga Kraemer, Frank Alexander Norwegian Univ Sci & Technol Dept Informat Secur & Commun Technol N-7491 Trondheim Norway

Value of Information (VoI) is a concept to assess the usefulness of information for a specific goal, and has in the last decade experienced a growing interest also for Wireless Sensor Network (WSN) applications and the Internet of Things (IoT). By making the value of information explicit in the form of VoI, WSN and IoT applications should be able to better assess which information to spend their constrained resources on. However, the definition of VoI is highly application-dependent, which has led to a fragmented understanding of VoI, and there is a lack of a comprehensive overview. In this structured review, we first categorize application use cases and examine what VoI is used for, and explore the different approaches to defining VoI. We then provide a well-structured and comprehensive discussion of the specific approaches used in the literature to determine VoI, together with examples of use cases. We categorize the different approaches to calculating VoI, describe their properties systematically and distinguish between observed VoI and expected VoI. We also discuss adaptive VoI approaches and point towards future directions within the field.

关键词： Wireless sensor networks Sensors Monitoring Internet of Things Sensor phenomena and characterization Measurement Systematics Data collection data reduction Internet of Things machine learning scheduling algorithms sensor data sensor networks wireless sensor networks value of information

来源：评论

学校读者我要写书评

暂无评论

Fully Distributed Event-Triggered Algorithm for Fixed-time Economic Dispatch with Input Delay

Fully Distributed Event-Triggered Algorithm for Fixed-time E...

引用

2024 China Automation Congress, CAC 2024

作者： Wan, Xiaofeng Duan, Zhiqiang School of Information Engineering Nanchang University Nanchang China

ISBN: (纸本)9798350368604

Traditional distributed optimization is capable of resolving the economic dispatch problem (EDP) in microgrids, but the time lag within information systems is real and cannot be ignored. In the text, We initially propose a new algorithm based on fixed-time consensus to surmount the difficulty posed by input delays, and the time required for fixed-time convergence is not dependent on initial states. Moreover, to decrease the demand for information sharing, an event-triggered control approach is developed to prevent continuous communication, and there is no occurrence of Zeno behavior. Additionally, the dependability of the algorithm is proved through the use of Lyapunov’s stability theory. In the end, the efficiency of the presented schemes is demonstrated by multiple case analyses. © 2024 IEEE.

关键词： scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Faster Algorithm for Converting an STNU into Minimal Dispatchable Form 31

Faster Algorithm for Converting an STNU into Minimal Dispatc...

引用

31st International Symposium on Temporal Representation and Reasoning, TIME 2024

作者： Hunsberger, Luke Posenato, Roberto Vassar College PoughkeepsieNY United States University of Verona Italy

ISBN: (纸本)9783959773492

A Simple Temporal Network with Uncertainty (STNU) is a data structure for representing and reasoning about temporal constraints on activities, including those with uncertain durations. An STNU is dispatchable if it can be flexibly and efficiently executed in real time while guaranteeing that all relevant constraints are satisfied. The number of edges in a dispatchable network affects the computational work that must be done during real-time execution. Recent work presented an O(kn3)-time algorithm for converting a dispatchable STNU into an equivalent dispatchable network having a minimal number of edges, where n is the number of timepoints and k is the number of actions with uncertain durations. This paper presents a modification of that algorithm, making it an order of magnitude faster, down to O(n3). Given that in typical applications k = O(n), this represents an effective order-of-magnitude reduction from O(n4) to O(n3). © Luke Hunsberger and Roberto Posenato.

关键词： scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Multi objective resource optimization simulation of multifunctional phased array radar 4

Multi objective resource optimization simulation of multifun...

引用

4th International Conference on Green Communication, Network, and Internet of Things, CNIoT 2024

作者： Zhang, Yonggang Meng, Xiangcai Zhang, Ge Liu, Yanpeng No.93986 Unit The PLA Hetian848000 China

ISBN: (纸本)9781510685710

In response to the shortage of time resources for traditional multifunctional phased array radar to perform multitasking, a multi-target tracking algorithm based on fusion measurement and a comprehensive strategy adaptive resource scheduling algorithm are proposed. The performance of these two algorithms in handling multitasking is verified through simulation experiments. This experimental platform integrates functions such as radar resource scheduling, signal processing, and data processing to evaluate the performance and resource scheduling efficiency of multifunctional phased array radar for target detection and tracking in multitasking environments. The results indicate that the proposed multi-target tracking algorithm based on fusion measurement can optimize the performance of the radar system and improve the accuracy of target signal detection and tracking within limited time resources. Compared to traditional resource scheduling algorithms, the comprehensive strategy adaptive resource scheduling algorithm can allocate system resources more reasonably in the context of multitasking scheduling, significantly improving the resource utilization efficiency of multifunctional phased array radar. © 2024 SPIE.

关键词： scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Enhanced Millimeter-Wave Communication and Radar Systems in Autonomous Vehicles 11

Enhanced Millimeter-Wave Communication and Radar Systems in ...

引用

11th International Conference on Electrical and Electronics Engineering, ICEEE 2024

作者： Tang, Yutong Zhang, Ziyun Tian, Jiale Chen, Chen Li, Motong College of Science University of Melbourne Melbourne3052 Australia College of Electronic Information Engineering Chongqing University of Technology Chongqing401135 China College of Science and Engineering University of Glasgow GlasgowG12 8QQ United Kingdom College of Electrical and Electronic Engineering University of Sheffield SheffieldS10 2TN United Kingdom Hefei University of Technology Electronic Engineering Xuancheng242000 China

ISBN: (纸本)9798350362541

This paper explores the integration of IEEE 802.11ad wireless communication protocol into millimeter-wave radar systems, especially the impact of the vehicle scheduling policy after collision on the performance of the system. By embedding radar functionality within the standard communication protocol, various scheduling algorithms, such as Greedy, Proportional Fairness (PF), Round-Robin (RR), and Randomized Algorithm (RA), are evaluated for their impact on system throughput and radar overhead. Simulation results demonstrate the effectiveness of these algorithms in optimizing signal-to-noise ratio (SNR) and throughput during vehicle movement. Finally, we propose to explore adaptive strategies based on real-time network conditions to dynamically balance throughput and fairness in the future to improve the performance of the system. © 2024 IEEE.

关键词： scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Literature Review on Constraint Satisfaction Problems Solving 8

Literature Review on Constraint Satisfaction Problems Solvin...

引用

8th International Symposium on Multidisciplinary Studies and Innovative Technologies, ISMSIT 2024

作者： Qefalija, Edlira Snopce, Halil Dermaku, Artan South East European University Faculty of Contemporary Sciences and Technologies Tetovo Macedonia Universiteti Kadri Zeka Gjilan Faculty of Contemporary Sciences and Technologies Kosovo Serbia

ISBN: (纸本)9798350354423

Problems known as Constraint Satisfaction issues (CSPs) are the ones on which every variable needs to be given e certain value in order to satisfy all the given constraints. In real life, many requirements such as resource allocation, scheduling, and planning, revolve around these Constraints Satisfaction Issues. This review offers a thorough rundown of the main approaches used to solve CSPs up to date, including heuristic techniques, contemporary and classical algorithms, and underlying theories for such issues. It focuses on specific CSPs and their solving methods, looks at real-life uses, and looks at potential paths for further study. The paper focuses on how the efficiency and scalability of CSP solvers are continuously being improved by developments in methods like constraint programming, SAT solvers, and machine learning © 2024 IEEE.

关键词： scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Implementation of Generative AI in Resource Management of Cloud Computing

Implementation of Generative AI in Resource Management of Cl...

引用

2024 International Conference on Artificial Intelligence and Quantum Computation-Based Sensor Applications, ICAIQSA 2024

作者： Wargantiwar, Tanmay Chandekar, Yash Agrawal, Pratik Badhiye, Sagarkumar Borkar, Pradnya Pune India

ISBN: (纸本)9798331517953

Virtual computing however has recently emerged as the new way of accessing computing resources and services through the internet. In this regard scheduling algorithms holds a prominent position which would determine the cumulative use of the resources as well as the efficiency of the entire system. In this paper, the author's aim is to assess and compare various forms of the scheduling algorithms used in cloud computing systems. Some of the basic scheduling techniques include the First-in First-out (FIFO), Shortest Job First (SJF), Round Robin (RR), Priority scheduling and few more complex scheduling techniques include the Multilevel Feedback Queues and the Shortest Timed Remaining (SRTF). Every one of them is described, compared and contrasted over this criterion:, including characteristics, strengths, weaknesses, and applications. In this section we present how scheduling decisions impact primary performance measures of response time, throughput, and user-to-user sharing criterion. Further, we present the ongoing issues and further research areas in the case of scheduling algorithms for cloud computing environment while elucidating the recent advancements in a cloud services and applications along with. It becomes beneficial for the system designers, cloud service providers as well as for the researchers to lift the efficiency of operation in cloud computing with the help of scheduling. © 2024 IEEE.

关键词： scheduling algorithms

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Edge Computing Model for Integrated Energy Systems 5

Reinforcement Learning Edge Computing Model for Integrated E...

引用

5th International Conference on Clean Energy and Electric Power Engineering, ICCEPE 2024

作者： Yang, Yuqiang Li, Lei Zhao, Qiming Lu, Pengfei State Grid Zhejiang Electric Power Company LTD. Marketing Department Hangzhou China

ISBN: (纸本)9798350390315

In the architecture of edge computing, edge servers have a faster data transmission rate and lower energy consumption than terminal devices. In the scenario of the integrated energy system, numerous edge servers and computing tasks will lead to an expansion of the problem-solving scale, greatly increasing the difficulty of workflow scheduling. In addition, due to the fluctuation in the performance of the servers themselves, the traditional method of treating the performance data of the servers as fixed values cannot guarantee the final reliability of the scheduling results. To ensure the reliability of the scheduling algorithm, we propose a server performance model based on probability distribution (PDSPM), which can utilize historical performance data to better characterize the fluctuations in server performance. Benefiting from the excellent performance of deep reinforcement learning in large-scale decision-making problems, this paper proposes a new workflow scheduling algorithm based on Deep-Q-network (DQN) and studies feasible improvement schemes. By combining PDSPM, this algorithm can ensure that the scheduling results with the highest probability of reliability are obtained under the fluctuation of server performance. © 2024 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：