检索结果-内蒙古大学图书馆

作者： Zhang, Jiachi Georgetown University

学位级别：Ph.D., Doctor of Philosophy

distributed systems have evolved into large-scale cloud platforms that support parallel computing of workloads from hundreds of thousands of users. Administrators of distributed systems are finding that improving resource utilization without violating service level agreements (SLAs) is becoming more and more challenging due to the ever-increasing complexity of workloads. Benefiting from adaptivity, statistical and machine learning (ML) algorithms, which automatically reconfigure the system based on historical and real-time workloads, have been widely adopted for resource optimization. Unfortunately, existing optimization approaches are far from optimal, particularly in terms of 1. resource scheduling, which allocates multi-dimensional resources for heterogeneous workloads; 2. auto-scaling, which automatically allocates/de-allocates resources based on dynamic workloads; 3. workload balancing, which balances skewed workloads; and 4. explainable AI (XAI) which aims to improve the explainability of black-box ML models, and enhance system robustness and transparency. In this dissertation, we show that the resource utilization of distributed systems can be improved through the collaboration of statistical and ML-based resource scheduling, auto-scaling and workload balancing, while the transparency and robustness of the systems can be enhanced through data dependency techniques that track data/computation flow and enable efficient XAI computing in large-scale. We validate our thesis through the design of three complementary systems: Eigen, ESDB, and PXAI. Eigen is a large-scale, cloud-native cluster management system that features end-to-end resource optimization in a hierarchical resource management system. The system hierarchically organizes machines in the cluster (i.e., machines are assigned to non-empty layer, empty layer, and offline layer respectively), and simultaneously optimizes resources using three novel algorithms. Vectorized Resource optimization (VRO) is a h

关键词： Auto-scaling distributed systems Machine learning Resource scheduling Workload balancing

来源：评论

学校读者我要写书评

暂无评论

Replicated multistage interconnection networks: QoS evaluation for parallel and distributed computing

引用

THEORETICAL COMPUTER SCIENCE 2024年 1016卷

作者： Gupta, Shilpa Pahuja, G. L. Chandigarh Univ Elect & Commun Engn Dept Mohali India Natl Inst Technol Elect Dept Kurukshetra India

Introduction to big data becomes very important with dealing in high-performance parallel distributed computing, especially in those systems where communication among a number of processors is required. The current paper takes into consideration different topologies for the Shuffle Exchange Network (SEN) in order to attain optimal data transfer among such scenarios. SEN topologies are a key feature in connecting several processors and implementing the data transfer among them where a single processor fails to handle the load. The study hereby reports in the performance, reliability, and cost analysis of these topologies. These topologies, some of which are advocated to have better performance in many studies, include replicated networks. Our research demystifies claims made in earlier papers that replicated networks have inflated reliability and higher costs due to their additional links. Researchers are therefore guided on accurate performance data that will lead them to make optimum choices of SEN topologies for targeted applications. These findings further highlight that the trade-offs between reliability and cost must be carefully considered during network design so as to arrive at better results for big data communication and computation in parallel and distributed systems. This work provides important insights into the correct evaluation of SEN topologies, helping to correct the misleading facts and to have better network selection for various real-time application realizations.

关键词： Sensor networks distributed system real-time data Efficient computing Multistage interconnection network (MIN) Shuffle exchange network (SEN) Reliability Cost

来源：评论

学校读者我要写书评

暂无评论

Mnemonic: A parallel Subgraph Matching System for Streaming Graphs 36

Mnemonic: A Parallel Subgraph Matching System for Streaming ...

引用

36th IEEE International parallel and distributed Processing Symposium (IEEE IPDPS)

作者： Bhattarai, Bibek Huang, Howie George Washington Univ Washington DC 20052 USA

ISBN: (纸本)9781665481069

Finding patterns in large highly connected datasets is critical for value discovery in business development and scientific research. This work focuses on the problem of subgraph matching on streaming graphs, which provides utility in a myriad of real-world applications ranging from social network analysis to cybersecurity. Each application poses a different set of control parameters, including the restrictions for a match, type of data stream, and search granularity. The problem-driven design of existing subgraph matching systems makes them challenging to apply for different problem domains. This paper presents Mnemonic, a programmable system that provides a high-level API and democratizes the development of a wide variety of subgraph matching solutions. Importantly, Mnemonic also delivers key data management capabilities and optimizations to support real-time processing on long-running, high-velocity multi-relational graph streams. The experiments demonstrate the versatility of Mnemonic, as it outperforms several state-of-the-art systems by up to two orders of magnitude.

关键词： subgraph graph pattern matching isomorphism streaming

来源：评论

学校读者我要写书评

暂无评论

Dual-Ascent Hierarchical Control-Based Distribution Power Loss Reduction of parallel-Connected distributed Energy Storage systems in DC Microgrids

IEEE JOURNAL OF EMERGING AND SELECTED TOPICS IN INDUSTRIAL E...

引用

IEEE JOURNAL OF EMERGING AND SELECTED TOPICS IN INDUSTRIAL ELECTRONICS 2023年第1期4卷 137-146页

作者： Jiang, Yajie Yang, Yun Tan, Siew-Chong Hui, Shu Yuen Ron Univ Hong Kong Dept Elect & Elect Engn Hong Kong 999077 Peoples R China Hong Kong Polytech Univ Dept Elect Engn Hong Kong 999077 Peoples R China Nanyang Technol Univ Sch Elect & Elect Engn 100 HKD Singapore Singapore Imperial Coll London Dept Elect & Elect Engn London SW7 2AZ England

In this article, the loss of dc microgrid with distributed energy storage systems (DESSs) is modeled as one unified function of the output currents. Based on the theoretical proof of this article, the loss model is a smooth concave function and has only one extreme point. Then, a dual-ascent algorithm is proposed to online optimize the current distribution coefficients. The current distribution coefficients move in the direction of minimizing the distribution loss iteratively. The adaptive secondary control is applied to realize the given current sharing rate among DESSs. To cope with the changes in model parameters, one online line resistance identification method is designed in this article. Besides, a state-of-charge limitation mechanism is added to the control strategy to prevent deep discharge or overcharge. Thereby, the real-time loss minimization operation is achieved, regardless of line resistance and load variations. The simulation and experimental results are presented to verify the proposed hierarchical control in mitigating the distribution loss in various cases, including charging/discharging operation, output power clip, plug-in and out of DESSs, and daily operation.

关键词： Microgrids Voltage control Optimization Resistance Convex functions Current distribution Batteries DC microgrid distributed energy storage systems (DESSs) distribution loss dual-ascent algorithm (DAA)

来源：评论

学校读者我要写书评

暂无评论

A parallel NAW-DBLSTM algorithm on Spark for traffic flow forecasting

引用

NEURAL COMPUTING & APPLICATIONS 2022年第2期34卷 1557-1575页

作者： Xia, Dawen Yang, Nan Jiang, Shunying Hu, Yang Li, Yantao Li, Huaqing Wang, Lin Guizhou Minzu Univ Coll Data Sci & Informat Engn Guiyang 550025 Peoples R China Guizhou Traff Tech & Transportat Coll Dept Automot Engn Guiyang 550008 Peoples R China Chongqing Univ Coll Comp Sci Chongqing 400044 Peoples R China Southwest Univ Coll Elect & Informat Engn Chongqing 400715 Peoples R China

Traffic flow forecasting (TFF) is critical for constructing intelligent transportation systems and offering real-time traffic applications, and especially accurate flow forecasting based on traffic big data can drive reliable strategies for traffic management and control. To consider the weight of the influence of the spatial correlation among the road segments and capture the nonlinear characteristics of traffic flow, this paper presents a parallel Normal Distribution and Attention Mechanism Weighted Deep Bidirectional Long Short-Term Memory (NAW-DBLSTM) algorithm on Spark. Specifically, we employ the resilient distributed data set (RDD) to preprocess large-scale mobile trajectory data (e.g., taxi GPS trajectory data), and then Kalman Filter (KF) is utilized to smooth the taxi trajectory big data. Next, the parallel NAW-DBLSTM algorithm is put forward on a Spark distributed computing platform to enhance the accuracy and scalability of TFF, combined with the attention mechanism and the normal distribution, and then the time window is used for TFF. Finally, the traffic flow is forecasted successfully on Spark by our NAW-DBLSTM algorithm with the real-world GPS trajectories of taxicabs. The experimental results demonstrate that, compared with LSTM, BiLSTM, DBLSTM, DNN, SVR, KNN, SAEs, BP, CNN, GRU, and ANNs, NAW-DBLSTM can produce better performance with the MAPE value that is 85.1%, 80.1%, 85.8%, 73.1%, 78.2%, 77.9%, 78.8%, 84.6%, 96.4%, 86.2%, and 73.2% lower than that of comparable algorithms, respectively. Particularly, the MAPE value of NAW-DBLSTM is 28.3%, 20.1%, 71.1%, and 79.1% lower than that of LSTM weighted with the normal distribution and the attention mechanism (NAW-LSTM), BiLSTM weighted with the normal distribution and the attention mechanism (NAW-BiLSTM), DBLSTM weighted with the normal distribution (NW-DBLSTM), and NAW-DBLSTM weighted without the time window (NT-NAW-DBLSTM), respectively.

关键词： Big data analytics Traffic flow forecasting DBLSTM neural network Attention mechanism Normal distribution Spark

来源：评论

学校读者我要写书评

暂无评论

Pioneering Cooperative Air-Ground Instant Delivery Using UAVs and Crowdsourced Couriers

引用

PROCEEDINGS OF THE ACM ON INTERACTIVE MOBILE WEARABLE AND UBIQUITOUS TECHNOLOGIES-IMWUT 2024年第4期8卷 1-26页

作者： Pan, Yen Gao, Junhui Duan, Jiashun Shi, Juan Guo, Bin Liang, Yunji Hu, Yujiao Natl Univ Def Technol Natl Key Lab Informat Syst Engn Changsha Peoples R China Natl Univ Def Technol Natl Key Lab Parallel & Distributed Comp Changsha Peoples R China Northwestern Polytech Univ Sch Comp Sci Xian Peoples R China Air Force Engn Univ Xian Peoples R China Purple Mt Labs Future Network Res Ctr Nanjing Peoples R China

Instant delivery, which has a strict time limit, has become a fundamental service in modern cities. Increasing demands and labor shortages make efficient instant delivery more challenging. Recently, the industry has recruited Unmanned Aerial Vehicles (UAVs) and part-time couriers to address this critical issue. However, the inherent delivery ability of crowdsourced couriers and the limited battery capacity of UAVs make them hard to solely meet the rapidly increasing instant delivery demands. Therefore, this paper proposes the first air-ground cooperative UAV and Courier Delivery paradigm, called UCD, to develop an optimal courier recruitment plan and assignment of instant delivery tasks for UAVs and couriers. In the UCD paradigm, courier and UAV delivery models are introduced, and a recruitment plan that considers both delivery demand and courier availability is designed. With this foundation, a data-driven algorithm is proposed to optimize delivery task assignments, maximizing the flexibility of UAVs and the capacity of couriers. Comprehensive evaluations are conducted on multiple long-term real-world datasets to demonstrate the superior performance of UCD.

关键词： UAV Courier Data-driven Air-Ground Instant Delivery Cooperative Delivery

来源：评论

学校读者我要写书评

暂无评论

An edge-fog architecture for distributed 3D reconstruction

引用

FUTURE GENERATION COMPUTER systems-THE INTERNATIONAL JOURNAL OF ESCIENCE 2022年 135卷 146-158页

作者： Vidal, Vinicius F. Honorio, Leonardo M. Pinto, Milena F. Dantas, Mario A. R. Aguiar, Maria Julia Capretz, Miriam Univ Fed Juiz de Fora Dept Elect Engn Juiz De Fora Brazil Fed Ctr Technol Educ Rio de Janeiro Dept Elect Engn Rio De Janeiro Brazil Univ Fed Juiz de Fora Dept Comp Sci Juiz De Fora Brazil Western Univ Dept Elect & Comp Engn London ON N6A 5B9 Canada

Nowadays, numerous facilities that provide essential services operate with little or even no human supervision. In this context, electrical power substations can be entirely autonomous or remotely operated, and may be difficult to access. This scenario increases the need of remote monitoring for predictive maintenance and problem analysis by using imaging and 3D reconstruction of the environment. 3D reconstruction processes are concentrated in academic and commercial applications, but they are non scalable and fail to provide remote real time data analysis. This research proposes a novel color 3D scanner architecture environment for remote real time multiple sensor processing and reconstruction. The goal is to present a more efficient system based upon scalability and low latency applications, where multiple sensors can be added without losing the overall processing capability. For this purpose, this study approaches this problem in two ways. First, it improves 3D reconstruction algorithms by enhancing individual performance. Second, to optimize the entire system, it distributes the running processes in individual layers, interconnected by an edge-fog architecture. This architecture enables the use of multiple devices by optimizing payload distribution, latency, and throughput in the network. Unlike previous studies, the results present a thorough analysis of architecture efficiency when multiple sensors are operating in parallel instead of the traditional centralized architecture. Finally, this work provides the basis for real-time remote presence applications. (c) 2022 Elsevier B.V. All rights reserved.

关键词： Multiple 3D scanning real time modeling Edge-fog architecture Fog robotics Virtual reality

来源：评论

学校读者我要写书评

暂无评论

MTD: Multi-timestep Detector for Delayed Streaming Perception 6th

MTD: Multi-Timestep Detector for Delayed Streaming Perceptio...

引用

6th Chinese Conference on Pattern Recognition and Computer Vision (PRCV)

作者： Huang, Yihui Chen, Ningjiang Guangxi Univ Sch Comp & Elect Informat Nanning Peoples R China Guangxi Intelligent Digital Serv Res Ctr Engn Tec Nanning Peoples R China Guangxi Univ Educ Dept Guangxi Zhuang Autonomous Reg Key Lab Parallel Distributed & Intelligent Comp Nanning Peoples R China

ISBN: (纸本)9789819984343;9789819984350

Autonomous driving systems require real-time environmental perception to ensure user safety and experience. Streaming perception is a task of reporting the current state of the world, which is used to evaluate the delay and accuracy of autonomous driving systems. In real-world applications, factors such as hardware limitations and high temperatures inevitably cause delays in autonomous driving systems, resulting in the offset between the model output and the world state. In order to solve this problem, this paper propose the Multi-timestep Detector (MTD), an end-to-end detector which uses dynamic routing for multi-branch future prediction, giving model the ability to resist delay fluctuations. A Delay Analysis Module (DAM) is proposed to optimize the existing delay sensing method, continuously monitoring the model inference stack and calculating the delay trend. Moreover, a novel timestep Branch Module (TBM) is constructed, which includes static flow and adaptive flow to adaptively predict specific timesteps according to the delay trend. The proposed method has been evaluated on the Argoverse-HD dataset, and the experimental results show that it has achieved state-of-the-art performance across various delay settings.

关键词： Streaming Perception Object Detection Dynamic Network

来源：评论

学校读者我要写书评

暂无评论

A Study on Integrating HRRC Network for Robust CVR Solutions 15

A Study on Integrating HRRC Network for Robust CVR Solutions

引用

15th International Conference on Ubiquitous and Future Networks (ICUFN)

作者： Choi, Sungsoo Kang, Jimyoung Korea Electrotechnol Res Inst KERI Power ICT Res Ctr 1271-19 Sa Dong Ansan South Korea

ISBN: (纸本)9798350385304;9798350385298

Conservation Voltage Reduction (CVR) technology optimizes distribution grid voltage to reduce power demand and losses, improving power system efficiency and stability. Effective real-time monitoring and control of power system voltage and load need a reliable communication network. Ensuring time-sensitive stability in measuring and sharing extensive data from distributed power resources is crucial, especially in unpredictable electrical environments. This paper proposes a solution in the form of a High Reliable Redundancy Communication (HRRC) network. HRRC aims to enhance the network performance and reliability of CVR technology for future power grid systems. The design and implementation of HRRC involves Ethernet-based High Availability Seamless Redundancy (HSR), parallel Redundancy Protocol (PRP), and Merging Unit (MU), offering robust solutions for CVR.

关键词： Conservation Voltage Reduction (CVR) High Reliable Redundancy Communication (HRRC) Merging Unit (MU) High-availability Seamless Redundancy (HSR) parallel Redundancy of Protocol (PRP) IEC 61850

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Effects of Experience Replay on Deep Reinforcement Learning-based Power Allocation in Wireless Networks 25

Unveiling the Effects of Experience Replay on Deep Reinforce...

引用

IEEE Wireless Communications and Networking Conference (IEEE WCNC)

作者： Kopic, Amna Perenda, Erma Gacanin, Haris Rhein Westfal TH Aachen Chair Distributed Signal Proc Aachen Germany

ISBN: (纸本)9798350303582;9798350303599

Deep reinforcement learning has emerged as a powerful tool for dynamic power allocation, as it allows continuous learning and real-time responsiveness to environmental changes through its core element, experience replay. Experience replay involves two critical hyperparameters: the replay buffer and mini-batch sizes. While state-of-the-art solutions primarily concentrate on designing input features and reward-shaping methods, the impact of experience replay parameters on system performance has often been overlooked. This paper aims to address this gap by exploring the effects of experience replay parameters in the context of dynamic power allocation in multi-carrier wireless systems. To address the power allocation problem, we propose a multi-agent cooperative deep reinforcement learning framework. The results show that a minimum of 2000 experiences in the replay buffer is necessary for the proposed solution to outperform conventional approaches. Moreover, many obsolete experiences within a larger replay buffer slightly decrease system performance. Interestingly, the increase in batch size does not significantly affect the learning models' training time due to parallel execution, yet, it improves performance.

关键词： Experience replay Dynamic power allocation Deep reinforcement learning Multi-carrier systems

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：