检索结果-内蒙古大学图书馆

Multi-SP Network Slicing parallel Relieving Edge Network Conflict

IEEE TRANSACTIONS ON parallel AND distributed systems 2023年第11期34卷 2860-2875页

作者： Han, Rongxin Chen, Dezhi Guo, Song Wang, Jingyu Qi, Qi Lu, Lu Liao, Jianxin Beijing Univ Posts & Telecommun State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Hong Kong Polytech Univ Dept Comp Hong Kong Peoples R China China Mobile Res Inst Dept Network & IT Technol Beijing 100032 Peoples R China

Network slicing is rapidly prevailing in the edge network, which provides computing, network, and storage resources for various services. When the multiple service providers (SPs) respond to their tenants in parallel, individual decisions on the dynamic and shared edge network may lead to resource conflicts, which affects the delivery of network slicing services. Existing works ignore resource interaction and coordination in the multi-SP scenario, which is not in line with the actual situation. Indeed, the complexity of resource interaction caused by the coexistence of multiple SP policies increases the difficulty to solve the formulated optimization model. In this article, we focus on the multi-SP network slicing deployment in parallel. The coordination of network resources between SPs is designed as an effective multi-agent communication mechanism that is merged into multi-agent deep reinforcement learning (MADRL). To deal with dynamic edge networks, we design the neurons hotplugging learning which realizes scalability without a high cost of model retraining. Experiments on real and random networks demonstrate that the proposed multi-SP network slicing mechanism can successfully learn coordination policies and easily adapt to various network scales. It improves the accepted requests by 7.4%, reduces resource conflicts by 14.5%, and shortens the model convergence time by 83.3%.

关键词： Network slicing Resource management Neurons Scalability Privacy Network topology Adaptation models resource conflict MADRL multi-agent communication neurons hotplugging learning

来源：评论

学校读者我要写书评

暂无评论

Scheduling Tool for Deterministic Communication in distributed real-time systems 10

Scheduling Tool for Deterministic Communication in Distribut...

引用

10th workshop on Software Quality Analysis, Monitoring, Improvement, and Applications, SQAMIA 2023

作者： Mach, Jan Tašková, Valéria Kohútka, Lukáš Institute of Computer Engineering and Applied Informatics Faculty of Informatics and Information Technologies Slovak University of Technology Bratislava Slovakia Institute of Informatics Information Systems and Software Engineering Faculty of Informatics and Information Technologies Slovak University of Technology Bratislava Slovakia

A network with critical data streams, where the timing of incoming and outgoing data is a necessity, is called a deterministic network. These networks are mostly used in association with real-time systems that use periodic hard-real-time data which need to be scheduled. The algorithm proposed in this paper is focused on achieving the lowest possible latency within the specified network topology depending on the physical parameters of the network and the periodic requirements of the communicating nodes. The algorithm allows to add priorities to the data flow between nodes and also the option to specify if preemption is allowed within the network, since not all devices support it. The result is a schedule of hard-real-time data communication within a specified network topology where all requirements of communicating nodes are met if such a solution is possible. © 2023 Copyright for this paper by its authors.

关键词： deadline deterministic scheduling Ethernet scheduling algorithm time-sensitive networking

来源：评论

学校读者我要写书评

暂无评论

ProfIT AI 2023 - Proceedings of the 3rd International workshop of IT-Professionals on Artificial Intelligence 2023

ProfIT AI 2023 - Proceedings of the 3rd International Worksh...

引用

3rd International workshop of IT-Professionals on Artificial Intelligence, ProfIT AI 2023

The proceedings contain 27 papers. The topics discussed include: artificial intelligence-driven cargo optimization service for logistics;estimation of Ukrainian refugees impact on COVID-19 dynamics in Czech Republic using Prophet model;cluster method applying to Covid-19 event study for the largest USA banks;the higher educational information system: management of the timetable scheduling;development of a syntax for representing regular constraints on the behavior of distributed systems with output;intelligent solution for improving winery operations: wine production management system;competencies model for the socialization of artificial intelligence systems;approaches to organization of change tables for real- time business intelligence;and deep learning models for estimating number of lambda- term reduction steps.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Implementation of Asynchronous distributed Gauss-Newton Optimization Algorithms for Uncertainty Quantification by Conditioning to Production Data

引用

SPE Journal 2023年第3期28卷 1451-1472页

作者： Gao, Guohua Florez, Horacio Jost, Sean Shaikh, Shakir Wang, Kefei Vink, Jeroen Blom, Carl Wells, Terence J. Saaf, Fredrik Inc United States Shell Exploration & Production Company United States Shell Global Solutions International B.V. Netherlands

Previous implementation of the distributed Gauss-Newton (DGN) optimization algorithm ran multiple optimization threads in parallel, employing a synchronous running mode (S-DGN). As a result, it waits for all simulations submitted in each iteration to complete, which may significantly degrade performance because a few simulations may run much longer than others, especially for time-consuming real-field cases. To overcome this limitation and thus improve the DGN optimizer’s execution, we propose two asynchronous DGN (A-DGN) optimization algorithms in this paper. The two A-DGN optimization algorithms are (1) the local-search algorithm (A-DGN-LS) to locate multiple maximum a-posteriori (MAP) estimates and (2) the integrated global-search algorithm with the randomized maximum likelihood (RML) method (A-DGN + RML) to generate hundreds of RML samples in parallel for uncertainty quantification. We propose using batch together with a checking time interval to control the optimization process. The A-DGN optimizers check the status of all running simulations after every checking time frame. The iteration index of each optimization thread is updated dynamically according to its simulation status. Thus, different optimization threads may have different iteration indices in the same batch. A new simulation case is proposed immediately once the simulation of an optimization thread is completed, without waiting for the completion of other simulations. We modified the training data set updating algorithm using each thread’s dynamically updated iteration index to implement the asynchronous running mode. We apply the modified QR decomposition method to estimate the sensitivity matrix at the best solution of each optimization thread by linear interpolation of all or a subset of the training data to avoid the issue of solving a linear system with a singular matrix because of insufficient training data points in early batches. A new simulation case (or search point) is generated by solvi

关键词： Linear systems

来源：评论

学校读者我要写书评

暂无评论

Tardiness Bounds for Sporadic Gang Tasks Under Preemptive Global EDF Scheduling

引用

IEEE TRANSACTIONS ON parallel AND distributed systems 2021年第12期32卷 2867-2879页

作者： Dong, Zheng Yang, Kecheng Fisher, Nathan Liu, Cong Wayne State Univ Dept Comp Sci Detroit MI 48202 USA Texas State Univ Dept Comp Sci San Marcos TX 78666 USA Univ Texas Dallas Dept Comp Sci Dallas TX 75080 USA

Following the trend of increasing autonomy in cyber-physical systems, parallel embedded architectures have enabled devices to better handle the large streams of data and intensive computation required by such autonomous systems. However, while the explosion of highly-parallel platforms has seen a proportional growth in the number of applications/devices that utilize these platforms, the embedded systems community's understanding of how to build time-predictable, safety-critical systems with parallel platforms has not kept pace. As a well-motivated but challenging parallel scheduling model, gang scheduling requires all parallel threads of each parallel task to simultaneously execute in unison, which is in contrast to traditional, multi-threaded parallel scheduling, where a parallel task may spawn multiple threads, and each thread will be scheduled independently of other threads of the same task. While increasing research efforts on hard real-time (HRT) gang scheduling have recently been seen, the problem of gang scheduling in the context of soft real-time (SRT) systems, where provably bounded deadline tardiness can be tolerated, has hardly been studied yet. In this article, we derive and prove the first tardiness bounds for sporadic gang task systems under preemptive GEDF scheduling. A total utilization bound for SRT-schedulability is required for ensuring such tardiness bounds but it is shown to be tight with respect to the platform capacity and maximum parallelism-induced idleness. Furthermore, we also empirically evaluate the effects of different degrees of task parallelism upon the SRT-schedulability.

关键词： Task analysis real-time systems parallel processing Message systems Schedules Multicore processing Instruction sets real-time scheduling gang tasks schedulability test tardiness bound Global-Earliest-Deadline

来源：评论

学校读者我要写书评

暂无评论

Privacy vs. Efficiency: Achieving Both Through Adaptive Hierarchical Federated Learning

引用

IEEE TRANSACTIONS ON parallel AND distributed systems 2023年第4期34卷 1331-1342页

作者： Guo, Yeting Liu, Fang Zhou, Tongqing Cai, Zhiping Xiao, Nong Natl Univ Def Technol Coll Comp Changsha 410073 Hunan Peoples R China Hunan Univ Sch Design Changsha 410082 Hunan Peoples R China Sun Yat sen Univ Sch Comp Sci & Engn Guangzhou 510000 Guangdong Peoples R China

As a decentralized training paradigm, Federated learning (FL) promises data privacy by exchanging model parameters instead of raw local data. However, it is still impeded by the resource limitations of end devices and privacy risks from the 'curious' cloud. Yet, existing work predominately ignores that these two issues are non-orthogonal in nature. In this article, we propose a joint design (i.e., AHFL) that accommodates both the efficiency expectation and privacy protection of clients towards high inference accuracy. Based on a cloud-edge-end hierarchical FL framework, we carefully offload the training burden of devices to one proximate edge for enhanced efficiency and apply a two-level differential privacy mechanism for privacy protection. To resolve the conflicts of dynamical resource consumption and privacy risk accumulation, we formulate an optimization problem for choosing configurations under correlated learning parameters (e.g., iterations) and privacy control factors (e.g., noise intensity). An adaptive algorithmic solution is presented based on performance-oriented resource scheduling, budget-aware device selection, and adaptive local noise injection. Extensive evaluations are performed on three different data distribution cases of two real-world datasets, using both a networked prototype and large-scale simulations. Experimental results show that AHFL relieves the end's resource burden (w.r.t. computation time 8.58% down arrow, communication time 59.35%down arrow and memory consumption 43.61%down arrow) and has better accuracy (6.34%down arrow) than 3 typical baselines under the limited resource and privacy budgets.

关键词： Privacy Training Computational modeling Task analysis Performance evaluation Data models Adaptation models distributed machine learning edge computing federated learning privacy protection

来源：评论

学校读者我要写书评

暂无评论

A Compensated distributed-Parameter Line Decoupling Approach for real time Applications

引用

IEEE TRANSACTIONS ON SMART GRID 2021年第2期12卷 1761-1771页

作者： Ahmed, Babikir Abdelgadir, Amira Saied, Noman A. Karrar, Abdelrahman A. Univ Tennessee Dept Elect Engn Chattanooga TN 37403 USA

This article proposes a new method called the Compensated distributed-Parameter Line Decoupling (CDLD) method, and used for decoupling distribution networks among parallel processing cores in a real-time multi-core environment. Due to the short length of distribution grid lines, decoupling the distribution network for real-time processing is challenging and approaches such as Stublines and State Space Nodal (SSN) solvers have been proposed. Both approaches have limitations and the method proposed in this work addresses these limitations to implement improvements. Specifically, the CDLD method can be used as an enhanced Stubline decoupling, improving on its accuracy and transient response, or it can be combined with an SSN solver to improve its computational performance and remove bottleneck issues. The CDLD method was tested on three IEEE benchmark systems in a real-time environment, and significant improvement was realized in network response and computational performance compared to the prevailing methods. The combined SSN-CDLD method proved to be the most promising approach for network decoupling.

关键词： real-time systems Capacitance Propagation delay Computational modeling Mathematical model Impedance Delays real-time computation decoupling parallel processing state-space nodal

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning based two-timescale energy management for energy hub

引用

IET RENEWABLE POWER GENERATION 2024年第3期18卷 372-383页

作者： Chen, Jinfan Mao, Chengxiong Sha, Guanglin Sheng, Wanxing Fan, Hua Wang, Dan Qiu, Shushan Wu, Yunzhao Zhang, Yao Huazhong Univ Sci & Technol Sch Elect & Elect Engn Wuhan 430074 Peoples R China China Elect Power Res Inst Beijing Peoples R China

Maintaining energy balance and economical operation is significant for energy hub (EH) which serves as the central component. Implementing real-time regulation for heating and cooling equipment within the EH is challenging due to their slow response time in response to the stochastic fluctuation in renewable energy sources and demands while the opposite is true for electric energy storage equipment (EST), a conventional single timescale energy management strategy is no longer sufficient to take into account the operating characteristics of all equipment. With this motivation, this study proposes a deep reinforcement learning based two-timescale energy management strategy for EH, which controls heating & cooling equipment on a long timescale of 1 h, and EST on a short timescale of 15 min. The actions of the EST are modelled as discrete to reduce the action spaces, and the discrete-continuous hybrid action sequential TD3 model is proposed to address the problem of handling both discrete and continuous actions in long timescale policy. A joint training approach based on the centralized training framework is proposed to learn multiple levels of policies in parallel. The case studies demonstrate that the proposed strategy reduces the economic cost and carbon emissions by 1%, and 0.5% compared to the single time-scale strategy respectively. This paper proposes a deep reinforcement learning based two-timescale energy management strategy for energy hubs to reduce the economic cost and carbon emissions, with hour-ahead and intra-hour policies that respectively control the heating and cooling equipment at a long timescale, and electrical equipment at a short timescale. image

关键词： artificial intelligence distributed power generation energy management systems microgrids optimal control planning power conversion power generation scheduling renewable energy sources energy conservation

来源：评论

学校读者我要写书评

暂无评论

distributed Cooperative Energy Management System of Connected Hybrid Electric Vehicles With Personalized Non-Stationary Inference

引用

IEEE TRANSACTIONS ON TRANSPORTATION ELECTRIFICATION 2022年第2期8卷 2996-3007页

作者： Li, Ji Zhou, Quan He, Yinglong Williams, Huw Xu, Hongming Lu, Guoxiang Univ Birmingham Dept Mech Engn Birmingham B15 2TT W Midlands England Shenzhen BYD Auto Co Ltd Guangzhou 518118 Peoples R China

This article develops a distributed cooperative energy management system (EMS) with two distributed control layers for speed-coupling plug-in hybrid electric vehicles (PHEVs). By introducing personalized non-stationary inference, this system can fuse driving behavior and vehicle state information to adaptively adjust power-split control parameters for the improvement of vehicle energy economy. In the on-board control layer, five sets of personalized control parameters are optimized offline using chaos-enhanced accelerated particle swarm optimization (CAPSO). In the distributed control layer, interval type 2 (IT2) fuzzy sets are applied to develop a real-time driving style recognition function. The driving behavior is detected remotely, via the vehicle-to-everything (V2X) network, and downloaded to adaptively adjust the power-split control parameters in the on-board vehicle controller. Hardware-in-the-loop testing is carried out based on the four laboratory driving cycles and four personal driving cycles. The proposed system has been demonstrated with strong robustness that saves energy by up to 5.25% over the equivalent consumption minimization strategy (ECMS), especially for gentle drivers. Even under harsh communication conditions (with signal loss 80+%), it still performs better than the ECMS (by 0.57%) and the series-parallel (SP) control strategy (by 2.66%).

关键词： Torque Connected vehicles Batteries Vehicle-to-infrastructure real-time systems Optimization Minimization Connected hybrid electric vehicle distributed decision-making energy management personalization interval type 2 (IT2) fuzzy logic set non-stationary inference

来源：评论

学校读者我要写书评

暂无评论

PISTIS: An Event-Triggered real-time Byzantine-Resilient Protocol Suite

引用

IEEE TRANSACTIONS ON parallel AND distributed systems 2021年第9期32卷 2277-2290页

作者： Kozhaya, David Decouchant, Jeremie Rahli, Vincent Esteves-Verissimo, Paulo ABB Res CH-5405 Baden Switzerland Delft Univ Technol NL-2628 CD Delft Netherlands Univ Birmingham Birmingham B15 2TT W Midlands England King Abdullah Univ Sci & Technol RC3 Thuwal 23955 Saudi Arabia

The accelerated digitalisation of society along with technological evolution have extended the geographical span of cyber-physical systems. Two main threats have made the reliable and real-time control of these systems challenging: (i) uncertainty in the communication infrastructure induced by scale, and heterogeneity of the environment and devices;and (ii) targeted attacks maliciously worsening the impact of the above-mentioned communication uncertainties, disrupting the correctness of real-time applications. This article addresses those challenges by showing how to build distributed protocols that provide both real-time with practical performance, and scalability in the presence of network faults and attacks, in probabilistic synchronous environments. We provide a suite of real-time Byzantine protocols, which we prove correct, starting from a reliable broadcast protocol, called PISTIS, up to atomic broadcast and consensus. This suite simplifies the construction of powerful distributed and decentralized monitoring and control applications, including state-machine replication. Extensive empirical simulations showcase PISTIS's robustness, latency, and scalability. For example, PISTIS can withstand message loss (and delay) rates up to 50 percent in systems with 49 nodes and provides bounded delivery latencies in the order of a few milliseconds.

关键词： Protocols Uncertainty Scalability Process control Bandwidth real-time systems Monitoring real-time distributed systems probabilistic losses consensus atomic broadcast Byzantine resilience intrusion tolerance

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：