检索结果-内蒙古大学图书馆

IEEE international conference on High Performance Computing and Communications (HPCC)

作者： Dianzhu Gao Jun Peng Shengnan Wang Yijun Cheng Yingze Yang Yun Cheng Yao Lu Xiaoyong Zhang School of Automation Central South University Changsha China Hunan Engineering Laboratory of Rail Vehicles Braking Technology Changsha China School of Computer Science and Engineering Central South University Changsha China

ISBN: (纸本)9781728176499;9781728176505

the equalizing reservoir control system is the core part of the DK-2 brake system, and its health condition is important to the railway safety. In this paper, a health condition assessment scheme for the equalizing reservoir control system is proposed based on the physical health indicators and back propagation (BP) neural network. First, after analysis of the system, the phase indicators and the following indicators are extracted. Second, the virtual health indicator is constructed to represent the health status of the system based on multiobjective programming. Finally, a BP neural network is trained based on the virtual health indicator. the experimental platform of the equalizing reservoir control system is built to verify the proposed health condition assessment scheme. the results shows the superiorities compared with other assessment methods in terms of RMSE and Scores.

关键词： Computational modeling High performance computing conferences Neural networks Railway safety programming Predictive models

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning based Heterogeneous Resource Provisioning for Cloud Web Applications

Reinforcement Learning based Heterogeneous Resource Provisio...

引用

IEEE international conference on High Performance Computing and Communications (HPCC)

作者： Yipei Fang Zhicheng Cai School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9781728176505

Cloud computing enables enterprises to deploy Web applications on elastically rented Virtual Machines (VMs). In order to minimize VM rental costs while fulfilling Service Level Agreements (SLAs), it is crucial to design effective VM provisioning algorithms. Queueing and control theories based methods are widely used in existing works. However, complex nonlinear system characteristics restrict these methods from getting well performance and most of them are tailored for homogeneous resources. In this paper, a deep reinforcement learning method is proposed for provisioning heterogeneous multi-type VMs which takes advantage of the deep-learning-network's nonlinear modeling ability, incremental-VM-capacity-based action space definition and Integer Linear programming based mapping from the incremental capacity to the multi-type VM renting plan. Experimental results demonstrate that our approach achieves the fastest convergence speed and highest total rewards.

关键词： Cloud computing High performance computing Reinforcement learning Integer linear programming Virtual machining Control theory Nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

GPTE: Efficient Graph Partitioning-based Traffic engineering in Hybrid SDN/IP Networks

GPTE: Efficient Graph Partitioning-based Traffic Engineering...

引用

IEEE international conference on High Performance Computing and Communications (HPCC)

作者： Huijun Dai Min Zhu Li Wang Jianlong Zhao Xiaolin Gui Guangyu Peng School of Computer Science Shanxi Province Key Laboratory of Computer Network Xi’an Jiaotong Univercity Shanxi Xi’an China School of Communication Engineering Xi’an Jiaotong Univercity Shanxi Xi’an China Huawei Company Shanxi Xi’an China Qingdao Hisense TransTech Co. Ltd Shandong Qingdao China School of Computer Science Xi’an Jiaotong Univercity Shanxi Xi’an China

ISBN: (纸本)9781728176505

Due to the lack of a centralized global view on the Traditional IP network, it may cause load imbalance or network congestion. Because of the high economical costs and technical conditions of the migration to full SDN, network operators prefer partial deployment of SDN-enabled devices in the IP network. An efficient graph partitioning-based TE (GPTE) in hybrid SDN/IP networks is proposed by considering the network topology, in which legacy devices and SDN-enabled devices co-exist. Firstly, GPTE models the partial SDN deployment as a Network Partitioning Problem solved by transforming the original network into its dual, which make the representation applicable to partitioning. Afterwards, GPTE formulates the TE as an Integer Linear programming (ILP) by considering hybrid SDN/IP routing mechanism. Finally, through intensive experiments under different topologies, GPTE can achieve a significant improvements in terms of load balancing performance and can provide better TE capabilities.

关键词： Biological system modeling High performance computing conferences Quality of service Integer linear programming Routing Load management

来源：评论

学校读者我要写书评

暂无评论

Control Design Based on Sum of Squares programming for Non-affine in Input Systems

Control Design Based on Sum of Squares Programming for Non-a...

引用

IEEE international conference on Control science and Systems engineering (CCSSE)

作者： Alexandre M. Ribeiro André R. Fioravanti Alexandra Moutinho Ely C. de Paiva Department of Computational Mechanics - DMC University of Campinas - UNICAMP São Paulo Brazil Mechanical Engineering Institute - IDMEC Instituto Superior Técnico - IST Lisbon Portugal Department of Integrated Systems - DSI University of Campinas - UNICAMP São Paulo Brazil

ISBN: (数字)9781728198460

ISBN: (纸本)9781728198477

this paper addresses the state feedback control synthesis for the class of nonaffine in input systems using the sum of squares (SOS) programming. Due to the nature of these systems, the SOS control design technique becomes a non-convex problem. In order to circumvent this issue, two input-affine approximations are proposed, both based on linearization. In order to ensure better approximations, we propose the inclusion of new restrictions, which are inserted into the SOS program. Two examples are given to provide analytical and graphical illustration of the given approaches. It is performed the stability analysis of the open-loop system by estimating its region of attraction (RoA) and their enlargement, achieved with a state feedback controller.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Submodular Stochastic Probing with Prices 6

Submodular Stochastic Probing with Prices

引用

6th international conference on Control, Decision and Information Technologies (CoDIT)

作者： Chugg, Ben Maehara, Takanori School of Mechanical Electrical and Information Engineering Shandong University Weihai China

ISBN: (纸本)9781728105215

We introduce Stochastic Probing with Prices (SPP), a variant of the Stochastic Probing (SP) model in which we must pay a price to probe an element. A SPP problem involves two set systems (N;I-in) and (N;I-out) where each e is an element of N is active with probability p(e). To discover whether an element e is active, it must be probed by paying the price Delta(e). If an element is probed and is active, then it is irrevocably added to the solution. Moreover, at all times, the set of probed elements must lie in I-out, and the solution (the set of probed and active elements) must lie in I-in. the goal is to maximize a submodular set function f minus the cost of the probes. We give a bi-criteria approximation algorithm to the online version of this problem, in which the elements are shown to the algorithm in a possibly adversarial order. Our results translate to state-of-the-art approximations for the traditional (online) stochastic probing problem.

关键词： Approximation algorithms Linear programming Computational modeling Probes Markov processes Uncertainty

来源：评论

学校读者我要写书评

暂无评论

Relief Mapping Assessment using Two-Echelon Vehicle Routing Problem with Drone

Relief Mapping Assessment using Two-Echelon Vehicle Routing ...

引用

international conference on science and Technology-Computer (ICST)

作者： A. A. N. Perwira Redi Rahmad Inca Liperda Bertha Maya Sopha Anna Maria Sri Asih Nandini Niramaya Sekaringtyas Handina Boedhy Astiana BINUS Graduate Program - Master of Industrial Engineering Bina Nusantara University Jakarta Indonesia Universitas Pertamina Jakarta Indonesia Universitas Gadjah Mada (UGM) Yogyakarta Indonesia

ISBN: (纸本)9781728194738

this study considers the two-echelon vehicle routing problem using drones in the postdisaster situation. the problem takes into account using a collaboration between a drone with a ground vehicle to conduct an information gathering so-called mapping operation. Each ground vehicle is associated with a drone. the first echelon depicts the routes travelled from depot to stopover point and from a stopover point to another stopover point. the first echelon is travelled by a ground vehicle to extend the limitation of drone's range coverage to gather information. the second echelon is the assignment of the drone to the target point. A target point is an area being mapped or in this case that is affected by the disaster. the problem is modelled as an integer linear programming problem denoted as 2EVRP-MOD. It is assumed that drone can only be released from a stopover point. the mapping operation is associated with the amount of area being covered at each target area. the objective is to minimize the total mapping operation time. the entire mapping operation time is limited by the drone flying capacity limit. the model is tested on a real-case dataset in Bekasi, Indonesia. the computational results show that the model can effectively provide a solution for the 2EVRP-MOD.

关键词： Computational modeling Vehicle routing Collaboration Integer linear programming Land vehicles Drones

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient Resource Allocation for Time Switching Wireless Powered NOMA Networks

Energy Efficient Resource Allocation for Time Switching Wire...

引用

international conference on Computer and Communications (ICCC)

作者： Chengyu Cao Jian Zhao School of Electronic Science and Engineering Nanjing University Nanjing China

ISBN: (数字)9781728186351

ISBN: (纸本)9781728186368

Non-orthogonal multiple access (NOMA) has attracted much attention from not only industry but also academia and has the potential to meet the demand of increasing data rate. In this paper, the problem of joint resource allocation and time switching (TS) control in wireless-powered NOMA internet of things (IoT) network is considered. We aim to maximize the sum of user-centric energy efficiency (EE) in the system. the optimization problem is divided into subcarrier allocation, power control and TS control. Firstly, the subcarrier allocation problem is a mixed-integer non-linear programming problem which is non-convex. thus two-sided matching algorithm is proposed to optimize subcarrier allocation with low complexity. then because the sum of user-centric EE is the sum of fractional programming problem, successive convex approximation (SCA) is applied to solve the problem. Finally, the simulation results show convergence of the proposed optimization scheme and we achieve better performance than orthogonal frequency division multiple access (OFDMA) scheme.

关键词： NOMA Simulation Switches programming Energy efficiency Resource management Optimization

来源：评论

学校读者我要写书评

暂无评论

Preface

Smart Innovation, Systems and Technologies

引用

Smart Innovation, Systems and Technologies 2022年 249卷 v-vi页

作者： Mealha, Óscar Dascalu, Mihai Di Mascio, Tania Department of Communication and Art/DigiMedia University of Aveiro Aveiro Portugal Department of Engineering Computer Science and Mathematics University of L’Aquila L’Aquila Italy Department of Computer Science University Politehnica of Bucharest Bucharest Romania

来源：评论

学校读者我要写书评

暂无评论

Automatic Parking Guidance System Based on Ultraviolet Communication 1

引用

6th EAI international conference on Green Energy and Networking, GreeNets 2019

作者： Ye, Zhengpeng Wang, Jinpeng Zou, Nianyu Zou, Ailing School of Information Science and Engineering Dalian Polytechnic University Dalian116034 China

ISBN: (数字)9783030217303

ISBN: (纸本)9783030217297

In view of the existing parking guidance system in the process of vehicle guide dynamic programming efficiency is not high, poor compatibility in different parking environment, thus give negative influence large parking guidance system reliability problems, compatible with a variety of parking environment was designed based on the "blind" technology of ultraviolet communication parking guidance system, adopts the path planning algorithm in the preprocessing module, promote efficiency of dynamic programming, using the "blind" ultraviolet communication technology on the environment compatibility strong, less susceptible to environmental characteristics, improve the compatibility of the parking guidance system. Experiments show that the system can effectively reduce the dynamic path planning time, ensure the effective communication distance of single node of 4Â m in a variety of parking environments, and meet the basic requirements of parking guidance system. © 2019, ICST Institute for Computer sciences, Social Informatics and Telecommunications engineering.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Approach Based on Gene Expression programming for Dynamic Production Scheduling Problem 6

Machine Learning Approach Based on Gene Expression Programmi...

引用

2019 6th international conference on Advanced Composite Materials and Manufacturing engineering, ACMME 2019

作者： Nie, Li Wang, Xiaogang Bai, Yuewei Wu, Xiaoyan School of Intelligent Manufacturing and Control Engineering Shanghai Polytechnic University Shanghai201209 China

Dynamic Job shop scheduling problem (DJSSP) which involves the dynamic characteristic of job arriving over time is one of the most popular scheduling problems in manufacturing system. In the paper, a machine learning approach is proposed for DJSSP. the proposed machine learning approach employs gene expression programming (GEP) which introduces automatically defined functions (ADF) into the representation of chromosome to construct efficient scheduling rules (SRs) automatically for DJSSP. the proposed GEP-based machine learning approach is evaluated and the results show that the approach is effective. © Published under licence by IOP Publishing Ltd.

关键词： Manufacture

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：