检索结果-内蒙古大学图书馆

real-time Model Predictive Control for a parallel Hybrid Electric Vehicle using Outer Approximation and Semi-Convex Cut Generation**This work has been carried out within the framework of KU Leuven - BOF PFV/10/002 Centre of Excellence: Optimization in Engineering (OPTEC) and DrivetrainCodesign: Flanders Make ICON: Physical and control co-design of electromechanical drivetrains for machines and vehicles. Flanders Make is the Flemish strategic research centre for the manufacturing industry.

Real-Time Model Predictive Control for a Parallel Hybrid Ele...

引用

International workshop on Advanced Motion Control (AMC)

作者： Massimo De Mauri Joris Gillis Goele Pipeleers Jan Swevers KU Leuven and DMMS lab Flanders Make Leuven Belgium

ISBN: (数字)9781728131894

ISBN: (纸本)9781728131900

Hybrid Electric Vehicles (HEVs) have the potential of yielding better fuel economy and lower emissions compared to their traditional counterparts. This advantage comes with the drawback that drivers are no longer capable of efficiently controlling the power-train of their vehicles. Consequently, good automatic control is crucial for HEV design. In this paper the full development of the power-train control system of a parallel-HEV is presented. The proposed control approach is Mixed-Integer Model Predictive Control (MI-MPC). A suitable MI-MPC formulation is developed starting from the modeling of the propulsion components of the power-train based on a set of real-world data. After guiding the reader through the development of the model. An innovative solution approach is presented to deal with the inherit non-convexity of the resulting problem formulation. The peculiar form of non-convexity in the model is harnessed in order to develop a variation of the Outer Approximation algorithm capable of efficiently tackling the solution of the mixed-integer optimization problems required by the MI-MPC framework. In conclusion, a numerical experiment will show the real-time applicability of the resulting control system and highlight its limits.

关键词： Control systems Prediction algorithms real-time systems Numerical models Hybrid electric vehicles Optimization Predictive control

来源：评论

学校读者我要写书评

暂无评论

Optimization Methods for Computing System in Mobile CPS 19

Optimization Methods for Computing System in Mobile CPS

引用

2nd International Conference on Big Data Technologies (ICBDT) / 3rd International Conference on Business Information systems workshop (ICBIS)

作者： Zhang, Yang Xing, Zuocheng Wang, Yu Chen, Lirui Wang, Qinglin Zhu, Yufei Natl Univ Def Technol Natl Lab Parallel & Distributed Proc Changsha Peoples R China

ISBN: (纸本)9781450371926

In Mobile Cyber-physical system (CPS) is a popular research field in recent years. It aims to control and monitor mobile devices in complex and real-time scenes, and provide people with convenience and economy by using intelligent applications. The scenes in mobile CPS have close relationships with everyone's life and it has pervasive effect on people's life anytime and anywhere. In the paper, we focus on the intelligent transportation systems (ITS) in mobile CPS. Specifically, we analyse the bottlenecks in automated and autonomous vehicles and find the on-car computer is the key component for low latency and low power self-driving vehicles. We show detailed research developments on the most advanced CPU-GPU platform including four aspects, mainly putting focus on the methods to reduce latency and energy in the system. The four aspects cover reducing data transferring overhead, reducing power consumption with power-gating, optimizing warp scheduling scheme and optimizing cache performance in coprocessors. Finally, we give the prospects and development trends in the computing platform of self-driving on-car system.

关键词： CPS Intelligent Transportation systems CPU-GPU platform

来源：评论

学校读者我要写书评

暂无评论

Large-Scale Dynamic Graph Updating Algorithm in distributed Computing System 19

Large-Scale Dynamic Graph Updating Algorithm in Distributed ...

引用

2nd International Conference on Big Data Technologies (ICBDT) / 3rd International Conference on Business Information systems workshop (ICBIS)

作者： Rong Xuanyu Cui Huanqing Shandong Univ Sci & Technol Coll Comp Sci & Engn Qingdao Peoples R China

ISBN: (纸本)9781450371926

distributed graph computing technology for processing large-scale graph data has been widely used in social network, communication network and so on. The foundation of distributed graph computing is reasonable partitioning of large-scale graph in distributed system. Most proposed graph partitioning algorithms cannot achieve the goals of load balance and minimizing the number of edge-cuts at the same time. This paper constructs a cost function to measure the efficiency of partitioning large-scale graphs in a distributed system, where the graph is dynamically updated in real time. Based on the cost function, the update algorithm is proposed for the addition of vertex and edge. Experimental results show that the proposed algorithm can yield significant reduction in load imbalance and number of edge-cuts.

关键词： Graph computing Dynamic graph Graph partitioning

来源：评论

学校读者我要写书评

暂无评论

Advances in OpenDSS smart inverter modelling for quasi-static time-series simulations

Advances in OpenDSS smart inverter modelling for quasi-stati...

引用

CIRED 2020 Berlin workshop (CIRED 2020)

作者： Paulo Radatz Celso H.S. Rocha Jouni Peppanen Matthew Rylander Electric Power Research Institute Palo Alto California USA

The fleet of smart distributed energy resource (DER) inverters is expected to grow rapidly as a result of growing DER penetration levels and requirements in interconnection standards/rules such as IEEE Std 1547-2018. Smart inverters have the potential to help to maintain and/or enhance grid safety, reliability and customer affordability. Advanced modelling and analytical capabilities are required from distribution planning tools to understand the full potential of smart inverters. This study presents enhanced smart inverter modelling and simulation features included in a recent release of the open-source distribution system modelling and simulation software suite OpenDSS. The enhanced features include detailed modelling of the inverter capability curve along with significant improvements to the simulation speed and convergence. The enhanced features make it more practical to perform long quasi-static time-series load flow simulations with thousands of time steps on large-scale utility feeder models with up to thousands of autonomously controlled smart inverters. Some of the enhanced speed, convergence and other features are demonstrated on a large-scale real U.S. utility feeder model with >1100 solar photovoltaic systems.

关键词： invertors power system simulation smart power grids time series distributed power generation power system interconnection IEEE standards power distribution planning load flow photovoltaic power systems

来源：评论

学校读者我要写书评

暂无评论

Emergent Scheduling of distributed Execution Frameworks 4

Emergent Scheduling of Distributed Execution Frameworks

引用

IEEE 4th International workshops on Foundations and Applications of Self* systems (FAS*W)

作者： Dean, Paul Allan Porter, Barry Univ Lancaster Sch Comp & Commun Lancaster England

ISBN: (纸本)9781728124063

distributed execution Frameworks (DEFs) provide a platform for handling the increasing volume of data available to distributed computational processes, forming the creation and usage of a large number of DEFs for performing distributed computations. For example, sorting and analyzing large data sets through map and reduce operations, performing a set of operations across points in a data stream to provide near real-time analysis, and the training and testing of machine learning models for varying methods of learning, such as, supervised, unsupervised and reinforcement learning, exploiting the vast amounts of data available. Leading to varying DEFs becoming optimal for either fine or coarse grained computations, for example Apache Spark provides a framework for coarse grained data parallel processes providing data locality adding latency to scheduling decisions which would hinder performance of fine-grained computation. Whereas Ray and Apache Flink provide solutions to avoid the latency incurred by the scheduling method used by apache Spark while potentially incurring longer job completion times as data locality is no longer a priority. Therefore, this PhD will focus on overcoming the issue of trading performance for differing workloads by exploiting the capabilities presented by emergent software systems which learn how to assemble and re-assemble themselves in response to their current deployment conditions and input pattern. This allows the creation of a component based DEF capable of altering both the local behaviour of a DEF (i.e. Local Schedulers and placement polices within a centralised scheduler) to potentially improve the performance of single DEF as well as global behaviour of a DEF, for example the adaptation of a centralised to two-level scheduler.

关键词： Reinforcement learning Task analysis Cluster computing Processor scheduling real-time systems Training

来源：评论

学校读者我要写书评

暂无评论

DistStream: An Order-Aware distributed Framework for Online-Offline Stream Clustering Algorithms

DistStream: An Order-Aware Distributed Framework for Online-...

引用

International Conference on distributed Computing systems

作者： Lijie Xu Xingtong Ye Kai Kang Tian Guo Wensheng Dou Wei Wang Jun Wei State Key Lab of Computer Science Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences Worcester Polytechnic Institute Institute of Software Technology Chinese Academy of Sciences Nanjing

ISBN: (数字)9781728170022

ISBN: (纸本)9781728170039

Stream clustering is an important data mining technique to capture the evolving patterns in real-time data streams. Today's data streams, e.g., IoT events and Web clicks, are usually high-speed and contain dynamically-changing patterns. Existing stream clustering algorithms usually follow an online-offline paradigm with a one-record-at-a-time update model, which was designed for running in a single machine. These stream clustering algorithms, with this sequential update model, cannot be efficiently parallelized and fail to deliver the required high throughput for stream clustering. In this paper, we present DistStream, a distributed framework that can effectively scale out online-offline stream clustering algorithms. To parallelize these algorithms for high throughput, we develop a mini-batch update model with efficient parallelization approaches. To maintain high clustering quality, DistStream's mini-batch update model preserves the update order in all the computation steps during parallel execution, which can reflect the recent changes for dynamically-changing streaming data. We implement DistStream atop Spark Streaming, as well as four representative stream clustering algorithms based on DistStream. Our evaluation on three real-world datasets shows that DistStream-based stream clustering algorithms can achieve sublinear throughput gain and comparable (99%) clustering quality with their single-machine counterparts.

关键词： Heuristic algorithms Computational modeling Clustering algorithms distributed databases Throughput real-time systems Sparks

来源：评论

学校读者我要写书评

暂无评论

SNTA 2019 - Proceedings of the ACM workshop on systems and Network Telemetry and Analytics, co-located with HPDC 2019

SNTA 2019 - Proceedings of the ACM Workshop on Systems and N...

引用

2nd International workshop on systems and Network Telemetry and Analytics, SNTA 2019, co-located with HPDC 2019

ISBN: (纸本)9781450367615

The proceedings contain 8 papers. The topics discussed include: automatic detection of network traffic anomalies and changes;time series analysis for efficient sample transfers;similarity-based compression with multidimensional pattern matching;a software defined network design for analyzing streaming data in transit;understanding parallel I/O performance trends under various HPC configurations;performance prediction for data transfers in LCLS workflow;generating labeled flow data from MAWILab traces for network intrusion detection;and real-time multi-process tracing decoder architecture.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Study of Graph Analytics for Massive Datasets on distributed Multi-GPUs

A Study of Graph Analytics for Massive Datasets on Distribut...

引用

International Symposium on parallel and distributed Processing (IPDPS)

作者： Vishwesh Jatala Roshan Dathathri Gurbinder Gill Loc Hoang V. Krishna Nandivada Keshav Pingali The University of Texas at Austin Austin Texas USA IIT Madras Chennai Tamil Nadu India

ISBN: (数字)9781728168760

ISBN: (纸本)9781728168777

There are relatively few studies of distributed GPU graph analytics systems in the literature and they are limited in scope since they deal with small data-sets, consider only a few applications, and do not consider the interplay between partitioning policies and optimizations for computation and *** this paper, we present the first detailed analysis of graph analytics applications for massive real-world datasets on a distributed multi-GPU platform and the first analysis of strong scaling of smaller real-world datasets. We use D-IrGL, the state-of-the-art distributed GPU graph analytical framework, in our study. Our evaluation shows that (1) the Cartesian vertex-cut partitioning policy is critical to scale computation out on GPUs even at a small scale, (2) static load imbalance is a key factor in performance since memory is limited on GPUs, (3) device-host communication is a significant portion of execution time and should be optimized to gain performance, and (4) asynchronous execution is not always better than bulk-synchronous execution.

关键词： Graphics processing units Performance evaluation Optimization Computer architecture Mirrors Synchronization Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Efficient parallel optimizations of a high-performance SIFT on GPUs

引用

JOURNAL OF parallel AND distributed COMPUTING 2019年 124卷 78-91页

作者： Li, Zhihao Jia, Haipeng Zhang, Yunquan Liu, Shice Li, Shigang Wang, Xiao Zhang, Hao Chinese Acad Sci Inst Comp Technol State Key Lab Comp Architecture Beijing Peoples R China Univ Chinese Acad Sci Sch Comp & Control Engn Beijing Peoples R China Fudan Univ Shanghai Key Lab Intelligent Informat Proc Shanghai Peoples R China

Stable local image feature detection is a fundamental problem in computer vision and is critical for obtaining the corresponding interest points among images. As a popular and robust feature extraction algorithm, the scale invariant feature transform (SIFT) is widely used in various domains, such as image stitching and remote sensing image registration. However, the computational complexity of SIFT is extremely high, which limits its application in real-time systems and large-scale data processing tasks. Thus, we propose several efficient optimizations to realize a high-performance SIFT (HartSift) by exploiting the computing resources of CPUs and GPUs in a heterogeneous machine. Our experimental results show that HartSift processes an image within 3.07 similar to 7.71 ms, which is 55.88 similar to 121.99 times, 5.17 similar to 6.88 times, and 1.25 similar to 1.79 times faster than OpenCV SIFT, SiftGPU, and CudaSift, respectively. (C) 2018 Elsevier Inc. All rights reserved.

关键词： HartSift SIFT CPU High performance Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Block-Free distributed Ledger for P2P Energy Trading: Case with IOTA? 31st

A Block-Free Distributed Ledger for P2P Energy Trading: Case...

引用

31st Int Conf Adv Informat Syst Engn / 7th Int workshop Cognit Aspects of Informat Syst Engn / 1st Int workshop on Key Enabling Technologies for Digital Factories / Joint workshop on Blockchains for Inter-Org Collaborat and Flexible Adv Informat Syst

作者： Park, Joon Chitchyan, Ruzanna Angelopoulou, Anastasia Murkin, Jordan Univ Bristol Bristol BS8 1UB Avon England Columbus State Univ Columbus GA USA

ISBN: (纸本)9783030212902;9783030212896

Across the world, the organisation and operation of the electricity markets is quickly changing, moving towards decentralised, distributed, renewables-based generation with real-time data exchange-based solutions. In order to support this change, blockchain-based distributed ledgers have been proposed for implementation of peer-to-peer energy trading platform. However, blockchain solutions suffer from scalability problems as well as from delays in transaction confirmation. This paper explores the feasibility of using IOTA's DAG-based block-free distributed ledger for implementation of energy trading platforms. Our agent-based simulation research demonstrates that an IOTA-like DAG-based solution could overcome the constraints that blockchains face in the energy market. However, to be usable for peer-to-peer energy trading, even DAG-based platforms need to consider specificities of energy trading markets (such as structured trading periods and assured confirmation of transactions for every completed period).

关键词： Blockchain Peer to peer energy trading platform DAG-based distributed ledger Block-free ledger IOTA Agent-based simulation

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：