Search | Engineering

订阅投稿

首页工程期刊工程焦点工程成就工程前沿关于我们 English

资源类型

期刊论文 2

会议视频 1

年份

2022 1

2021 1

2020 1

关键词

工程管理 1

运行环境；应用部署；高性能计算（HPC）；容器；点对点（P2P）；网络拓扑 1

检索范围：

排序：展示方式：

Last Planner System and Scrum: Comparative analysis and suggestions for adjustments

Roshan POUDEL, Borja GARCIA de SOTO, Eder MARTINEZ

《工程管理前沿（英文）》 2020年第7卷第3期页码 359-372 doi: 10.1007/s42524-020-0117-1

摘要： This study provides a critical review of the concepts of Agile, Lean, Scrum, and Last Planner System (LPS). A comparative analysis is conducted between LPS and Scrum to expand LPS by considering Scrum’s best practices. Eight dimensions, namely, 1) origins, 2) main purpose, 3) overall system/framework process, 4) tools or artifacts maintained by the team, 5) team composition and main roles, 6) regular events or team meetings, 7) metrics/dashboards, and 8) approach to learning, are evaluated. After analyzing side by side the eight dimensions, it was found that many aspects from Scrum already exist in LPS in the same or similar form. However, the authors identify four main elements from Scrum that can be leveraged to improve the LPS benchmark, such as considering the Scrum “Increment” concept into LPS, having a clear definition of roles and responsibilities, or adding an equivalent to a Scrum Master to have a designated “rule keeper” in LPS. These opportunities to be considered in new LPS benchmarks need to be tested and validated with real applications. To the best of the authors’ knowledge, this work is the first to comprehensively compare Scrum (Agile) and LPS (Lean) and could be seen as a contribution toward the evolution of the Last Planner System for the academic and industrial environments.

关键词： Lean Construction Last Planner System Agile Scrum comparative analysis AEC projects project teams

HTML PDF 收藏

TEES：一种面向高性能计算快速、灵活应用程序部署的拓扑感知的运行环境服务 Research Article

邵明天,卢凯,迟万庆,王睿伯,戴屹钦,张文喆

《信息与电子工程前沿（英文）》 2022年第23卷第11期页码 1631-1645 doi: 10.1631/FITEE.2100284

摘要：

高性能计算（HPC）即将达到新的高度：百亿亿次。应用程序部署正成为一个日益突出的问题。容器技术解决了应用程序及其运行环境的封装和迁移问题。但是，容器镜像太过笨重，在大量计算结点上的部署过程非常耗时。虽然点对点（P2P）方式带来更高的传输效率，但也引入更大的网络负载。所有这些问题都会导致应用程序的高启动延迟。为解决这些问题，提出拓扑感知的运行环境服务（TEES），用于在高性能计算系统上快速、灵活地部署应用程序。TEES为用户创建了一个更轻量级的运行环境，并使用一种更有效的拓扑感知P2P方法减少部署时间。结合分步传输和提前启动机制，TEES降低了应用程序的启动延迟。在天河高性能计算系统中，TEES在3秒内实现了在17560个计算结点上的一个典型应用程序的部署和启动。与基于容器的应用程序部署方式相比，速度提高了12倍，网络负载减少了85%。

关键词：运行环境；应用部署；高性能计算（HPC）；容器；点对点（P2P）；网络拓扑

HTML PDF 收藏