MEPaxos:低延迟的共识算法

共识问题作为分布式计算中最重要的基本问题之一,被广泛应用在状态机复制、原子广播、领导者选举等领域。解决共识问题的算法通常存在单领导者性能瓶颈、响应延迟受命令冲突的影响等问题。针对这些问题,在非拜占庭故障下的异步分布式系统中,提出了一种低延迟的共识算法MEPaxos(modified Egalitarian Paxos)。首先,提出了系统平均延迟的计算方法;然后,引入超时机制对二阶段提交算法进行改进;接着,根据系统平均延迟计算结果,利用改进的二阶段提交算法自动选择平均延迟较小的算法模式执行;最后,在亚马逊弹性计算云(elastic compute cloud,EC2)平台上将此算法与当前共识算法进行实验对比分析,结果表明,MEPaxos算法下,系统延迟性能得到了提升。     

Weighted Nuclear Norm Minimization and Its Applications to Low Level Vision

As a convex relaxation of the rank minimization model, the nuclear norm minimization (NNM) problem has been attracting significant research interest in recent years. The standard NNM regularizes each singular value equally, composing an easily calculated convex norm. However, this restricts its capability and flexibility in dealing with many practical problems, where the singular values have clear physical meanings and should be treated differently. In this paper we study the weighted nuclear norm minimization (WNNM) problem, which adaptively assigns weights on different singular values. As the key step of solving general WNNM models, the theoretical properties of the weighted nuclear norm proximal (WNNP) operator are investigated. Albeit nonconvex, we prove that WNNP is equivalent to a standard quadratic programming problem with linear constrains, which facilitates solving the original problem with off-the-shelf convex optimization solvers. In particular, when the weights are sorted in a non-descending order, its optimal solution can be easily obtained in closed-form. With WNNP, the solving strategies for multiple extensions of WNNM, including robust PCA and matrix completion, can be readily constructed under the alternating direction method of multipliers paradigm. Furthermore, inspired by the reweighted sparse coding scheme, we present an automatic weight setting method, which greatly facilitates the practical implementation of WNNM. The proposed WNNM methods achieve state-of-the-art performance in typical low level vision tasks, including image denoising, background subtraction and image inpainting.     

云边智能: 电力系统运行控制的边缘计算方法及其应用现状与展望

本文分析了当前我国电力系统的运行与控制面临的挑战, 对边缘计算的发展背景和关键技术进行了介绍, 阐述了云边协同和边边协同的功能与特征, 并对边缘协同技术下的边缘智能技术进行了探讨. 结合电力系统的层级式构架, 讨论了在电网部署边缘计算层的方法, 提出利用云边协同、边边协同、边缘智能等技术解决电力系统面临的实时性高、数据周期短、任务复杂等难题, 在减轻边缘节点与云中心通信压力的同时, 提高业务服务质量, 保障边缘节点的数据隐私. 通过对边缘计算在“源 − 网 − 荷”各环节的应用前景进行分析与讨论, 阐述了边缘计算在电网中的可行性与实用性. 最后, 对边缘计算的应用范式与方案进行了总结, 并对其在未来电力系统中的发展方向进行了展望.     

GOLD: A Framework for Developing Intelligent-Vehicle Vision Applications

To develop real-time vision applications for use in highly dynamic environments, such as automotive traffic, researchers must gather large amounts of data from different sensors and systems at different rates. Software capable of real-time data acquisition, synchronization, logging, and - ultimately - data processing and visualization is fundamentally important to improving researcher efficiency. The general obstacle and lane detection framework supports different devices and makes it easy to add new system functionalities. GOLD can easily become the engine for many automotive applications, and it could work in other application domains as well.     

光互连技术及其在计算机视觉中的应用

可重构的光互连技术具有针对不同的应用提供相应的网络结构的能力。在大规模并行系统中具有很大的优势,可以作为电互连的替代技术应用于计算机视觉这一类计算机和通信速度很高的系统中。     

机器人4.0: 边缘计算支撑下的持续学习和时空智能

随着全球机器人市场规模的不断扩大,机器人技术正在从机器人3.0时代迈向机器人4.0时代.这除了要求机器人具备感知能力,实现智能协作外,还要求其具有理解和决策的能力,最终实现自主的服务.尽管人工智能研究已经借深度学习技术取得突破性进展,但要实现机器人如人类一样做出决策,依然是非常具有挑战的目标,还有许多难点亟待解决.对有望解决这些问题的3项关键技术——持续学习、时空智能和边缘计算进行了初步探讨：通过持续学习,机器人能够将旧任务的知识快速迁移到新的任务中,并解决灾难性遗忘问题;通过时空智能让机器人对周围的环境建立起从高层到底层的表示,并像人一样从不同的粒度上分享和解决问题;最后充分利用边缘计算提供更高性价比的服务,把各种智能和知识很好地组合起来,实现规模化部署.     

边缘计算：平台、应用与挑战

随着万物联网的趋势不断加深,智能手机、智能眼镜等端设备的数量不断增加,使数据的增长速度远远超过了网络带宽的增速;同时,增强现实、无人驾驶等众多新应用的出现对延迟提出了更高的要求.边缘计算将网络边缘上的计算、网络与存储资源组成统一的平台为用户提供服务,使数据在源头附近就能得到及时有效的处理.这种模式不同于云计算要将所有数据传输到数据中心,绕过了网络带宽与延迟的瓶颈,引起了广泛的关注.首先介绍边缘计算的概念,并给出边缘计算的定义;随后,比较了当前比较有代表性的3个边缘计算平台,并通过一些应用实例来分析边缘计算在移动应用和物联网应用上的优势;最后阐述了当前边缘计算面临的挑战.     

人工智能与计算机视觉产业发展

随着世界科技化进程的不断加快,人工智能领域逐渐被推向世界舞台,作为人工智能领域中的重要一部分,计算机视觉技术已取得了较大的进步。计算机视觉发展的目标是为了能够让机器和人类一样拥有视觉,进行事物识别,计算机视觉已从之前对计算机图片的识别慢慢转变为对实际生活中的识别,由此迈出了技术发展的重要一步。但计算机视觉在发展过程中也不是一帆风顺的,在发展中也存在一些问题,笔者就人工智能与计算机视觉领域的发展这一话题进行深入探讨。     

面向边缘计算应用的宽度孪生网络

边缘计算是将计算、存储、通信等任务分配到网络边缘的计算模式. 它强调在用户终端附近执行数据处理过程, 以达到降低延迟, 减少能耗, 保护用户隐私等目的. 然而网络边缘的计算、存储、能源资源有限, 这给边缘计算应用的推广带来了新的挑战. 随着边缘智能的兴起, 人们更希望将边缘计算应用与人工智能技术结合起来, 为我们的生活带来更多的便利. 许多人工智能方法, 如传统的深度学习方法, 需要消耗大量的计算、存储资源, 并且伴随着巨大的时间开销. 这不利于强调低延迟的边缘计算应用的推广. 为了解决这个问题, 我们提出将宽度学习系统(Broad learning system, BLS)等浅层网络方法应用到边缘计算应用领域, 并且设计了一种宽度孪生网络算法. 我们将宽度学习系统与孪生网络结合起来用于解决分类问题. 实验结果表明我们的方法能够在取得与传统深度学习方法相似精度的情况下降低时间和资源开销, 从而更好地提高边缘计算应用的性能.     

一种低延迟高吞吐率的浮点整型乘累加单元

针对目前浮点运算单元在处理向量点乘运算时存在数据相关性的问题,提出一种低延迟单周期的累加单元结构.该结构用于7级流水的可配置乘累加单元,可兼容双精度浮点、双单精度浮点以及32位有符号数,且能对后置模块进行操作数隔离与门控时钟的低功耗处理.在Viterx-4平台上实验结果表明,该结构具有高性能、低延迟、单周期完成数据吞吐等特点,与使用Xilinx浮点IP的设计面积相比,时间积减少30％以上.     

边缘计算环境下应用驱动的网络延迟测量与优化技术

互联网、移动计算、物联网技术的进步推动了人-机-物环境的深度融合,催生了一大批面向边缘用户的网络搜索、在线社会网络、电子商务、视频监控、智能助理等类型的边缘计算应用.边缘计算应用具有规模巨大、服务质量敏感等特性,对延迟性能提出迫切需求,然而,由于用户访问请求跨边缘网络、广域网、数据中心异构环境,“长尾延迟”问题导致边缘用户的体验质量严重下降.首先综述边缘计算应用的系统架构特征,然后分析长尾延迟的产生原因,分类介绍网络延迟测量的主要理论和方法,并归纳对长尾延迟的优化技术,最后提出在线优化运行环境的思想以及面临的挑战.     

一种低延迟高带宽路由器芯片的研究

本文研究了三维环形拓扑结构高性能路由器芯片,该路由芯片能形成多计算机系统的开关网络。     

SR-MAC: A Low Latency MAC Protocol for Multi-Packet Transmissions in Wireless Sensor Networks

Event detection is one of the major applications of wireless sensor networks (WSNs). Most of existing medium access control (MAC) protocols are mainly optimized for the situation under which an event only generates one packet on a single sensor node. When an event generates multiple packets on a single node, the performance of these MAC protocols degrades rapidly. In this paper, we present a new synchronous duty-cycle MAC protocol called SR-MAC for the event detection applications in which multiple packets are generated on a single node. SR-MAC introduces a new scheduling mechanism that reserves few time slots during the SLEEP period for the nodes to transmit multiple packets. By this approach, SR-MAC can schedule multiple packets generated by an event on a single node to be forwarded over multiple hops in one operational cycle without collision. We use event delivery latency (EDL) and event delivery ratio (EDR) to measure the event detection capability of the SR-MAC protocol. Through detailed ns-2 simulation, the results show that SR-MAC can achieve lower EDL, higher EDR and higher network throughput with guaranteed energy efficiency compared with R-MAC, DW-MAC and PR-MAC.     

Real-Time Vision and Speech Driven Avatars for Multimedia Applications

Recent progress in advanced video communication services and multimedia applications is grounded on novel human machine interfaces, improved usability, and user friendliness driven by user centric research and development. In this paper, we describe a complete system concept and algorithmic details of an example application within this area. The key features of the system are vision and speech based interfaces, which are used to animate an avatar for an audio-visual representation of a communication partner. The system is applied in two application scenarios, namely video chat and customer care services. Both applications are mass-market oriented and therefore careful design and development of robust and supporting user interfaces are required. The presented approach is integrated into a complete real-time prototype system, which is permanently demonstrated in the showcase at the head quarter of Deutsche Telekom, Bonn, Germany.