公开(公告)号：US08738724B2

公开(公告)日：2014-05-27

申请号：US12786447

申请日：2010-05-25

Applicant: Philip A. Bernstein ,  Dahlia Malkhi ,  Colin Wilson Reid ,  Mahesh Balakrishnan

Inventor： Philip A. Bernstein ,  Dahlia Malkhi ,  Colin Wilson Reid ,  Mahesh Balakrishnan

IPC: G06F15/167

CPC classification number: G06F11/1471 ,  G06F11/2094 ,  G06F2201/82

Abstract: Computers are provided with a totally ordered, durable shared log. Shared storage is used and can be directly accessed by the computers over a network. Append-log operations are made atomic in the face of failures by committing provisional append ordering information onto a log. The log may comprise multiple flash packages or non-volatile memory devices, referred to as segments, although any shared storage device(s) may be used. Each log record is a multi-page stripe, where each page of a stripe is written to a different segment. Fault-tolerant protocol variants append stripes to the log, such that stripes are totally ordered in the log and each stripe is written atomically.

Abstract translation: 计算机提供了一个完全有序，耐用的共享日志。 共享存储被使用，可以由网络上的计算机直接访问。 通过将临时附加订单信息提交到日志，Append-log操作在面临故障时被做成原子。 尽管可以使用任何共享的存储设备，该日志可以包括被称为段的多个闪存包或非易失性存储设备。 每个日志记录是一个多页条带，其中每个条带的页面被写入不同的段。 容错协议变体将条纹附加到日志，使得条纹在日志中完全排序，每个条带是原子写入的。

公开(公告)号：US20110208958A1

公开(公告)日：2011-08-25

申请号：US12814493

申请日：2010-06-14

Applicant: Patrick Stuedi ,  Mahesh Balakrishnan ,  Iqbal Mohomed ,  Venugopalan Ramasubramanian ,  Zhuoqing Morley Mao ,  Edward P. Wobber

Inventor： Patrick Stuedi ,  Mahesh Balakrishnan ,  Iqbal Mohomed ,  Venugopalan Ramasubramanian ,  Zhuoqing Morley Mao ,  Edward P. Wobber

IPC: G06F15/16 ,  H04L9/00 ,  G06F15/173

CPC classification number: H04L9/0825 ,  G06F17/30017 ,  G06F17/30165 ,  H04L51/12

Abstract: A cloud infrastructure that communicates with computing devices is provided. The computing devices install filters on other computing devices that they wish to receive items from including pictures, messages, and documents. The filters include criteria that are evaluated on the computing devices, rather than at a server, to determine if an item may be sent to another computing device. The computing devices may then send items that match the criteria to the cloud infrastructure, and the items may be stored and queued for delivery to other computing devices. The items may be encrypted before being provided to the cloud infrastructure, and decrypted when received by the computing devices.

Abstract translation: 提供与计算设备通信的云基础设施。 计算设备在他们希望从包括图片，消息和文档接收项目的其他计算设备上安装过滤器。 过滤器包括在计算设备上而不是在服务器上评估的标准，以确定物品是否可以发送到另一个计算设备。 然后，计算设备可以将符合标准的项目发送到云基础架构，并且可以将项目存储和排队，以便传送到其他计算设备。 项目可以在被提供给云基础设施之前被加密，并且在被计算设备接收时被解密。

公开(公告)号：US20080304421A1

公开(公告)日：2008-12-11

申请号：US11759473

申请日：2007-06-07

Applicant: Venugopalan Saraswati Ramasubramanian ,  Dahlia Malkhi ,  Mahesh Balakrishnan ,  Fabian Daniel Kuhn ,  Ittai Abraham

Inventor： Venugopalan Saraswati Ramasubramanian ,  Dahlia Malkhi ,  Mahesh Balakrishnan ,  Fabian Daniel Kuhn ,  Ittai Abraham

IPC: H04L12/26

CPC classification number: H04L41/147 ,  H04L43/0852

Abstract: A prediction tree for estimating values of a network performance measure. Leaf nodes of the prediction tree are associated with networked computing devices and interior nodes are not necessarily representative of physical network connections. Values are assigned to edges in the prediction tree and the network performance measure relative to two computing devices represented by two nodes of the tree is estimated by aggregating the values assigned to the edges in the path in the prediction tree joining the two edges. Mechanisms for adding nodes representing computing devices to the prediction tree, for identifying a closest node representing a computing device in the prediction tree, for identifying a cluster of devices represented by nodes of the tree, and for rebalancing the prediction tree are provided.

Abstract translation: 用于估计网络性能测量值的预测树。 预测树的叶节点与网络计算设备相关联，而内部节点不一定代表物理网络连接。 值被分配给预测树中的边缘，并且通过聚合分配给连接两个边缘的预测树中的路径中的边缘的值来估计相对于由树的两个节点表示的两个计算设备的网络性能测量。 提供了将表示计算设备的节点添加到预测树的机制，用于识别表示预算树中的计算设备的最接近的节点，用于识别由树的节点表示的设备的集群以及用于重新平衡预测树。

公开(公告)号：US06836512B2

公开(公告)日：2004-12-28

申请号：US09975626

申请日：2001-10-11

Applicant: Mihaela Van Der Schaar ,  Mahesh Balakrishnan

Inventor： Mihaela Van Der Schaar ,  Mahesh Balakrishnan

IPC: H04N712

CPC classification number: H04N21/2662 ,  H04N19/33 ,  H04N19/34 ,  H04N19/36 ,  H04N19/59 ,  H04N19/61 ,  H04N21/234327 ,  H04N21/234354 ,  H04N21/234363 ,  H04N21/234381 ,  H04N21/2402

Abstract: A method and system for high resolution formatting of video images and dynamically adjusting the transmission resolution of the high-resolution images is presented. The method first downscales the high-resolution images and encodes the downscaled images into base layer frames. Quality enhancement layer data is generated from the downscaled video images and the encoded data contained in corresponding base layer frames. The quality enhancement layer data is encoded into quality enhancement layer frames. The data contained in the base layer frames and corresponding quality layer frames are then upscaled and spatial scalability data is determined from the upscaled data and the original image. The spatial scalability data is then encoded into spatial scalability data. During transmission of the encoded video image, each available encoded frame is transmitted using different amounts or portions of the enhancement layers so as to occupy the available bandwidth.

Abstract translation: 提出了高分辨率格式化视频图像和动态调整高分辨率图像传输分辨率的方法和系统。 该方法首先降低高分辨率图像，并将缩小的图像编码为基本层帧。 从缩小的视频图像和包含在相应的基本层帧中的编码数据生成质量增强层数据。 质量增强层数据被编码成质量增强层帧。 然后将包含在基层帧和对应的质量层帧中的数据放大，并且从放大的数据和原始图像确定空间可伸缩性数据。 然后将空间可伸缩性数据编码为空间可伸缩性数据。 在传输编码视频图像期间，使用不同量或增强层的部分来发送每个可用编码帧，以便占用可用带宽。

公开(公告)号：US07532621B2

公开(公告)日：2009-05-12

申请号：US11513006

申请日：2006-08-30

Applicant: Kenneth Paul Birman ,  Mahesh Balakrishnan

Inventor： Kenneth Paul Birman ,  Mahesh Balakrishnan

IPC: H04L12/28

CPC classification number: H04L12/1868 ,  H04L1/1812 ,  H04L2001/0093

Abstract: A system and method for providing a low-latency reliable multicast protocol designed for time-critical clustered applications. Internet Protocol (IP) multicast is used to transmit data and recovers from packet loss in end-hosts using a repair mechanism involving the exchange of XOR repairs between receivers and across groups. The system and method of the present invention can be embodied in a scalable, reliable and fast multicast primitive that can be layered under high-level abstractions such as publish-subscribe, group communication and replicated service/object infrastructures.

Abstract translation: 一种用于为时间关键的集群应用程序提供设计的低延迟可靠多播协议的系统和方法。 互联网协议（IP）组播用于传输数据，并使用修复机制从终端主机的丢包中恢复，这种修复机制涉及接收器和组之间的XOR修复交换。 本发明的系统和方法可以以可扩展，可靠和快速的多播原语来实现，其可以在诸如发布订阅，组通信和复制服务/对象基础设施的高级抽象下分层。

公开(公告)号：US6101278A

公开(公告)日：2000-08-08

申请号：US16038

申请日：1998-01-30

Applicant: Yingwei Chen ,  Kiran Challapali ,  Mahesh Balakrishnan

Inventor： Yingwei Chen ,  Kiran Challapali ,  Mahesh Balakrishnan

IPC: H04N7/26 ,  H04N7/30 ,  G06K9/36 ,  H04N7/12

CPC classification number: H04N19/40 ,  H04N19/124 ,  H04N19/126 ,  H04N19/136 ,  H04N19/14 ,  H04N19/172 ,  H04N19/176 ,  H04N19/60 ,  H04N19/85 ,  H04N19/146 ,  H04N19/149 ,  H04N19/15

Abstract: A system extracts, from uncoded video data, coding parameters that correspond substantially to coding parameters used in a coding operation that was previously performed on the video data. The system generates a histogram for at least one AC frequency band in the uncoded video data and calculates a correlation function for the histogram. A maximum value of the correlation function is then identified, and a coding parameter for the at least one AC frequency band is determined using the maximum value of the correlation function.

Abstract translation: 系统从未编码的视频数据中提取与以前对视频数据执行的编码操作中使用的编码参数基本相符的编码参数。 系统为未编码视频数据中的至少一个AC频带生成直方图，并计算直方图的相关函数。 然后识别相关函数的最大值，并且使用相关函数的最大值来确定用于至少一个AC频带的编码参数。

公开(公告)号：US6049569A

公开(公告)日：2000-04-11

申请号：US987701

申请日：1997-12-09

Applicant: Hayder Radha ,  Mahesh Balakrishnan

Inventor： Hayder Radha ,  Mahesh Balakrishnan

IPC: H04N7/26 ,  G06T9/00 ,  H04N21/234 ,  H04N7/32

CPC classification number: G06T9/007 ,  H04N21/23406 ,  H04N21/23424

Abstract: A method of encoding a digital video bit stream which includes a plurality of successively-encoded pictures. The method includes the steps of constructing a seamless In Point in accordance with a constraint expressed by the following equation (1):dd.sub.f.sbsb.--.sub.ip .ltoreq.minimum {DD.sub.thr.sbsb.--.sub.ip, (B.sub.d /r.sub.n.sbsb.--.sub.ip)}, (1)where dd.sub.f.sbsb.--.sub.ip represents an amount of time by which a first byte of the digital video bit stream after the seamless In Point must stay in a decoder buffer before it is decoded; B.sub.d is a size of the decoder buffer; r.sub.n.sbsb.--.sub.ip is a bit rate at which the digital video bit stream is normally encoded at the seamless In Point; and, DD.sub.thr.sbsb.--.sub.ip represents a prescribed minimum decoding delay threshold for seamless In Points, where DD.sub.thr.sbsb.--.sub.ip is defined by the following equation (2):DD.sub.thr.sbsb.--.sub.ip =((MSR/r.sub.n.sbsb.--.sub.ip)*SDD)+T.sub.p.sbsb.--.sub.i *(1-(MSR/r.sub.n.sbsb.--.sub.ip), (2)where T.sub.p.sbsb.--.sub.i is a time needed for displaying a picture which starts being displayed at a time of decoding of a last picture prior to the seamless In Point; SDD is a prescribed splice decoding delay; and, MSR is a prescribed maximum splice rate, and then inserting the seamless In Point at a first point in the digital video bit stream at which another digital video bit stream can be spliced into the digital video bit stream. The method also includes the steps of constructing a seamless Out Point in accordance with a constraint expressed by the following equation (3):DD.sub.thr.sbsb.--.sub.op .ltoreq.dd.sub.f.sbsb.--.sub.op .ltoreq.(B.sub.d /r.sub.n.sbsb.--.sub.op), (3)where dd.sub.f.sbsb.--.sub.op represents an amount of time by which a first byte of the digital video bit stream after the seamless Out Point must stay in a decoder buffer before it is decoded; r.sub.n.sbsb.--.sub.op is a bit rate at which the digital video bit stream is normally encoded at the seamless Out Point; and DD.sub.thr.sbsb.--.sub.op represents a prescribed minimum decoding delay threshold for seamless Out Points, where DD.sub.thr.sbsb.--.sub.op is defined by the following equation (4):DD.sub.thr.sbsb.--.sub.op =((MSR/r.sub.n.sbsb.--.sub.op)*SDD)-T.sub.p.sbsb.--.sub.o *((MSR/r.sub.n.sbsb.--.sub.op)-1), (4)wherein T.sub.p.sbsb.--.sub.o is a time needed for displaying a picture which starts being displayed at a time of decoding of a last picture prior to the seamless Out Point; and then inserting the seamless Out Point at a first point in the digital video bit stream at which it can be spliced into another digital video bit stream.

公开(公告)号：US5793425A

公开(公告)日：1998-08-11

申请号：US713311

申请日：1996-09-13

Applicant: Mahesh Balakrishnan

Inventor： Mahesh Balakrishnan

IPC: H04N7/26 ,  H04J3/00 ,  H04J3/04 ,  H04J3/16 ,  H04N7/08 ,  H04N7/081 ,  H04N7/50 ,  H04N21/2365 ,  H04N21/434

CPC classification number: H04N21/2365 ,  H04J3/1688 ,  H04N19/115 ,  H04N19/14 ,  H04N19/149 ,  H04N19/154 ,  H04N19/159 ,  H04N19/172 ,  H04N19/61 ,  H04N21/23406 ,  H04N21/23655 ,  H04N21/2401 ,  H04N19/146

Abstract: A method and apparatus for dynamically allocating the available bandwidth of a common transmission channel of a multiplexed system among multiple encoders in such a manner as to maximize and equalize the quality of the encoded data output by all of the encoders, while also preventing underflow or overflow of encoder or decoder buffers at each end of the common transmission channel, and moreover, while also ensuring compliance with (i.e., without violating) the data encoding and transmission protocol utilized by the system. Further, the bandwidth of the common transmission channel is preferably allocated using an algorithm that does not impose any constraints on the size of the encoder or decoder buffers, other than any constraints specified by the data transmission protocol employed in transmitting the encoded data over the common transmission channel. In a presently preferred embodiment, in which video signals from multiple sources are encoded, both the output channel rate ("bit rate") of each of the encoders and the target number of bits for each picture that is encoded by each encoder are controlled by a controller in accordance with a control algorithm which ensures that the quality of the encoded pictures output by all of the encoders is equalized and maximized, that no underflow or overflow of the encoder or decoder buffers occurs, and that the data encoding and transmission protocol utilized by the system is not violated. Further, the control algorithm employed by the controller preferably does not impose any constraints on the sizes or relative sizes of the encoder or decoder buffers. Moreover, the control algorithm employed by the controller preferably maintains all of the encoder buffers as empty as possible in order to provide increased flexibility to the rate allocation procedure.

Abstract translation: 一种用于在多个编码器之间动态地分配复用系统的公共传输信道的可用带宽的方法和装置，以便最大化和均衡所有编码器输出的编码数据的质量，同时还防止下溢或溢出 的编码器或解码器缓冲器在公共传输信道的每一端，而且还确保符合（即，不违反）系统使用的数据编码和传输协议。 此外，公共传输信道的带宽优选地使用不对编码器或解码器缓冲器的大小施加任何约束的算法来分配，除了在通过公共传输方式发送编码数据时使用的数据传输协议所指定的任何约束 传输通道。 在其中编码来自多个源的视频信号的当前优选实施例中，每个编码器的输出信道速率（“比特率”）和由每个编码器编码的每个图像的目标比特数都由 根据控制算法的控制器，其确保由所有编码器输出的编码图像的质量均衡和最大化，不会发生编码器或解码器缓冲器的下溢或溢出，并且使用数据编码和传输协议 由系统没有违反。 此外，控制器采用的控制算法优选地不对编码器或解码器缓冲器的尺寸或相对尺寸施加任何约束。 此外，控制器采用的控制算法优选地将所有的编码器缓冲器保持为空，以便为速率分配过程提供增加的灵活性。

公开(公告)号：US20120203888A1

公开(公告)日：2012-08-09

申请号：US13022635

申请日：2011-02-08

Applicant: Mahesh Balakrishnan ,  Marcos K. Aguilera ,  Birjodh Tiwana ,  Hitesh Ballani

Inventor： Mahesh Balakrishnan ,  Marcos K. Aguilera ,  Birjodh Tiwana ,  Hitesh Ballani

IPC: G06F15/173

CPC classification number: G06F9/505 ,  G06F11/2094

Abstract: A cloud statistics server generates statistics for a cloud service based on an identified data item and an identified operation. The cloud service may include various computing nodes and storage nodes. The cloud statistics may include expected completion times for the identified operation and the identified data item with respect to each of the computing nodes. A computing node may be selected to execute the identified operation based on the expected completion times. The generated statistics may be generated by the cloud statistics server using a network topology associated with the data item that is based on the latencies or expected transfer times between the various storage nodes and computing nodes, and a replication strategy used by the cloud service. The topology may be implemented as a directed graph with edge weights corresponding to expected transfer times between each node.

Abstract translation: 云统计服务器根据识别的数据项和识别的操作生成云服务的统计信息。 云服务可以包括各种计算节点和存储节点。 云统计可以包括针对每个计算节点的所识别的操作和所识别的数据项的预期完成时间。 可以选择计算节点以基于预期的完成时间来执行所识别的操作。 所生成的统计信息可以由云统计服务器使用与数据项关联的网络拓扑生成，该网络拓扑基于各种存储节点和计算节点之间的延迟或预期传送时间，以及由云服务使用的复制策略。 拓扑可以被实现为具有对应于每个节点之间的预期传送时间的边权重的有向图。

公开(公告)号：US07463683B2

公开(公告)日：2008-12-09

申请号：US09998361

申请日：2001-11-29

Applicant: Mihaela Van Der Schaar ,  Mahesh Balakrishnan

Inventor： Mihaela Van Der Schaar ,  Mahesh Balakrishnan

IPC: H04N7/18

CPC classification number: H04N19/36 ,  H04N19/31 ,  H04N19/33 ,  H04N19/34 ,  H04N19/44 ,  H04N19/59 ,  H04N19/61 ,  H04N21/234327 ,  H04N21/234363 ,  H04N21/4621 ,  H04N21/64792

Abstract: A method and system for producing decoding the transmission of high-resolution images transmitted as a low resolution spatially scalable FGS encoded base layer and at least one enhancement layer is presented. The low resolution received base layer is representative of a downscaled image of the original image. In this manner, a minimum resolution base layer is transmitted and higher resolutions may be obtained and utilized depending on the available bandwidth and the receiving system resolution capability. In one aspect of the invention, the base layer is decoded and a quality enhancement is next applied to the base layer. The combined base layer and quality layer video frames are then upscaled and the upscaled image is combined with a decoded spatial enhancement layer information. The spatial enhancement layer information fills in resolution lacking in the upscaled base layer/quality layer image. Thus, a high resolution image is formed. In another aspect of the invention, a temporal layer, containing information regarding image motion, is further applied to the upscaled base layer image to produce a spatially enhanced/temporally enhanced high resolution image.

Abstract translation: 提出了一种用于产生对作为低分辨率空间可缩放的FGS编码的基础层和至少一个增强层发送的高分辨率图像的传输进行解码的方法和系统。 低分辨率接收基层代表原始图像的缩小图像。 以这种方式，发送最小分辨率基础层，并且可以根据可用带宽和接收系统分辨能力获得和使用更高分辨率。 在本发明的一个方面中，对基本层进行解码，接下来将基础层应用质量增强。 然后将组合的基层和质量层视频帧放大，并且将放大的图像与解码的空间增强层信息组合。 空间增强层信息填补了放大的基本层/质量层图像中缺少的分辨率。 因此，形成高分辨率图像。 在本发明的另一方面，包含关于图像运动的信息的时间层进一步应用于放大的基本层图像以产生空间增强/时间增强的高分辨率图像。