Cisco Technology, Inc.

The University of North Carolina at Chapel Hill

Cicso Technology, Inc.

Madhav V Marathe

David Anthony Hughes

Debojyoti Dutta

Raghunath Nambiar

Yathiraj B Udupi

Jiandong Huang

Henry Fuchs

Senhua Huang

Madhu Grandhi

Man Pak Yip

Amit Kumar Agrawal

Ronak K Desai

Philip Roland Graham

Gary S Goldman

J William Mauchly

Gene K Chui

Eugene T Wang

Jan-Michael Frahm

Gurmohan Singh Samrao

Hisham Sami Abdelhamid

Frank Chui

Gary Kipnis

Mark M Perkins

Sejun Song

Mingsong Dou

Song Sejun

Lionel A King

Dan Klausmeier

Daryn Lau

Chang-Yu Wang

Systems and methods are described for allocating resources in a cloud computing environment. The method includes receiving a computing request, the request for use of at least one virtual machine and a portion of memory. In response to the request, a plurality of hosts is identified and a cost function is formulated using at least a portion of those hosts. Based on the cost function, at least one host that is capable of hosting the virtual machine and memory is selected.

Optimizing placement of virtual machines

In one embodiment, data indicative of the size of an intermediate data set generated by a first resource device is received at a computing device. The intermediate data set is associated with a virtual machine to process the intermediate data set. A virtual machine configuration is determined based on the size of the intermediate data set. A second resource device is selected to execute the virtual machine based on the virtual machine configuration and on an available bandwidth between the first and second resource devices. The virtual machine is then assigned to the second resource device to process the intermediate data set.

Allocating resources for multi-phase, distributed computing jobs

In one embodiment, a device receives information regarding a data set to be processed by a map-reduce process. The device generates a set of virtual clusters for the map-reduce process based on network bandwidths between nodes of the virtual clusters, each node of the virtual cluster corresponding to a resource device, and associates the data set with a map-reduce process task. The device then schedules the execution of the task by a node of the virtual clusters based on the network bandwidth between the node and a source node on which the data set resides.

Task scheduling using virtual clusters

The present disclosure relates to assignment or generation of reducer virtual machines after the 'map' phase is substantially complete in MapReduce. Instead of a priori placement, distribution of keys after the 'map' phase over the mapper virtual machines can be used to efficiently reducer tasks in virtualized cloud infrastructure like OpenStack. By solving a constraint optimization problem, reducer VMs can be optimally assigned to process keys subject to certain constraints. In particular, the present disclosure describes a special variable matrix. Furthermore, the present disclosure describes several possible cost matrices for representing the costs determined based on the key distribution over the mapper VMs (and other suitable factors).

Optimized assignments and/or generation virtual machine for reducer tasks

A video conference server receives a plurality of video frames including a current frame and at least one previous frame. Each of the video frames includes a corresponding image and a corresponding depth map. The server produces a directional distance function (DDF) field that represents an area surrounding a target surface of the object captured in the current frame. A forward transformation is generated that modifies the reference surface to align with the target surface. Using at least a portion of the forward transformation, a backward transformation is calculated that modifies the target surface of the current frame to align with the reference surface. The backward transformation is then applied to the DDF to generate a transformed DDF. The server updates the reference model with the transformed DDF and transmits data for the updated reference model to enable a representation of the object to be produced at a remote location.

Scanning and tracking dynamic objects with depth cameras

A method is provided in one example and includes capturing panoramic image data through a first camera in a camera cluster, and capturing close-up image data through a second camera included as part of a spaced array of cameras. The presence of a user in a field of view of the second camera can be detected. The close-up image data and the panoramic image data can be combined to form a combined image. In more specific embodiments, the detecting includes evaluating a distance between the user and the second camera. The combined image can reflect a removal of a portion of panoramic image data associated with the user in a video conferencing environment.

System and method for providing depth adaptive video conferencing

During a video conference between a local endpoint and a remote endpoint, a display at the local endpoint may be configured to provide perspective-dependent views to local video conference participants. A local endpoint may receive a plurality of video streams and identify a first video stream that provides a first view of a remote participant and a second video stream that provides a second view of that participant taken concurrently from a different angle. A display at the local endpoint may display the first video stream at a first viewing angle that only allows the first view of the remote participant to be seen from a first region. The display may also concurrently display the second video stream at a second viewing angle that only allows the second view of the remote participant to be seen from a second region different than the first region.

Providing perspective-dependent views to video conference participants

A method and apparatus are described for controlling connection admission for a connection request in a network. A first estimator estimates an equivalent cell rate (ECR) based on description of the connection request. The description includes a booking factor. A second estimator estimates a measured utilization factor for admitted connections in the network using measurements of data streams arriving at queues. A controller is coupled to the first and second estimators to generate an admission decision for the connection request based on the estimated ECR and the estimated measured utilization factor.

Hybrid connection admission control using combined model-based and measurement-based estimators

An Outage Measurement System (OMS) monitors and measures outage data at a network processing device. The outage data can be stored in the device and transferred to a Network Management System (NMS) or other correlation tool for deriving outage information. The OMS automates the outage measurement process and is more accurate, efficient and cost effective than previous outage measurement systems.

Method and apparatus for outage measurement

An Outage Measurement System (OMS) monitors and measures outage data at a network processing device. The outage data can be stored in the device and transferred to a Network Management System (NMS) or other correlation tool for deriving outage information. The OMS automates the outage measurement process and is more accurate, efficient and cost effective than pervious outage measurement systems.

A system and method for improving reliability of a packet network are described. Data is transmitted on a first virtual circuit in the network. A message signaling a failure in receipt of the data is received on a second virtual circuit in the network. Finally, transmission of data is switched to the second virtual circuit within a predetermined period of time.

System and method for improving reliability of a packet network

A method to utilize unscheduled bandwidth in a calendar-based VC scheduling scheme by caching a plurality of virtual connections for processing. A plurality of virtual connection addresses are stored in a cache memory. A virtual connection corresponding to one of these addresses is processed if one of the time periods for transmitting on the trunk is liable to be wasted because no cell is available through the normal calendaring algorithm. A VC cache is added to the VC scheduler in 'parallel' with the calendar-based scheduler. When the calendar-based scheduler has a time period in which no VC is scheduled for transmission on the trunk, a VC address is obtained from the cache and that VC is processed. What makes this scheme work is the observation that the VCs that have been active will have more cells to transmit.

Virtual connection service cache for filling available bandwidth

A method and apparatus are described for determining an equivalent capacity of a transport device in a network switch for a traffic data stream. A data collector collects at least one traffic parameter for the traffic data stream arriving at a queue of the transport device for a specified quality of service (QoS) class. A bandwidth estimator is coupled to the data collector to estimate an effective bandwidth using the at least one traffic parameter. The estimated effective bandwidth corresponds to the equivalent capacity of the transport device.

Estimating equivalent bandwidth capacity for a network transport device using on-line measurements

A system and method for automated switching of data traffic in a network are described. Data is transmitted along a first virtual circuit among multiple virtual circuits in a network. Next, a failure is detected on the first virtual circuit. As a result, transmission of data is switched from the first virtual circuit to a second virtual circuit among the multiple virtual circuits in the network.

Growing community of inventors

Cupertino, CA, United States of America

Madhav V Marathe