International Business Machines Corporation

Lenovo (singapore) Pte. Ltd.

Aviz Networks, Inc.

Globalfoundries Inc.

Kyndryl, Inc.

Globalfoundries U.S. 2 LLC Company

Vishal Shukla

Ashish Kapur

Venkata Siva N Amulothu

Venkata S Amulothu

Saritha Yeddula

Kavita Gadde

Nitin J Huralikuppi

Rupal A Kaneriya

Khurram Khani

Thu Quoc Tran

Chidambaram Bhagavathiperumal

Nitin Kumar J Huralikuppi

Naveen Kumar Vemulapalli

Gautam Agrawal

The present disclosure provides a system and a method of creating a data lake configured to ingest data from heterogeneous network equipment and provide access to a plurality of applications using any kind of public cloud. In one general aspect, a method to create a data lake may include installing a plurality of agents by an end-user may include a multivendor environment. The method may also include adding a plurality of data sources to be monitored to a collector module, where the plurality of data sources further may include of one or more devices and endpoints. The method may furthermore include establishing a secure connection between the collector module and the plurality of data sources. The method may in addition include collecting, by the collector module, input data from one or more organic agents and one or more vendor specific agents to create collected data.

System and method of creating multi-vendor network data lake

In some implementations, a method of flow monitoring and identification may include identifying one or more ingress interfaces, where customer flow and traffic enters a switch. In addition, the method may include identifying one or more egress interfaces where the customer flow and traffic exits the switch. The method may include determining accurate information of the customer flow passing through the one or more ingress interfaces and the one or more egress interfaces, which includes metadata from a Layer 3 IP Header.

Systems and methods for accurate monitoring and reporting of flows impacted due to link failures in data centers

A computer-implemented method comprising: receiving, by a first controller device in a first OpenFlow domain, a packet from an originating endpoint in the first OpenFlow domain destined for a destination endpoint in a second OpenFlow domain that is separate from the first OpenFlow domain; outputting, by the first controller device, a broadcast message identifying the destination endpoint to a plurality of respective controller devices associated with separate OpenFlow domains; receiving, by the first controller device, a response to the broadcast message from the destination endpoint via a second controller device associated with the second OpenFlow domain; updating, by the first controller device, a local flow table identifying a flow for transmitting the packet to the destination endpoint based on information included in the response; and transmitting, by the first controller device, the packet towards the destination endpoint based on updating the local flow table.

Interconnecting multiple separate openflow domains

A method and associated systems for on-demand cellular-network bandwidth allocation in response to continuously changing populations of sensor devices. A sensor device adds itself to or deletes itself from a cluster of sensors. A physical controller that manages the cluster detects this change, identifies a resulting change in the cluster's bandwidth requirements, and stores this information in a local database. When such a sensor-population change satisfies a triggering condition, the controller requests that a network-management component of the cellular network adjust the controller's bandwidth allocation. The network-management component aggregates this and similar requests from all connected controllers in a global database, and when controller bandwidth requirements satisfy a second triggering condition, the component, using a standard API, asks the network-management component to reprovision the component's virtual bandwidth allocation. The component then distributes the adjusted bandwidth among its sensor-cluster controllers, which in turn allocate their adjusted bandwidths among their sensor devices.

Dynamic resource allocation for sensor devices on a cellular network

A method and associated systems for on-demand bandwidth allocation on a mixed-infrastructure network in response to continuously changing populations of sensor devices. Sensors autonomously add themselves to or delete themselves from sensor clusters available to the network. A physical cluster controller detects each change, identifies resulting changes in a cluster's bandwidth requirements, and stores this information in a local database. If a sensor-population change satisfies a triggering condition, the controller requests that a network-management component of the network adjust the controller's bandwidth allocation. The network-management component aggregates this and similar requests from all connected controllers in a global database, and when controller bandwidth requirements satisfy a second triggering condition, the component, using a standard API, asks the network-management component to reprovision the component's virtual bandwidth allocation. The component then distributes the adjusted bandwidth among its sensor-cluster controllers, which in turn allocate their adjusted bandwidths among their sensor devices.

Dynamic resource allocation for sensor devices on a mixed-infrastructure network

A first information comprising an identification of an encryption algorithm supported by a first component from the first component of a software defined network (SDN) is received at a controller of the SDN. A set of policies and a set of encryption algorithms are sent to the first component. A policy determines a cryptographic operation applicable to a path in the SDN between the first component and a second component of the SDN. The first component comprises an originating point of the path and the second component comprises a destination point of the path.

End-to-end encryption in a software defined network

A method and associated systems for on-demand Internet of Things bandwidth allocation in response to changing sensor populations. An IOT sensor device adds itself to or deletes itself from a cluster of IOT sensors. A physical IOT controller that manages the cluster detects this change, identifies a resulting change in the cluster's bandwidth requirements, and stores this information in a local database. When such a sensor-population change satisfies a triggering condition, the controller requests that a cloud-based application server adjust the controller's bandwidth allocation. The server aggregates this and similar requests from all connected controllers in a global database, and when controller bandwidth requirements satisfy a second triggering condition, the server, using a standard API, asks the cloud-management platform to reprovision the server's virtual bandwidth allocation. The server then distributes the adjusted bandwidth among its IOT controllers, which in turn allocate their adjusted bandwidths among their sensor devices.

Dynamic virtualized resource allocation

A method, computer program product and computer system is provided. A processor receives at least one tunnel endpoint load information of a plurality of virtual network tunnel endpoints associated with a first virtual network. A processor receives a request directed to the first virtual network from a requesting virtual machine of a second virtual network. A processor generates a destination network address of a virtual network tunnel endpoint associated with the first virtual network based, at least in part, on the at least one load information of the plurality of virtual network tunnel endpoints. A processor sends the destination network address to the requesting virtual machine.

Load balancing with software defined network controllers

Embodiments of the present invention provide methods, computer program products, and systems for generating a shortest data path for data packets. Embodiments of the present invention can be used to exclude switches at or near their maximum capacity of flow entries from the shortest data path calculation. Embodiments of the present invention can be used to reduce the 'lag time' users can experience while waiting for data packets to be forwarded through different switches.

Adaptive software defined networking controller

Cloud-based dynamic IOT resource allocation in response to a changing sensor status

Auditing networking devices is provided. A first traceroute is initiated from a first computing device to a second computing device. The first traceroute identifies at least one networking device along a data path from the first computing device to the second computing device. The first computing device is caused to send a first resource discovery packet to the second computing device. The first resource discovery packet includes a value matching a reserved multicast MAC address. Information describing one or more networking devices is compiled. The information is based, at least in part, on replies generated by one or more networking devices that received a resource discovery packet. One or more networking devices described by the information from the data path is excluded responsive to receiving a request.

Auditing networking devices

A method and associated systems for using a software-defined network (SDN) controller to automatically test cloud performance. A bandwidth measuring and optimizing system associated with the SDN controller detects a triggering condition and, in response, directs a network-management tool to measure a bandwidth of a segment of a physical infrastructure of a network and directs the SDN controller to provision a virtual machine that then measures a bandwidth of a corresponding segment of virtual infrastructure that is overlaid upon the physical segment. In some embodiments, these two tests are synchronized so as to concurrently measure physical and virtual bandwidths while the same test data passes through the virtual infrastructure segment. The measured bandwidth of the virtual segment is then compared to the measured bandwidth of the physical segment in order to determine an efficiency of the virtual network.

Growing community of inventors

San Jose, CA, United States of America

Vishal Shukla