公开(公告)号：US11516133B2

公开(公告)日：2022-11-29

申请号：US16920993

申请日：2020-07-06

Applicant: Nokia Solutions and Networks OY

Inventor： Hyunseok Chang ,  Fang Hao ,  Muralidharan Kodialam ,  T. V. Lakshman ,  Sarit Mukherjee ,  Limin Wang

IPC: H04L12/747 ,  H04L12/721 ,  G06F12/0802 ,  H04L12/743 ,  H04L12/931 ,  H04L45/74 ,  H04L45/7453 ,  H04L49/00 ,  H04L45/00

Abstract: Packet-processing circuitry including one or more flow caches whose contents are managed using a cache-entry replacement policy that is implemented based on one or more updatable counters maintained for each of the cache entries. In an example embodiment, the implemented policy enables the flow cache to effectively catch and keep elephant flows by giving to the caught elephant flows appropriate preference in terms of the cache dwell time, which can beneficially improve the overall cache-hit ratio and/or packet-processing throughput. Some embodiments can be used to implement an Open Virtual Switch (OVS). Some embodiments are advantageously capable of implementing the cache-entry replacement policy with very limited additional memory allocation.

公开(公告)号：US20240430202A1

公开(公告)日：2024-12-26

申请号：US18336675

申请日：2023-06-16

Applicant: Nokia Solutions and Networks Oy

Inventor： Muralidharan Kodialam ,  TV Lakshman

IPC: H04L47/122 ,  G06N3/084 ,  H04L43/0882

Abstract: In some embodiments, there may be provided a method that includes receiving, as a first input to a machine learning model, a measured link load; receiving, as a second input to the machine learning model, information indicating a network topology; receiving, as a third input to the machine learning model, at least one deflection parameter; learning, by the machine learning model, a first output to provide at least one updated deflection parameter, wherein the at least one updated deflection parameter indicates the fractional amount of traffic that is to be carried between the source node and the destination node and deflected through the intermediate node; and learning, by the machine learning model, a second output to provide dual variables that serve as a surrogate for a traffic matrix that could have generated the measured link load that is measured for the link of the network.

公开(公告)号：US20220006737A1

公开(公告)日：2022-01-06

申请号：US16920993

申请日：2020-07-06

Applicant: Nokia Solutions and Networks OY

Inventor： Hyunseok Chang ,  Fang Hao ,  Muralidharan Kodialam ,  T.V. Lakshman ,  Sarit Mukherjee ,  Limin Wang

IPC: H04L12/747 ,  G06F12/0802 ,  H04L12/721 ,  H04L12/743 ,  H04L12/931

Abstract: Packet-processing circuitry including one or more flow caches whose contents are managed using a cache-entry replacement policy that is implemented based on one or more updatable counters maintained for each of the cache entries. In an example embodiment, the implemented policy enables the flow cache to effectively catch and keep elephant flows by giving to the caught elephant flows appropriate preference in terms of the cache dwell time, which can beneficially improve the overall cache-hit ratio and/or packet-processing throughput. Some embodiments can be used to implement an Open Virtual Switch (OVS). Some embodiments are advantageously capable of implementing the cache-entry replacement policy with very limited additional memory allocation.

公开(公告)号：US20210058424A1

公开(公告)日：2021-02-25

申请号：US16999548

申请日：2020-08-21

Applicant: Nokia Solutions and Networks Oy

Inventor： Hyunseok Chang ,  Muralidharan Kodialam ,  T.V. Lakshman ,  Sarit Mukherjee

IPC: H04L29/06 ,  G06F11/34 ,  G06N3/04 ,  G06K9/62

Abstract: System, method, and software for detecting anomalies in data generated by microservices. In one embodiment, an anomaly detector collects performance metrics for a microservice deployed in a data center for an application. The anomaly detector transforms the performance metrics into a time-series structured dataset for the microservice, and feeds the structured dataset to a machine learning system to determine whether an anomaly exists in the structured dataset based on an anomaly detection model. The anomaly detector performs an anomaly classification with the machine learning system based on an anomaly classification model and the structured dataset when an anomaly is detected in the structured dataset, and performs an action based on the anomaly classification.

公开(公告)号：US20250088429A1

公开(公告)日：2025-03-13

申请号：US18466195

申请日：2023-09-13

Applicant: Nokia Solutions and Networks Oy

Inventor： Muralidharan Kodialam ,  TV Lakshman

IPC: H04L41/16 ,  H04L41/147

Abstract: In some embodiments, there may be provided a method that includes receiving, as a first input to a first machine learning model, at least a first traffic matrix indicative of an amount of traffic routed among at least one node pair of an overlay network; receiving, as a second input to the first machine learning model, information indicative of overlay network routing among the at least one node pair of the overlay network; receiving, as a third input to the first machine learning model, measured delay between the at least one node pair of the overlay network; and learning, by the first machine learning model, a representation of an underlay network, the learning using a minimization of a difference between an average delay in the underlay network and the measured delay between the at least one node pair of the overlay network.

公开(公告)号：US11309972B2

公开(公告)日：2022-04-19

申请号：US17025353

申请日：2020-09-18

Applicant: Nokia Solutions and Networks OY

Inventor： Juan Ignacio Bonetti ,  Rene-Jean Essiambre ,  Muralidharan Kodialam

IPC: H04B10/25 ,  H04B10/516 ,  H04J14/06 ,  H04B10/564 ,  H04B10/61

Abstract: A machine-implemented method of constructing multidimensional constellations having increased minimum distances between the constellation symbols thereof compared to those of comparable conventional constellations, e.g., QPSK and QAM constellations. An example multidimensional constellation so constructed may have eight or more dimensions and may be mapped onto degrees of freedom selected from, e.g., time, space, wavelength, polarization, and the in-phase and quadrature-phase components, of the optical field. The disclosed method is beneficially used to generate multidimensional modulation formats characterized by constant total optical transmit power per modulation time slot and/or applicable to the transmission of multidimensional constellation symbols having separate parts thereof primarily carried by different respective guided modes of the optical fiber. Example methods and apparatus for implementing such multidimensional modulation formats are also disclosed herein.

公开(公告)号：US20210091858A1

公开(公告)日：2021-03-25

申请号：US17025353

申请日：2020-09-18

Applicant: Nokia Solutions and Networks OY

Inventor： Juan Ignacio Bonetti ,  Rene-Jean Essiambre ,  Muralidharan Kodialam

IPC: H04B10/516 ,  H04J14/06 ,  H04B10/61 ,  H04B10/25 ,  H04B10/564

Abstract: A machine-implemented method of constructing multidimensional constellations having increased minimum distances between the constellation symbols thereof compared to those of comparable conventional constellations, e.g., QPSK and QAM constellations. An example multidimensional constellation so constructed may have eight or more dimensions and may be mapped onto degrees of freedom selected from, e.g., time, space, wavelength, polarization, and the in-phase and quadrature-phase components, of the optical field. The disclosed method is beneficially used to generate multidimensional modulation formats characterized by constant total optical transmit power per modulation time slot and/or applicable to the transmission of multidimensional constellation symbols having separate parts thereof primarily carried by different respective guided modes of the optical fiber. Example methods and apparatus for implementing such multidimensional modulation formats are also disclosed herein.

公开(公告)号：US10601521B2

公开(公告)日：2020-03-24

申请号：US15979376

申请日：2018-05-14

Applicant: Nokia Solutions and Networks Oy

Inventor： Rene-Jean Essiambre ,  Roland Ryf ,  Muralidharan Kodialam

IPC: H04B10/516 ,  H04B10/61 ,  H04J14/06

Abstract: An optical data receiver includes optical hybrids, light detectors and a digital signal processor. Each optical hybrid outputs mixtures of a corresponding one of the polarization components of a received data-modulated optical carrier with reference light. Each light detector outputs digital measurements of the mixtures from a corresponding one of the optical hybrids. The digital signal processor identifies data symbols of a constellation having parts transmitted on both polarization components of the data-modulated optical carrier responsive to receipt of the digital measurements. The transmitted data-modulated optical carrier has about a same total light intensity in each modulation time slot thereof. Each data symbol is defined by in-phase and quadrature-phase electric field coordinates of both polarization components. Pairs of in-phase and quadrature-phase electric coordinates of each of the polarization components are on a preselected set of one or more concentric circles about an origin. The constellation has 4D dimensions, D being an integer.

公开(公告)号：US12255821B2

公开(公告)日：2025-03-18

申请号：US18336675

申请日：2023-06-16

Applicant: Nokia Solutions and Networks Oy

Inventor： Muralidharan Kodialam ,  TV Lakshman

IPC: H04L47/122 ,  G06N3/084 ,  H04L43/0882

Abstract: In some embodiments, there may be provided a method that includes receiving, as a first input to a machine learning model, a measured link load; receiving, as a second input to the machine learning model, information indicating a network topology; receiving, as a third input to the machine learning model, at least one deflection parameter; learning, by the machine learning model, a first output to provide at least one updated deflection parameter, wherein the at least one updated deflection parameter indicates the fractional amount of traffic that is to be carried between the source node and the destination node and deflected through the intermediate node; and learning, by the machine learning model, a second output to provide dual variables that serve as a surrogate for a traffic matrix that could have generated the measured link load that is measured for the link of the network.

公开(公告)号：US20240348547A1

公开(公告)日：2024-10-17

申请号：US18298660

申请日：2023-04-11

Applicant: Nokia Solutions and Networks Oy

Inventor： Muralidharan Kodialam ,  TV Lakshman

IPC: H04L47/12 ,  H04L41/16 ,  H04L45/00

CPC classification number: H04L47/12 ,  H04L41/16 ,  H04L45/34

Abstract: In some embodiments, there may be provided a method that includes receiving a first traffic matrix; receiving information regarding links associated with each segment of the network; determining a total amount of segment flow using the at least one non-linear deflection parameter applied to the traffic demand of the first traffic matrix; determining a link flow for each of the links using the total amount of segment flow and the second input to the machine learning model; determining link utilization for each of the links using the link flows and a capacity for each of the links; learning, by the machine learning model using a gradient descent, a minimum of a maximum amount of the link utilization over the links by at least adjusting a value of the at least one non-linear deflection parameter. Related systems, methods, and articles of manufacture are also disclosed.