Method to Mitigate Hash Correlation in Multi-Path Networks

    公开(公告)号:US20220131800A1

    公开(公告)日:2022-04-28

    申请号:US17569096

    申请日:2022-01-05

    Applicant: Google LLC

    Abstract: Methods are provided for mitigating hash correlation. In this regard, a hash correlation may be found between a first switch and a second switch in a network. In this network, a first egress port is to be selected among a first group of egress ports at the first switch for forwarding packets, and a second egress port is to be selected among a second group of egress ports at the second switch for forwarding packets, where the first group has a first group size and the second group has a second group size. Upon finding the hash correlation, a new second group size coprime to the first group size may be selected, and the second group of egress ports may be mapped to a mapped group having the new second group size. The second switch may be configured to route packets according to the mapped group.

    Configuring Data Center Network Wiring

    公开(公告)号:US20220014428A1

    公开(公告)日:2022-01-13

    申请号:US17119614

    申请日:2020-12-11

    Applicant: Google LLC

    Abstract: A datacenter network can be made of points of deliveries and patch panels. Rewiring the logical links within the datacenter network to meet a new network topology is computationally intense. Methods, systems, and apparatuses are provided to modify an existing network topology with a provided existing physical topology and logical topology into the new network topology. For example, the provided physical topology can include changes to the network, such as adding new points of delivery, adding additional patch panels, increasing the number of physical connections between points of delivery and patch panels, or removing a point of delivery.

    Configuring data center network wiring

    公开(公告)号:US11223527B1

    公开(公告)日:2022-01-11

    申请号:US17119614

    申请日:2020-12-11

    Applicant: Google LLC

    Abstract: A datacenter network can be made of points of deliveries and patch panels. Rewiring the logical links within the datacenter network to meet a new network topology is computationally intense. Methods, systems, and apparatuses are provided to modify an existing network topology with a provided existing physical topology and logical topology into the new network topology. For example, the provided physical topology can include changes to the network, such as adding new points of delivery, adding additional patch panels, increasing the number of physical connections between points of delivery and patch panels, or removing a point of delivery.

    Method To Mitigate Hash Correlation In Multi-Path Networks

    公开(公告)号:US20210336884A1

    公开(公告)日:2021-10-28

    申请号:US16857862

    申请日:2020-04-24

    Applicant: Google LLC

    Abstract: Methods are provided for mitigating hash correlation. In this regard, a hash correlation may be found between a first switch and a second switch in a network. In this network, a first egress port is to be selected among a first group of egress ports at the first switch for forwarding packets, and a second egress port is to be selected among a second group of egress ports at the second switch for forwarding packets, where the first group has a first group size and the second group has a second group size. Upon finding the hash correlation, a new second group size coprime to the first group size may be selected, and the second group of egress ports may be mapped to a mapped group having the new second group size. The second switch may be configured to route packets according to the mapped group.

    Koopman Neural Forecaster for Time Series with Temporal Distribution Shifts

    公开(公告)号:US20240119265A1

    公开(公告)日:2024-04-11

    申请号:US18373417

    申请日:2023-09-27

    Applicant: Google LLC

    CPC classification number: G06N3/0455 G06N3/08

    Abstract: Aspects of the disclosure provide a deep sequence model, referred to as Koopman Neural Forecaster (KNF), for time series forecasting. KNF leverages deep neural networks (DNNs) to learn the linear Koopman space and the coefficients of chosen measurement functions. KNF imposes appropriate inductive biases for improved robustness against distributional shifts, employing both a global operator to learn shared characteristics, and a local operator to capture changing dynamics, as well as a specially-designed feedback loop to continuously update the learnt operators over time for rapidly varying behaviors. KNF achieves superior performance on multiple time series datasets that are shown to suffer from distribution shifts.

    Method to Mitigate Hash Correlation in Multi-Path Networks

    公开(公告)号:US20250016094A1

    公开(公告)日:2025-01-09

    申请号:US18798184

    申请日:2024-08-08

    Applicant: Google LLC

    Abstract: Methods are provided for mitigating hash correlation. In this regard, a hash correlation may be found between a first switch and a second switch in a network. In this network, a first egress port is to be selected among a first group of egress ports at the first switch for forwarding packets, and a second egress port is to be selected among a second group of egress ports at the second switch for forwarding packets, where the first group has a first group size and the second group has a second group size. Upon finding the hash correlation, a new second group size coprime to the first group size may be selected, and the second group of egress ports may be mapped to a mapped group having the new second group size. The second switch may be configured to route packets according to the mapped group.

Patent Agency Ranking