Plume Design, Inc.

Nike, Inc.

Balaji Rengarajan

William John McFarland

Aman Singla

Sameer Vaidya

Evan Jeng

Qinghai Gao

Adam R Hotchkiss

Paul White

Vikram Chandrasekhar

Kiran Kumar Edara

Andrea Goldsmith

Ritesh Kumar Madan

Vasudha Shivamoggi

Ritesh Madan

Devavrat D Shah

Santhosh Krishna

Ying-zong Huang

Vishal Doshi

Murugesan Guruswamy

Kaixiang Hu

Abhishek Kumar

Jian Lu

Hong Fan

Igal Gutkin

Srinivasa Tagirisa

Evan Rusackas

Thomas Paul

William Mcfarland

Computer-implemented prediction methods, in accordance with various embodiments, involve storing key-value pairs each including a key tuple and an associated value in a data store, building a prediction model associated with at least a subset of the key-value pairs, and in response to receipt of a prediction query that specifies a key tuple, generating a prediction response based on the prediction model that includes a predicted value for the specified key tuple. In one example application, the key tuples each include an operation specifying a purchase and a two-part identifier specifying a customer and a product.

Event prediction

Systems and methods for Wi-Fi network optimization include receiving inputs related to signal strength and interference during operation of the Wi-Fi network; performing an optimization to determine operational parameters of one or more access points in the Wi-Fi network, wherein the optimization is based on the inputs and is configured to address an objective associated with the Wi-Fi network; and providing outputs comprising the operational parameters for configuration of the Wi-Fi network, based on the optimization, wherein the operational parameters include channel and bandwidth selection, and topology of the one or more access points.

Optimization of distributed Wi-Fi networks

A system for event prediction is configured to ingest at least partially incomplete unstructured data from at least one data source, convert at least a subset of the ingested data into a prediction model in accordance with a received model definition, receive a prediction query, and in response, supply an event prediction based on the prediction model. In some embodiments, ingesting the data involves transforming the unstructured data into a universal structured format in which the data is represented as key-value pairs each comprising a key tuple and an associated value, the key tuple specifying an operation and at least one identifier; the prediction query includes a key tuple specifying an operation and at least one identifier; and the event prediction generated with the prediction model includes a value associated with the key tuple that is missing from the transformed data.

Systems and methods include obtaining measurements from a Wi-Fi network that includes i) a plurality of access points interconnected to one another and at least one connected to a gateway, and ii) a plurality of Wi-Fi client devices that each connect to an access point of the plurality of access points; learning usage patterns in the Wi-Fi network through analysis with one or more machine learning algorithms; and providing a configuration to the Wi-Fi network based on the learned usage pattern where the configuration includes a topology of the plurality of access points.

Cloud-based control of a Wi-Fi network

A system includes at least one connector configured to gather at least partially incomplete data from at least one data source. The gathered data is communicated to a model definition module that converts at least a subset of the gathered data into a prediction model in accordance with a received definition. A prediction module receives a prediction query and, in response, supplies an event prediction based on the prediction model.

Systems and methods for visualization and troubleshooting of a distributed Wi-Fi network, implemented through one of a mobile application and a web page, include, responsive to obtaining data from the distributed Wi-Fi network, providing a map of the distributed Wi-Fi network based on the obtained data, wherein the map includes a first icon designating a gateway node, one or more second icons each designating one or more nodes, and connectors between the gateway node, wherein the gateway node and the one or more nodes are in a tree topology; providing a visualization in the map based on a current operational status of the distributed Wi-Fi network from the obtained data, wherein the visualization comprises a plurality of visual indicators of the current operational status; and providing notifications based on the current operational status.

Distributed Wi-Fi network visualization and troubleshooting

Systems and methods include obtaining data associated with operation of a Wi-Fi network, via a network interface connected to the one or more processors; analyzing the obtained data to determine one or more of forecasts, predictions, trends, and interference associated with the Wi-Fi network based on the obtained data and correlations determined therein; and causing configuration of the Wi-Fi network based on the determined one or more forecasts, predictions, trends, and interference, wherein the configuration includes at least one of channel selection, bandwidth selection, topology selection of access points in the Wi-Fi network, and client associations with the access points.

Optimization of distributed Wi-Fi networks estimation and learning

Systems and methods include obtaining measurements from a Wi-Fi network that includes one or more access points; determining a configuration of the Wi-Fi network based on the measurements, wherein the configuration includes one or more of i) steering a client device to associate with a specific access point of the one or more access points and ii) steering the client device to connect to a specific frequency band of the one or more access points; and providing the configuration to the Wi-Fi network for implementation thereof.

A distributed Wi-Fi system includes a first Wi-Fi access point communicatively coupled to a modem/router for connectivity to the Internet and to a cloud controller via the Internet; and at least one additional Wi-Fi access point with wireless backhaul connections to the modem/router via the first Wi-Fi access point, wherein the first Wi-Fi access point and the at least one additional access point cooperatively form a single Wi-Fi network; wherein the cloud controller is configured to receive inputs related to operation of the single Wi-Fi network, perform an optimization based on the inputs with an objective function, and provide operational parameters for the single Wi-Fi network based on the optimization.

Systems and methods implemented by a cloud-based controller to control a Wi-Fi network with a plurality of access points include obtaining measurements from the Wi-Fi network; determining a configuration of the Wi-Fi network based on the measurements, wherein the configuration comprises a topology of the Wi-Fi network and the topology comprises the plurality of access points selectively interconnected to one another via backhaul links; and providing the configuration to the Wi-Fi network for implementation thereof.

A method of evaluating an application performance metric of a Wi-Fi device that is running an application and that is receiving application data from another Wi-Fi device transmitting the application data is disclosed. An indication of a delay in one or more of a plurality of access category queues at the Wi-Fi device transmitting the application data is received. The delay over time is characterized, wherein the characterization of the delay over time includes a statistical measure of the delay determined based on the received indication of the delay in the one or more of the plurality of access category queues. An application quality-of-experience (QoE) metric is determined based on a mapping from the characterization of the delay over time to an application performance.

Application quality of experience metric

Systems and methods for estimation and learning for optimization of a distributed Wi-Fi network performed by a cloud controller include obtaining data associated with operation of the distributed Wi-Fi network; processing the obtained data; determining one or more of forecasts, predictions, trends, and interference for the distributed Wi-Fi network based on the processed data; and performing an optimization of the distributed Wi-Fi network based on the determined one or more forecasts, predictions, trends, and interference. The obtained data can time-series data, and wherein the processing comprises collating the time-series data across all nodes in the distributed Wi-Fi network and segmenting the time-series data into time periods with similar load characteristics.

Systems and methods for gathering data by an access point in a Wi-Fi system for optimization include periodically or based on command from a cloud-based system performing one or more of i) obtaining on-channel scanning data while operating on a home channel and ii) switching off the home channel and obtaining off-channel scanning data for one or more off-channels; and providing measurement data based on one or more of the on-channel scanning data and the off-channel scanning data to the cloud-based system for use in the optimization of the Wi-Fi system, wherein the measurement data comprises one or more of raw data and processed data.

Data gathering to enable the optimization of distributed Wi-Fi networks

Systems and methods for setting up an access point in a Wi-Fi system, subsequent to booting up, determining whether the access point is a gateway node with a connection to a modem/router or a Wi-Fi node without a connection to the modem/router; connecting to a cloud configuration service when the access point is a gateway node for obtaining configuration parameters of the Wi-Fi system; and connecting to a predefined Service Set Identifier (SSID) when the access point is a Wi-Fi node for obtaining the configuration parameters from the gateway node.

Growing community of inventors

Campbell, CA, United States of America

Balaji Rengarajan