Cisco Technology, Inc.

Nike, Inc.

Ritesh Madan

Rohit U Nabar

Vikram Chandrasekhar

Kedar Shirali

Qing Zhao

Vasudha Shivamoggi

Devavrat D Shah

Balaji Rengarajan

Ying-zong Huang

Vishal Doshi

Vivek Farias

Chad Yan

Guang Yang

Aryan Iden Khojandi

Ehsan Haghani

Sushanth Chandappa Kulal

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 the automated fulfillment of orders from a fulfillment network including consumer-facing retail locations. Orders are partitioned into suborders, which are in turn assigned to retail locations based on forecasted demand for the suborder items at the retail locations. The assignment process considers operational data for each retail location such as the number of employees, the inventory of suborder items, shipping rate cards, return policies, business hours, pick decline estimations, etc.

Order fulfillment

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.

A method is provided in one example embodiment and may include generating feedback information by a small cell radio and a macro cell radio; setting a high mobility handover threshold for the macro cell radio based, at least in part, on the feedback information, wherein the high mobility handover threshold is used to trigger handover of one or more high mobility user equipment (UE) associated with the macro cell radio to the small cell radio; and setting a maximum downlink transmit power for the small cell radio based, at least in part, on the feedback information and the high mobility handover threshold.

System and method to provide small cell power control and load balancing for high mobility user equipment in a network environment

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.

The present disclosure provides a fine-grained link adaptation mechanism that allows for link adaptation at a resource block granularity. To this end, the fine-grained link adaptation mechanism can determine the effective signal-to-interference-plus-noise ratio for individual user equipment in a particular cell at the resource block granularity. This way, the transmitter can use the effective signal-to-interference-plus-noise ratio to adapt the modulation and coding scheme at the resource block granularity. The fine-grained link adaptation mechanism can be introduced to a long term evolution (LTE) network without substantial redesign of the LTE network.

Link adaptation based on neighboring cell transmission information

A method is provided in one example embodiment and may include determining for each of one or more macro cell radios, a corresponding set of one or more small cell radios that are under a coverage area of each of the one or more macro cell radios, wherein each corresponding set is associated with a corresponding macro cell radio; calculating interference coordination parameters for each small cell radio belonging to each corresponding set, wherein the interference coordination parameters for each small cell radio belonging to each corresponding set comprises an uplink interference budget for each small cell radio; and communicating the interference coordination parameters to each small cell radio belonging to each corresponding set.

System and method to provide uplink interference coordination in a network environment

An example method is provided in one example embodiment and includes receiving performance metric information from a plurality of small cell radios, wherein the performance metric information includes, at least in part, a number of user equipment that are to be scheduled on a first type and a second type of subframes for each small cell radio; determining resource allocation parameters for the plurality of small cell radios; exchanging interference information between two or more small cell radios of the plurality of small cell radios that includes an indication of whether a particular small cell radio is interfering with or is interfered by another small cell radio of the two or more small cell radios; and scheduling downlink resource transmissions on the first type and the second type of subframes for user equipment served by the two or more small cell radios.

System and method for frequency and time domain downlink inter-cell interference coordination

A method is provided in one example embodiment and may include calculating, by one or more of a plurality of small cell radios, one or more sets of candidate power control parameters using a first interference constraint for uplink user equipment (UE) transmissions for UE served by the one or more of the plurality of small cell radios; determining, at a central management entity, whether an average of a sum of an expected interference for UE associated with the plurality of small cell radios violates a second interference constraint for any of the one or more sets of candidate power control parameters; and generating one or more messages for each of the plurality of small cell radios identifying one or more particular sets of power control parameters that provide for meeting the second interference constraint.

System and method to facilitate small cell uplink power control in a network environment

An example method is provided in one example embodiment and includes receiving at least one performance metric from each of a plurality of cells, the at least performance metric associated with a downlink transmission from the cell to one or more user equipment devices associated with the cell. The method further includes determining a fraction of resources for allocation within a fractional frequency reuse portion of a frequency spectrum based upon the received at least one performance metric, and determining a fraction of the resources for allocation within a reuse one portion of the frequency spectrum based upon the determined fraction of resources for allocation within the fractional frequency reuse portion of the frequency spectrum.

Resource adaptation for frequency domain downlink inter-cell interference coordination

A method is provided in one example embodiment and includes generating feedback information at a first remote access point (AP), wherein the feedback information is associated with one or more user equipment served by the first remote AP; determining constraints for the first remote AP at a central controller based on the feedback information received from the first remote AP and feedback information received from one or more other remote APs that neighbor the first remote AP, wherein the constraints are determined for a plurality of transmission time intervals (TTIs); and scheduling resource blocks (RBs) for the one or more user equipment served by the first remote AP for one or more of the plurality of TTIs based, at least in part, on constraints received from the central controller.

System and method to facilitate centralized radio resource management in a split radio access network environment

An example method is provided in one example embodiment and includes receiving feedback information from at least one controlled cell indicative of interference received at one or more user equipment devices served by the at least one cell. The at least one controlled cell is controlled by an operator associated with the at least one controlled cell. The method further includes selecting one or more user equipment devices that is determined to have received interference from at least one non-controlled cell that is greater than a predetermined threshold. The at least one non-controlled cell is not controlled by the operator associated with the at least one controlled cell. The method still further includes determining a power level for a subset of common resources from among a set of common resources shared among the at least one controlled cell based upon the received feedback information.

Growing community of inventors

Berkeley, CA, United States of America

Ritesh Madan