Intel Corporation

Arjun Anand

Ravikumar Balakrishnan

Rath Vannithamby

Nageen Himayat

Vinod Kristem

Mustafa Akdeniz

Sagar Dhakal

Ariela Zeira

Shahrnaz Azizi

Alexander W Min

Vallabhajosyula S Somayazulu

Maruti Gupta Hyde

Navid Naderializadeh

Ajay Gupta

Mark R Eisen

Jacob Winick

An apparatus of a transmitter computing node n (TX node n) of a wireless network, one or more computer readable media, a system, and a method. The apparatus includes one or more processors to: implement machine learning (ML) based training rounds, each training round including: determining a local action value function Q(h, a; θ) corresponding to a value of performing a radio resource management (RRM) action aat a receiving computing node n (RX node n) associated with TX node n using policy parameter θand based on h, hincluding channel state information at RX node n; and determining, based on an overall action value function Qat time t, an estimated gradient of an overall loss at time t for overall policy parameter θ(∇L(θ)), wherein Qcorresponds to a mixing of local action value functions Q(h, a; θ) for all TX nodes i in the network at time t including TX node n; and determine, in response to a determination that ∇L(θ) is close to zero for various values of t during training, a trained local action value function Qto generate a trained action value relating to data communication between TX node n and RX node n.

Apparatus, system, method and computer-implemented storage media to implement radio resource management policies using machine learning

In one embodiment, an apparatus of an access point (AP) node of a network includes an interconnect interface to connect the apparatus to one or more components of the AP node and a processor to: access scheduling requests from a plurality of devices, select a subset of the devices for scheduling of resource blocks in a time slot, and schedule wireless resource blocks in the time slot for the subset of devices using a neural network (NN) trained via deep reinforcement learning (DRL).

Model-assisted deep reinforcement learning based scheduling in wireless networks

An apparatus of an edge computing node, a method, and a machine-readable storage medium. The apparatus is to decode messages from a plurality of clients within the edge computing network, the messages including respective coded data for respective ones of the plurality of clients; computing estimates of metrics related to a global model for federated learning using the coded data, the metrics including a gradient on the coded data; use the metrics to update the global model to generate an updated global model, wherein the edge computing node is to update the global model by calculating the gradient on the coded data based on a linear fit of the global model to estimated labels from the federated learning; and send a message including the updated global model for transmission to at least some of the clients.

Uses of coded data at multi-access edge computing server

For example, a wireless communication device may be configured to, based on a grouping criterion, select from a plurality of STAs a group of two or more STAs for a Trigger-Based (TB) Multi-User (MU) UL OFDMA control frame transmission to be communicated from the group of two or more STAs to the wireless communication device, the grouping criterion based on two or more RSSI values corresponding to the two or more STAs, respectively; to transmit a trigger frame to trigger the TB MU UL OFDMA control frame transmission, the trigger frame including two or more STA Identifiers to identify the two or more STAs, respectively; and to process the TB MU UL OFDMA control frame transmission from the group of two or more STAs, the TB MU UL OFDMA control frame transmission including two or more control frames from the two or more STAs, respectively.

Apparatus, system and method of trigger-based (TB) multi-user (MU) uplink (UL) orthogonal-frequency-division-multiple-access (OFDMA) control frame transmission

Methods, apparatus, systems, and articles of manufacture are disclosed that generate dynamic latency values. An example apparatus includes an active status controller to determine that a modem is active based on a number of packets obtained from a network, a prediction controller to predict that the number of packets are indicative of a workload type based on a trained model, and a latency value generator to generate a latency value based on the workload type of the number of packets, the latency value to cause a processor processing the number of packets to enter a power saving state or a power executing state.

Methods and apparatus to generate dynamic latency messages in a computing system

For example, a wireless communication device may be configured to determine a Resource Unit (RU) allocation of a plurality of RUs to a plurality of wireless communication stations (STAs), respectively, the RU allocation to allocate to a STA of the plurality of STAs an RU of the plurality of RUs, wherein an RU size of the RU allocated to the STA is based at least on a traffic rate parameter, which is dependent on a traffic rate of Downlink (DL) traffic for the STA; and to transmit a Multi-User (MU) DL Orthogonal-Frequency-Division-Multiple-Access (OFDMA) Physical-layer Protocol Data Unit (PPDU) to the plurality of STAs according to the RU allocation.

Apparatus, system and method of resource unit (RU) allocation for multi user (MU) downlink orthogonal-frequency-division-multiple-access (OFDMA) transmission

Growing community of inventors

Santa Clara, CA, United States of America

Arjun Anand