Qualcomm Incorporated

Madhup Chandra

Tom Chin

Sharad Shahi

Shailesh Maheshwari

Gavin Bernard Horn

Alexei Yurievitch Gorokhov

Peter Pui Lok Ang

Linhai He

Arvind Vardarajan Santhanam

Ping Liu

Yongle Wu

Shanshan Wang

Vanitha Aravamudhan Kumar

Chun-Hao Hsu

Scott Hoover

Nate Chizgi

Sharif Ahsanul Matin

Prashant Udupa Sripathi

Gurvinder Singh Chhabra

Deepak Krishnamoorthi

Atul Arvind Salvekar

Hemanth Kumar Rayapati

Ramesh Chandra Chirala

Yung-Yih Jian

Yue Hong

Sandeep Ramannavar

Arundhathi Rajshekher Swami

Fnu Saikrishna Vasudevan

Andrew Chen

Rohit Bhasi Thazhath

Khyati Bhupendrabhai Mardia

Shraddha Ramachandra Phadnis

Sandeep C Ramannavar

Methods, systems, and devices for wireless communications are described. For example, the described techniques provide for a user equipment (UE) to predict a gain state for an initial acquisition procedure. For example, the UE may use a machine learning (ML) model to predict an initial gain state which is likely to result in a successful initial acquisition procedure (e.g., without adjusting the gain state and reattempting the initial acquisition procedure). The UE may input UE history data or crowdsourced data (e.g., from a local network or a cloud-based server) into the ML model to generate a predicted gain state which may be more likely to result in a successful initial acquisition (e.g., without reattempting the initial acquisition procedure). The UE may use the initial gain state generated by the ML model to attempt an initial acquisition procedure with a network entity.

Efficient initial acquisition with gain state prediction using machine learning

Certain aspects of the present disclosure relate to methods and apparatus for reliable transmission of system information (SI). In some cases, a UE may send an indication to request SI in an on-demand manner. For example, a method for wireless communications by a UE may include determining system information (SI) desired by the UE is not currently being broadcast. The method for further include sending, in response to the determination, a first indication to request the SI, and sending a second indication to confirm reception of the requested SI or to indicate the UE has not received the requested SI after a time period.

Reliable delivery of system information

Various embodiments may provide systems and methods for managing transmit (TX) timing of data transmissions. The methods include applying a plurality of radio frequency (RF) channel factors related to data uplink transmissions by the wireless device to a TX timing model configured to provide as an output a TX timing for a data transmission to a base station and a number of carriers for sending the data transmission, and selecting a TX time and a number of carriers for sending a next data transmission to the base station based in part on the TX timing model output.

Managing transmit timing of data transmissions

Methods, systems, and devices for wireless communications are described. In some examples, a user equipment (UE) may communicate with a base station using multiple receivers and receive an indication from the base station to activate a second bandwidth part of a set of bandwidth parts configured for the UE. In response to the indication, the UE may switch from operating in a first bandwidth part to operating in the second bandwidth part and adjust a quantity of active receivers at the UE based on switching from operating in the first bandwidth part to operating in the second bandwidth part. Additionally or alternatively, the UE may adjust the quantity of active receivers at the UE based on monitoring for downlink grants from the base station.

Receiver adjustment for wireless communication

Various aspects of the present disclosure generally relate to wireless communication. In some aspects, an apparatus of a user equipment (UE) may determine a set of inputs to a neural network configured to predict radio frequency channel conditions or a user context associated with the UE. In some aspects, the set of inputs includes historical data related to a wireless environment, a communication pattern, or a behavior pattern associated with the UE. The apparatus of the UE may determine, using the neural network and based at least in part on the set of inputs, an optimal number of aggregated carriers to maximize one or more of a power parameter or a performance parameter. The apparatus of the UE may communicate using the optimal number of aggregated carriers. Numerous other aspects are described.

Carrier aggregation optimization using machine learning

The present disclosure presents a method and apparatus for reducing power consumption during a voice communication in a user equipment (UE). For example, the method may include receiving a plurality of frames associated with the voice communication. Further, such an example method may include determining whether a frame pattern based at least on the received plurality of frames corresponds to a transition from a speech burst period to a non-speech period, and disabling a portion of a receiver subsystem at the UE for at least a portion of a frame associated with the non-speech period. As such, the power consumption in a UE may be reduced.

Voice state assisted frame early termination

Growing community of inventors

San Diego, CA, United States of America

Madhup Chandra