Adaptive power save with reinforcement learning
AssigneeQUALCOMM Incorporated
InventorsSandip Homchaudhuri, Pradeep Kumar Kumar Yenganti, Bhasker Neti
Life of this patent
Estimating the term…
Abstract
Methods, systems, and devices for wireless communication are described. A station may be communicating with an access point during a first active communication period. The communication may be performed in a first power mode. The station may switch to a second power mode to transition to a sleep period. The station may determine, based on traffic indicator metric(s), whether to perform a speculative wakeup and switch to the first power mode at the end of the sleep period.
Claims24
A method for wireless communication, comprising:
- monitoring, at a wireless station and during an observation window, one or more metrics associated with power mode changes;
- updating one or more values of an inactivity timeout (ITO) look up table (LUT) based on the one or more metrics to produce an updated ITO LUT;
- and
- updating an ITO period based at least in part on the updated ITO LUT.
An apparatus for wireless communications, comprising a processor, memory in electronic communication with the processor, and instructions stored in the memory and operable, when executed by the processor, to cause the apparatus to:
- monitor, at a wireless station and during an observation window, one or more metrics associated with power mode changes;
- update one or more values of an inactivity timeout (ITO) look up table (LUT) based on the one or more metrics to produce an updated ITO LUT;
- and
- update an ITO period based at least in part on the updated ITO LUT.
Dependencies are inferred from the claim text.