# US 12,192,940 B2 · Method and apparatus for timing advance prediction > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,192,940 B2 - Document ID: US12192940B2 - Status: Granted - Kind: B2 - Application number: 17/703,879 - Filed: 2022-03-24 - Published: 2022-09-29 - Granted: 2025-01-07 - Earliest claimed: 2021-03-29 - Assignees: Semtech Corporation - Applicants: Sierra Wireless, Inc. - Inventors: Gautham Prasad; Nadhem Rojbi; Gustav Gerald Vos; Lutz Hans-Joachim Lampe - Web page: https://patentgrep.com/patent/US12192940B2 ## CPC - H04W 56/0045: {compensating for timing error by altering transmission time} - H04B 17/27: for locating or positioning the transmitter - H04B 17/328: {Reference signal received power [RSRP]; Reference signal received quality [RSRQ]} - H04B 17/373: Predicting channel quality {or other radio frequency [RF]} parameters - H04B 17/3913: {Predictive models, e.g. based on neural network models} - H04W 56/0055: {determining timing error of reception due to propagation delay} - H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72) - H04B: TRANSMISSION ## Abstract There are provided methods for predicting timing advance (TA) with respect to a base station. According to some embodiments, the method includes determining, by a user equipment (UE), a set of TAs, each TA corresponding to a particular distance from the base station and measuring, by the UE, a set of instances of a power metric, each instance of the power metric associated with a respective distance from the base station. The method further includes determining, by the UE, a set of differences between each of the instances of the power metric and determining, by the UE, a new TA at least in part using the set of TAs and the set of differences. ## Claims ### Claim 1 A method for predicting timing advance (TA) with respect to a base station, the method comprising: determining, by a user equipment (UE), a set of TAs, each TA corresponding to a particular distance from the base station; receiving, by the UE from the base station, one or more signals; measuring, by the UE, a set of instances of a power metric, each instance of the power metric associated with a respective distance from the base station, the measuring based at least in part on the one or more signals; determining, by the UE, a set of differences between each of the instances of the power metric; and determining, by the UE, a new TA at least in part using the set of TAs and the set of differences. ### Claim 2 (depends on 1) The method of claim 1 wherein the power metric is at least one of: a reference signal received power (RSRP); an earliest arriving multipath; and a received signal strength indicator (RSSI). ### Claim 3 (depends on 1) The method of claim 1 wherein the power metric is measured over only one sub-frame of a cell-specific reference signal (CRS) or a set of sub-frames of the CRS. ### Claim 4 (depends on 3) The method of claim 3 wherein a maximum measurement from the set of sub-frames is used. ### Claim 5 (depends on 1) The method of claim 1 wherein the set of TAs includes a single TA or a plurality of TAs. ### Claim 6 (depends on 1) The method of claim 1 wherein the step of determining the new TA is performed using a machine learning regressor. ### Claim 7 (depends on 6) The method of claim 6, wherein the machine learning regressor is configured as a multi-point regressor, the machine learning regressor determining the new TA using the set of TAs and the set of differences simultaneously. ### Claim 8 (depends on 6) The method of claim 6, wherein the machine learning regressor is configured as a multi-point regressor, the machine learning regressor determining a plurality of estimated TAs, each estimated TA based on one or more determined TAs and one or more associated differences, the machine learning regressor further determining the new TA based on an average of the plurality of estimated TAs. ### Claim 9 (depends on 6) The method of claim 6, wherein the machine learning regressor at least in part uses feedback from a base station for determining the new TA. ### Claim 10 (depends on 6) The method of claim 6, wherein the machine learning regressor at least in part uses a pattern of movement of the UE for determining the new TA. ### Claim 11 A user equipment (UE) comprising: a processor; and a memory having stored thereon machine executable instructions which when executed by the processor configure the UE to: determine a set of timing advances (TAs), each TA corresponding to a particular distance from the base station; receive from the base station, one or more signals; measure a set of instances of a power metric, each instance of the power metric associated with a respective distance from the base station, the measuring based at least in part on the one or more signals; determine a set of differences between each of the instances of the power metric; and determine a new TA at least in part using the set of TAs and the set of differences. ### Claim 12 (depends on 11) The UE of claim 11 wherein a machine learning regressor is configured to determine the new TA. ### Claim 13 A method for predicting timing advance (TA) with respect to a base station, the method comprising: determining, by a user equipment (UE), a set of TAs, each TA corresponding to a particular distance from base station; receiving, by the UE from the base station, one or more signals; measuring, by the UE, a set of instances of a communication metric, each instance associated with a particular distance from the base station, the measuring based at least in part on the one or more signals; determining, by the UE, a set of differences between each of the instances of the communication metric; and determining, by the UE, a new TA at least in part using the set of TAs and the set of differences. ### Claim 14 (depends on 13) The method of claim 13 wherein the communication metric is at least one of: a time of arrival (ToA); and a strongest multipath component of a received signal. ### Claim 15 (depends on 13) The method of claim 13 wherein the communication metric is measured over only one sub-frame of a cell-specific reference signal (CRS) or a set of sub-frames of the CRS. ### Claim 16 (depends on 15) The method of claim 15 wherein a maximum measurement from the set of sub-frames is used. ### Claim 17 (depends on 13) The method of claim 13 wherein the set of TAs includes a single TA or a plurality of TAs. ### Claim 18 (depends on 13) The method of claim 13 wherein the set of instances of the communication metric includes a plurality of instances of the communication metric. ### Claim 19 A user equipment (UE) comprising: a processor; and a memory having stored thereon machine executable instructions which when executed by the processor configure the UE to: determine a set of time advances (TAs), each TA corresponding to a particular distance from base station; receive, from the base station, one or more signals; measure a set of instances of a communication metric, each instance associated with a particular distance from the base station, the measuring based at least in part on the one or more signals; determine a set of differences between each of the instances of the communication metric; and determine a new TA at least in part using the set of TAs and the set of differences. ### Claim 20 A user equipment (UE) comprising: a processor; and a memory having stored thereon machine executable instructions which when executed by the processor configure the UE to: determine a set of time advances (TAs), each TA corresponding to a particular distance from base station; measure a set of instances of a communication metric, each instance associated with a particular distance from the base station; determine a set of differences between each of the instances of the communication metric; and determine, by a machine learning regressor, a new TA at least in part using the set of TAs and the set of differences.