Optimizing wireless networking using a virtual geographic information system overlay
In a connected vehicle environment, network connection parameters such as a network congestion window and bit rate are automatically adjusted dependent on a location of a vehicle in order to optimize network performance. A geospatial database stores learned relationships between network performance of a connected vehicle at different physical locations when configured in accordance with different network parameters. The vehicle can then adjust its network parameters dynamically dependent on its location. A vehicle may maintain multiple connections to different networks concurrently for transmitting duplicate data of a data stream, with the vehicle independently adjusting parameters associated with different networks to optimize performance.
1. A method for controlling network parameters of a vehicle, the method comprising:
establishing, by the vehicle, a first connection to a first network;
predicting based on sensed information of the vehicle, a predicted future state of the vehicle including future position information;
obtaining first network performance data of the first network associated with the predicted future state of the vehicle;
determining, based on the first network performance data, first network parameters associated with the first connection to the first network that result in a first target predicted quality score associated with the first connection;
configuring a communication system of the vehicle according to the first network parameters;
transmitting, by the communication system, a first data stream over the first network;
measuring performance of the first connection to the first network;
determining if the measured performance sufficiently matches performance associated with the first target predicted quality score; and
responsive to the measured performance sufficiently matching, recording a successful update of the first network parameters.
2. The method of claim 1 , further comprising:
establishing, by the vehicle, a second connection to a second network concurrently with the first connection to the first network;
obtaining second network performance data of the second network associated with the predicted future state of the vehicle;
determining, based on the second network performance data, second network parameters associated with the second connection to the second network that result in a second target predicted quality score associated with the second connection;
configuring the communication system of the vehicle according to the second network parameters; and
transmitting, by the communication system, a second data stream over the second network.
3. The method of claim 2 , wherein the second data stream includes data redundant to the first data stream.
4. The method of claim 2 , further comprising:
measuring performance of the second network connection;
determining if the measured performance sufficiently matches performance associated with the second target predicted quality score;
responsive to the measured performance not sufficiently matching, recording an anomaly with respect to the second performance data retrieved from a geospatial database.
5. The method of claim 1 , wherein determining the first network parameters comprises:
determining, from a geospatial database, a plurality of predicted candidate quality scores resulting from a range of candidate network parameters; and
identifying the first network parameters from the candidate network parameters that results in the first target predicted quality score.
6. The method of claim 1 , wherein determining the first network parameters comprises:
obtaining a first predicted performance value associated with a first performance attribute based on the predicted future state of the vehicle;
obtaining a second predicted performance value associated with a second performance attribute based on the predicted future state of the vehicle; and
applying a predefined utility function to the first predicted performance value and the second predicted performance value to generate the first target predicted quality score.
7. The method of claim 1 , wherein the first network performance data in a geospatial database is obtained according to a data collection process comprising obtaining network performance data for a population of vehicles operating at different locations while applying a range of different network parameters.
8. The method of claim 1 , wherein the first network parameters comprise at least one of a congestion window value and a bit rate.
9. The method of claim 1 , wherein determining the first network parameters comprises:
receiving one or more functions mapping the predicted future state of the vehicle to a set of candidate quality scores for a range of network parameters;
applying the one or more functions to the predicted future state of the vehicle; and
identifying network parameters associated with first target predicted quality score selected from the set of candidate quality scores.
10. A non-transitory computer-readable storage medium storing instructions for controlling network parameters of a vehicle, the instructions when executed by a processor causing the processor to perform steps including:
establishing, by the vehicle, a first connection to a first network;
predicting based on sensed information of the vehicle, a predicted future state of the vehicle including future position information;
obtaining first network performance data of the first network associated with the predicted future state of the vehicle;
determining, based on the first network performance data, first network parameters associated with the first connection to the first network that result in a first target predicted quality score associated with the first connection;
configuring a communication system of the vehicle according to the first network parameters;
transmitting, by the communication system, a first data stream over the first network,
measuring performance of the first connection to the first network;
determining if the measured performance sufficiently matches performance associated with the first target predicted quality score; and
responsive to the measured performance sufficiently matching, recording a successful update of the first network parameters.
11. The non-transitory computer-readable storage medium of claim 10 , the instructions when executed further causing the processor to perform steps including:
establishing, by the vehicle, a second connection to a second network concurrently with the first connection to the first network;
obtaining second network performance data of the second network associated with the predicted future state of the vehicle;
determining, based on the second network performance data, second network parameters associated with the second connection to the second network that result in a second target predicted quality score associated with the second connection;
configuring the communication system of the vehicle according to the second network parameters; and
transmitting, by the communication system, a second data stream over the second network.
12. The non-transitory computer-readable storage medium of claim 11 , wherein the second data stream includes data redundant to the first data stream.
13. The non-transitory computer-readable storage medium of claim 11 , the instructions when executed further causing the processor to perform steps including:
measuring performance of the second network connection;
determining if the measured performance sufficiently matches performance associated with the second target predicted quality score;
responsive to the measured performance not sufficiently matching, recording an anomaly with respect to the second performance data retrieved from a geospatial database.
14. The non-transitory computer-readable storage medium of claim 10 , wherein determining the first network parameters comprises:
determining, from a geospatial database, a plurality of predicted candidate quality scores resulting from a range of candidate network parameters; and
identifying the first network parameters from the candidate network parameters that results in the first target predicted quality score.
15. The non-transitory computer-readable storage medium of claim 10 , wherein determining the first network parameters comprises:
obtaining a first predicted performance value associated with a first performance attribute based on the predicted future state of the vehicle;
obtaining a second predicted performance value associated with a second performance attribute based on the predicted future state of the vehicle; and
applying a predefined utility function to the first predicted performance value and the second predicted performance value to generate the first target predicted quality score.
16. The non-transitory computer-readable storage medium of claim 10 , wherein the first network performance data in a geospatial database is obtained according to a data collection process comprising obtaining network performance data for a population of vehicles operating at different locations while applying a range of different network parameters.
17. The non-transitory computer-readable storage medium of claim 10 , wherein the first network parameters comprise at least one of a congestion window value and a bit rate.
18. A vehicle system comprising:
a drive system;
a plurality of vehicle sensors;
a processor; and
a non-transitory computer-readable storage medium storing instructions for controlling network parameters of a vehicle, the instructions when executed by the processor causing the processor to perform steps including:
establishing, by the vehicle, a first connection to a first network;
predicting based on sensed information of the vehicle, a predicted future state of the vehicle including future position information;
obtaining first network performance data of the first network associated with the predicted future state of the vehicle;
determining, based on the first network performance data, first network parameters associated with the first connection to the first network that result in a first target predicted quality score associated with the first connection;
configuring a communication system of the vehicle according to the first network parameters;
transmitting, by the communication system, a first data stream over the first network;
measuring performance of the first connection to the first network;
determining if the measured performance sufficiently matches performance associated with the first target predicted quality score; and
responsive to the measured performance sufficiently matching, recording a successful update of the first network parameters.
19. The vehicle system of claim 18 , wherein the instructions when executed by the processor further cause the processor to perform steps including:
establishing, by the vehicle, a second connection to a second network concurrently with the first connection to the first network;
obtaining second network performance data of the second network associated with the predicted future state of the vehicle;
determining, based on the second network performance data, second network parameters associated with the second connection to the second network that result in a second target predicted quality score associated with the second connection;
configuring the communication system of the vehicle according to the second network parameters; and
transmitting, by the communication system, a second data stream over the second network.
20. The vehicle system of claim 19 , wherein the second data stream includes data redundant to the first data stream.