Self-configuring wireless networks

1. An iterative method for configuring a network, the network comprising one or more nodes each configured to provide wireless coverage to one or more transceivers, the iterative method comprising:

deploying, to a location, at least one of the one or more nodes with an initial configuration;

obtaining a wireless propagation model and at least one of a target coverage and a target capacity;

iteratively measuring, in real-time at the location, a set of wireless parameters with respect to operation of at least one of the one or more transceivers and the at least one node;

dynamically adjusting the propagation model using the most recent set of measured parameters;

determining a set of operating parameters using the dynamically adjusted model; and

self-configuring, via a computing device of at least one of the one or more transceivers and the at least one node, with the set of operating parameters until at least one of the target coverage and the target capacity is satisfied.

2. The method of claim 1 ,

wherein each of the one or more transceivers is communicatively coupled to a sensor.

3. The method of claim 1 , wherein the computing device is embedded in at least one of the one or more transceivers and the at least one node.

4. The method of claim 1 , wherein the computing device is part of a node that is different from the one or more transceivers and the at least one node.

5. The method of claim 1 , wherein the computing device is integrated with a transceiver otherwise used to facilitate communication to and/or from the at least one node that provides the transceiver coverage.

6. The method of claim 1 , further comprising:

determining, via the computing device, an area of the wireless coverage using the propagation model or the dynamically adjusted model;

determining, via the computing device for the at least one node, a different location using the determined coverage area; and

deploying the at least one node to the different location,

wherein the operation of the at least one node is performed at the location, and

wherein, as a result of the deployment to the different location, the at least one node performs better.

7. The method of claim 6 , further comprising:

wherein the propagation model is a radio frequency (RF) propagation model,

wherein the set of measured parameters comprises one or more RF parameters, and

wherein the dynamically adjusted model is deterministic,

wherein the better performance, as a result of the deployment of the at least one node to the different location, is based on speed, RF spectrum usage, or a combination of the speed and RF spectrum usage, and

wherein, as a result of the dynamic adjustment(s), the at least one node performs with better accuracy.

8. The method of claim 1 , wherein the set of operating parameters comprises information about two or more of an output power, a frequency, a bandwidth, a type of channel coding, an amount of forward error correction, and a modulation.

9. The method of claim 1 , wherein the use of the dynamically adjusted model involves environmental terrain data and clutter data.

10. The method of claim 9 , wherein the clutter data identifies a three-dimensional (3D) location of each of a plurality of objects, the 3D location comprising a height of the each object.

11. The method of claim 1 , further comprising:

determining, via the propagation model or the dynamically adjusted model, a capacity per unit area based on an aggregate throughput supported by the one or more transceivers operating in the unit area.

12. The method of claim 7 , further comprising:

triggering a redetermination, via the computing device, of at least one of the set of operating parameters using the dynamically adjusted model based on a detected change in at least one of (i) an environment of the at least one node, (ii) an interference with respect to wireless operation of the at least one deployed node, and (iii) a performance required from the one or more respective transceivers; and

reconfiguring, via the computing device, the at least one node with the at least one redetermined operating parameter such that an area of the coverage for the one or more transceivers changes,

wherein, as a result of the reconfiguration, the at least one node performs with better accuracy.

13. The method of claim 6 , further comprising:

determining that one or more other nodes need to be deployed to satisfy desired coverage;

determining, via the computing device for one of the other nodes, another location different from the location and the different location using coverage information determined after the at least one node is deployed to the different location; and

deploying the one other node to the determined other location,

wherein the locations are 3D locations, and

wherein the better performance, as a result of the deployment of the at least one node to the different location, is based on accuracy.

14. The method of claim 13 , further comprising:

determining a number of the one or more transceivers needed to satisfy desired capacity; and

determining a 3D location for installing each of the one or more transceivers.

15. The method of claim 1 , wherein each of the one or more nodes is an access point radio.

16. The method of claim 13 , wherein the determination of the other location comprises determining a dead zone and using one or more RF parameters measured by the at least one node at the first different location.

17. The method of claim 12 , further comprising:

machine-learning behavior of the network such that the change is detected as regularly occurring at a certain location and time, wherein the machine-learning comprises a prediction of the behavior by a trained model,

wherein the better performance, as a result of the reconfiguration, is based on speed, RF spectrum usage, or a combination of the speed and RF spectrum usage.

18. The method of claim 6 ,

wherein parameters of the initial configuration are determined based on a link budget analysis and on a different propagation model, and

wherein the different propagation model is statistical.

19. An apparatus, comprising:

one or more sensors;

a non-transitory memory including instructions stored thereon for configuring a network, the network comprising one or more nodes each configured to provide wireless coverage to one or more transceivers; and

one or more processors operably coupled to the non-transitory memory, the one or more processors being configured to execute the instructions, causing:

initially configuring at least one of the one or more nodes;

obtaining a target coverage and a target capacity;

iteratively obtaining, via the one or more sensors over time, a set of wireless parameters in relation to at least one of the one or more transceivers and the at least one node;

dynamically determining a set of operating parameters using (i) an RF propagation model and (ii) the set of most recently obtained parameters; and

reconfiguring the at least one node with the dynamically determined set of operating parameters until the target coverage and the target capacity are satisfied.

20. An iterative method for configuring a network, the network comprising a plurality of radios each configured to provide wireless coverage to a plurality of transceivers, and the method comprising:

deploying one of the plurality of radios to a location using a wireless propagation model;

self-configuring, via the one node, a plurality of operating parameters based on desired coverage, desired capacity, and measurements taken at the deployed location; and

iteratively deploying each of the other radios, to a different location determined by a previously deployed radio, until the desired coverage and/or capacity is satisfied by the deployed nodes,

wherein each of the radios is self-configured before determining a location of a next-deployed radio.