Big-data-mining-based wireless channel modeling method

1. A big-data-mining-based wireless channel modeling method, comprising:

obtaining image information of a measurement environment and a channel impulse response data sample under a preset condition, wherein the preset condition comprises at least one of: a scenario type, an antenna configuration parameter, or a frequency value;

obtaining at least one multipath wave and a channel parameter of each of the multipath wave according to the channel impulse response data sample by using a channel parameter estimation algorithm; and clustering the at least one multipath wave according to the channel parameter of each of the multipath wave by using a clustering algorithm to obtain at least one cluster;

obtaining at least one scattering object in the measurement environment according to the image information of the measurement environment;

matching each of the cluster with each of the scattering object to obtain a cluster kernel which is a cluster matching with the scattering object;

establishing a base wireless channel model under the preset condition according to the cluster kernel.

2. The method according to claim 1 , wherein the establishing a base wireless channel model under the preset condition according to the cluster kernel comprises:

obtaining a cluster-kernel-based base wireless channel model under the preset condition by using a machine learning algorithm.

3. The method according to claim 1 , wherein after the establishing a base wireless channel model under the preset condition according to the cluster kernel, the method further comprises:

obtaining a varying pattern of a channel characteristic, varying with the preset condition, according to channel impulse response data samples under at least two different preset conditions by using a data mining method;

establishing, an extended wireless channel model under an arbitrary condition, according to the arbitrary condition, the varying pattern and the base wireless channel model;

wherein the varying pattern of the channel characteristic, varying with the preset condition, includes at least one of: the varying pattern of the channel characteristic in a multi-antenna element, the varying pattern of the channel characteristic varying with frequency, and non-stationary of the channel characteristic varying with motion variations.

4. The method according to claim 1 , wherein the matching each of the cluster with each of the scattering object comprises:

determining a matched scattering object for each of the cluster in all of the scattering object by using a matching algorithm.

5. The method according to claim 1 , wherein the obtaining at least one scattering object in the measurement environment according to the image information of the measurement environment comprises:

performing texture recognition on the image information of the measurement environment to obtain at least one texture identification;

determining a corresponding scattering object for each of the texture identification according to each of the texture identification to obtain at least one scattering object in the measurement environment.

6. The method according to claim 1 , wherein the clustering the at least one multipath wave according to the channel parameter of each of the multipath wave by using a clustering algorithm to obtain at least one cluster, comprising:

clustering the at least one multipath wave according to a delay parameter, an amplitude parameter or an angle domain parameter in the channel parameter of each of the multipath wave by using the clustering algorithm to obtain the at least one cluster.

7. The method according to claim 2 , wherein after the establishing a base wireless channel model under the preset condition according to the cluster kernel, the method further comprises:

obtaining a varying pattern of a channel characteristic, varying with the preset condition, according to channel impulse response data samples under at least two different preset conditions by using a data mining method;

establishing, an extended wireless channel model under an arbitrary condition, according to the arbitrary condition, the varying pattern and the base wireless channel model;

wherein the varying pattern of the channel characteristic, varying with the preset condition, includes at least one of: the varying pattern of the channel characteristic in a multi-antenna element, the varying pattern of the channel characteristic varying with frequency, and non-stationary of the channel characteristic varying with motion variations.

8. The method according to claim 2 , wherein the matching each of the cluster with each of the scattering object comprises:

determining a matched scattering object for each of the cluster in all of the scattering object by using a matching algorithm.

9. The method according to claim 2 , wherein the obtaining at least one scattering object in the measurement environment according to the image information of the measurement environment comprises:

performing texture recognition on the image information of the measurement environment to obtain at least one texture identification;

determining a corresponding scattering object for each of the texture identification according to each of the texture identification to obtain at least one scattering object in the measurement environment.

10. The method according to claim 2 , wherein the clustering the at least one multipath wave according to the channel parameter of each of the multipath wave by using a clustering algorithm to obtain at least one cluster, comprising:

clustering the at least one multipath wave according to a delay parameter, an amplitude parameter or an angle domain parameter in the channel parameter of each of the multipath wave by using the clustering algorithm to obtain the at least one cluster.