Handling beam pairs in a wireless network
A method performed by a first radio node for handling a beam pair with a second radio node is provided. The first radio node receives a first information from one or more other radio nodes. The first information comprises a number of quality values related to a number of beam pairs. The first radio node predicts a time to failure for a first beam pair. The first radio node then decides whether or not there is enough time until the predicted time to failure, for performing a beam pair switch from the first beam pair to a second beam pair. When there is enough time, the first radio node switches to the second beam pair before the predicted time to failure. When there is not enough time, the first radio node prepares an upcoming beam pair failure.
1. A method for handling a beam pair between a first radio node and a second radio node, which first radio node, the second radio node and one or more other radio nodes operate in a wireless communication network, the method comprising:
receiving a first information from respective one or more other radio nodes, which first information comprises a number of quality values related to a number of beam pairs, each beam pair out of the number of beam pairs being associated to at least one quality value out of the number of quality values;
predicting a time to failure for a first beam pair between the first radio node and the second radio node, which first beam pair has a first quality value, the predicting being based on the first quality value and the number of quality values; and
deciding whether there is enough time until the predicted time to failure, for performing a beam pair switch from the first beam pair to a second beam pair between the first radio node and the second radio node;
when there is enough time, switching to the second beam pair before the predicted time to failure;
when there is not enough time, preparing an upcoming beam pair failure;
training a training model by inputting the number of quality values related to the number of beam pairs, and obtaining the time to failure for the respective beam pair out of the number of beam pairs; and
predicting the time to failure for the first beam pair further based on the first quality value, and the trained training model.
2. The method according to claim 1 , further comprising:
updating the training model based on an accuracy of the predicted time to failure for the first beam pair.
3. The method according to claim 1 , wherein the method further comprises:
when there is enough time, sending a beam indication to the second radio node for establishing the second beam pair, before switching to the second beam pair.
4. The method according to claim 1 , the method further comprising:
after switching to the second beam pair, receiving an indication, indicating whether the switching to the second beam pair is acknowledged; and
when indicating is not acknowledged, updating the training model based on an accuracy of the prediction comprises updating the training model according to the indication; and
when indicating is acknowledged, receiving a second information from the second radio node, which second information comprises a number of quality values related to a number of beam pairs, wherein each beam pair out of the number of beam pairs is associated to at least one quality value out of the number of quality values.
5. The method according to claim 1 , wherein there is not enough time, and when a decision is obtained that the predicted time to failure for the first beam pair was not correct, the updating of the training model based on an accuracy of the prediction comprises updating the training model according to the obtained decision.
6. The method according to claim 1 , wherein the method is performed by anyone of: a network node, a wireless communication device, and a cloud.
7. A non-transitory computer storage medium storing a computer program comprising instructions, which when executed by a processor, cause the processor to:
receive a first information from respective one or more other radio nodes, which first information comprises a number of quality values related to a number of beam pairs, each beam pair out of the number of beam pairs being configured to associate to at least one quality value out of the number of quality values;
predict a time to failure for a first beam pair between the first radio node and the second radio node, which first beam pair is adapted to have a first quality value, the predicting being configured to be based on the first quality value and the number of quality values;
decide whether there is enough time until the predicted time to failure for performing a beam pair switch from the first beam pair to a second beam pair between the first radio node and the second radio node;
when there is enough time, switch to the second beam pair before the predicted time to failure;
when there is not enough time, prepare an upcoming beam pair failure;
train a training model by inputting the number of quality values related to the number of beam pairs, and obtaining the time to failure for the respective beam pair out of the number of beam pairs; and
predict the time to failure for the first beam pair further based on the first quality value, and the trained training model.
8. A first radio node for handling a beam pair with a second radio node, which first radio node, second radio node and one or more other radio nodes are operable in a wireless communications network, the first radio node being configured to:
receive a first information from respective one or more other radio nodes, which first information comprises a number of quality values related to a number of beam pairs, each beam pair out of the number of beam pairs is configured to associate to at least one quality value out of the number of quality values;
predict a time to failure for a first beam pair between the first radio node and the second radio node, which first beam pair is adapted to have a first quality value, the predicting is configured to be based on the first quality value and the number of quality values;
decide whether there is enough time until the predicted time to failure for performing a beam pair switch from the first beam pair to a second beam pair between the first radio node and the second radio node;
when there is enough time, switch to the second beam pair before the predicted time to failure;
when there is not enough time, prepare an upcoming beam pair failure;
train a training model by inputting the number of quality values related to the number of beam pairs, and obtaining the time to failure for the respective beam pair out of the number of beam pairs; and
predict the time to failure for the first beam pair further based on the first quality value, and the trained training model.
9. The first radio node according to claim 8 , further configured to update the training model based on an accuracy of the predicted time to failure for the first beam pair.
10. The first radio node according to claim 8 , further configured to:
when there is enough time, send a beam indication to the second radio node for establishing the second beam pair, before switching to the second beam pair.
11. The first radio node according to claim 8 , further configured to:
after switching to the second beam pair, receive an indication, indicating whether the switching to the second beam pair is acknowledged;
when indicating is not acknowledged, update the training model based on an accuracy of the prediction by updating the training model according to the indication; and
when indicating is acknowledged, receive a second information from the second radio node, which second information is configured to comprise a number of quality values related to a number of beam pairs, and wherein each beam pair out of the number of beam pairs is configured to be associated to at least one quality value out of the number of quality values.
12. The first radio node according to claim 8 , further configured to:
when there is not enough time, and when a decision is obtained that the predicted time to failure for the first beam pair was not correct, update the training model is based on an accuracy of the prediction by updating the training model according to the decision.
13. The first radio node according to claim 8 , wherein the first radio node is anyone of: a network node, a wireless communication device, and a cloud.
14. The method according to claim 1 , further comprising:
updating the training model based on an accuracy of the predicted time to failure for the first beam pair.
15. The method according to claim 1 , the method further comprising:
when there is enough time, sending a beam indication to the second radio node for establishing the second beam pair, before switching to the second beam pair.
16. The method according to claim 1 , the method further comprising:
after switching to the second beam pair, receiving an indication, indicating whether the switching to the second beam pair is acknowledged; and
when indicating is not acknowledged, updating the training model based on an accuracy of the prediction comprises updating the training model according to the indication; and
when indicating is acknowledged, receiving a second information from the second radio node, which second information comprises a number of quality values related to a number of beam pairs, wherein each beam pair out of the number of beam pairs is associated to at least one quality value out of the number of quality values.
17. The method according to claim 1 , wherein there is not enough time, and when a decision is obtained that the predicted time to failure for the first beam pair was not correct, the updating of the training model based on an accuracy of the prediction comprises updating the training model according to the obtained decision.
18. The method according to claim 1 , wherein the method is performed by anyone of: a network node, a wireless communication device, and a cloud.