Method and device for controlling an autonomous device

1. A method for controlling an autonomous device of a cellular network, the method being performed by a network device and comprising the steps of:

predicting a need to increase coverage of said cellular network or a need to increase capacity of said cellular network, comprising the steps of:

inputting live data features into a trained classifier; and

outputting a launch class from said classifier;

activating an autonomous device of said cellular network, to improve said cellular network, wherein said step of activating comprises initiating a physical move of said autonomous device from a first idle location to a second active location; and

enabling a wireless communication device to be connected to said cellular network through said autonomous device.

2. The method according to claim 1 , wherein said autonomous device is outside high data capacity coverage of said cellular network in said first idle location and is connectable to said cellular network in said second active location with high data capacity.

3. The method according to claim 1 , wherein said step of activating comprises signalling said autonomous device over a low data capacity protocol.

4. The method according to claim 1 , wherein said live data features comprise one or more of the following: signal strength, location, wireless communication device activation, performance measurement, and configuration measurement.

5. The method according to claim 1 , wherein said classifier is a Support Vector Machine, a decision tree, a neural network or a Bayesian network.

6. The method according to claim 1 , wherein said step of predicting comprises utilization of a time series forecasting.

7. The method according to claim 1 , comprising the further step of determining, wherein the step of determining comprises detecting one or more of the following: application use, scheduled event, user action on said wireless communication device, and measurements in said wireless communication device.

8. The method according to claim 1 , comprising the further step of:

deactivating said autonomous device.

9. The method according to claim 1 , comprising the further steps of:

collecting use data of said wireless communication device;

storing said use data; and

identifying a use pattern from the stored use data.

10. A network device for a cellular network, said network device arranged to control an autonomous device of the network device comprising:

a processor; and

a computer program product storing instructions that, when executed by the processor, causes the network device to:

predict a need to increase coverage of said cellular network or a need to increase capacity of said cellular network, comprising:

input live data features into a trained classifier; and

output a launch class from said classifier;

activate an autonomous device of said cellular network, to improve said cellular network, wherein said instruction to activate comprises the instruction to initiating a physical move of said autonomous device from a first idle location to a second active location; and

enable a wireless communication device to be connected to said cellular network through said autonomous device.

11. The network device according to claim 10 , wherein said autonomous device is outside high data capacity coverage of said cellular network in said first idle location and is connectable to said cellular network in said second active location with high data capacity.

12. The network device according to claim 10 , wherein said instruction to activate comprises an instruction to signal said autonomous device over a low data capacity protocol.

13. The network device according to claim 10 , wherein said live data features comprise one or more of the following: signal strength, location, wireless communication device activation, performance measurement, and configuration measurement.

14. The network device according to claim 10 , wherein said classifier is a Support Vector Machine, a decision tree, a neural network or a Bayesian network.

15. The network device according to claim 14 , wherein said instruction to predict comprises an instruction to utilize a time series forecasting.

16. The network device according to claim 10 , wherein said instruction to predict comprises instruction to detecting one or more of the following: application use, scheduled event, user action on said wireless communication device, and measurements in said wireless communication device.

17. The network device according to claim 10 , wherein said instructions comprise the further instruction to:

deactivate said autonomous device.

18. The network device according to claim 10 , wherein said instructions comprise the further instructions to:

collect use data of said wireless communication device;

store said use data; and

identify a use pattern from the stored use data.

19. A computer program product comprising a computer program and a computer readable storage memory on which the computer program is stored, wherein the computer program comprises computer program code which, when run on a network device for a cellular network, causes the network device to:

predict a need to increase coverage of said cellular network or a need to increase capacity of said cellular network, comprising:

input live data features into a trained classifier; and

output a launch class from said classifier;

activate an autonomous device of said cellular network, to improve said cellular network, by initiating a physical move of said autonomous device from a first idle location to a second active location; and

enable a wireless communication device to be connected to said cellular network through said autonomous device.