Movement control device, communication system, movement control method, and computer program

Abstract

To provide a movement control device capable of quickly and efficiently controlling handover of a user terminal moving together with a moving body.SOLUTION: A movement control device 27 includes: a state observation unit 35 that generates observation data having a binary sequence representing a state of whether or not each of user terminals 11n is located in a cell of any of base stations 201 to 20K; a clustering unit 36 that classifies the observation data into one of a plurality of clusters based on a mixed probability distribution having a maximum likelihood parameter estimated through machine learning; and an allocation unit 37 that generates handover data indicating correspondence relations between identifiers of the user terminals 111 to 11N and the base stations that are respective next handover destinations by allocating the base stations that are the respective next handover destinations associated with the clusters into which the observation data is classified to the identifiers of the user terminals 11n.SELECTED DRAWING: Figure 1

Claims

1. A mobile control device in a mobile communication system including a plurality of base stations capable of wireless communication with a plurality of user terminals, a state observation unit that generates observation data having a binary sequence representing a state of whether each of the plurality of user terminals is present in a cell of any of the plurality of base stations; a clustering unit that classifies the observation data into one of a plurality of clusters based on a mixture probability distribution having a maximum likelihood parameter estimated by machine learning; an allocation unit that generates handover data indicating a correspondence relationship between identifiers of the plurality of user terminals and base stations that are next handover destinations by allocating a base station that is a next handover destination and that is associated with the cluster into which the observation data is classified, among the plurality of base stations, to an identifier of the user terminal; A mobile control device comprising:

2. The mobile control device according to claim 1 , wherein the mixed probability distribution is a mixed Bernoulli distribution.

3. The mobile control device according to claim 1 , wherein the machine learning includes maximum likelihood estimation using an Expectation-Maximization (EM) algorithm.

4. The movement control device according to claim 1 , the state observation unit is configured to estimate a moving direction in which the user terminal moves, among a plurality of predetermined moving directions, by using a series of timestamps indicating a time when each of the user terminals is present in a cell of the base station; The movement control device, wherein the clustering unit is configured to classify the observation data into clusters for each of the plurality of movement directions.

5. The movement control device according to claim 4, the plurality of base stations are arranged along an up-track and a down-track of a railway line; A mobility control device, wherein the multiple movement directions include the up line direction and the down line direction.

6. 5. The mobile control device according to claim 4, wherein the handover data is data indicating a correspondence relationship between identifiers of the plurality of user terminals, a base station that is a next handover destination, and a moving direction of the user terminal.

7. A mobile control device according to any one of claims 1 to 6, a communication device that performs handover control using handover data supplied from the mobile control device; A communication system comprising:

8. A mobility control method executed in a mobile communication system including a plurality of base stations capable of wireless communication with a plurality of user terminals, comprising: generating observation data having a binary sequence representing a state of whether each of the plurality of user terminals is present in a cell of any one of the plurality of base stations; classifying the observed data into one of a plurality of clusters based on a mixture probability distribution having a maximum likelihood parameter estimated by machine learning; a step of generating handover data indicating a correspondence relationship between identifiers of the plurality of user terminals and base stations that are next handover destinations by assigning, to an identifier of the user terminal, a base station that is a next handover destination and that is associated with the cluster into which the observation data has been classified, among the plurality of base stations; A movement control method comprising:

9. The method of claim 8 , wherein the mixed probability distribution is a mixed Bernoulli distribution.

10. The mobility control method according to claim 8 , wherein the machine learning includes maximum likelihood estimation using an Expectation-Maximization (EM) algorithm.

11. The movement control method according to claim 8, The method further comprises estimating a moving direction in which each of the user terminals moves, among a plurality of predetermined moving directions, using a timestamp sequence indicating a time when each of the user terminals is present in a cell of the base station; The movement control method, wherein the observation data is classified into clusters for each of the plurality of movement directions.

12. 12. The mobility control method according to claim 11, wherein the handover data is data indicating a correspondence between identifiers of the plurality of user terminals, a base station that is a next handover destination, and a moving direction of the user terminal.

13. 9. The mobility control method according to claim 8, further comprising the step of performing handover control using handover data supplied from the mobility control device.

14. A computer program for at least one device with one or more processors, configured to, when executed by said one or more processors, cause said at least one device to implement a method for controlling mobility according to any one of claims 8 to 13.

Images