Search

US-12621692-B2 - Tracking user equipment dynamics in wireless networks

US12621692B2US 12621692 B2US12621692 B2US 12621692B2US-12621692-B2

Abstract

In some aspects, the techniques described herein relate to a method including: identifying a first base station (BS) that is out of service at a first time; identifying a first set of user equipment (UE) connected to the first BS in a pre-outage time window occurring before the first time; identifying a second set of UEs, the second set of UEs including UEs connected to other BSs in a wireless network; computing a set of seen UEs based on the second set of UEs and the first set of UEs; computing a set of unseen UEs based on the set of seen UEs and the first set of UEs; predicting a set of UEs that have left a service region that includes the first BS and the other BSs; computing a set of UEs without service based on the first set of UEs, the set of seen UEs, and the set of UEs that have left the service region; and generating a visualization of the set of UEs without service.

Inventors

  • Farid Khafizov
  • Muhammad IBRAHEEM

Assignees

  • VERIZON PATENT AND LICENSING INC.

Dates

Publication Date
20260505
Application Date
20230330

Claims (20)

  1. 1 . A method comprising: identifying a first base station (BS) that is out of service at a first time; identifying a first set of user equipment (UE) connected to the first BS in a pre-outage time window occurring before the first time; identifying a second set of UEs, the second set of UEs comprising UEs connected to other BSs in a wireless network in a post-outage time window after the first time; computing a set of seen UEs by computing intersections between the first set of UEs and the second set of UEs; computing a set of unseen UEs as a difference between the set of seen UEs and the first set of UEs; predicting a set of UEs that have left a service region that includes the first BS and the other BSs based on historical UE activity patterns; computing a set of UEs without service based on the first set of UEs, the set of seen UEs, and the set of UEs that have left the service region; and updating at least one operating parameter of a cellular network based on the set of UEs without service.
  2. 2 . The method of claim 1 , wherein identifying the first BS further comprises identifying an out-of-service cellular base station.
  3. 3 . The method of claim 1 , wherein identifying the first set of UEs connected to the first BS in a pre-outage time window further comprises querying a mobility manager for a set of UEs connected to the first BS in a time window preceding the first time.
  4. 4 . The method of claim 1 , wherein identifying the second set of UEs further comprises querying a mobility manager for sets of UEs connected to the other BSs in a time window after the first time.
  5. 5 . The method of claim 4 , wherein identifying the second set of UEs further comprises computing intersections between the sets of UEs connected to the other BSs in the time window with the first set of UEs.
  6. 6 . The method of claim 1 , wherein computing a set of seen UEs based on the second set of UEs and the first set of UEs comprises iterating through a plurality of time windows for each of the other UEs and combining sets of UEs associated with each combination of time window and other BS to form the set of seen UEs.
  7. 7 . The method of claim 1 , wherein computing a set of unseen UEs comprises computing a difference of the first set of UEs and the set of seen UEs.
  8. 8 . The method of claim 1 , wherein predicting a set of UEs that have left a service region including the first BS and the other BSs comprises predicting a size of the set of UEs based on historical UE activity with the first BS.
  9. 9 . The method of claim 1 , wherein computing a set of UEs without service comprises computing a difference of the first set of UEs, the set of seen UEs, and the set of UEs that have left the service region.
  10. 10 . The method of claim 1 , wherein generating a visualization of the set of UEs without service comprises generating one of a heat map or tabular display of the set of UEs without service.
  11. 11 . A non-transitory computer-readable storage medium for tangibly storing computer program instructions capable of being executed by a computer processor, the computer program instructions defining steps of: identifying a first base station (BS) that is out of service at a first time; identifying a first set of user equipment (UE) connected to the first BS in a pre-outage time window occurring before the first time; identifying a second set of UEs, the second set of UEs comprising UEs connected to other BSs in a wireless network in a post-outage time window after the first time; computing a set of seen UEs by computing intersections between the first set of UEs and the second set of UEs; computing a set of unseen UEs as a difference between the set of seen UEs and the first set of UEs; predicting a set of UEs that have left a service region that includes the first BS and the other BSs based on historical UE activity patterns; computing a set of UEs without service based on the first set of UEs, the set of seen UEs, and the set of UEs that have left the service region; and updating at least one operating parameter of a cellular network based on the set of UEs without service.
  12. 12 . The non-transitory computer-readable storage medium of claim 11 , wherein identifying the first set of UEs connected to the first BS in a pre-outage time window further comprises querying a mobility manager for a set of UEs connected to the first BS in a time window preceding the first time.
  13. 13 . The non-transitory computer-readable storage medium of claim 11 , wherein identifying the second set of UEs further comprises querying a mobility manager for sets of UEs connected to the other BSs in a time window after the first time.
  14. 14 . The non-transitory computer-readable storage medium of claim 11 , wherein computing a set of seen UEs based on the second set of UEs and the first set of UEs comprises iterating through a plurality of time windows for each of the other UEs and combining sets of UEs associated with each combination of time window and other BS to form the set of seen UEs.
  15. 15 . The non-transitory computer-readable storage medium of claim 11 , wherein computing a set of UEs without service comprises computing a difference of the first set of UEs, the set of seen UEs, and the set of UEs that have left the service region.
  16. 16 . A device comprising: a processor configured to: identify a first base station (BS) that is out of service at a first time; identify a first set of user equipment (UE) connected to the first BS in a pre-outage time window occurring before the first time; identify a second set of UEs, the second set of UEs comprising UEs connected to other BSs in a wireless network in a post-outage time window after the first time; compute a set of seen UEs by computing intersections between the first set of UEs and the second set of UEs; compute a set of unseen UEs as a difference between the set of seen UEs and the first set of UEs; predict a set of UEs that have left a service region that includes the first BS and the other BSs based on historical UE activity patterns; compute a set of UEs without service based on the first set of UEs, the set of seen UEs, and the set of UEs that have left the service region; and updating at least one operating parameter of a cellular network based on the set of UEs without service.
  17. 17 . The device of claim 16 , wherein identifying the first set of UEs connected to the first BS in a pre-outage time window further comprises querying a mobility manager for a set of UEs connected to the first BS in a time window preceding the first time.
  18. 18 . The device of claim 16 , wherein identifying the second set of UEs further comprises querying a mobility manager for sets of UEs connected to the other BSs in a time window after the first time.
  19. 19 . The device of claim 16 , wherein computing a set of seen UEs based on the second set of UEs and the first set of UEs comprises iterating through a plurality of time windows for each of the other UEs and combining sets of UEs associated with each combination of time window and other BS to form the set of seen UEs.
  20. 20 . The device of claim 16 , wherein computing a set of UEs without service comprises computing a difference of the first set of UEs, the set of seen UEs, and the set of UEs that have left the service region.

Description

BACKGROUND INFORMATION In wireless networks, computing devices communicate with base station (BS) devices. For example, in a cellular network, user equipment (UE) can communicate with a plurality of geographically distributed base stations. In such networks, the computing devices may be mobile and may thus communicate with multiple BSs over a given time window. As such, the distribution of computing devices can be highly dynamic and current approaches to monitoring this distribution generally fail to reliably identify the distribution. BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a block diagram illustrating a system for tracking UE dynamics. FIG. 2 is a flow diagram illustrating a method for identifying UEs that are without service within a geographic region. FIG. 3 is a flow diagram illustrating method for generating a heat map of UEs in a wireless network. FIG. 4 is a block diagram of a cellular network according to some embodiments. FIG. 5 is a block diagram illustrating a cellular network according to some embodiments. FIG. 6 is a block diagram illustrating a computing device showing an example of a client or server device used in the various embodiments of the disclosure. DETAILED DESCRIPTION The example embodiments solve technical problems in wireless networks by accurately reflecting the dynamic distribution of UEs in a wireless network. Current techniques for analyzing UEs in a wireless network generally includes statistical analyses of historical activity. For example, if a given UE has attached to a given BS consistently over a historical time horizon (e.g., the last three weeks), it can be predicted that for the current time horizon (e.g., the next week), the same UE will be attached to the given BS. If this prediction fails, current approaches will generally then manually search a wireless network to identify where a given UE is located. The example embodiments can generate a data structure representing the distribution of UEs which can then be used to optimize the wireless network. In some implementations, this data structure can represent how many UEs are distributed across the wireless network and how they are distributed. Further, in some implementations, the data structure can represent the presence or absence of UEs for each BS of the wireless network. The wireless network can use this data structure to improve the allocation of resources (both physical and virtual) and thus improve the overall functioning of the wireless network and its underlying computing devices. The disclosed embodiments describe methods as well as devices, systems, and computer-readable media for perform such methods. In some implementations, the method can include identifying a first base station (BS) that is out of service at a first time and then identifying a first set of user equipment (UE) connected to the first BS in a pre-outage time window that occurs before the first time. Next, the method can include identifying a second set of UEs that includes UEs connected to other BSs in a wireless network. Based on the second set of UEs and the first set of UEs the method then computes a set of seen UEs and then computes a set of unseen UEs based on the set of seen UEs and the first set of UEs. Next, the method predicts a set of UEs that have left a service region which includes the first BS and the other BSs and from this data (the first set of UEs, the set of seen UEs, and the set of UEs that have left the service region) computes a set of UEs without service. Finally, the method can include generating a visualization of the set of UEs without service and/or updating at least one operating parameter of a cellular network based on. In some implementations, the method can identify the first BS by identifying an out-of-service cellular base station. In some implementations, the the method can identify the first set of UEs connected to the first BS in a pre-outage time window by querying a mobility manager for a set of UEs connected to the first BS in a time window preceding the first time. In some implementations, the method can identify the second set of UEs by querying a mobility manager for sets of UEs connected to the other BSs in a time window after the first time. In some implementations, the method can identify the second set of UEs by computing intersections between the sets of UEs connected to the other BSs in the time window with the first set of UEs. In some implementations, the method can compute a set of seen UEs based on the second set of UEs and the first set of UEs by iterating through a plurality of time windows for each of the other UEs and combining sets of UEs associated with each combination of time window and other BS to form the set of seen UEs. In some implementations, the method can compute a set of unseen UEs by computing the difference of the first set of UEs and the set of seen UEs. In some implementations, the method can predict a set of UEs that have left a service region including the fir