Search

US-12627554-B2 - Management data analytics

US12627554B2US 12627554 B2US12627554 B2US 12627554B2US-12627554-B2

Abstract

Disclosed embodiments are related to Management Data Analytics (MDA) relation with Self-Organizing Network (SON) functions and coverage issues analysis use case. An MDA Service (MDAS) obtains input data related to one or more managed networks and services from one or more data sources; generates an analytics report based on analysis of the input data; and sends an analytics report to a Self-Organizing Network (SON) function for root cause analysis of ongoing issues, prevention of potential issues, and/or prediction of network or service demands. The analytics report may describe an identified network or cell coverage issue related to the SON function. Other embodiments may be described and/or claimed.

Inventors

  • Yizhi Yao
  • Joey Chou

Assignees

  • INTEL CORPORATION

Dates

Publication Date
20260512
Application Date
20240215

Claims (19)

  1. 1 . An apparatus to be employed as a Management Data Analytics Service (MDAS) producer, wherein the apparatus comprises: memory circuitry; and processor circuitry communicatively coupled with the memory circuitry, wherein the processor circuitry configures the MDAS producer to: identify analytics data related to coverage of a cellular network with which the MDAS producer is associated; identify, based on the analytics data, a problem related to the coverage of the cellular network; determine a root cause of the problem; determine a recommended action to take to mitigate the root cause of the problem; generate an analytics report related to the problem, the analytics report containing the recommended action, an indication of a type of the problem, a start time and a stop time of the problem, a severity level of the problem, an indication of whether the problem exists in 5G only or in all radio access technologies, an identification of cells affected by the problem, the root cause of the problem, and an indication of a geographical area of the problem; and transmit, to a MDAS consumer, the analytics report for the MDAS consumer to take the recommended action.
  2. 2 . The apparatus of claim 1 , wherein the analytics report is generated based at least in part on a machine learning (ML) model.
  3. 3 . The apparatus of claim 1 , wherein the analytics data is related to a minimization of drive test (MDT) report that is related to reference signal received power (RSRP) measurements of a serving cell and neighbor cells of the cellular network.
  4. 4 . The apparatus of claim 1 , wherein the analytics data is related to a geographical area of a radio access network (RAN) of the cellular network.
  5. 5 . One or more non-transitory computer-readable media (NTCRM) comprising instructions that, upon execution of the instructions by one or more processors of an electronic device, are to cause a Management Data Analytics Service (MDAS) producer to: identify analytics data related to coverage of a cellular network with which the MDAS producer is associated; identify, based on the analytics data, a problem related to the coverage of the cellular network; determine a root cause of the problem; determine a recommended action to take to mitigate the root cause of the problem; generate an analytics report related to the problem, the analytics report containing the recommended action, an indication of a type of the problem, a start time and a stop time of the problem, a severity level of the problem, an indication of whether the problem exists in 5G only or in all radio access technologies, an identification of cells affected by the problem, the root cause of the problem, and an indication of a geographical area of the problem; and transmit, to a MDAS consumer, the analytics report for the MDAS consumer to take the recommended action.
  6. 6 . The one or more NTCRM of claim 5 , wherein the analytics report is generated based at least in part on a machine learning (ML) model.
  7. 7 . The one or more NTCRM of claim 5 , wherein the analytics data is related to a minimization of drive test (MDT) report that is related to reference signal received power (RSRP) measurements of a serving cell and neighbor cells of the cellular network.
  8. 8 . The one or more NTCRM of claim 5 , wherein the analytics data is related to a geographical area of a radio access network (RAN) of the cellular network.
  9. 9 . An apparatus to be employed as a Management Data Analytics Service (MDAS) consumer, wherein the apparatus comprises: memory circuitry to store an analytics report, received from a MDAS producer, related to a coverage problem of a cellular network associated with the MDAS consumer the analytics report based on analytics data related to the coverage problem, and including an indication of a recommended action to be taken to remedy a root cause of the coverage problem, an indication of a type of the coverage problem, a start time and a stop time of the coverage problem, a severity level of the coverage problem, an indication of whether the coverage problem exists in 5G only or in all radio access technologies, an identification of cells affected by the coverage problem, the root cause of the coverage problem, and an indication of a geographical area of the coverage problem; and processor circuitry communicatively coupled with the memory circuitry, wherein the processor circuitry is configured perform the recommended action.
  10. 10 . The apparatus of claim 9 , wherein the analytics report is generated based at least in part on a machine learning (ML) model.
  11. 11 . The apparatus of claim 9 , wherein the analytics data is related to a minimization of drive test (MDT) report that is related to reference signal received power (RSRP) measurements of a serving cell and neighbor cells of the cellular network.
  12. 12 . The apparatus of claim 9 , wherein the analytics data is related to a geographical area of a radio access network (RAN) of the cellular network.
  13. 13 . The apparatus of claim 1 , wherein the processor circuitry is configured to identify a plurality of problems based on the analytics data and determine the root cause as a basis for the plurality of problems and the recommended action to take to mitigate the root cause of the plurality of problems.
  14. 14 . The apparatus of claim 1 , wherein the severity level of the problem is selected from a group that includes critical severity level, at least one non-critical severity level, and cleared.
  15. 15 . The apparatus of claim 1 , wherein the type of the problem is selected from a group of problems that include weak coverage, coverage hole, pilot pollution, overshoot coverage, and downlink/uplink channel coverage mismatch.
  16. 16 . The apparatus of claim 1 , wherein the processor circuitry is further configured to receive, from the MDAS consumer, execution reports describing actions taken in response to the analytics report, and to update subsequent analytics reports based at least in part on the execution reports.
  17. 17 . The apparatus of claim 1 , wherein the analytics report further includes an indication of a confidence level associated with the problem.
  18. 18 . The apparatus of claim 1 , wherein the analytics report includes information describing ongoing coverage problems and predicted potential coverage problems.
  19. 19 . The apparatus of claim 1 , wherein the analytics report further includes an identifier of the problem.

Description

CROSS REFERENCE TO RELATED APPLICATION The present application is a continuation of U.S. application Ser. No. 17/062,006 filed Oct. 2, 2020, which claims priority to U.S. Provisional App. No. 62/910,053 filed Oct. 3, 2019, the contents of each of which are hereby incorporated by reference in their entireties. FIELD Embodiments relate generally to the technical field of wireless communications and communication networks, and in particular to Management Data Analytics (MDA) in relation to coverage issue analysis for self-organizing networks (SON). BACKGROUND Fifth Generation (5G) networks have the capability to support a variety of communication services, such as Internet of Things (IOT) and Enhanced Mobile Broadband (eMBB). The increasing flexibility of the networks to support services with diverse requirements may present operational and management challenges. Therefore, 5G networks management system can benefit from Management Data Analytics (MDA) for improving networks performance and efficiency to accommodate and support the diversity of services and requirements. BRIEF DESCRIPTION OF THE DRAWINGS Embodiments will be readily understood by the following detailed description in conjunction with the accompanying drawings. To facilitate this description, like reference numerals designate like structural elements. Embodiments are illustrated by way of example and not by way of limitation in the figures of the accompanying drawings. FIG. 1 illustrates functionality provided by a Management Data Analytics (MDA), according to various embodiments. FIG. 2 illustrates analytics in a management loop, according to various embodiments. FIG. 3 illustrates an example of coordination between a Network Data Analytics Function (NWDAF), next generation NodeB (gNB), and a Management Data Analytics Service (MDAS) producer for data analytics, according to various embodiments. FIG. 4 illustrates an example of coordination between NWDAF, gNB and MDAS producer for data analytics, according to various embodiments. FIGS. 5 and 6 illustrate example MDA processes according to various embodiments. FIG. 7 illustrates an example MDAS and Self-Organizing Network (SON) functions. FIG. 8 illustrates an example relation between MDA and SON according to various embodiments. FIG. 9 illustrates an example network architecture according to various embodiments. FIGS. 10 and 11 illustrate example core network architectures according to various embodiments. FIG. 12 illustrates an example of infrastructure equipment in accordance with various embodiments. FIG. 13 schematically illustrates a wireless network in accordance with various embodiments. FIG. 14 illustrates components able to read instructions from a machine-readable or computer-readable medium (e.g., a non-transitory machine-readable storage medium) and perform any of the methodologies discussed herein. FIG. 15 illustrates an example management architecture of mobile networks that include virtualized network functions. FIG. 16 illustrates another example of a management services architecture. FIG. 17 illustrates an example procedure for practicing various embodiments discussed herein. DETAILED DESCRIPTION 5G networks have the capability to support a variety of communication services, such as IoT and eMBB. The increasing flexibility of the networks to support services with diverse requirements may present operational and management challenges. 5G networks management system can therefore benefit from Management Data Analytics (MDA) for improving networks performance and efficiency to accommodate and support the diversity of services and requirements. MDA Service(s) (MDAS) can potentially be consumed by various Management Functions (MFs) (e.g., Management Service (MnS) producers/consumers) and Network Functions (NFs) including, for example, Network Data Analytics Function (NWDAF), Self-Organizing Network (SON) functionalities, Network Function Management Function (NFMF), Communication Service Management Function (CSMF), etc. However, the MDA has not yet been completely specified, for example, it is still unclear what and how MDAS is provided and/or consumed. According to 3GPP TS 28.550 (“[1]”), MDA can be performed to diagnose ongoing issues impacting the performance of the mobile network and predict any potential issues (e.g., potential failure and/or performance degradation). For diagnosis of network issues, the root cause(s) need to be figured out precisely. One network issue may result in multiple symptoms, such as alarms, performance degradation, user complaints, etc., and the MDAS can analyse these symptoms and provide (or be part of process of providing, such as SON) the precise root cause indication to the consumer. For instance, repeated coverage holes and interference spots in the radio coverage of a network may result in low data throughput, high packet loss rate, high power consumption and potentially leading to RRC connection setup failures affecting the quality of end user expe