US-12627571-B2 - Telecommunications infrastructure device cluster management using machine learning

Abstract

A method comprises receiving telecommunications infrastructure data corresponding to a plurality of devices, and determining a number of a plurality of clusters comprising respective subsets of the plurality of devices. The determination is based on at least a portion of the telecommunications infrastructure data and is performed using at least one machine learning algorithm. The plurality of clusters are identified and performance of respective ones of the plurality of clusters is predicted using the at least one machine learning algorithm. The method further comprises generating a report including the predicted performance of the respective ones of the plurality of clusters and causing transmission of the report to one or more user devices.

Inventors

• Nithish Kote
• Sajit Siddalingappa Manvi
• Nitin Khatkar

Assignees

• DELL PRODUCTS L.P.

Dates

Publication Date

20260512

Application Date

20240124

Claims (20)

1. 1 . A method, comprising: collecting telecommunications infrastructure data corresponding to a plurality of devices comprising baseband processing units of at least one telecommunications network, wherein the collected telecommunications infrastructure data comprises data that is indicative of current performance states of the baseband processing units; processing the collected telecommunications infrastructure data using a time series machine learning model to determine current and future performance states of the baseband processing units; processing at least a portion of the collected telecommunications infrastructure data and the determined current and future performance states of the baseband processing units using at least one machine learning algorithm to partition the plurality of devices comprising the baseband processing units into a plurality of clusters by: determining a number of clusters for partitioning the plurality of devices comprising the baseband processing units, using the at least one machine learning algorithm; identifying respective subsets of the plurality of devices comprising the baseband processing units to include in each cluster of the determined number of clusters, using the at least one machine learning algorithm; and predicting a performance of the clusters having the identified respective subsets of the plurality of devices comprising the baseband processing units, using the at least one machine learning algorithm; generating a report including a predicted performance level and a visualization of the predicted performance of the clusters; and causing transmission of the report to one or more user devices; wherein the steps of the method are executed by a processing device operatively coupled to a memory.
2. 2 . The method of claim 1 , wherein the at least one machine learning algorithm comprises a K-means clustering algorithm.
3. 3 . The method of claim 2 , wherein determining of the number of clusters for partitioning the plurality of devices comprising the baseband processing units comprises using an elbow curve method to determine a K value for the K-means clustering algorithm.
4. 4 . The method of claim 1 , further comprising selecting one or more parameters as the portion of the collected telecommunications infrastructure data, wherein the one or more parameters comprise at least one of central processing unit utilization, memory utilization, network utilization, server utilization, bandwidth, throughput, latency and a number of users of the telecommunications network.
5. 5 . The method of claim 4 , further comprising training the at least one machine learning algorithm based at least in part on the one or more parameters and the number of clusters.
6. 6 . The method of claim 1 , wherein the telecommunications infrastructure data comprises at least one of a time period, a number of users of the at least one telecommunications network, a service radius of the at least one telecommunications network, baseband processing unit identifiers, one or more protocols of the at least one telecommunications network, one or more types of the at least one telecommunications network, operating system information for the plurality of devices, Internet Protocol addresses for the plurality of devices and disk information for the plurality of devices.
7. 7 . The method of claim 1 , wherein the telecommunications infrastructure data comprises one or more performance parameters of the plurality of devices, the one or more performance parameters comprising at least one of central processing unit utilization, memory utilization, network utilization, storage utilization, throughput, bandwidth, latency and processing speed.
8. 8 . The method of claim 1 , wherein the plurality of devices comprise respective baseband unit servers which comprise the baseband processing units.
9. 9 . The method of claim 1 , wherein the time series machine learning model comprises an autoregressive integrated moving average time series machine learning model.
10. 10 . The method of claim 1 , wherein the data that is indicative of the current performance states of the baseband processing units comprises operating parameters that identify at least one of central processing unit utilization, memory utilization, network utilization and storage utilization of the plurality of devices.
11. 11 . The method of claim 1 , further comprising: dividing data corresponding to the current performance states into a training dataset and a testing dataset; training the at least one machine learning algorithm using at least the training dataset; and testing the at least one machine learning algorithm using at least the testing dataset.
12. 12 . The method of claim 1 , further comprising generating at least one visualization of the predicted performance of the clusters.
13. 13 . The method of claim 1 , wherein the clusters comprise a plurality of virtual machines.
14. 14 . An apparatus comprising: at least one processing device that is operatively coupled to a memory, wherein the memory stores program instructions that are executed by the at least one processing device to instantiate an engine which operates to: collect telecommunications infrastructure data corresponding to a plurality of devices comprising baseband processing units of at least one telecommunications network, wherein the collected telecommunications infrastructure data comprises data that is indicative of current performance states of the baseband processing units; process the collected telecommunications infrastructure data using a time series machine learning model to determine current and future performance states of the baseband processing units; process at least a portion of the collected telecommunications infrastructure data and the determined current and future performance states of the baseband processing units using at least one machine learning algorithm to partition the plurality of devices comprising the baseband processing units into a plurality of clusters by: determining a number of clusters for partitioning the plurality of devices comprising the baseband processing units, using the at least one machine learning algorithm; identifying respective subsets of the plurality of devices comprising the baseband processing units to include in each cluster of the determined number of clusters, using the at least one machine learning algorithm; and predicting a performance of the clusters having the identified respective subsets of the plurality of devices comprising the baseband processing units, using the at least one machine learning algorithm; generate a report including a predicted performance level and a visualization of the predicted performance of the clusters; and cause transmission of the report to one or more user devices.
15. 15 . The apparatus of claim 14 , wherein the time series machine learning model comprises an autoregressive integrated moving average time series machine learning model.
16. 16 . The apparatus of claim 14 , wherein the engine further operates to: divide data corresponding to the current performance states into a training dataset and a testing dataset; train the at least one machine learning algorithm using at least the training dataset; and test the at least one machine learning algorithm using at least the testing dataset.
17. 17 . An article of manufacture comprising a non-transitory processor- readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device causes said at least one processing device to perform the steps of: collecting telecommunications infrastructure data corresponding to a plurality of devices comprising baseband processing units of at least one telecommunications network, wherein the collected telecommunications infrastructure data comprises data that is indicative of current performance states of the baseband processing units; processing the collected telecommunications infrastructure data using a time series machine learning model to determine current and future performance states of the baseband processing units; processing at least a portion of the collected telecommunications infrastructure data and the determined current and future performance states of the baseband processing units using at least one machine learning algorithm to partition the plurality of devices comprising the baseband processing units into a plurality of clusters by: determining a number of clusters for partitioning the plurality of devices comprising the baseband processing units, using the at least one machine learning algorithm; identifying respective subsets of the plurality of devices comprising the baseband processing units to include in each cluster of the determined number of clusters, using the at least one machine learning algorithm; and predicting a performance of the clusters having the identified respective subsets of the plurality of devices comprising the baseband processing units, using the at least one machine learning algorithm; generating a report including a predicted performance level and a visualization of the predicted performance of the clusters; and causing transmission of the report to one or more user devices.
18. 18 . The article of manufacture of claim 17 , wherein the time series machine learning model performance states of respective ones of the plurality of devices comprises an autoregressive integrated moving average time series machine learning model.
19. 19 . The article of manufacture of claim 18 , wherein the program code further causes said at least one processing device to perform the steps of: dividing data corresponding to the current performance states into a training dataset and a testing dataset; training the at least one machine learning algorithm using at least the training dataset; and testing the at least one machine learning algorithm using at least the testing dataset.
20. 20 . The article of manufacture of claim 17 , where the at least a portion of the collected telecommunications infrastructure data comprises one or more parameters comprising at least one of central processing unit utilization, memory utilization, network utilization, server utilization, bandwidth, throughput, latency and a number of users of the at least one telecommunications network.

Description

COPYRIGHT NOTICE A portion of the disclosure of this patent document contains material which is subject to copyright protection. The copyright owner has no objection to the facsimile reproduction by anyone of the patent document or the patent disclosure, as it appears in the Patent and Trademark Office patent file or records, but otherwise reserves all copyright rights whatsoever. FIELD The field relates generally to information processing systems, and more particularly to management of telecommunications infrastructure device clusters. BACKGROUND Telecommunications stations (e.g., multi-cloud telecommunications stations) include various devices such as, for example, network switches and servers. In an area where there is a high concentration of telecommunications network users, such telecommunications stations can put high stress on the components that serve the telecommunications stations. In an effort to alleviate this stress, several servers may be connected to form a pool in a network. Current approaches are not able to identify circumstances under which clusters of servers can be formed. SUMMARY Illustrative embodiments provide techniques for automated management of telecommunications infrastructure device clusters. In one embodiment, a method comprises receiving telecommunications infrastructure data corresponding to a plurality of devices, and determining a number of a plurality of clusters comprising respective subsets of the plurality of devices. The determination is based on at least a portion of the telecommunications infrastructure data and is performed using at least one machine learning algorithm. The plurality of clusters are identified and performance of respective ones of the plurality of clusters is predicted using the at least one machine learning algorithm. The method further comprises generating a report including the predicted performance of the respective ones of the plurality of clusters and causing transmission of the report to one or more user devices. Further illustrative embodiments are provided in the form of a non-transitory computer-readable storage medium having embodied therein executable program code that when executed by a processor causes the processor to perform the above steps. Still further illustrative embodiments comprise an apparatus with a processor and a memory configured to perform the above steps. These and other features and advantages of embodiments described herein will become more apparent from the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 depicts details of an information processing system with a cluster management platform for managing telecommunications infrastructure device clusters, according to an illustrative embodiment. FIG. 2 depicts a cloud radio access network (C-RAN) network, according to an illustrative embodiment. FIG. 3 depicts an operational flow for cluster management, according to an illustrative embodiment. FIG. 4 depicts different types of data collected by a data collection and forecasting engine, according to an illustrative embodiment. FIG. 5 depicts example pseudocode for forecasting server utilization based on a number of user requests a base band processing unit (BBU) can process, according to an illustrative embodiment. FIG. 6 depicts a plot of a number of users versus server utilization for a plurality of clusters, according to an illustrative embodiment. FIG. 7 depicts details of machine learning algorithms for forecasting real-time data, identifying similar data usage patterns and characteristics of a network and its users and recommending corrective actions, according to an illustrative embodiment. FIG. 8 depicts an operational flow for optimizing server utilization, according to an illustrative embodiment. FIG. 9 depicts a process for managing telecommunications infrastructure device clusters, according to an illustrative embodiment. FIGS. 10 and 11 show examples of processing platforms that may be utilized to implement at least a portion of an information processing system in illustrative embodiments. DETAILED DESCRIPTION Illustrative embodiments will be described herein with reference to exemplary information processing systems and associated computers, servers, storage devices and other processing devices. It is to be appreciated, however, that embodiments are not restricted to use with the particular illustrative system and device configurations shown. Accordingly, the term “information processing system” as used herein is intended to be broadly construed, so as to encompass, for example, processing systems comprising cloud computing and storage systems, as well as other types of processing systems comprising various combinations of physical and virtual processing resources. An information processing system may therefore comprise, for example, at least one data center or other type of cloud-based system that includes one or more clouds hosting tenants that acces