IP Library › Granted Patent US 12,737,432
Granted Patent B2
US 12,737,432 · App. 18/512,126 · Granted Sep 15, 2026

Hypothetical configuration analysis

Inventors: Mary Diane Swift (Rochester, NY); Irene Lizeth Manotas Gutiérrez (White Plains, NY); Jonathan D. Dunne (Dungarvan, IE)
Assignee: International Business Machines Corporation
G06F17/18
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,737,432
App. No.
18/512,126
Granted
Sep 15, 2026
Kind
B2
Abstract

An embodiment for dynamically tuning system configuration settings across multiple systems using hypothetical configuration analysis. The embodiment may gather input data for a target system, the input data including configuration settings data, a series of configuration setting parameters, and telemetry data. The embodiment may generate, from the input data, a machine learning model configured to process network data and the configuration settings data from the target system. The embodiment may determine dependencies between a given parameter from the series of configuration setting parameters and a given resource from a series of resources using the generated machine learning model. The embodiment may further predict, using the generated machine learning model, and based on the determined dependencies, performance outcomes under a tuneable range of the series of configuration setting parameters. The embodiment may generalize the generated machine learning model across a plurality of secondary systems.

Claims (52)

1 . A computer-based method for dynamically tuning system configuration settings across multiple systems using hypothetical configuration analysis, the method comprising:

gathering input data for a target system, the input data including configuration settings data, a series of configuration setting parameters, and telemetry data;

leveraging analysis of variance (ANOVA) techniques to determine if the telemetry data may be drawn from a same population;

generating, from the input data, a machine learning model configured to process network data and the configuration settings data from the target system;

determining dependencies between a given parameter from the series of configuration setting parameters and a given resource from a series of resources using the generated machine learning model;

predicting, using the generated machine learning model, and based on the determined dependencies, performance outcomes under a tuneable range of the series of configuration setting parameters; and

generalizing the generated machine learning model across a plurality of secondary systems.

2 . The computer-based method of claim 1 , further comprising:

performing entity analysis on the gathered input data to determine a proportion of setting types.

3 . The computer-based method of claim 1 , further comprising:

storing the chat history, using a chatbot backend server, within a storage component.

4 . The computer-based method of claim 1 , further comprising:

performing statistical computations on the gathered input data to determine preliminary dependencies between the configuration setting parameters on the telemetry data.

5 . The computer-based method of claim 1 , wherein determining dependencies between a given parameter from the series of configuration setting parameters and a given resource from a series of resources using the generated machine learning model further comprises:

calculating a score reflecting the dependency between the given parameter and the given resource; and

normalizing the calculated score.

6 . The computer-based method of claim 1 , further comprising:

outputting the predicted performance outcomes to a user via a user interface.

7 . A computer system, the computer system comprising:

one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions stored on at least one of the one or more computer-readable tangible storage medium for execution by at least one of the one or more processors via at least one of the one or more computer-readable memories, wherein the computer system is capable of performing a method comprising:

gathering input data for a target system, the input data including configuration settings data, a series of configuration setting parameters, and telemetry data;

leveraging analysis of variance (ANOVA) techniques to determine if the telemetry data may be drawn from a same population;

generating, from the input data, a machine learning model configured to process network data and the configuration settings data from the target system;

determining dependencies between a given parameter from the series of configuration setting parameters and a given resource from a series of resources using the generated machine learning model;

predicting, using the generated machine learning model, and based on the determined dependencies, performance outcomes under a tuneable range of the series of configuration setting parameters; and

generalizing the machine learning model across a plurality of secondary systems.

8 . The computer system of claim 7 , performing entity analysis on the gathered input data to determine a proportion of setting types.

9 . The computer system of claim 7 , further comprising:

storing the chat history, using a chatbot backend server, within a storage component.

10 . The computer system of claim 7 , further comprising:

performing statistical computations on the gathered input data to determine preliminary dependencies between the configuration setting parameters on the telemetry data.

11 . The computer system of claim 7 , wherein determining dependencies between a given parameter from the series of configuration setting parameters and a given resource from a series of resources using the generated machine learning model further comprises:

calculating a score reflecting the dependency between the given parameter and the given resource; and

normalizing the calculated score.

12 . The computer system of claim 7 , further comprising:

outputting the predicted performance outcomes to a user via a user interface.

13 . A computer program product, the computer program product comprising:

one or more computer-readable tangible storage medium and program instructions stored on at least one of the one or more computer-readable tangible storage medium, the program instructions executable by a processor capable of performing a method, the method comprising:

gathering input data for a target system, the input data including configuration settings data, a series of configuration setting parameters, and telemetry data;

leveraging analysis of variance (ANOVA) techniques to determine if the telemetry data may be drawn from a same population;

generating, from the input data, a machine learning model configured to process network data and the configuration settings data from the target system;

determining dependencies between a given parameter from the series of configuration setting parameters and a given resource from a series of resources using the generated machine learning model;

predicting, using the generated machine learning model, and based on the determined dependencies, performance outcomes under a tuneable range of the series of configuration setting parameters; and

generalizing the machine learning model across a plurality of secondary systems.

14 . The computer program product of claim 13 , performing entity analysis on the gathered input data to determine a proportion of setting types.

15 . The computer program product of claim 13 , further comprising:

storing the chat history, using a chatbot backend server, within a storage component.

16 . The computer program product of claim 13 , further comprising:

performing statistical computations on the gathered input data to determine preliminary dependencies between the configuration setting parameters on the telemetry data.

17 . The computer program product of claim 16 , wherein determining dependencies between a given parameter from the series of configuration setting parameters and a given resource from a series of resources using the generated machine learning model further comprises:

calculating a score reflecting the dependency between the given parameter and the given resource; and

normalizing the calculated score.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 17, 2023
From: SWIFT, MARY DIANE; MANOTAS GUTIÉRREZ, IRENE LIZETH; DUNNE, JONATHAN D.
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 065593/0697 →
Continuity (1)
Related Publication 20250165557A1 · May 22, 2025
References Cited (30)
US 7596518B2 · Rappaport · 2009 [cited by examiner]
US 8296424B2 · Malloy · 2012 [cited by examiner]
US 8315960B2 · Chen · 2012 [cited by examiner]
US 8494806B2 · Kato · 2013 [cited by examiner]
US 9448832B2 · Du · 2016 [cited by examiner]
US 11544582B2 · Suryakantha · 2023 [cited by examiner]
US 11809966B2 · Chen · 2023 [cited by examiner]
US 20040243548A1 · Hulten · 2004 [cited by examiner]
US 20090183028A1 · Arnold · 2009 [cited by examiner]
US 20090204561A1 · Sabato · 2009 [cited by examiner]
US 20100131440A1 · Chen · 2010 [cited by examiner]
US 20120310618A1 · B'Far · 2012 [cited by examiner]
US 20120310870A1 · Caves · 2012 [cited by examiner]
US 20140156557A1 · Zeng · 2014 [cited by examiner]
US 20140330536A1 · Chen · 2014 [cited by examiner]
US 20160380908A1 · Larsson · 2016 [cited by examiner]
US 20200073788A1 · Saha · 2020 [cited by examiner]
US 20200356838A1 · Selvakumar · 2020 [cited by examiner]
US 20210012239A1 · Arzani · 2021 [cited by examiner]
US 20210065033A1 · Kunde · 2021 [cited by examiner]
US 20220207388A1 · Thakkar · 2022 [cited by examiner]
US 20220215013A1 · Mercier · 2022 [cited by examiner]
US 20240265273A1 · Sun · 2024 [cited by examiner]
US 20250094299A1 · Rajagopal · 2025 [cited by examiner]
Akhtar, “An overview of some network modeling, simulation and performance analysis tools.” IEEE Xplore, 1997, pp. 344-348. [cited by applicant]
Hsu et al. “Performance of mobile ad hoc networking routing protocols in realistic scenarios.” IEEE Xplore, Nov. 2003, 7 Pages. https://www.researchgate.net/publication/4070829_Performance_of_mobile_ad_hoc_networking_ro… [cited by applicant]
Siraj, et al., “Network Simulation Tools Survey”, International Journal of Advanced Research in Computer and Communication Engineering, vol. 1, Issue 4, Jun. 2012, 10 Pages. [cited by applicant]
Soles et al., “Creating a cost-effective air-to-ground network simulation environment.” Proceedings of the IEEE SoutheastCon 2015, Apr. 9-12, 2015, 5 Pages. [cited by applicant]
Wang, et al., “Efficient Network Security Policy Enforcement With Policy Space Analysis”, IEEE/ACM Transactions on Networking, vol. 24., No. 5, Oct. 2016, pp. 2926-2938. [cited by applicant]
Zhao, et al., “Performance of Container Networking Technologies”, Proceedings of HotConNet'17, Aug. 25, 2017, 6 pages. [cited by applicant]