Exponential decay real-time capacity planning

Patent metadata

Field	Value
Publication number	US-11748230-B2
Application number	US-202117325602-A
Country	US
Kind code	B2
Filing date	May 20, 2021
Priority date	May 22, 2019
Publication date	Sep 5, 2023
Grant date	Sep 5, 2023

Abstract

Various examples are disclosed for transitioning usage forecasting in a computing environment. Usage of computing resources of a computing environment are forecasted using a first forecasting data model and usage measurements obtained from the computing resources. A use of the first forecasting data model in forecasting the usage is transitioned to a second forecasting data model without incurring downtime in the computing environment. After the transition, the usage of the computing resources of the computing environment is forecasted using the second forecasting data model and the usage measurements obtained from the computing resources. The second forecasting data model exponentially decays the usage measurements based on a respective time period at which the usage measurements were obtained.

First claim

Therefore, the following is claimed:

1. A system for transitioning usage forecasting in a computing environment, comprising:
at least one computing device comprising at least one hardware processor; and
program instructions stored in memory and executable in the at least one computing device that, when executed, direct the at least one computing device to:
forecast usage of a plurality of computing resources of the computing environment using a first forecasting data model and a plurality of usage measurements obtained from the computing resources;
transition the use of the first forecasting data model in forecasting the usage to a second forecasting data model without incurring downtime in the computing environment; and
after the transition, forecast the usage of the computing resources of the computing environment using the second forecasting data model and the usage measurements obtained from the computing resources, wherein the second forecasting data model exponentially decays the usage measurements based on a respective time period at which the usage measurements were obtained.

2. The system of claim 1 , wherein the at least one computing device is further directed to:
maintain a first plurality of accumulators for use with the first forecasting data model;
in response to a transition of the use of the first forecasting data model to the second forecasting data model, initialize a second plurality of accumulators for use with the second forecasting data model; and
as usage measurements are received in a stream of usage measurements, exponentially decay the first plurality of accumulators until the first plurality of accumulators are not used in subsequent forecasts of usage made using the second forecasting data model.

3. The system of claim 2 , wherein the first plurality of accumulators and the second plurality of accumulators accrue the usage measurement or statistics associated with the usage measurements in the memory over a predetermined time interval.

4. The system of claim 1 , wherein transitioning the use of the first forecasting data model in forecasting the usage to the second forecasting data model without incurring downtime in the computing environment further comprises:
initializing a plurality of accumulators that receive new ones of the usage measurements, the accumulators being initialized in at least one data object, wherein the usage of the computing resources is forecasted using the accumulators;
assigning a weight to the plurality of accumulators that exponentially decay the accumulators over time;
determining a time of convergence of the usage of the computing resources as forecasted from the first forecasting data model to the second forecasting data model; and
transition the use of the first forecasting data model in forecasting the usage to the second forecasting data model in accordance with the time of convergence.

5. The system of claim 4 , wherein the time of convergence is determined using a tail-weight ratio.

6. The system of claim 4 , wherein the time of convergence is specified by an administrator client device.

7. The system of claim 4 , wherein the at least one computing device is further directed to:
access an effective window size, a subset of the usage measurements received in a time window, and a total number of the usage measurements in the subset;
determine a time at which the usage of the computing resources as forecasted will fully transition from use of the first forecasting data model to the second forecasting data model; and
display the time at which the usage of the computing resources as forecasted will fully transition from use of the first forecasting data model to the second forecasting data model in at least one user interface.

8. A method for transitioning usage forecasting in a computing environment, comprising:
forecasting usage of a plurality of computing resources of the computing environment using a first forecasting data model and a plurality of usage measurements obtained from the computing resources;
transitioning use of the first forecasting data model in forecasting the usage to a second forecasting data model without incurring downtime in the computing environment; and
after the transitioning of the use, forecasting the usage of the computing resources of the computing environment using the second forecasting data model and the usage measurements obtained from the computing resources, wherein the second forecasting data model exponentially decays the usage measurements based on a respective time period at which the usage measurements were obtained.

9. The method of claim 8 , further comprising:
maintaining a first plurality of accumulators for use with the first forecasting data model;
in response to a transition of the use of the first forecasting data model to the second forecasting data model, initializing a second plurality of accumulators for use with the second forecasting data model; and
as usage measurements are received in a stream of usage measurements, exponentially decaying the first plurality of accumulators until the first plurality of accumulators are not used in subsequent forecasts of usage made using the second forecasting data model.

10. The method of claim 9 , further comprising using the first plurality of accumulators and the second plurality of accumulators to accrue the usage measurement or statistics associated with the usage measurements in the memory over a predetermined time interval.

11. The method of claim 8 , wherein transitioning the use of the first forecasting data model in forecasting the usage to the second forecasting data model without incurring downtime in the computing environment further comprises:
initializing a plurality of accumulators that receive new ones of the usage measurements, the accumulators being initialized in at least one data object, wherein the usage of the computing resources is forecasted using the accumulators;
assigning a weight to the plurality of accumulators that exponentially decay the accumulators over time;
determining a time of convergence of the usage of the computing resources as forecasted from the first forecasting data model to the second forecasting data model; and
transition the use of the first forecasting data model in forecasting the usage to the second forecasting data model in accordance with the time of convergence.

12. The method of claim 11 , wherein the time of convergence is determined using a tail-weight ratio.

13. The method of claim 11 , wherein the time of convergence is specified by an administrator client device.

14. The method of claim 11 , further comprising:
accessing an effective window size, a subset of the usage measurements received in a time window, and a total number of the usage measurements in the subset;
determining a time at which the usage of the computing resources as forecasted will fully transition from use of the first forecasting data model to the second forecasting data model; and
displaying the time at which the usage of the computing resources as forecasted will fully transition from use of the first forecasting data model to the second forecasting data model in at least one user interface.

15. A non-transitory computer-readable medium embodying program instructions for transitioning usage forecasting in a computing environment that, when executed by at least one computing device comprising at least one hardware processor, direct the at least one computing device to:
forecast usage of a plurality of computing resources of the computing environment using a first forecasting data model and a plurality of

Assignees

• Vmware Inc

Inventors

• Mathur Keshav
• Lu Jinyi
• Pedersen Paul
• Lin Junyuan
• Brown Darren
• Gao Peng
• Nutman Leah
• Wang Xing

Classifications

• G06F11/3442 Primary

  for planning or managing the needed capacity · CPC title

• G06F9/5027

  the resource being a machine, e.g. CPUs, Servers, Terminals · CPC title

• G06F11/3006

  where the computing system is distributed, e.g. networked systems, clusters, multiprocessor systems (multiprogramming arrangements G06F9/46; allocation of resources G06F9/50) · CPC title

• G06F11/3447

  Performance evaluation by modeling · CPC title

• G06N5/048

  Fuzzy inferencing · CPC title