Information technology resource forecasting based on time series analysis

Patent metadata

Field	Value
Publication number	US-11520667-B1
Application number	US-201715585353-A
Country	US
Kind code	B1
Filing date	May 3, 2017
Priority date	May 3, 2017
Publication date	Dec 6, 2022
Grant date	Dec 6, 2022

Abstract

Information technology resource forecasting based on time series analysis is described. A system creates multiple forecasts for an information technology resource by applying corresponding multiple time series models to first data associated with the information technology resource. The system selects a model of the multiple time series models by comparing the multiple forecasts for the information technology resource to second data associated with the information technology resource. The system outputs a forecast that is created by applying the selected model to third data associated with the information technology resource.

First claim

What is claimed is:

1. A system for information technology resource forecasting based on time series analysis, the system comprising:
a processor-based application stored on a non-transitory computer-readable medium, which when executed on a computer, will cause one or more processors to:
create multiple forecasts for an information technology resource based on first data associated with the information technology resource by applying multiple different time series models to the first data, the multiple forecasts being estimates of future events associated with the information technology resource;
select a model of the multiple time series models by comparing each of the multiple forecasts for the information technology resource created using the first data to second data associated with the information technology resource, the second data being test data that is different than the first data and generated after generation of the first data;
generate a forecast by applying the selected model to third data associated with the information technology resource and a subsequent forecast by applying the selected model to subsequent data associated with the information technology resource, the third data being created after the selection of the model, the subsequent data being created after the creation of the third data; and
output the forecasts that are created by applying the selected model to the third data and the subsequent data, wherein outputting the forecasts includes outputting a graphical interface displayed on a display as an alert when a value associated with the subsequent forecast satisfies a threshold, the graphical interface comprising a graph displaying both the created forecast based on the third data and the subsequent forecast based on the subsequent data.

2. The system of claim 1 , wherein creating the multiple forecasts for the information technology resource comprises creating a linear regression forecast for the information technology resource by applying a linear regression model to the first data associated with the information technology resource, and selecting the model of the multiple time series models comprises selecting one of the multiple time series models and the linear regression model by comparing the multiple forecasts for the information technology resource and the linear regression forecast to the second data associated with the information technology resource.

3. The system of claim 1 , wherein the multiple time series models comprise at least one of a stochastic model, an autoregressive model, an integrated model, a moving average model, an autoregressive moving average model, an autoregressive integrated moving average model, an autoregressive fractionally integrated moving average model, a vector autoregression model, a multivariate model, an exogenous model, a nonlinear autoregressive exogenous model, an autoregressive conditional heteroskedasticity model, a doubly stochastic model, a markov switching multifractal model, a hidden markov model, a general state space model, an unobserved components model, and a holt-winter model.

4. The system of claim 1 , wherein the processor-based application further causes the one or more processors to at least one of receive and retrieve the third data associated with the information technology resource in at least one of real-time and near real-time.

5. The system of claim 1 , wherein the forecast created by applying the selected model to third data associated with the information technology resource comprises at least one of a remaining time until depletion of the information technology resource and a usage of the information technology resource during a period of time.

6. The system of claim 1 , wherein the processor-based application further causes the one or more processors to:
create additional multiple forecasts for the information technology resource by applying the corresponding multiple time series models to fourth data associated with the information technology resource;
select another model of the multiple time series models by comparing the additional multiple forecasts for the information technology resource to fifth data associated with the information technology resource; and
output another forecast created by applying the selected other model to sixth data associated with the information technology resource.

7. A computer-implemented method for information technology resource forecasting based on time series analysis, the method comprising:
creating multiple forecasts for an information technology resource based on first data associated with the information technology resource by applying multiple different time series models to the first data, the multiple forecasts being estimates of future events associated with the information technology resource;
selecting a model of the multiple time series models by comparing each of the multiple forecasts for the information technology resource created using the first data to second data associated with the information technology resource, the second data being test data that is different than the first data and generated after generation of the first data; and
generating a forecast by applying the selected model to third data associated with the information technology resource and a subsequent forecast by applying the selected model to subsequent data associated with the information technology resource, the third data being created after the selection of the model, the subsequent data being created after the creation of the third data; and
outputting the forecasts that are created by applying the selected model to third data and the subsequent data, wherein outputting the forecasts includes outputting a graphical interface displayed on a display as an alert when a value associated with the subsequent forecast satisfies a threshold, the graphical interface comprising a graph displaying both the created forecast based on the third data and the subsequent forecast based on the subsequent data.

8. The method of claim 7 , wherein creating the multiple forecasts for the information technology resource comprises creating a linear regression forecast for the information technology resource by applying a linear regression model to the first data associated with the information technology resource, and selecting the model of the multiple time series models comprises selecting one of the multiple time series models and the linear regression model by comparing the multiple forecasts for the information technology resource and the linear regression forecast to the second data associated with the information technology resource.

9. The method of claim 7 , wherein the multiple time series models comprise at least one of a stochastic model, an autoregressive model, an integrated model, a moving average model, an autoregressive moving average model, an autoregressive integrated moving average model, an autoregressive fractionally integrated moving average model, a vector autoregression model, a multivariate model, an exogenous model, a nonlinear autoregressive exogenous model, an autoregressive conditional heteroskedasticity model, a doubly stochastic model, a markov switching multifractal model, a hidden markov model, a general state space model, an unobserved components model, and a holt-winter model.

10. The method of claim 7 , wherein the method further comprises at least one of receiving and retrieving the third data associated with the information technology resource in at least one of real-time and near real-time.

11. The method of claim 7 , wherein the forecast created by applying the selected model to third data associated with the information technology resource comprises at

Assignees

• Emc Ip Holding Co Llc

Inventors

• Savir Amihai
• Levy Idan
• Harmelin Shai
• Gaber Shiri
• Gefen Avitan
• Braine Lindsay

Classifications

• G06Q10/0631 Primary

  Resource planning, allocation, distributing or scheduling for enterprises or organisations · CPC title

• G06F11/1458 Primary

  Management of the backup or restore process · CPC title

• G06F11/3442

  for planning or managing the needed capacity · CPC title

• G06F11/1448

  Management of the data involved in backup or backup restore · CPC title