LOADING PREDICTION METHOD AND ELECTRONIC DEVICE USING THE SAME

• US 20140122403A1
• Filed: 03/18/2013
• Published: 05/01/2014
• Est. Priority Date: 10/31/2012
• Status: Abandoned Application

• Current Assignee: Inventec Corporation, Inventec Technology Company Limited (Inventec Corporation)
• Original Assignee: Inventec Corporation, Inventec Technology Company Limited (Inventec Corporation)
• Inventors: Liu, Te-Yen, Huang, Bo-Wei, Wang, Kun-Wei, Peng, Wen-Chih, Li, Chung-Chih
• Application Number:
  US13/846,767
• Publication Number:
  US 20140122403A1
• Time in Patent Office: Days
• US Class Current: 706/45
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 10/06375 Prediction of business process outcome or impact based on a proposed change
• CPC Class Codes: G06Q 10/067 Enterprise or organisation modelling

Abstract

A loading prediction method, applicable to an electronic device, includes the following steps. Multiple resource loading records of the electronic device at multiple time periods are recorded, respectively. A predicted time point is received. A time difference between the predicted time point and a current time point is calculated. The predicted time point is greater than the current time point on a timeline. Whether the time difference is less than a threshold value is determined. A regression-based prediction according to the resource loading records is performed when the time difference is less than the threshold value. A clustering-based prediction according to the resource loading records is performed when the time difference is not less than the threshold value.

Claims

1. A loading prediction method, applicable to an electronic device, the method comprising:

recording a plurality of resource loading records of the electronic device at a plurality of time periods, respectively;

receiving a predicted time point;

calculating a time difference between the predicted time point and a current time point, and wherein the predicted time point is greater than the current time point on a timeline;

determining whether the time difference is less than a threshold value;

performing a regression-based prediction according to the plurality of resource loading records when the time difference is less than the threshold value; and

performing a clustering-based prediction according to the plurality of resource loading records when the time difference is not less than the threshold value.

2. The loading prediction method according to claim 1, wherein the step of performing a regression-based prediction according to the plurality of resource loading records further comprises:

performing a regression analysis algorithm for the plurality of resource loading records to acquire the prediction model; and

retrieving a predicted value corresponding to the predicted time point in the prediction model.

3. The loading prediction method according to claim 1, wherein the step of performing a clustering-based prediction according to the plurality of resource loading records further comprises:

dividing each of the plurality of time periods into a plurality of time segments, so that each of the plurality of resource loading records is divided into a plurality of data fragments;

selecting a predicted time segment corresponding to the predicted time point from the time segments;

performing a cluster analysis on the plurality data fragments in the predicted time segment of the plurality of time periods, to divide the plurality of data fragments into a plurality of clusters;

selecting one of the plurality of clusters with the most counts from the plurality of clusters; and

calculating an average value of the plurality of data segments included in the cluster which is selected, to be used as the predicted value of the predicted time point.

4. The loading prediction method according to claim 3, wherein the step of performing a cluster analysis to the predicted time segment during the time period further comprises:

calculating a similarity among the plurality of data segments of each of the plurality of time segments, and performing a cluster analysis according to the similarity.

5. The loading prediction method according to claim 1, wherein the step of recording the plurality of resource loading records of the electronic device at the plurality of time periods respectively further comprises:

acquiring a plurality of amounts of resource usage according to a sampling rate during each of the plurality of time periods, and wherein each of the plurality of resource loading records includes the plurality of amounts of resource usage during each of the plurality of time periods.

6. An electronic device, comprising:

a recording module configured to record a plurality of resource loading records of an electronic device at a plurality of time periods, respectively;

a receiving module configured to receive a predicted time point;

a time calculating module configured to calculate a time difference between the predicted time point and a current time point, and wherein the predicted time point is greater than the current time point on a timeline;

a regression analysis module configured to perform a regression-based prediction according to the plurality of resource loading records;

a cluster analysis module configured to perform a clustering-based prediction according to the plurality of resource loading records; and

a determining module configured to determine whether the time difference is less than threshold value, and wherein, when the time difference is less than the threshold value, the determining module notifies the regression analysis module to perform the regression-based prediction, and when the time difference is not less than the threshold value, the determining module notifies the cluster analysis module to perform the clustering-based prediction.

7. The electronic device according to claim 6, wherein the regression analysis module is configured to perform a regression analysis algorithm for the plurality of resource loading records to acquire the prediction model, the regression analysis module is configured to retrieve a predicted value corresponding to the predicted time point in the prediction model, and the plurality of resource loading records are recorded by the recording module respectively during the plurality of time periods.

8. The electronic device according to claim 6, wherein the cluster analysis module further comprises:

a dividing module configured to divide each of the plurality of time periods into a plurality of time segments, so that each of the plurality of resource loading records is divided into a plurality of data fragments;

a prediction module configured to select a predicted time segment corresponding to the predicted time point from the plurality of time segments;

a clustering module configured to perform a cluster analysis on the data fragments in the predicted time segment of the plurality of time periods, to divide the plurality of data fragments into a plurality of clusters;

a selecting module configured to select one of the plurality of clusters with the most counts from the plurality of clusters; and

a prediction calculation module configured to calculate an average value of the plurality of data segments included in the cluster which is selected, to be used as the predicted value of the predicted time point.

9. The electronic device according to claim 8, wherein the clustering module is configured to calculate a similarity among the plurality of data segments of each of the plurality of time segments, and is configured to perform a cluster analysis according to the similarity.

10. The electronic device according to claim 6, wherein the recording module is configured to acquire a plurality of amounts of resource usage according to a sampling rate during each of the plurality of time periods, and wherein each of the plurality of resource loading records includes the amounts of the resource usage during each of the plurality of time periods.