System and method for controlling an operation of an application by forecasting a smoothed transport block size

Patent metadata

Field	Value
Publication number	US-9474064-B2
Application number	US-201514607990-A
Country	US
Kind code	B2
Filing date	Jan 28, 2015
Priority date	Jan 28, 2015
Publication date	Oct 18, 2016
Grant date	Oct 18, 2016

Abstract

A smoothed transport block size is forecasted by predicting future value information based on historical time series data obtained at an e-Node B. The historical time series data includes historical transport block size information and historical modulation and coding scheme information. A mapping function is used to correlate the future value information with historical transport block size information. Once the mapping function is determined, the mapping function forecasts the average transport block sizes by inputting the future value information into the mapping function. The smoothed transport block sizes and the future value information is then transmitted to an application server and/or an application client at a user equipment to control an operation of an application.

First claim

What is claimed is:

1. A method of exporting a smoothed transport block size to control an operation of an application, comprising:
obtaining, by one or more processors of at least one network node, historical time series data, the historical time series data including historical transport block size information, historical modulation and coding scheme information and historical physical resource block utilization information;
predicting, by the one or more processors, future value information based on the historical time series data, the future value information including modulation and coding scheme future values and physical resource block future values;
producing, by the one or more processors, a mapping function regressing first input data to first output data, the first input data including the historical modulation and coding scheme information and the historical physical resource block utilization information, the first output data including the historical transport block size information;
forecasting, by the one or more processors, a smoothed transport block size by inputting the future value information into the mapping function; and
exporting, by the one or more processors, the smoothed transport block size to a network node to control an operation of an application.

2. The method of claim 1 , wherein the exporting of the smoothed transport block size includes exporting the smoothed transport block size to at least one of an application server and an application client server at a user equipment in order to control the operation of the application.

3. The method of claim 2 , further comprising:
exporting at least one of the modulation and coding scheme future values and the physical resource block future values to at least one of the application server and the application client at the user equipment in order to control the operation of the application.

4. The method of claim 1 , further comprising:
smoothing the historical time series data prior to predicting the future value information, wherein the future value information is smoothed future value information.

5. The method of claim 1 , wherein the predicting of the future value information based on the historical time series data includes using Auto-Regressive Integrated Moving Average (ARIMA) regression modeling to predict the future value information.

6. The method of claim 5 , wherein the predicting of the future value information based on the historical time series data includes the future value information being quantized to a first and second set of discrete numbers, the first set of discrete numbers being the modulation and coding scheme future values, and the second set of discrete numbers being the physical resource block future values.

7. The method of claim 6 , wherein the forecasting of the smoothed transport block size further includes forecasting a third set of discrete numbers by inputting the first set of discrete numbers and the second set of discrete numbers into the mapping function, the mapping function being a functional regression model, the third set of discrete numbers being transport block size future values.

8. The method of claim 7 , wherein the first set of discrete numbers, the second set of discrete numbers, and the third set of discrete numbers each are assigned an observation period, wherein the observation period is one of preselected, adjustable and adaptable.

9. The method of claim 7 , wherein the forecasting of the smoothed transport block size further includes smoothing the transport block size future values, the smoothing being accomplished via a kernel utilizing a smoothing bandwidth and distance measure, the smoothing bandwidth and the distance measure being one of preselected, adjustable and adaptable.

10. The method of claim 1 , wherein the future value information and the forecasted average transport block size are determined for a selectable time-increment that is ahead of real-time.

11. The method of claim 1 , wherein the obtaining step is performed at an e-Node B, and the predicting, the producing and the forecasting step is performed at a managing entity outside of the e-Node B.

12. A network node, comprising:
one or more processors configured to,
obtain historical time series data, the historical time series data including historical transport block size information, historical modulation and coding scheme information and historical physical resource block utilization information,
predict future value information based on the historical time series data, the future value information including modulation and coding scheme future values and physical resource block future values,
produce a mapping function regressing first input data to first output data, the first input data including the historical modulation and coding scheme information and the historical physical resource block utilization information, the first output data including the historical transport block size information,
forecast a smoothed transport block size by inputting the future value information into the mapping function, and
export the smoothed transport block size to a network node to control an operation of an application.

13. The network node of claim 12 , wherein the one or more processors is further configured to export the smoothed transport block size by exporting the smoothed transport block size to at least one of an application server and an application client server at a user equipment in order to control the operation of the application.

14. The network node of claim 13 , wherein the one or more processors is further configured to,
export at least one of the modulation and coding scheme future values and the physical resource block future values to at least one of the application server and the application client at the user equipment in order to control the operation of the application.

15. The network node of claim 12 , wherein the one or more processors is further configured to:
smooth the historical time series data prior to predicting the future value information, wherein the future value information is smoothed future value information.

16. The network node of claim 12 , wherein the one or more processors is further configured to predict the future value information based on the historical time series data includes using Auto-Regressive Integrated Moving Average (ARIMA) regression modeling to predict the future value information.

17. The network node of claim 16 , wherein the one or more processors is further configured to predict the future value information based on the historical time series data by the future value information being quantized to a first and second set of discrete numbers, the first set of discrete numbers being the modulation and coding scheme future values, and the second set of discrete numbers being the physical resource block future values.

18. The network node of claim 17 , wherein the one or more processors is further configured to forecast the smoothed transport block size by forecasting a third set of discrete numbers by inputting the first set of discrete numbers and the second set of discrete numbers into the mapping function, the mapping function being a functional regression model, the third set of discrete numbers being transport block size future values.

19. The network node of claim 18 , wherein the one or more processors is further configured to assigned an observation period for each of the first set of discrete numbers, the second set of discrete numbers, and the third set of discrete numbe

Assignees

• Sayeed Zulfiquar
• Liao Qi
• Grinshpun Edward
• Faucher David
• Sharma Sameer
• Alcatel Lucent

Inventors

• Sayeed Zulfiquar
• Liao Qi
• Grinshpun Edward
• Faucher David
• Sharma Sameer

Classifications

• H04L1/002

  Algorithms with memory of the previous states, e.g. Markovian models · CPC title

• H04L1/0007 Primary

  by modifying the frame length · CPC title

• H04W72/044 Primary

  based on the type of the allocated resource · CPC title

• H04L1/0003

  by switching between different modulation schemes · CPC title

• H04W84/042

  Public Land Mobile systems, e.g. cellular systems · CPC title