Predicting a network performance measurement from historic and recent data

Patent metadata

Field	Value
Publication number	US-9625497-B2
Application number	US-201314042502-A
Country	US
Kind code	B2
Filing date	Sep 30, 2013
Priority date	Apr 26, 2013
Publication date	Apr 18, 2017
Grant date	Apr 18, 2017

Abstract

Prediction techniques are presented for predicting a current value of a performance measurement using historic performance measurement data and recent performance measurement data, which may not reflect the current conditions. A daily trend in a series of performance measurements is obtained. The daily trend comprises a set of data points at different times of day, wherein each data point represents an average value of the performance measurements at a corresponding time of day over a plurality of days. One or more recent performance measurements over a recent time interval are also obtained. A current value of the performance measurements is predicted, based on the daily trend and the recent performance measurements.

First claim

What is claimed is:

1. A method implemented by a network node in a communication network of controlling admission of user terminals in the communication network, the method comprising:
obtaining a daily trend in a series of performance measurements, the daily trend comprising a set of data points at different times of day, wherein each data point represents an average value of the performance measurements at a corresponding time of day over a plurality of days;
obtaining one or more recent performance measurements over a recent time interval;
predicting, based on the daily trend and the recent performance measurements, the current value of the performance measurement; and
controlling admission to the communication network based on the predicted current value of the performance measurement,
wherein controlling admission to the communication network comprises determining an admission threshold based on the predicted current value of the performance measurement, and admitting user terminals to the communication network based on the admission threshold.

2. The method of claim 1 wherein predicting the current value of the performance measurement comprises:
computing a first average value of the recent performance measurements over the recent time interval;
computing a second average value of the daily trend over the recent time interval; and
predicting the current value of the performance measurement as a function of the first and second average values.

3. The method of claim 2 wherein predicting the current value of the performance measurement as a function of the first and second average values comprises:
computing a difference between the second average value of the daily trend and a current value of the daily trend; and
adding the difference to the first average value to obtain the current value of the performance measurement.

4. The method of claim 1 wherein obtaining a daily trend in a series of performance measurements comprises maintaining a record of historic performance measurements, and computing the daily trend from the record of historic performance measurements.

5. The method of claim 1 wherein the daily trend comprises a weekday trend based on performance measurements over a plurality of weekdays.

6. The method of claim 1 wherein the daily trend comprises a calendar day trend based on performance measurements taken on the same calendar day over a plurality of weeks.

7. The method of claim 1 wherein the performance measurement comprises an average throughput.

8. The method of claim 1 wherein the method comprises predicting the current value of the performance measurement in response to determining that the one or more recent performance measurements are not current.

9. The method of claim 1 wherein the controlling admission to the communication network comprises controlling admission based on the predicted current value of the performance measurement and a network bias that is dynamically adjusted based on network conditions.

10. A network node in a wireless communication network for controlling admission of user terminals in the communication network, the network node comprising:
a network interface circuit for communicating with other network nodes; and
a processing circuit configured to predict a current value of a performance measurement, the processing circuit being configured to:
obtain a daily trend in a series of performance measurements, the daily trend comprising a set of data points at different times of day, wherein each data point represents an average value of the performance measurements at a corresponding time of day over a plurality of days;
obtain one or more recent performance measurements over a recent time interval;
predict, based on the daily trend and the recent performance measurements, the current value of the performance measurement; and
control admission to the communication network based on the predicted current value of the performance measurement by:
determining an admission threshold based on the predicted current value of the performance measurement, and
admitting user terminals to the communication network based on the admission threshold.

11. The network node of claim 10 wherein the processing circuit is configured to predict the current value of the performance measurement by:
computing a first average value of the recent performance measurements over the recent time interval;
computing a second average value of the daily trend over the recent time interval; and
predicting the current value of the performance measurement as a function of the first and second average values.

12. The network node of claim 11 wherein the processing circuit is configured to predict the current value of the performance measurement as a function of the first and second average values by:
computing a difference between the second average value and a current value of the daily trend; and
adding the difference to the first average value to obtain the current value of the performance measurement.

13. The network node of claim 10 wherein the processing circuit is configured to obtain a daily trend in a series of performance measurements by maintaining a record of historic performance measurements, and computing the daily trend from the record of historic performance measurements.

14. The network node of claim 10 wherein the daily trend obtained by the processing circuit comprises a weekday trend based on performance measurements over a plurality of weekdays.

15. The network node of claim 10 wherein the daily trend obtained by the processing circuit comprises a calendar day trend based on performance measurements taken on the same calendar day over a plurality of weeks.

16. The network node of claim 10 wherein the performance measurement predicted by the processing circuit comprises an average throughput.

17. The network node of claim 10 wherein the processing circuit is configured to control admission to the communication network based on the predicted current value of the performance measurement and a network bias that is dynamically adjusted based on network conditions.

Assignees

• Ericsson Telefon Ab L M
• ERICSSON TELEFON AB L M (publ)

Inventors

• Huang Kaiyuan
• Tam Gary

Classifications

• H04L41/147 Primary

  for predicting network behaviour · CPC title

• H04L43/067

  using time frame reporting · CPC title

• G01R19/0092 Primary

  Measuring current only · CPC title

• H04B17/26

  using historical data, averaging values or statistics · CPC title

• H04B17/373

  Predicting channel quality {or other radio frequency [RF]} parameters · CPC title