Telecommunications network traffic metrics evaluation and prediction

• US 10,644,979 B2
• Filed: 06/06/2019
• Issued: 05/05/2020
• Est. Priority Date: 06/06/2018
• Status: Active Grant

• Current Assignee: The Joan and Irwin Jacobs Technion-Cornell Institute
• Original Assignee: The Joan and Irwin Jacobs Technion-Cornell Institute
• Inventors: Samadi, Payman
• Primary Examiner(s): Mejia, Anthony
• Application Number:
  US16/433,434
• Publication Number:
  US 20190379592A1
• Time in Patent Office: 334 Days
• Field of Search: 709224
• CPC Class Codes: H04L 41/145 involving simulating, designing, planning or modelling of a network
• CPC Class Codes: H04L 43/045 for graphical visualisation of monitoring data
• CPC Class Codes: H04L 43/062 related to network traffic
• CPC Class Codes: H04L 43/0852 Delays
• CPC Class Codes: H04L 43/0882 Utilisation of link capacity
• CPC Class Codes: H04L 43/14 using software, i.e. software packages network security related monitoring H04L63/1408
• CPC Class Codes: H04W 4/021 Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences

Abstract

A method for evaluating and predicting telecommunications network traffic includes receiving site data for multiple geographic areas via a processor. The processor also receives weather data, event data, and population demographic data for the geographic areas. The processor also generates predicted occupancy data for each of the geographic areas and for multiple time intervals. The processor also determines a predicted telecommunications network metric for each of the geographic areas and for each of the time intervals, based on the predicted occupancy data.

Claims

1. A method, comprising:

generating a first domain-specific machine learning algorithm, for a first domain, the generating the first domain-specific machine learning algorithm including at least one of time series sampling, time series resampling, or an introduction of seasonal terms to a time series;

receiving, via a processor, site data for each geographic area of a plurality of geographic areas, the plurality of geographic areas including a cellular base station, the site data including at least one of;

property layout data, facility type data, facility size data, facility usage data, or maximum site occupancy data;

receiving, via one of a graphical user interface (GUI) or an application programming interface (API);

(1) an indication of a first geographic area of the plurality of geographic areas and (2) an indication of a first time interval of a plurality of time intervals;

generating, via the processor and for the first geographic area and for the first time interval, predicted occupancy data using the first domain-specific machine learning algorithm;

generating a second domain-specific machine learning algorithm, for a second domain different from the first domain; and

determining, via the processor and based on the predicted occupancy data and using the second domain-specific machine learning algorithm, a predicted telecommunications network metric for at least one geographic area from the plurality of geographic areas and for a time interval from the plurality of time intervals, the predicted telecommunications network metric including one of total telecommunications network traffic volume for a predetermined time interval, telecommunications network traffic type, telecommunications network traffic volume per unit time, or telecommunications network latency distribution for a predetermined time interval.

2. The method of claim 1, further comprising generating, via the processor and for each geographic area of the plurality of geographic areas and for each time interval of a plurality of time intervals, predicted activity category data,

wherein the determining the predicted telecommunications network metric is further based on the predicted activity category data.

3. The method of claim 1, further comprising:

sending, in response to receiving the indication of the first geographic area of the plurality of geographic areas and the indication of the first time interval of the plurality of time intervals, a signal to cause at least one of;

display within the GUI of the predicted telecommunications network metric associated with the first geographic area and the first time interval, delivery of the predicted telecommunications network metric associated with the first geographic area and the first time interval via the API, or delivery of the predicted telecommunications network metric associated with the first geographic area and the first time interval via an associated CSV file.

4. The method of claim 1, wherein the generating the predicted occupancy data is based on the site data, weather data, event data, and population demographic data.

5. The method of claim 1, wherein the site data includes site occupancy capacity data.

6. The method of claim 1, wherein the generating the predicted occupancy data includes an autoregressive moving average process.

7. The method of claim 1, wherein the generating the predicted occupancy data is performed using time series modeling.

8. The method of claim 1, further comprising receiving at least one of:

event data, historical data, predictive data, live data, or static data for the plurality of geographic areas,

the generating the predicted occupancy data being based on the at least one of event data, historical data, predictive data, live data, or static data.

9. The method of claim 1, further comprising sending a signal to cause at least one of:

display of the predicted telecommunications network metrics within the GUI, delivery of the predicted telecommunications network metrics via the API, or delivery of the predicted telecommunications network metrics via a comma-separated values (CSV) file.

10. The method of claim 1, wherein the receiving the site data is via at least one of the GUI, the API, or a CSV file.