Method and apparatus for detecting a traffic suppression turning point in a cellular network

An apparatus for detecting a traffic suppression turning point in a communication system comprising:

• a non-transitory memory storage comprising instructions;
• and
• one or more processors in communication with the memory storage, wherein the one or more processors execute the instructions to:
• retrieve a set of measurement values of a key performance indicator (KPI) generated in a wireless network experiencing traffic loads within a lower range during a first period;
• predict, prior to a subsequent period, values for the KPI if the wireless network experienced traffic loads within an upper range based on the set of measurement values of the KPI;
• retrieve subsequent measurement values of the KPI generated in the wireless network experiencing traffic loads within the upper range during the subsequent period;
• calculate a prediction error for the KPI corresponding to the upper range, based on differences between the predicted values for the KPI and the subsequent measurement values of the KPI;
• and
• identify a traffic suppression condition in the wireless network based on the prediction error for the KPI when a prediction error criteria is satisfied.

A non-transitory computer-readable media storing computer instructions for detecting a traffic suppression turning point in a communications system, that when executed by one or more processors, cause the one or more processors to perform the steps of:

• receiving a set of measurement values of a key performance indicator (KPI) generated in a wireless network experiencing traffic loads within a lower range during a first period;
• predicting, prior to a subsequent period, values for the KPI if the wireless network experienced traffic loads within an upper range based on the set of measurement values of the KPI;
• receiving, subsequent measurement values of the KPI generated in the wireless network experiencing traffic loads within the upper range during the subsequent period;
• calculating, a prediction error for the KPI corresponding to the upper range, based on differences between the predicted values for the KPI and the subsequent measurement values of the KPI;
• and
• identifying, a traffic suppression condition in the wireless network based on the prediction error for the KPI when a prediction error criteria is satisfied.