Elastic scaling method and device based on Kubernetes container cloud platform and application

The invention provides an elastic scaling method and device based on a Kubernetes container cloud platform and application, and the method comprises the following steps: continuously obtaining the current task data of an algorithm pod at the current moment, and calculating the current comprehensive load rate of the current task data, inputting the comprehensive load rate time sequence into an ARIMA-Kalman prediction model for prediction to obtain a predicted comprehensive load rate; when the predicted comprehensive load rate at a certain moment is greater than a first set threshold value, the algorithm pod is expanded after a first set time period after the moment; and when the predicted comprehensive load rate at a certain moment is smaller than a second set threshold value, carrying out capacity reduction on the algorithm pod after a second set time period after the moment. According to the scheme, the comprehensive load rate of various resources is predicted in real time through the ARIMA-Kalman prediction