Optimization of Container Cloud Elastic Scaling Integrating ARIMA Forecasting and HPA Response

Load changes of cloud computing resources show more and more complex characteristics. Load forecasting is crucial for elastic scaling of cloud computing resources. Kubernetes is a mainstream container cloud platform. Its built-in HPA policy automatically adjusts the number of Pod replicas according to load changes to achieve elastic scaling, but it has the problems of single load metric and user response delay during peak periods. This paper proposes a container cloud elastic scaling optimization method based on load forecasting and response, which dynamically monitors and calculates the combined load of CPU and Memory in the Pod set, uses ARIMA model to complete the combined load forecasting value based on historical data, and HPA responsive algorithm to make up for the lack of forecasting. Experimental results show that compared with the HPA strategy, our method can execute the corresponding scaling operations in advance, and can effectively reduce the response delay time and improve the Qos quality.