Research on the optimization of university container cloud resource scheduling based on the ARIMA-LSTM combination

With the advancement of university informatization construction, container cloud technology is being increasingly widely used in universities. However, the resource scheduling problem has become a key factor restricting its efficient operation. This paper proposes an optimization scheme for university container cloud resource scheduling based on the ARIMA-LSTM combination. It predicts resource usage by constructing an ARIMA-LSTM combined model, realizes dynamic resource scheduling using a multi-objective optimization algorithm, and improves the static resource scheduling strategy of the Kubernetes platform. The experimental results show that this scheme can effectively improve the accuracy and efficiency of resource scheduling, balance multiple performance indicators, and provide new ideas and methods for the rational utilization of university container cloud resources.