Cloud server resource performance prediction method using ARIMA-RNN combined model

Abstract

The invention discloses a cloud server resource performance prediction method using an ARIMA-RNN combined model, and the method comprises the steps: firstly carrying out the preprocessing of sequencedata, and enabling the original sequence data to be mapped to [-1, 1]; determining an ARIMA model, and then training, predicting and storing existing data; determining an RNN model structure, and training the RNN model by using the existing data and the prediction result of the ARIMA model on the existing data; and inputting the prediction result of the ARIMA model for the moment t data and the data of the moments t1, t2,..., tn into the RNN model to predict the data of the moment t. According to the method, the limitation that the ARIMA model is relatively low in prediction precision for datawith relatively large fluctuation is overcome, the problems of low convergence rate and instability of the RNN model are solved, finally, prediction and analysis of performance parameters of the cloud server system are realized, and the software aging phenomenon is predicted more accurately.

Description

technical field [0001] The invention belongs to the technical field of time series prediction, and specifically relates to a cloud server resource performance prediction method using an ARIMA-RNN combined model. Background technique [0002] With the development of cloud computing, the use of cloud servers is becoming more and more common. Cloud servers are characterized by long-running, high complexity, and frequent resource exchange, which increases the risk of resource exhaustion and software system anomalies and failures. With the accumulation of failures and resource consumption, the cloud server system will experience slow performance degradation, increased failure rate and even crash. This phenomenon is called "software aging". Software aging is affected by many factors, such as software anomalies, resource utilization, workload, etc. Software aging in cloud server systems is a common phenomenon. For example, with the long-term operation of the cloud service syste...

AI Technical Summary

Problems solved by technology

It solves the problem of low accuracy in the prediction process of cloud service system aging trend existing in the prior art, and overcomes the limitation of ARIMA model with low prediction accuracy for data with large fluctuations. Based on the gray relational degree analysis method, the proposed Time series data correlation calculation method to determine the number and dimension of data input in the combination model, overcome the slow and unstable convergence speed of the RNN model, and finally realize the prediction and analysis of cloud server system performance parameters, and more accurately predict software aging phenomenon

Images