关键词: 负载预测, 凌日搜索, 云计算, 参数寻优, 长短期记忆网络, 差分自回归移动平均

Abstract:

Facing resource wastage and performance challenges in cloud platform resource scheduling， especially the low prediction accuracy of cloud resource prediction due to the difficulty in selecting hyperparameters manually for Long Short-Term Memory （LSTM） network models， a combined prediction model optimized by Transit Search （TS） algorithm named TS-ARIMA-LSTM was proposed. The combined prediction model integrates the AutoRegressive Integrated Moving Average （ARIMA） model with the LSTM model. Firstly， TS algorithm was used to optimize the hyperparameters of the LSTM model， including the neuron counts in three layers and the transmission delays. Then， the optimized LSTM model was used for preliminary prediction， and the ARIMA model was used to correct the error of the LSTM prediction. Finally， the prediction results of the ARIMA and LSTM models were combined to obtain the final prediction value. Experimental results on the public Alibaba Cloud dataset Cluster-trace-v2018 show that the proposed model optimized by the TS algorithm improves the prediction accuracy significantly compared to the traditional single prediction models ARIMA and LSTM， as well as the combined prediction model ARIMA-LSTM. Specifically， compared to the best-performing ARIMA-LSTM model among the baseline models， the proposed model has the Mean Square Error （MSE） decreased by 49.72%， the Root Mean Square Error （RMSE） decreased by 29.24%， and the Mean Absolute Error （MAE） decreased by 33.94%. It can be seen that the application of the proposed model in cloud resource prediction demonstrates high prediction accuracy， offering a new pathway for improving cloud platform task scheduling strategies.

Key words: load prediction, Transit Search (TS), cloud computing, parameter optimization, Long Short-Term Memory (LSTM) network, AutoRegressive Integrated Moving Average (ARIMA)