Accurate prediction of overall trends and peak loads in container cloud resource requests is crucial for improving resource utilization and optimizing allocation strategies. To address the limitations of existing prediction methods, such as insufficient accuracy of single models and inadequate capture of long-term temporal features, a hybrid cloud resource prediction model was proposed, which integrated polar lights optimization (PLO), variational mode decomposition (VMD), temporal convolutional network (TCN), and Informer (PLO-VMD-TCN-Informer). In the combined model, structures such as dilated convolutions were utilized to effectively extract local time patterns and enhance the model’s ability to capture detailed features. VMD was employed to improve the modeling capability for non-stationary and nonlinear time series, while PLO was applied to dynamically optimize the parameters of VMD and Informer, thereby increasing the level of modeling automation. Experiments based on the public Alibaba dataset show that the proposed model outperforms mainstream benchmark models across all key metrics. Specifically, the root mean square error (RMSE) is reduced by 24.03% to 28.00%, and the mean absolute percentage error (MAPE) is reduced by 22.37% to 31.59%, validating the effectiveness of the proposed model.
WANG Yu-yang, XIE Xiao-lan, LIU Ya-rong.
Cloud Resource Prediction Model Based on Polar Lights Optimization and Variational Mode Decomposition-Informer[J].
Science Technology and Engineering, 2026, 26(15): 6496-6505 DOI:10.12404/j.issn.1671-1815.2505348
Morichetta L Austdar S. Time series predictions for cloud workloads: a comprehensive evaluation[C]// 2024 IEEE International Conference on Service-Oriented System Engineering (SOSE). Shanghai: IEEE, 2024: 36-45.
ZhaoLi. Load forecasting model of cloud computing resources based on support vector machine[J]. Journal of Nanjing University of Science and Technology, 2018, 42(6): 687-692.
ChenJili, ZhangChanghui, XieXiaolan. Few data cloud resource prediction based on generative adversarial network and deep learning[J]. Science Technology and Engineering, 2022, 22 (36): 16099-16107.
XueYufei. Cloud resource inventory demand forecast based on LSTM algorithm[J]. China Computer & Communication (Theoretical Edition), 2023, 35(10): 197-199.
[8]
PatelE, KushwahaD S. A hybrid CNN-LSTM model for predicting server load in cloud computing[J]. The Journal of Supercomputing, 2022, 78(8): 1-30.
ChenJili, LiHaijun, XieXiaolan. Short-term cloud resource prediction model based on temporal convolution and long short-term memory[J]. Science Technology and Engineering, 2025, 25(7): 2856-2864.
ShuWenjuan, ZengFanping, ChenGuozhu, et al. Cloud resource prediction based on variational mode decomposition and gated recurrent unit network[J]. Journal of Computer Applications, 2021, 41(S2): 159-164.
XieXiaolan, DongYu. A container cloud resource prediction model based on quadratic decomposition and broad learning system[J]. Research and Exploration in Laboratory, 2025, 44(3): 94-100.
FanZhiyong, ZhangJin, LiuTao. Aircraft state prediction method based on RF-TCN-SSA-Informer models[J]. Science Technology and Engineering, 2025, 25(28): 12139-12147.
HuangLüwen, LiuYuhang, QuKunyi, et al. Canopy area temperature prediction with fusion of LSTM and Informer[J]. Transactions of the Chinese Society of Agricultural Engineering, 2025, 41(8): 222-232.
[24]
LiJ C, SunL P, WuX, et al. Enhancing financial time series forecasting with hybrid deep learning: CEEMDAN-Informer-LSTM model[J]. Applied Soft Computing, 2025, 117: 113241.
YinJianhua, DaiGuanzheng, DingNing, et al. Heating load forecasting based on STL-Informer-BiLSTM-XGB model[J]. Science Technology and Engineering, 2024, 24(21): 8942-8949.