Research on Resource Prediction of Space-based Information Network Based on Improved GRU Algorithm

doi:10.12068/j.issn.1005-3026.2023.03.001

Abstract

Abstract: In orde to improve the resource utilization of space-based information metwork efficiency， a resource prediction model of space-based information network was presented based on the improved GRU (gated recurrent unit) algorithm. Firstly， a hierarchical three-level resource prediction framework was proposed to solve the problem of long delay in space-based environment. Then， Adam optimizer was used to optimize the learning rate of GRU network. Finally， Dropout technology was introduced to solve the over-fitting problem in the network. The experiments simulated the prediction of various space-based resources under different prediction models， and compared the prediction accuracy of GRU model under different optimizers. The results show that the resource prediction model based on improved GRU network has better performance.

Key words: space-based information network; resource prediction; GRU (gated recurrent unit) network; Adam optimizer; Dropout technology

CLC Number:

TP20

GENG Rong， WU Ya-qian， XIAO Qian-qian， XU Sai. Research on Resource Prediction of Space-based Information Network Based on Improved GRU Algorithm[J]. Journal of Northeastern University(Natural Science), 2023, 44(3): 305-314.

References

[1]Xue K，Meng W，Zhou H，et al.A lightweight and secure group key based handover authentication protocol for the software-defined space information network ［J］.IEEE Transactions on Wireless Communications，2020，19(6):3673-3684.
[2]章小宁，朱立东.通信与安全一体化的天地异构融合网络体系架构［J］.天地一体化信息网络，2020，1(2):11-16.(Zhang Xiao-ning，Zhu Li-dong.Communication and security integration of heterogeneous fusion network architecture［J］.Terrestrial Integration Information Network，2020，1(2):11-16.)
[3]Lin J，Cui D，Peng Z，et al.Virtualized resource scheduling in cloud computing environments:an review ［C］//2020 IEEE Conference on Telecommunications，Optics and Computer Science(TOCS).Shenyang，2020:303-308.
[4]Salinas D，Flunkert V，Gasthaus J，et al.DeepAR:probabilistic forecasting with autoregressive recurrent networks［J］.International Journal of Forecasting，2020，36(3):1181-1191.
[5]Hauser C B，Wesner S.Reviewing cloud monitoring:towards cloud resource profiling ［C］//2018 IEEE 11th International Conference on Cloud Computing(CLOUD).San Francisco，2018:678-685.
[6]Phung J，Lee Y C，Zomaya A Y.Lightweight power monitoring framework for virtualized computing environments ［J］.IEEE Transactions on Computers，2019，69(1):14-25.
[7]Peng H，Wen W S，Tseng M L，et al.A cloud load forecasting model with nonlinear changes using whale optimization algorithm hybrid strategy-extreme learning machine［J］.Soft Computing，2021，25(15):10205-10220.
[8]Ouhame S，Hadi Y，Ullah A.An efficient forecasting approach for resource utilization in cloud data center using CNN-LSTM model［J］.Neural Computing and Applications，2021，33:10043-10055.
[9]Englnder J，Wenger L，Kledzinski Y，et al.A methodology to realize energy-related use cases for a cloud-based smart energy management ［C］//2019 IEEE International Conference on Smart Cloud(SmartCloud).Tokyo，2019:19-24.
[10]Phung J，Lee Y C，Zomaya A Y.Lightweight power monitoring framework for virtualized computing environments ［J］.IEEE Transactions on Computers，2019，69(1):14-25.
[11]Kumar J，Singh A K.Performance assessment of time series forecasting models for cloud datacenter networks’ workload prediction［J］.Wireless Personal Communications，2021，116(3):1949-1969.
[12]王俊娜.一类混合预测模型的研究及其应用［D］.青岛:青岛大学，2020.(Wang Jun-na.Research and application of a kind of mixed prediction model ［D］.Qingdao:Qingdao University，2020.)
[13]Kumar J，Singh A K，Buyya R.Self directed learning based workload forecasting model for cloud resource management［J］.Information Sciences，2021，543:345-366.
[14]Kumar J，Goomer R，Singh A K.Long short term memory recurrent neural network(LSTM-RNN)based workload forecasting model for cloud datacenters［J］.Procedia Computer Science，2018，125:676-682.
[15]Cheng Y，Wang C，Yu H，et al.Gru-es:resource usage prediction of cloud workloads using a novel hybrid method［C］//IEEE 21st International Conference on High Performance Computing and Communications; IEEE 17th International Conference on Smart City; IEEE 5th International Conference on Data Science and Systems(HPCC/SmartCity/DSS).Zhangjiajie，2019:1249-1256.
[16]Adhikari S，Plewnia C，Netramai C，et al.A simulation for forecasting compute resource usage［C］//3rd Asia Pacific Information Technology Conference.Bangkok，2021:26-32.
[17]束文娟，曾凡平，陈国柱，等.基于变分模态分解与门控循环单元网络的云资源预测［J］.计算机应用，2021，41(sup2):159-164.(Shu Wen-juan，Zeng Fan-ping，Chen Guo-zhu，et al.Cloud resource prediction based on variational modal decomposition and gated cyclic unit network ［J/OL］.Computer Application，2021，41(sup2):159-164.)
[18]Li X，Ma X，Xiao F，et al.Time-series production forecasting method based on the integration of bidirectional gated recurrent unit(Bi-GRU)network and sparrow search algorithm(SSA)［J］.Journal of Petroleum Science and Engineering，2022，208:109309.
[19]程杰仁，罗逸涵，唐湘滟，等.基于LSTM流量预测的DDoS攻击检测方法［J］.华中科技大学学报(自然科学版)，2019，47(4):32-36.(Cheng Jie-ren，Luo Yi-han，Tang Xiang-yan，et al.DDoS attack detection method based on LSTM traffic prediction ［J］.Journal of Huazhong University of Science and Technology(Natural Science Edition)，2019，47(4):32-36.)
[20]Ke K，Hongbin S，Chengkang Z，et al.short-term electrical load forecasting method based on stacked auto-encoding and GRU neural network［J］.Evolutionary Intelligence，2019，12(3):385-394.
[21]Han P，Wang W，Shi Q，et al.Real-time short-term trajectory prediction based on GRU neural network ［C］//IEEE/AIAA 38th Digital Avionics Systems Conference(DASC).California，2019:1-8.
[22]Sri H M，Rao P，Kammardi P K，et al.A smart adaptive LSTM technique for electrical load forecasting at source［C］//2nd IEEE International Conference on Recent Trends in Electronics，Information & Communication Technology(RTEICT).Bangalore，2017:1717-1721.
[23]Gan D，Wang Y，Zhang N，et al.Enhancing short-term probabilistic residential load forecasting with quantile long-short-term memory［J］.The Journal of Engineering，2017，2017(14):2622-2627.
[24]高德亮.基于AdamW算法的WT-GRU模型在高频股指预测中的应用［D］.济南:山东大学，2021.(Gao De-liang.Application of WT-GRU model based on Adam algorithm in high frequency stock index prediction ［D］.Jinan:Shandong University，2021.)
[25]李静，莫思敏.基于改进遗传算法的深度神经网络优化研究［J］.计算机工程与科学，2021，43(8):1503-1511.(Li Jing，Mo Si-min.Research on depth neural network optimization based on improved genetic algorithm ［J］ Computer Engineering and Science，2021，43(8):1503-1511.)
[26]谢晓兰，梁荣华.基于PF-LSTM的云资源预测［J］.计算机工程与设计，2021，42(10):2823-2829.(Xie Xiao-an，Liang Rong-hua.Cloud resource prediction based on PF-LSTM［J］ Computer Engineering and Design，2021，42(10):2823-2829.)
[27]王悦悦，谢晓兰，郭杨，等.基于自适应神经网络的云资源预测模型［J］.科学技术与工程，2021，21(25):10814-10819.(Wang Yue-yue，Xie Xiao-lan，Guo Yang，et al Cloud resource prediction model based on adaptive neural network ［J］ Science，Technology and Engineering，2021，21(25):10814-10819.)