Page 104 - 《软件学报》2026年第2期

曾文瑄 等: 云计算中基于 SAC 的多视角工作负载预测集成框架 583

IEEE Int’l Conf. on Services Computing (SCC). Honolulu: IEEE, 2012. 609–616. [doi: 10.1109/SCC.2012.47]
[21] Chen ZJ, Zhu YC, Di YQ, Feng SC. Self-adaptive prediction of cloud resource demands using ensemble model and subtractive-fuzzy
clustering based fuzzy neural network. Computational Intelligence and Neuroscience, 2015, 2015(1): 919805. [doi: 10.1155/2015/
919805]
[22] Yang QP, Peng CL, Zhao H, Yu Y, Zhou Y, Wang ZQ, Du SD. A new method based on PSR and EA-GMDH for host load prediction in
cloud computing system. The Journal of Supercomputing, 2014, 68(3): 1402–1417. [doi: 10.1007/s11227-014-1097-x]
[23] Kumar AS, Mazumdar S. Forecasting HPC workload using ARMA models and SSA. In: Proc. of the 2016 Int’l Conf. on Information
Technology (ICIT). Bhubaneswar: IEEE, 2016. 294–297. [doi: 10.1109/ICIT.2016.065]
[24] Baig SUR, Iqbal W, Berral JL, Erradi A, Carrera D. Adaptive prediction models for data center resources utilization estimation. IEEE
Trans. on Network and Service Management, 2019, 16(4): 1681–1693. [doi: 10.1109/TNSM.2019.2932840]
[25] Yazdanian P, Sharifian S. E2LG: A multiscale ensemble of LSTM/GAN deep learning architecture for multistep-ahead cloud workload
prediction. The Journal of Supercomputing, 2021, 77(10): 11052–11082. [doi: 10.1007/s11227-021-03723-6]
[26] Gao HH, Huang WQ, Duan YC. The cloud-edge-based dynamic reconfiguration to service workflow for mobile ecommerce
environments: A QoS prediction perspective. ACM Trans. on Internet Technology (TOIT), 2021, 21(1): 6. [doi: 10.1145/3391198]
[27] Ruan L, Bai Y, Li SN, Lv JX, Zhang TY, Xiao LM, Fang HG, Wang CH, Xue YZ. Cloud workload turning points prediction via cloud
feature-enhanced deep learning. IEEE Trans. on Cloud Computing, 2023, 11(2): 1719–1732. [doi: 10.1109/TCC.2022.3160228]
[28] Yi K, Zhang Q, Fan W, Wang SJ, Wang PY, He H, Lian DF, An N, Cao LB, Niu ZD. Frequency-domain MLPs are more effective
learners in time series forecasting. In: Proc. of the 37th Int’l Conf. on Neural Information Processing Systems. New Orleans: Curran
Associates Inc., 2023. 3349.
[29] Zhang TP, Zhang YZ, Cao W, Bian J, Yi XH, Zheng S, Li J. Less is more: Fast multivariate time series forecasting with light sampling-
oriented MLP structures. arXiv:2207.01186, 2022.
[30] Nie YQ, Nguyen NH, Sinthong P, Kalagnanam J. A time series is worth 64 words: Long-term forecasting with Transformers. In: Proc. of
the 11th Int’l Conf. on Learning Representations (ICLR 2023). Kigali: OpenReview.net, 2023.
[31] Patel E, Kushwaha DS. An integrated deep learning prediction approach for efficient modelling of host load patterns in cloud computing.
Journal of Grid Computing, 2023, 21(1): 5. [doi: 10.1007/s10723-022-09639-6]
[32] Saadallah A, Tavakol M, Morik K. An actor-critic ensemble aggregation model for time-series forecasting. In: Proc. of the 37th IEEE Int’l
Conf. on Data Engineering (ICDE). Chania: IEEE, 2021. 2255–2260. [doi: 10.1109/ICDE51399.2021.00233]
[33] Zhang YQ, Goiri Í, Chaudhry GI, Fonseca R, Elnikety S, Delimitrou C, Bianchini R. Faster and cheaper serverless computing on
harvested resources. In: Proc. of the 28th ACM SIGOPS Symp. on Operating Systems Principles. Koblenz: ACM, 2021. 724–739. [doi:
10.1145/3477132.3483580]
[34] Verma A, Pedrosa L, Korupolu M, Oppenheimer D, Tune E, Wilkes J. Large-scale cluster management at Google with Borg. In: Proc. of
the 10th European Conf. on Computer Systems. Bordeaux: ACM, 2015. 18. [doi: 10.1145/2741948.2741964]
[35] Bai SJ, Kolter JZ, Koltun V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling.
arXiv:1803.01271, 2018.
[36] Zhang YH, Yan JC. Crossformer: Transformer utilizing cross-dimension dependency for multivariate time series forecasting. In: Proc. of
the 11th Int’l Conf. on Learning Representations (ICLR 2023). Kigali: OpenReview.net, 2023.
[37] Zhou HY, Zhang SH, Peng JQ, Zhang S, Li JX, Xiong H, Zhang WC. Informer: Beyond efficient Transformer for long sequence time-
series forecasting. In: Proc. of the 2021 AAAI Conf. on Artificial Intelligence. AAAI, 2021. 11106–11115. [doi: 10.1609/aaai.v35i12.
17325]
[38] Liu Y, Hu TG, Zhang HR, Wu HX, Wang SY, Ma LT, Long MS. iTransformer: Inverted Transformers are effective for time series
forecasting. In: Proc. of the 12th Int’l Conf. on Learning Representations (ICLR 2024). Vienna: OpenReview.net, 2024.

作者简介
曾文瑄, 硕士生, 主要研究领域为云计算, 资源管理.
应时, 博士, 教授, 博士生导师, CCF 杰出会员, 主要研究领域为云计算与云服务软件, 机器学习, 人工智能, 复杂软件系统智能化运维管
理, 软件工程的形式化理论与方法.
李田港, 博士生, CCF 学生会员, 主要研究领域为云计算, 软件工程, 资源管理, 强化学习.
田相波, 博士生, 主要研究领域为软件工程, 微服务, 智能化运维.
姜宇虹, 博士, 讲师, CCF 专业会员, 主要研究领域为智能运维, 图神经网络, 因果机器学习及应用.
刘虎杰, 主要研究领域为云计算解决方案的设计与实施, 智能运维, IT 服务管理.
郝诗魁, 硕士, 主要研究领域为云平台建设, 云运营管理, 自动化运维.