{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T18:08:10Z","timestamp":1757614090154,"version":"3.44.0"},"reference-count":61,"publisher":"Association for Computing Machinery (ACM)","issue":"11","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Proc. VLDB Endow."],"published-print":{"date-parts":[[2025,7]]},"abstract":"<jats:p>Workload forecasting is pivotal in cloud service applications, such as auto-scaling and scheduling, with profound implications for operational efficiency. Although Transformer-based forecasting models have demonstrated remarkable success in general tasks, their computational efficiency often falls short of the stringent requirements in large-scale cloud environments. Given that most workload series exhibit complicated periodic patterns, addressing these challenges in the frequency domain offers substantial advantages. To this end, we propose Fremer, an efficient and effective deep forecasting model. Fremer fulfills three critical requirements: it demonstrates superior efficiency, outperforming most Transformer-based forecasting models; it achieves exceptional accuracy, surpassing all state-of-the-art (SOTA) models in workload forecasting; and it exhibits robust performance for multi-period series. Furthermore, we collect and open-source four high-quality, open-source workload datasets derived from ByteDance's cloud services, encompassing workload data from thousands of computing instances. Extensive experiments on both our proprietary datasets and public benchmarks demonstrate that Fremer consistently outperforms baseline models, achieving average improvements of 5.5% in MSE, 4.7% in MAE, and 8.6% in SMAPE over SOTA models, while simultaneously reducing parameter scale and computational costs. Additionally, in a proactive auto-scaling test based on Kubernetes, Fremer improves average latency by 18.78% and reduces resource consumption by 2.35%, underscoring its practical efficacy in real-world applications.<\/jats:p>","DOI":"10.14778\/3749646.3749656","type":"journal-article","created":{"date-parts":[[2025,9,4]],"date-time":"2025-09-04T17:55:06Z","timestamp":1757008506000},"page":"3812-3825","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Fremer: Lightweight and Effective Frequency Transformer for Workload Forecasting in Cloud Services"],"prefix":"10.14778","volume":"18","author":[{"given":"Hengyu","family":"Ye","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong Univerisity"}]},{"given":"Jiadong","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong Univerisity and University of New South Wales"}]},{"given":"Fuxin","family":"Jiang","sequence":"additional","affiliation":[{"name":"ByteDance Inc."}]},{"given":"Xiao","family":"He","sequence":"additional","affiliation":[{"name":"ByteDance Inc."}]},{"given":"Tieying","family":"Zhang","sequence":"additional","affiliation":[{"name":"ByteDance Inc."}]},{"given":"Jianjun","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance Inc."}]},{"given":"Xiaofeng","family":"Gao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong Univerisity"}]}],"member":"320","published-online":{"date-parts":[[2025,9,4]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3101147"},{"key":"e_1_2_1_2_1","volume-title":"Simulation of SLA-based VM-scaling algorithms for cloud-distributed applications. Future Generation computer systems 54","author":"Antonescu Alexandru-Florian","year":"2016","unstructured":"Alexandru-Florian Antonescu and Torsten Braun. 2016. Simulation of SLA-based VM-scaling algorithms for cloud-distributed applications. Future Generation computer systems 54 (2016), 260\u2013273."},{"key":"e_1_2_1_3_1","volume-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271","author":"Bai Shaojie","year":"2018","unstructured":"Shaojie Bai, J Zico Kolter, and Vladlen Koltun. 2018. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271 (2018)."},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-015-1520-y"},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.2307\/2985674"},{"key":"e_1_2_1_6_1","volume-title":"Workload prediction using ARIMA model and its impact on cloud applications' QoS","author":"Calheiros Rodrigo N","year":"2014","unstructured":"Rodrigo N Calheiros, Enayat Masoumi, Rajiv Ranjan, and Rajkumar Buyya. 2014. Workload prediction using ARIMA model and its impact on cloud applications' QoS. IEEE transactions on cloud computing 3, 4 (2014), 449\u2013458."},{"key":"e_1_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Cristian Challu Kin G. Olivares Boris N. Oreshkin Federico Garza Max Mergenthaler-Canseco and Artur Dubrawski. 2022. N-HiTS: Neural Hierarchical Interpolation for Time Series Forecasting. arXiv:2201.12886 [cs.LG]","DOI":"10.1609\/aaai.v37i6.25854"},{"key":"e_1_2_1_8_1","volume-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555","author":"Chung Junyoung","year":"2014","unstructured":"Junyoung Chung, Caglar Gulcehre, KyungHyun Cho, and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)."},{"key":"e_1_2_1_9_1","volume-title":"International Conference on Learning Representations.","author":"Dai Tao","year":"2024","unstructured":"Tao Dai, Beiliang Wu, Peiyuan Liu, Naiqi Li, Jigang Bao, Yong Jiang, and Shu-Tao Xia. 2024. Periodicity decoupling framework for long-term series forecasting. In International Conference on Learning Representations."},{"key":"e_1_2_1_10_1","first-page":"25390","article-title":"Earthformer: Exploring space-time transformers for earth system forecasting","volume":"35","author":"Gao Zhihan","year":"2022","unstructured":"Zhihan Gao, Xingjian Shi, Hao Wang, Yi Zhu, Yuyang Bernie Wang, Mu Li, and Dit-Yan Yeung. 2022. Earthformer: Exploring space-time transformers for earth system forecasting. Advances in Neural Information Processing Systems 35 (2022), 25390\u201325403.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2021.04.006"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.14778\/3583140.3583155"},{"key":"e_1_2_1_13_1","volume-title":"International journal of forecasting 20, 1","author":"Holt Charles C","year":"2004","unstructured":"Charles C Holt. 2004. Forecasting seasonals and trends by exponentially weighted moving averages. International journal of forecasting 20, 1 (2004), 5\u201310."},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2023.102158"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3113714"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2021.10.019"},{"key":"e_1_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Reihaneh Khorsand Mostafa Ghobaei-Arani and Mohammadreza Ramezanpour. 2018. WITHDRAWN: a fuzzy auto-scaling approach using workload prediction for MMOG application in a cloud environment.","DOI":"10.1016\/j.simpat.2018.07.009"},{"key":"e_1_2_1_18_1","volume-title":"International Conference on Learning Representations.","author":"Kim Taesung","year":"2021","unstructured":"Taesung Kim, Jinhee Kim, Yunwon Tae, Cheonbok Park, Jang-Ho Choi, and Jaegul Choo. 2021. Reversible instance normalization for accurate time-series forecasting against distribution shift. In International Conference on Learning Representations."},{"key":"e_1_2_1_19_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_2_1_20_1","volume-title":"Reformer: The efficient transformer. arXiv preprint arXiv:2001.04451","author":"Kitaev Nikita","year":"2020","unstructured":"Nikita Kitaev, \u0141ukasz Kaiser, and Anselm Levskaya. 2020. Reformer: The efficient transformer. arXiv preprint arXiv:2001.04451 (2020)."},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIT.2016.065"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210006"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10951-015-0423-3"},{"key":"e_1_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCWAMTIP53232.2021.9674067"},{"key":"e_1_2_1_25_1","volume-title":"Asia-Pacific Network Operations and Management Symposium (APNOMS). IEEE, 1\u20136.","author":"Li Shengming","year":"2013","unstructured":"Shengming Li, Ying Wang, Xuesong Qiu, Deyuan Wang, and Lijun Wang. 2013. A workload prediction-based multi-vm provisioning mechanism in cloud computing. In Asia-Pacific Network Operations and Management Symposium (APNOMS). IEEE, 1\u20136."},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i12.26676"},{"key":"e_1_2_1_27_1","volume-title":"Sparsetsf: Modeling long-term time series forecasting with 1k parameters. arXiv preprint arXiv:2405.00946","author":"Lin Shengsheng","year":"2024","unstructured":"Shengsheng Lin, Weiwei Lin, Wentai Wu, Haojun Chen, and Junjie Yang. 2024. Sparsetsf: Modeling long-term time series forecasting with 1k parameters. arXiv preprint arXiv:2405.00946 (2024)."},{"key":"e_1_2_1_28_1","first-page":"5816","article-title":"Scinet: Time series modeling and forecasting with sample convolution and interaction","volume":"35","author":"Liu Minhao","year":"2022","unstructured":"Minhao Liu, Ailing Zeng, Muxi Chen, Zhijian Xu, Qiuxia Lai, Lingna Ma, and Qiang Xu. 2022. Scinet: Time series modeling and forecasting with sample convolution and interaction. Advances in Neural Information Processing Systems 35 (2022), 5816\u20135828.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_29_1","volume-title":"International Conference on Learning Representations.","author":"Liu Shizhan","year":"2022","unstructured":"Shizhan Liu, Hang Yu, Cong Liao, Jianguo Li, Weiyao Lin, Alex X Liu, and Schahram Dustdar. 2022. Pyraformer: Low-complexity pyramidal attention for long-range time series modeling and forecasting. In International Conference on Learning Representations."},{"key":"e_1_2_1_30_1","volume-title":"itransformer: Inverted transformers are effective for time series forecasting. arXiv preprint arXiv:2310.06625","author":"Liu Yong","year":"2023","unstructured":"Yong Liu, Tengge Hu, Haoran Zhang, Haixu Wu, Shiyu Wang, Lintao Ma, and Mingsheng Long. 2023. itransformer: Inverted transformers are effective for time series forecasting. arXiv preprint arXiv:2310.06625 (2023)."},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2019.03.003"},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2460756.2460758"},{"volume-title":"A workload prediction approach using models stacking based on recurrent neural network and autoencoder. In 2016 IEEE 18th International Conference on High Performance Computing and Communications","author":"Nguyen Hoang Minh","key":"e_1_2_1_33_1","unstructured":"Hoang Minh Nguyen, Sungpil Woo, Janggwan Im, Taejoon Jun, and Daeyoung Kim. 2016. A workload prediction approach using models stacking based on recurrent neural network and autoencoder. In 2016 IEEE 18th International Conference on High Performance Computing and Communications; IEEE 14th International Conference on Smart City; IEEE 2nd International Conference on Data Science and Systems (HPCC\/SmartCity\/DSS). IEEE, 929\u2013936."},{"key":"e_1_2_1_34_1","first-page":"71222","article-title":"Basisformer: Attention-based time series forecasting with learnable and interpretable basis","volume":"36","author":"Ni Zelin","year":"2023","unstructured":"Zelin Ni, Hang Yu, Shizhan Liu, Jianguo Li, and Weiyao Lin. 2023. Basisformer: Attention-based time series forecasting with learnable and interpretable basis. Advances in Neural Information Processing Systems 36 (2023), 71222\u201371241.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_35_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Nie Yuqi","year":"2022","unstructured":"Yuqi Nie, Nam H Nguyen, Phanwadee Sinthong, and Jayant Kalagnanam. 2022. A Time Series is Worth 64 Words: Long-term Forecasting with Transformers. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_2_1_36_1","volume-title":"N-BEATS: Neural basis expansion analysis for interpretable time series forecasting. arXiv preprint arXiv:1905.10437","author":"Oreshkin Boris N","year":"2019","unstructured":"Boris N Oreshkin, Dmitri Carpov, Nicolas Chapados, and Yoshua Bengio. 2019. N-BEATS: Neural basis expansion analysis for interpretable time series forecasting. arXiv preprint arXiv:1905.10437 (2019)."},{"key":"e_1_2_1_37_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671928"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.14778\/3665844.3665863"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2015.06.019"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.15439\/2020F213"},{"key":"e_1_2_1_42_1","volume-title":"Workload forecasting and resource management models based on machine learning for cloud computing environments. arXiv preprint arXiv:2106.15112","author":"Saxena Deepika","year":"2021","unstructured":"Deepika Saxena and Ashutosh Kumar Singh. 2021. Workload forecasting and resource management models based on machine learning for cloud computing environments. arXiv preprint arXiv:2106.15112 (2021)."},{"key":"e_1_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CloudTech.2016.7847713"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-017-2044-4"},{"key":"e_1_2_1_45_1","volume-title":"FreDo: Frequency Domain-based Long-Term Time Series Forecasting. arXiv e-prints","author":"Sun Fan-Keng","year":"2022","unstructured":"Fan-Keng Sun and Duane S Boning. 2022. FreDo: Frequency Domain-based Long-Term Time Series Forecasting. arXiv e-prints (2022), arXiv-2205."},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-1078-5_2"},{"key":"e_1_2_1_47_1","unstructured":"G\u00f6kalp Urul. 2018. Energy efficient dynamic virtual machine allocation with CPU usage prediction in cloud datacenters. Master's thesis. Bilkent Universitesi (Turkey)."},{"key":"e_1_2_1_48_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_2_1_49_1","volume-title":"Micn: Multi-scale local and global context modeling for long-term series forecasting. In The eleventh international conference on learning representations.","author":"Wang Huiqiang","year":"2023","unstructured":"Huiqiang Wang, Jian Peng, Feihu Huang, Jince Wang, Junhui Chen, and Yifei Xiao. 2023. Micn: Multi-scale local and global context modeling for long-term series forecasting. In The eleventh international conference on learning representations."},{"key":"e_1_2_1_50_1","volume-title":"Etsformer: Exponential smoothing transformers for time-series forecasting. arXiv preprint arXiv:2202.01381","author":"Woo Gerald","year":"2022","unstructured":"Gerald Woo, Chenghao Liu, Doyen Sahoo, Akshat Kumar, and Steven Hoi. 2022. Etsformer: Exponential smoothing transformers for time-series forecasting. arXiv preprint arXiv:2202.01381 (2022)."},{"key":"e_1_2_1_51_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Wu Haixu","year":"2022","unstructured":"Haixu Wu, Tengge Hu, Yong Liu, Hang Zhou, Jianmin Wang, and Mingsheng Long. 2022. TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_2_1_52_1","first-page":"22419","article-title":"Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting","volume":"34","author":"Wu Haixu","year":"2021","unstructured":"Haixu Wu, Jiehui Xu, Jianmin Wang, and Mingsheng Long. 2021. Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. Advances in Neural Information Processing Systems 34 (2021), 22419\u201322430.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_53_1","volume-title":"FITS: Modeling Time Series with 10k Parameters. arXiv:2307.03756 [cs.LG]","author":"Xu Zhijian","year":"2024","unstructured":"Zhijian Xu, Ailing Zeng, and Qiang Xu. 2024. FITS: Modeling Time Series with 10k Parameters. arXiv:2307.03756 [cs.LG]"},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD.2013.146"},{"key":"e_1_2_1_55_1","first-page":"55115","article-title":"Filternet: Harnessing frequency filters for time series forecasting","volume":"37","author":"Yi Kun","year":"2024","unstructured":"Kun Yi, Jingru Fei, Qi Zhang, Hui He, Shufeng Hao, Defu Lian, and Wei Fan. 2024. Filternet: Harnessing frequency filters for time series forecasting. Advances in Neural Information Processing Systems (NeurIPS) 37 (2024), 55115\u201355140.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_2_1_56_1","volume-title":"Thirty-seventh Conference on Neural Information Processing Systems.","author":"Yi Kun","year":"2023","unstructured":"Kun Yi, Qi Zhang, Wei Fan, Shoujin Wang, Pengyang Wang, Hui He, Ning An, Defu Lian, Longbing Cao, and Zhendong Niu. 2023. Frequency-domain MLPs are More Effective Learners in Time Series Forecasting. In Thirty-seventh Conference on Neural Information Processing Systems."},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26317"},{"key":"e_1_2_1_58_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Zhang Yunhao","year":"2022","unstructured":"Yunhao Zhang and Junchi Yan. 2022. Crossformer: Transformer utilizing cross-dimension dependency for multivariate time series forecasting. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"e_1_2_1_60_1","first-page":"12677","article-title":"Film: Frequency improved legendre memory model for long-term time series forecasting","volume":"35","author":"Zhou Tian","year":"2022","unstructured":"Tian Zhou, Ziqing Ma, Qingsong Wen, Liang Sun, Tao Yao, Wotao Yin, Rong Jin, et al. 2022. Film: Frequency improved legendre memory model for long-term time series forecasting. Advances in Neural Information Processing Systems 35 (2022), 12677\u201312690.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_61_1","volume-title":"International Conference on Machine Learning. PMLR, 27268\u201327286","author":"Zhou Tian","year":"2022","unstructured":"Tian Zhou, Ziqing Ma, Qingsong Wen, Xue Wang, Liang Sun, and Rong Jin. 2022. Fedformer: Frequency enhanced decomposed transformer for long-term series forecasting. In International Conference on Machine Learning. PMLR, 27268\u201327286."}],"container-title":["Proceedings of the VLDB Endowment"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.14778\/3749646.3749656","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T03:09:21Z","timestamp":1757041761000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.14778\/3749646.3749656"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":61,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["10.14778\/3749646.3749656"],"URL":"https:\/\/doi.org\/10.14778\/3749646.3749656","relation":{},"ISSN":["2150-8097"],"issn-type":[{"type":"print","value":"2150-8097"}],"subject":[],"published":{"date-parts":[[2025,7]]},"assertion":[{"value":"2025-09-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}