LSTM-Based Time-Series Forecasting for Green Low-Carbon Data Center Energy Consumption: A Dual-Carbon Data Element Management Perspective
Main Article Content
Abstract
Data centers already draw a fast-growing slice of global electricity, and operators cannot chase carbon peaking and carbon neutrality (“dual-carbon”) targets without knowing, ahead of time, how much power a facility is about to use. This paper builds an LSTM-based forecasting framework for data center energy consumption and places it inside a full-cycle dual-carbon data element management pipeline, one that tracks how operational data is collected, cataloged, shared across institutions, and eventually consumed by carbon-accounting services downstream. The forecaster itself is fairly simple to describe: a sliding-window preprocessing stage feeds a stacked LSTM encoder with attention-weighted temporal pooling, and a lightweight regression head predicts total facility power draw together with Power Usage Effectiveness (PUE) one to twenty-four steps ahead. We test it on a twelve-month, five-minute-resolution operational dataset built to reproduce typical hyperscale load and cooling patterns, benchmarking against ARIMA, Support Vector Regression (SVR), a Gated Recurrent Unit (GRU) network, and a vanilla single-layer LSTM. One-step-ahead Root Mean Square Error (RMSE) drops by 34.6% against ARIMA, 24.1% against SVR, 15.7% against GRU, and 9.8% against vanilla LSTM; an ablation study confirms that both attention pooling and multi-task PUE co-prediction contribute real, separable gains rather than overlapping ones. We also work through how this forecasting module behaves as a governed data product inside a cross-institution carbon data catalog, including downstream uses such as estimating carbon tariff exposure under the EU Carbon Border Adjustment Mechanism (CBAM). Taken together, the results suggest that pairing accurate short-horizon forecasting with structured data governance pays off on two fronts at once: operational efficiency and the auditability that low-carbon data center management increasingly requires.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
Y. Chen, X. Zhao, and L. Wang, “A hybrid ARIMA and machine learning approach for short-term load forecasting in industrial facilities,” Energy Reports, vol. 8, pp. 4213–4225, 2022.
M. Alharbi and S. Kim, “Support vector regression for short-term building energy load forecasting: A comparative study,” Energies, vol. 15, no. 3, p. 1103, 2022.
H. Zhang, “A hybrid DEA-XGBoost model for regional carbon-emission efficiency evaluation and crisis risk identification,” Journal of Cleaner Production, vol. 412, p. 137345, 2023.
R. Patel, A. Gupta, and J. Lee, “Deep learning-based prediction of data center power usage effectiveness using LSTM networks,” IEEE Transactions on Sustainable Computing, vol. 8, no. 2, pp. 289–301, 2023.
F. Torres and D. Nguyen, “Recurrent neural networks for data center thermal and power management: A survey of practical deployments,” Applied Energy, vol. 331, p. 120412, 2023.
W. Liu, Y. Sun, and Q. Xu, “Attention-based LSTM for multi-step energy load forecasting in smart buildings,” Energy and Buildings, vol. 274, p. 112421, 2022.
S. Park, T. Kim, and H. Choi, “Transformer-based long-horizon forecasting for electricity demand: Accuracy and computational trade-offs,” Applied Energy, vol. 349, p. 121567, 2023.
J. Wu and M. Chen, “CBAM-enhanced convolutional networks for industrial equipment condition monitoring,” in Proc. IEEE Int. Conf. Ind. Informatics, 2022, pp. 145–151.
A. Ivanov and K. Petrova, “Reinforcement learning for data center cooling control informed by IT load forecasts,” IEEE Access, vol. 11, pp. 55210– 55223, 2023.
L. Zhao, “Full-lifecycle data element management for dual-carbon objectives: Governance architecture and unified cataloging,” Sustainability, vol. 16, no. 4, p. 1587, 2024.
B. Fernandez and C. Rossi, “Cross-institution carbon data sharing mechanisms: Design principles and case evidence,” Journal of Environmental Management, vol. 331, p. 117234, 2023.
E. Novak and P. Dubois, “The EU Carbon Border Adjustment Mechanism: Compliance data requirements and firm-level reporting challenges,” Climate Policy, vol. 24, no. 2, pp. 178–194, 2024.
Y. Tan, “Spatial-temporal evolution of traffic carbon emission efficiency across 30 Chinese provinces: A data envelopment analysis approach,” Transportation Research Part D, vol. 118, p. 103712, 2023.
M. Xu and R. Song, “Digital education resource platforms and human capital: An evaluation of adoption and governance quality,” Computers & Education, vol. 197, p. 104742, 2023.
K. Osei and D. Adeyemi, “Generative and predictive AI adoption in operational energy systems: A governance-aware review,” Renewable and Sustainable Energy Reviews, vol. 189, p. 113921, 2024.