Research map / Time series / Foundation models for time series
HyperLoad: A Cross-Modality Enhanced Large Language Model-Based Framework for Green Data Center Cooling Load Prediction
Haoyu Jiang, Boan Qu, Junjie Zhu, Fanjie Zeng, Xiaojie Lin, Wei Zhong
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add ADPT (text prior prefix tuning) (ablation) | HyperLoad · DCData (100% train, PL=96) | MSE: 0.0220 -> 0.0192 | Improved |
| add EGIA cross-variable attention (ablation) | HyperLoad · DCData (100% train, PL=96) | MSE: 0.0211 -> 0.0192 | Improved |
| add KARI cross-modal alignment loss (ablation) | HyperLoad · DCData (100% train, PL=96) | MSE: 0.0194 -> 0.0192 | Improved |
| use LLaMA backbone instead of BERT (ablation) | HyperLoad · DCData (100% train, PL=96) | MSE: 0.0217 -> 0.0192 | Improved |
| use LLaMA backbone instead of GPT-2 (ablation) | HyperLoad · DCData (100% train, PL=96) | MSE: 0.0224 -> 0.0192 | Improved |
| use LLaMA instead of GPT-2 costs more training time (ablation) | HyperLoad · DCData | Time per iteration (s): 0.1943 -> 0.3928 | Hurt |
| HyperLoad vs best baseline with 50% training data | HyperLoad · DCData (50% train) | MSE: MSE reduced by 6.5%, 3.3%, 4.5%, 3.9% | Improved |
| HyperLoad vs best baseline with 25% training data | HyperLoad · DCData (25% train) | MSE: MSE reductions 16.7%, 13.2%, 1.7%, 2.6% | Improved |
| reduce training data from 100% to 25% (ablation) | HyperLoad · DCData (PL=96) | MSE: 0.0192 -> 0.0442 | Hurt |
| HyperLoad vs iTransformer at 100% data, PL=96 | HyperLoad · DCData (100% train, PL=96) | MAE: 0.0977 -> 0.0931 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- iTransformer — iTransformer: Inverted Transformers Are Effective for Time Series Forecasting (ICLR 2024) · better on 3 of 3 shared results
- SCINet — SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction (NeurIPS 2022) · better on 2 of 2 shared results
- TimesNet — TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis (ICLR 2023) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Carbon Footprint Reduction for Sustainable Data Centers in Real-Time (AAAI 2024 · similarity 0.88)
- DCcluster-Opt: Benchmarking Dynamic Multi-Objective Optimization for Geo-Distributed Data Center Workloads (NeurIPS 2025 · similarity 0.88)
- Hierarchical Multi-Agent Framework for Carbon-Efficient Liquid-Cooled Data Center Clusters (AAAI 2025 · similarity 0.86)
- SustainDC: Benchmarking for Sustainable Data Center Control (NeurIPS 2024 · similarity 0.84)
- LLMCarbon: Modeling the End-to-End Carbon Footprint of Large Language Models (ICLR 2024 · similarity 0.84)
- Sustainability of Data Center Digital Twins with Reinforcement Learning (AAAI 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
