Research map / Probabilistic and scientific modeling / Molecules and proteins
TrustEnergy: A Unified Framework for Accurate and Reliable User-level Energy Usage Prediction
Dahai Yu, Rongchao Xu, Dingyi Zhuang, Yuheng Bu, Shenhao Wang, Guang Wang
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 hierarchical (micro plus macro) spatiotemporal representation (ablation) | TrustEnergy · Florida (61,672 households) | MAE: 49.35 -> 45.72 | Improved |
| add memory-augmented parameter update (MASTGNN) (ablation) | TrustEnergy · Florida (61,672 households) | MAE: 47.54 -> 45.72 | Improved |
| use sequential CQR instead of traditional CQR (ablation) | TrustEnergy · Florida (61,672 households) | Winkler score: 104.70 -> 102.31 | Improved |
| add hierarchical representation (ablation) | TrustEnergy · NY | MAE: 0.431 -> 0.137 | Improved |
| add hierarchical representation (ablation) | TrustEnergy · CA | MAE: 0.471 -> 0.327 | Improved |
| add memory-augmented update (ablation) | TrustEnergy · NY | MAE: 0.358 -> 0.137 | Improved |
| add SCQR (ablation) | TrustEnergy · NY | Winkler score: 1.054 -> 0.727 | Improved |
| add SCQR (ablation) | TrustEnergy · CA | Winkler score: 2.463 -> 2.325 | Improved |
| TrustEnergy versus best baseline AGCRN | TrustEnergy · Florida (61,672 households) | MAE: 48.35 -> 45.72 | Improved |
| TrustEnergy versus baselines on NY and CA | TrustEnergy · NY/CA | MAE, RMSE, MAPE, MPIW, WINK: NY MAPE 0.57% vs STZINB 0.54%; CA WINK 2.325 vs 2.225 DeepSTUQ | Mixed |
Closest papers by meaning
- PowerPM: Foundation Model for Power Systems (NeurIPS 2024 · similarity 0.84)
- PowerGraph: A power grid benchmark dataset for graph neural networks (NeurIPS 2024 · similarity 0.82)
- The Hidden Joules: Evaluating the Energy Consumption of Vision Backbones for Progress Towards More Efficient Model Inference (ICML 2025 · similarity 0.81)
- PF∆: A Benchmark Dataset for Power Flow under Load, Generation, and Topology Variations (NeurIPS 2025 · similarity 0.81)
- Carbon Footprint Reduction for Sustainable Data Centers in Real-Time (AAAI 2024 · similarity 0.81)
- HiFi-Gas: Hierarchical Federated Learning Incentive Mechanism Enhanced Gas Usage Estimation (AAAI 2024 · similarity 0.81)
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.
