Time Series Forecasting2021en
Electricity Transformer Temperature - hourly (ETTh1)
ETTh1 is one of four ETT benchmark datasets for long-term time series forecasting. It records electricity transformer oil temperature and load at hourly granularity from a power station in China (July 2016 – July 2018). Results reported as averages across prediction horizons {96, 192, 336, 720}.
Current State of the Art
Chronos-Large
Amazon
0.588
mse
Top Models Performance Comparison
Top 3 models ranked by mse
Best Score
0.588
Top Model
Chronos-Large
Models Compared
3
Score Range
0.140
mae
| # | Model | Score | Paper / Code | Date |
|---|---|---|---|---|
| 1 | Chronos-LargeOpen Source Amazon | 0.466 | Feb 2025 | |
| 2 | TimeLLMOpen Source Tongji University / Ant Group | 0.456 | May 2024 | |
| 3 | TimesFMOpen Source Google Research | 0.443 | Feb 2025 |
msePrimary
| # | Model | Score | Paper / Code | Date |
|---|---|---|---|---|
| 1 | Chronos-LargeOpen Source Amazon | 0.588 | Feb 2025 | |
| 2 | TimesFMOpen Source Google Research | 0.473 | Feb 2025 | |
| 3 | TimeLLMOpen Source Tongji University / Ant Group | 0.448 | May 2024 |
Related Papers2
Sundial: A Family of Highly Capable Time Series Foundation Models
Feb 2025Models: Chronos-Large, TimesFM
Time-LLM: Time Series Forecasting by Reprogramming Large Language Models
May 2024Models: TimeLLM