Summary of From Rnns to Foundation Models: An Empirical Study on Commercial Building Energy Consumption, by Shourya Bose and Yijiang Li and Amy Van Sant and Yu Zhang and Kibaek Kim
From RNNs to Foundation Models: An Empirical Study on Commercial Building Energy Consumption
by Shourya Bose, Yijiang Li, Amy Van Sant, Yu Zhang, Kibaek Kim
First submitted to arxiv on: 21 Nov 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper addresses the challenge of accurate short-term energy consumption forecasting for commercial buildings using smart meters and deep learning models. To tackle data heterogeneity issues, the authors use the ComStock dataset, which provides synthetic energy consumption data for U.S. commercial buildings. They create two curated subsets with different building types to assess various time series forecasting models’ performance, including fine-tuned open-source foundation models (FMs). The results show that dataset heterogeneity and model architecture have a greater impact on post-training forecasting performance than the parameter count. Moreover, fine-tuned FMs demonstrate competitive performance compared to base models trained from scratch. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper tries to make energy consumption forecasts better for big buildings. They use a special data set that has fake information about building energy use. The authors want to see how well different kinds of forecasting models work when they’re given this data. They found out that the kind of data and the model used are more important than how much training the model gets. The best models were fine-tuned versions of big models, even though they took longer to train. |
Keywords
» Artificial intelligence » Deep learning » Time series
