Summary of Short-term Solar Irradiance Forecasting Under Data Transmission Constraints, by Joshua Edward Hammond (1) et al.
Short-Term Solar Irradiance Forecasting Under Data Transmission Constraints
by Joshua Edward Hammond, Ricardo A. Lara Orozco, Michael Baldea, Brian A. Korgel
First submitted to arxiv on: 19 Mar 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 introduces a novel machine learning model for short-term forecasting of solar irradiance, which inputs include reduced scalar features from sky camera images. The output values are transformed to focus on unknown short-term dynamics. Inspired by control theory, the model incorporates noise input reflecting unmeasured variables, leading to improved predictions. The model is evaluated using five years of data from NREL’s Solar Radiation Research Laboratory, with a mean absolute error of 74.34 W/m^2 compared to a baseline of 134.35 W/m^2 using the persistence of cloudiness model. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper creates a new way to predict how much sunlight will shine in the short term. It uses special cameras that take pictures of the sky and reduces this data into numbers that can be sent over the internet. The model then tries to guess how bright it will be tomorrow, based on these number inputs. To make the predictions better, the model includes some extra “noise” that represents things we can’t measure directly. This helps the model make more accurate predictions. The results show that this new approach is much better than just looking at past weather patterns. |
Keywords
* Artificial intelligence * Machine learning
