Summary of Deep and Probabilistic Solar Irradiance Forecast at the Arctic Circle, by Niklas Erdmann et al.
Deep and Probabilistic Solar Irradiance Forecast at the Arctic Circle
by Niklas Erdmann, Lars Ø. Bentsen, Roy Stenbro, Heine N. Riise, Narada Warakagoda, Paal Engelstad
First submitted to arxiv on: 10 Oct 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 Solar irradiance forecasts are crucial for optimizing energy generation near the Arctic circle. This study develops variations of Long-Short-Term Memory units (LSTMs) to improve forecast accuracy using Norwegian data. To enhance trustworthiness, probabilistic approaches Quantile Regression (QR) and Maximum Likelihood Estimation (MLE) are applied on top of LSTMs, providing measures of uncertainty for the results. The MLE is extended by incorporating various distributions, including Johnson’s SU and SB, Weibull, and normal Gaussian to model parameters. Compared against simple Multi-layer Perceptrons (MLPs), smart-persistence estimators, and deterministic LSTMs, the proposed LSTMs show improved accuracy for multi-horizon, day-ahead forecasts. The study highlights a trade-off between point-prediction and uncertainty estimation calibration when optimizing models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research helps predict solar energy levels near the Arctic circle. It uses special computer models called Long-Short-Term Memory units (LSTMs) to make more accurate predictions. To make sure the results are trustworthy, the study adds a layer of uncertainty calculation using techniques like Quantile Regression and Maximum Likelihood Estimation. The goal is to create a model that can accurately forecast solar energy levels for up to 36 hours in advance. |
Keywords
» Artificial intelligence » Likelihood » Regression
