Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Solarcast-ML: Per Node GraphCast Extension for Solar Energy Production

Cale Colony, Razan Andigani

TL;DR

The results demonstrate the model's effectiveness in accurately predicting solar radiation, with its convergence behavior, decreasing training loss, and accurate prediction of solar radiation patterns suggesting successful learning of the underlying relationships between weather conditions and solar radiation.

Abstract

This project presents an extension to the GraphCast model, a state-of-the-art graph neural network (GNN) for global weather forecasting, by integrating solar energy production forecasting capabilities. The proposed approach leverages the weather forecasts generated by GraphCast and trains a neural network model to predict the ratio of actual solar output to potential solar output based on various weather conditions. The model architecture consists of an input layer corresponding to weather features (temperature, humidity, dew point, wind speed, rain, barometric pressure, and altitude), two hidden layers with ReLU activations, and an output layer predicting solar radiation. The model is trained using a mean absolute error loss function and Adam optimizer. The results demonstrate the model's effectiveness in accurately predicting solar radiation, with its convergence behavior, decreasing training loss, and accurate prediction of solar radiation patterns suggesting successful learning of the underlying relationships between weather conditions and solar radiation. The integration of solar energy production forecasting with GraphCast offers valuable insights for the renewable energy sector, enabling better planning and decision-making based on expected solar energy production. Future work could explore further model refinements, incorporation of additional weather variables, and extension to other renewable energy sources.

Solarcast-ML: Per Node GraphCast Extension for Solar Energy Production

TL;DR

The results demonstrate the model's effectiveness in accurately predicting solar radiation, with its convergence behavior, decreasing training loss, and accurate prediction of solar radiation patterns suggesting successful learning of the underlying relationships between weather conditions and solar radiation.

Abstract

This project presents an extension to the GraphCast model, a state-of-the-art graph neural network (GNN) for global weather forecasting, by integrating solar energy production forecasting capabilities. The proposed approach leverages the weather forecasts generated by GraphCast and trains a neural network model to predict the ratio of actual solar output to potential solar output based on various weather conditions. The model architecture consists of an input layer corresponding to weather features (temperature, humidity, dew point, wind speed, rain, barometric pressure, and altitude), two hidden layers with ReLU activations, and an output layer predicting solar radiation. The model is trained using a mean absolute error loss function and Adam optimizer. The results demonstrate the model's effectiveness in accurately predicting solar radiation, with its convergence behavior, decreasing training loss, and accurate prediction of solar radiation patterns suggesting successful learning of the underlying relationships between weather conditions and solar radiation. The integration of solar energy production forecasting with GraphCast offers valuable insights for the renewable energy sector, enabling better planning and decision-making based on expected solar energy production. Future work could explore further model refinements, incorporation of additional weather variables, and extension to other renewable energy sources.
Paper Structure (8 sections, 5 figures)

This paper contains 8 sections, 5 figures.

Table of Contents

  1. Introduction
  2. Related Work
  3. Algorithmic Extension
  4. Experiments and Results
  5. Data Collection
  6. Experimental Setup
  7. Results
  8. Conclusions

Figures (5)

  • Figure 1: Image detailing specifics of weather sensor
  • Figure 2: Aerial view of the weather sensing array location, along with measurements indicating the distance and path from the array to the GraphCast prediction point provided in the ERA5 dataset.
  • Figure 3: Convergence of the model using SGD optimizer over the course of 100 epochs. Y-axis is watts per square meter mean square training loss.
  • Figure 4: Convergence of the model using Adam optimizer over the course of 100 epochs. Y-axis is watts per square meter mean square training loss.
  • Figure 5: Final convergence of the trained model over 1000 epochs, showing predicted solar radiation values. Y-axis is watts per square meter mean square training loss.