Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Two-Stage Photovoltaic Forecasting: Separating Weather Prediction from Plant-Characteristics

Philipp Danner, Hermann de Meer

Abstract

Several energy management applications rely on accurate photovoltaic generation forecasts. Common metrics like mean absolute error or root-mean-square error, omit error-distribution details needed for stochastic optimization. In addition, several approaches use weather forecasts as inputs without analyzing the source of the prediction error. To overcome this gap, we decompose forecasting into a weather forecast model for environmental parameters such as solar irradiance and temperature and a plant characteristic model that captures site-specific parameters like panel orientation, temperature influence, or regular shading. Satellite-based weather observation serves as an intermediate layer. We analyze the error distribution of the high-resolution rapid-refresh numerical weather prediction model that covers the United States as a black-box model for weather forecasting and train an ensemble of neural networks on historical power output data for the plant characteristic model. Results show mean absolute error increases by 11% and 68% for two selected photovoltaic systems when using weather forecasts instead of satellite-based ground-truth weather observations as a perfect forecast. The generalized hyperbolic and Student's t distributions adequately fit the forecast errors across lead times.

Two-Stage Photovoltaic Forecasting: Separating Weather Prediction from Plant-Characteristics

Abstract

Several energy management applications rely on accurate photovoltaic generation forecasts. Common metrics like mean absolute error or root-mean-square error, omit error-distribution details needed for stochastic optimization. In addition, several approaches use weather forecasts as inputs without analyzing the source of the prediction error. To overcome this gap, we decompose forecasting into a weather forecast model for environmental parameters such as solar irradiance and temperature and a plant characteristic model that captures site-specific parameters like panel orientation, temperature influence, or regular shading. Satellite-based weather observation serves as an intermediate layer. We analyze the error distribution of the high-resolution rapid-refresh numerical weather prediction model that covers the United States as a black-box model for weather forecasting and train an ensemble of neural networks on historical power output data for the plant characteristic model. Results show mean absolute error increases by 11% and 68% for two selected photovoltaic systems when using weather forecasts instead of satellite-based ground-truth weather observations as a perfect forecast. The generalized hyperbolic and Student's t distributions adequately fit the forecast errors across lead times.
Paper Structure (17 sections, 2 equations, 15 figures, 4 tables)

This paper contains 17 sections, 2 equations, 15 figures, 4 tables.

Table of Contents

  1. INTRODUCTION
  2. RELATED WORK
  3. METHODOLOGY
  4. Plant Characteristic Model
  5. Weather Forecast Model
  6. EXPERIMENTAL SETUP
  7. Plant Characteristic Model
  8. Dataset
  9. Input Feature Selection
  10. Hyperparameter Tuning
  11. Weather Forecast Model
  12. Error Analysis
  13. RESULTS AND DISCUSSION
  14. Plant Characteristic Model
  15. Weather Forecast Model
  16. ...and 2 more sections

Figures (15)

  • Figure 1: Inputs/outputs of the plant characteristic model on the time axis.
  • Figure 2: Plant characteristic model: ensemble of MLP.
  • Figure 3: Location of selected PV systems and the SOLRAD irradiance observation network.
  • Figure 4: Pre-processed AC power data from the selected PV systems with training and test data split.
  • Figure 5: Spearman correlation of input features to the AC power output of both PV systems.
  • ...and 10 more figures