# Neural network interpretability for forecasting of aggregated renewable generation

arXiv: https://arxiv.org/abs/2106.10476 · HTML: https://mlsanity.com/paper/2106.10476/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 23 references that are in the map.
- First posted on arXiv 19 Jun 2021.

## Builds on (most cited first, 6 of 6)

- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Learning Important Features Through Propagating Activation Differences](https://mlsanity.com/paper/1704.02685/) (2017)
- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [Solar Power Forecasting Using Support Vector Regression](https://mlsanity.com/paper/1703.09851/) (2017)

## Built on by (most cited first, 2 of 2)

- [An Interpretable Probabilistic Model for Short-Term Solar Power Forecasting Using Natural Gradient Boosting](https://mlsanity.com/paper/2108.04058/) (2021)
- [Explainable Global Wildfire Prediction Models using Graph Neural Networks](https://mlsanity.com/paper/2402.07152/) (2024)

## Abstract (arXiv)

With the rapid growth of renewable energy, lots of small photovoltaic (PV) prosumers emerge. Due to the uncertainty of solar power generation, there is a need for aggregated prosumers to predict solar power generation and whether solar power generation will be larger than load. This paper presents two interpretable neural networks to solve the problem: one binary classification neural network and one regression neural network. The neural networks are built using TensorFlow. The global feature importance and local feature contributions are examined by three gradient-based methods: Integrated Gradients, Expected Gradients, and DeepLIFT. Moreover, we detect abnormal cases when predictions might fail by estimating the prediction uncertainty using Bayesian neural networks. Neural networks, which are interpreted by gradient-based methods and complemented with uncertainty estimation, provide robust and explainable forecasting for decision-makers.