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 the gradient-based methods and complemented with uncertainty estimation, provide robust and explainable forecasting for decision-makers.
|Title of host publication||Proceedings of 2021 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids|
|Publication status||Published - 2021|
|Event||2021 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids - Aachen , Germany|
Duration: 25 Oct 2021 → 28 Oct 2021
|Conference||2021 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids|
|Period||25/10/2021 → 28/10/2021|