Uncertainty‐aware forecast interval for hourly PV power output

Abstract

A forecast interval is effective for handling the forecast uncertainty in solar photovoltaic systems. In estimating the forecast interval, most available approaches apply an identical policy to all the point forecasts. This results in an inefficient interval (e.g. an unnecessarily wide interval for an accurate forecast). They also adopt a complex model and even require modification of the available deterministic forecasting model, which may adversely affect their application. To overcome these limitations, the authors introduce a forecast uncertainty-aware forecast interval. They calculate a forecast accuracy-related uncertainty metric from an ensemble method based on the dropout technique. The dropout technique is widely used in deep learning models. This implies that the proposed approach can be applied to available deep learning forecasting models without modifying them. Using the uncertainty metric and relevant data of previous forecast results, they estimate the uncertainty-aware forecast interval. Through experiments using real-world data, they first demonstrate the close relation of their uncertainty metric to the forecasting accuracy. Then, they demonstrate that the uncertainty-aware forecast interval reduces the mean interval length by up to 25.7% and decreases the prediction interval coverage probability by 4.07%, compared to available approaches. This illustrates that their approach results in an effective interval.

Deep learning architecture for direct probability density prediction of small‐scale solar generation

“…Combining the fuzzy model and the wavelet neural network is presented in [12] to forecast the solar generation intervals for each time. In [13], an uncertainty metric, the dropout technique, and the deep learning structure are combined to construct PIs. Bayesian deep learning structure is used to predict point values, and the variational interface is used to construct PIs of large-scale solar generations in [14].…”

Randomised learning‐based hybrid ensemble model for probabilistic forecasting of PV power generation

“…In [20], an improved Markov chain is applied to forecast the quantiles of PV generation. In [21], the forecast uncertainty is calculated from an ensemble method based on the dropout technique of deep learning.…”