期刊
IET RENEWABLE POWER GENERATION
卷 14, 期 14, 页码 2657-2667出版社
INST ENGINEERING TECHNOLOGY-IET
DOI: 10.1049/iet-rpg.2019.1238
关键词
wind power; probability; autoregressive processes; regression analysis; recurrent neural nets; power engineering computing; load forecasting; optimisation; intelligent optimisation techniques; model training; LSTM model; exogenous models; benchmarking models; real-world data sets; uncertain wind power forecasting; LSTM-based prediction interval; recurrent neural network; long short-term memory; power uncertainty forecast; nonparametric lower upper bound estimation framework; mutual information; false nearest neighbours techniques; nonlinear auto-regressive; reliable prediction intervals; typical RNN models; wind power data sets; variational synchronicity; comprehensive objective function
Estimating prediction intervals (PIs) is an efficient and reliable way of capturing the uncertainties associated with wind power forecasting. In this study, a state of the art recurrent neural network (RNN) known as long short-term memory (LSTM) is used to produce reliable PIs for one-hour ahead wind power uncertainty forecast using the non-parametric lower upper bound estimation framework. Two realistic hourly stamped wind power data sets are obtained and by using mutual information and false nearest neighbours techniques, the data are made suitable for model inputs. A novel comprehensive objective function consisting of the coverage probability, the average width of the PIs, symmetricity and variational synchronicity is developed to train the LSTM model using intelligent optimisation techniques. The standard of the PIs generated for the test set as well as for different seasons are evaluated based on the indices used to design the objective function for model training, with one of them being modified. The performance of the proposed LSTM model is found to outperform typical RNN models like Elman, non-linear auto-regressive with exogenous models and other benchmarking models while tested on the real-world data sets.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据