A review on the forecasting of wind speed and generated power

By Ma Lei, Shijian Luan, Chuanwen Jiang, Hongling Liu, Zhang Yan. 2009

1,205 citations recorded by the source corpus.

Subfields: Electrical and Electronic Engineering

View Paper: https://www.semanticscholar.org/paper/53ad72c45c57bb71b1126c5e13e5740c700d0fd8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Electrical and Electronic Engineering

Citations in the corpus

A review of combined approaches for prediction of short-term wind speed and power (2014, neutral): “[28],”
Probabilistic Forecasting of Wind Power Generation Using Extreme Learning Machine (2014, background): “Traditionally, most research has focused on developing accurate point forecasting methods for wind power [2], [3].”
Exploiting sparsity of interconnections in spatio-temporal wind speed forecasting using Wavelet Transform (2016, background): “Wind power can be forecasted directly; however, forecasting wind speed and then converting the speed forecasts to power forecasts using commercially available wind turbine 20 power curves is generally considered as a better approach [7].”
Impacts of large-scale Intermittent Renewable Energy Sources on electricity systems, and how these can be modeled (2014, neutral): “For short horizons (o1 h), persistence forecasts are used, which assume that the current power output is the same as the power output in the future [87].”
Deep Learning for solar power forecasting — An approach using AutoEncoder and LSTM Neural Networks (2016, background): “Other overview papers also cover the forecasting of other types of regenerative power plants [2], [3], [4].”
Forecasting wind power – Modeling periodic and non-linear effects under conditional heteroscedasticity (2016, background): “Lei et al. (2009) as well as Soman et al. (2010) provide a time-scale classification of wind power and wind speed prediction models.”
Wind Power Scenario Generation and Reduction in Stochastic Programming Framework (2013, background): “A comprehensive review of forecasting techniques for wind speed and wind power offers a two-category classification: one based on physical methods and the other on statistical methods [4].”
On comparing three artificial neural networks for wind speed forecasting (2010, methodology): “Often, both physical and statistical models are utilized together, where NWF results are usually regarded as input variables, together with historical data, to train the system on the local conditions according to statistical theories [5].”
A Model Combining Convolutional Neural Network and LightGBM Algorithm for Ultra-Short-Term Wind Power Forecasting (2019, background): “The main difference between them is that the former uses real-time data such as weather, while the latter pays more attention to the mining of historical data [6].”
Current status and future advances for wind speed and power forecasting (2014, background): “Many different approaches are employed [2, 3, 5, 6, 11, 13].”
A new high-dimensional time series approach for wind speed, wind direction and air pressure forecasting (2017, background): “…it is possible to distinguish between five categories of wind speed forecasting approaches namely physical models, conventional statistical models, spatio-temporal prediction models, artificial intelligence models and combinations of all classes (hybrid structure models) (see Lei et al., 2009).”
Comparison of non-homogeneous regression models for probabilistic wind speed forecasting (2013, background): “…different lead times are required to regulate electricity markets, to schedule maintenance and, more generally, to improve the competitiveness of wind power compared to sources of electricity which allow for dispatchable generation (Genton and Hering, 2007; Pinson et al., 2007; Lei et al., 2009).”