.png){kind=icon}
Return
A New Multi-Resolution Closed-Loop Wind Power Forecasting Method
.png){kind=icon}
PRE
AI
DOI：10.1109/TSTE.2023.3259939.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
By the increasing number and size of wind farms, wind generation forecasting has become a basic requirement for their connection to the power grid; otherwise, power system operators and electricity market participants cannot make the right decisions and may incur significant costs and penalties. In this paper, a new multi-resolution closed-loop wind power forecasting method with a difference signal feedback loop is proposed. Within the proposed method, wind power is initially predicted in two different resolutions (such as with hourly and sub-hourly time steps) by two low/high-resolution pre-predictors and then the inconsistency between their predictions is measured through the difference signal. The generated difference signal is used as a guide for the two low/high-resolution wind power post-predictors. If their wind power forecasts are inconsistent, the difference signal is updated and used as the feedback for the low/high-resolution post-predictors. This closed-loop forecasting-updating process is iterated until the post-predictors reach consistent results. To evaluate the performance of the proposed multi-resolution closed-loop method, it is tested on two different real-world wind farms and the results are compared with the results of several other widely used/recently published wind power forecast methods using various error metrics and different forecast horizons.
Keywords:
Wind power prediction
closed-loop forecasting method
multi-resolution forecast
difference signal
Journal
IF:
5.4
Papers:
6.8K
Citations:
1.5W
Organization
Cited Papers
ShareSaveA novel hybrid methodology for short-term wind power forecasting based on adaptive neuro-fuzzy inference system.png)
RENEWABLE ENERGY
OAAI
RENEWABLE ENERGYIF9.1
OAAIShareSaveA hybrid deep learning-based neural network for 24-h ahead wind power forecastingAPPLIED ENERGY
APPLIED ENERGYIF11
PREAI
ShareSaveShort-Term Wind Power Prediction Based On Particle Swarm Optimization-Extreme Learning Machine Model Combined With Adaboost AlgorithmIEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAIShareSaveShareSaveShareSave
View more