The inherent randomness, intermittence and volatility of wind power generation compromise the quality of the wind power system, resulting in uncertainty in the system's optimal scheduling. As a result, it's critical to improve power quality and assure real-time power grid scheduling and grid-connected wind farm operation. Inferred statistics are utilized in this research to infer general features based on the selected information, confirming that there are differences between two forecasting categories: Forecast Category 1 (0–11 h ahead) and Forecast Category 2 (12–23 h ahead). In z-tests, the null hypothesis provides the corresponding quantitative findings. To verify the final performance of the prediction findings, five benchmark methodologies are used: Persistence model, LMNN (Multilayer Perceptron with LM learning methods), NARX (Nonlinear autoregressive exogenous neural network model), LMRNN (RNNs with LM training methods) and LSTM (Long short-term memory neural network). Experiments using a real dataset show that the LSTM network has the highest forecasting accuracy when compared to other benchmark approaches including persistence model, LMNN, NARX network, and LMRNN, and the 23-steps forecasting accuracy has improved by 19.61%.

Coal, petroleum and gas, among other non-renewable resources, will significantly contaminate the human living environment. Wind energy has gotten a lot of attention as a renewable, inexhaustible, and unlimited free energy source. Wind power is valuable not only because it is a renewable energy source, but also because of the megawatt scale of available wind turbines, easy operation, low maintenance costs and even government incentives [

The accuracy of wind speed and wind power predictions is usually influenced by the surface wind, precipitation probability, maximum temperature, and even the conditional probability of frozen precipitation. In short-term wind power forecasting, wind speed is the most important meteorological component. Stetco et al. [

The methods to select the variables among the many available meteorological variables which has a substantial impact on the output power prediction accuracy, should be considered.

The short-term wind power forecasting category and error distribution in benchmark models.

This paper is organized as follows: data description and preprocessing, correlation analysis and neural network-related approaches are provided in

The basic data description and distribution, data preprocessing methods, forecasting categories, and forecasting form are presented first in

The dataset is provided by the Software Engineer Divyam Khandelwal [

The values of ‘Hour’ ranges from 0 to 23, which indicates the number of hours-ahead needed to be forecasted in short-term. For convenience, all the dataset objects are converted in to the standardized ISO 8601 format by following the processing procedure proposed by data scientist Jon Lo. Correspondingly, the forecasting category is split into two following categories:

Category 1: 1 h to 12 h ahead data

Category 2: 13 h to 24 h ahead data

Assume variables listed in

Variables | Power |
Wind direction 100 m (deg) | Wind speed |
Air temperature |
Surface air pressure (Pa) | Density hub height (kg/m |
---|---|---|---|---|---|---|

Count | 105120 | 105120 | 105120 | 105120 | 105120 | 105120 |

Mean | 7.3838 | 163.4756 | 8.2059 | 288.4757 | 93868.7282 | 1.1182 |

Std | 5.9499 | 94.6037 | 3.6458 | 10.9733 | 622.2715 | 0.0436 |

Min | 0.0000 | 0.0050 | 0.0060 | 259.5210 | 91703.5520 | 1.0250 |

25% | 1.5170 | 90.2425 | 5.276000 | 279.5260 | 93464.1680 | 1.0830 |

50% | 6.2090 | 170.7265 | 8.112500 | 288.9200 | 93853.2800 | 1.1140 |

75% | 13.9120 | 211.5322 | 10.998000 | 297.0010 | 94254.2960 | 1.1510 |

Max | 16.0000 | 359.9940 | 28.720000 | 314.7810 | 96132.1040 | 1.2580 |

An ideal variable input is one that is extremely informative, especially when it is independent of each other, has a good number, and can be utilized to generate a set of variable interpretations. As a result, the ideal input variables will have the fewest input variables to represent the characteristics of the output variables, which promotes neural network structural design and promotional capacities. For linear argument selection approaches, there are forward-back and step-by-step regression methods. In reality, selecting procedures for nonlinear arguments remains a major challenge. Researchers are gradually learning various climate characteristics of wind power, as well as the feedback impact of wind power, radiation, and precipitation, mainly to the use of ground observation data. Station observation, on the other hand, has its own intractable flaws, such as wind power overlap error, weather dependence, and observation area constraints.
_{i}_{j}

The robustness of the artificial neural network can be determined by the network parameters and the specific morphology of the error surface around the sample (ANN). The network parameters can be coupled to the sample extreme points to make the network more resilient, and the resulting error surface distribution is generally flat. It is critical to evaluate the network output's resilience, which may help address practical difficulties and improve the network's promotion ability and application prospects. The input is effectively a set of feature vectors composed of the available variables from

with standard deviation is typically used according to the spread of the centers, where

are applied to the weights of output layers, where

The mean square error (RMSE) is used to predict the degree of discreteness or deviation between the desired output and forecasted ones, to measure the accuracy of the prediction, defined by

The new performance function RMSE leads the network to have smaller weights and biases, resulting in a smoother network response and less overfitting of the equation. In its most primitive sense, an RBF neural network has three layers with only one hidden layer that executes a nonlinear transition from input space to hidden space. It has a higher learning efficiency and function approximation than the BP network.

The pd.DataFrame.merge are applied to mearge the training sample with wind speed and wind power, and the mean wind speed, wind power and wind direction is 8.1951, 163.3769 and 0.461702, respectively. The curve of wind speed data for the whole year from January 2012 to December 2012 is shown in

The distribution pattern of wind speed under different forecasting categories is generally different, regardless of whether longer or shorter forecasting is used, and the inferential statistics results in

^{3}), which is followed by wind direction and air temperature 2 m (K) (correlation coefficients is about 0.0092 and 0.0051, respectively). This is particularly evidence that the randomness, intermittence, and seasonality of natural wind speed, as well as the wind power of wind turbines proportional to wind turbines, and the output voltage of wind turbines, are all closely related to wind speed fluctuations. Wind speed, to be more specific, has a considerable impact on wind power forecasting accuracy.

Inferred statistics are statistical methods for inferring population characteristics from selected samples. It have been used to compare forecasting categories to see if there are differences between them: Forecast Category 1 (0–11 h ahead) and Forecast Category 2 (12–23 h ahead). Assume the μ_{1} and μ_{2} are respectively, the mean of two outlined forecasting categories, the null hypothesis is

and the

Z scores is 36.6413 which is greater than z-tests scores Z = 1.96. This indicates that the two forecasting models are significantly different. In addition, as the number of forecasting steps increases, the accuracy of the forecasting will decrease dramatically. In short-term wind power forecasting, a tiny error can nonetheless result in large forecasting inaccuracies. This also shows that there is a distinction between two types of short-term wind power predictions.

Forecasting results 1–24-steps ahead wind power forecasting is obtained by LSTM network and tabulated in

Methods | 1-step (5 min) | 6-step (30 min) | 12-step (1 h) | 23-step (2 h) |
---|---|---|---|---|

Persistence | 0.3028 | 0.3417 | 0.5436 | 0.6867 |

LMNN | 0.1998 | 0.2708 | 0.2795 | 0.2821 |

NARX | 0.1842 | 0.2135 | 0.2457 | 0.2691 |

LMRNN | 0.1863 | 0.2027 | 0.2513 | 0.2746 |

LSTM | 0.1817 | 0.1875 | 0.2247 | 0.2692 |

FS | Training RMSE | Testing RMSE | Trainable param # |
---|---|---|---|

1-step | 0.3562 | 0.1817 | 199 |

2-step | 0.3577 | 0.1830 | 216 |

3-step | 0.3590 | 0.1836 | 242 |

4-step | 0.3610 | 0.1860 | 271 |

5-step | 0.3618 | 0.1872 | 295 |

6-step | 0.3623 | 0.1875 | 319 |

7-step | 0.3624 | 0.1885 | 343 |

8-step | 0.3637 | 0.1902 | 367 |

9-step | 0.3640 | 0.1907 | 391 |

10-step | 0.3642 | 0.1919 | 415 |

11-step | 0.4253 | 0.2242 | 439 |

12-step | 0.4253 | 0.2247 | 463 |

13-step | 0.4256 | 0.2256 | 487 |

14-step | 0.4258 | 0.2275 | 511 |

15-step | 0.4261 | 0.2291 | 535 |

16-step | 0.4271 | 0.2295 | 559 |

17-step | 0.4290 | 0.2307 | 583 |

18-step | 0.4293 | 0.2312 | 607 |

19-step | 0.4298 | 0.2313 | 631 |

20-step | 0.4391 | 0.2352 | 655 |

21-step | 0.4551 | 0.2548 | 679 |

22-step | 0.4588 | 0.2564 | 703 |

23-step | 0.4611 | 0.2692 | 727 |

24-step | 0.4975 | 0.3302 | 751 |

Training, validation and testing samples of the wind power and wind speed are shown in

Inferred statistics are used in this research to confirm that there is a significant difference between the two forecasting groups, i.e., Forecast Category 1 (0–11 h ahead) and Forecast Category 2 (12–23 h ahead) are the two types of forecasts. The wind speed has a significant impact on the forecasting accuracy of wind power when compared to the wind direction, air temperature 2 m (K), surface air pressure (Pa), and density hub height (kg/m^{3}) based on the correlation analysis. To verify the final performance of the forecasting output, five benchmark methodologies are used: persistence model, LMNN, NARX network, LMRNN, and LSTM. For accurate and dependable wind power forecasting, we would use dynamical analysis with error correction capability in combination with reinforcement learning in the future.

The authors acknowledge the reviewers providing valuable comments and helpful suggestions to improve the manuscript.