Wind power prediction method and system in wind power plant

Abstract

The invention discloses a wind power prediction method and system in a wind power plant, and the method comprises the steps: calculating the wake flow speed of natural wind speed passing through blades of a wind driven generator through a pre-built wind speed model according to the law of conservation of mass; calculating the input wind speed of any wind driven generator in the wind power plant based on the law of conservation of momentum according to the wake flow speed; performing wake flow correction on the input wind speed according to the input wind speed to obtain a corrected input windspeed; obtaining a predicted wind speed through a wind speed prediction model according to the corrected input wind speed; and according to the predicted wind speed, performing wind power prediction through a dynamic time sequence neural network prediction model to obtain predicted wind power. By considering the wind speed model under the wake flow effect, wake flow correction is performed on theinput wind speed of the wind turbine generator of the whole wind power plant, and the corrected wind speed is used as the input of the wind speed prediction model, so that the obtained wind speed prediction precision is improved, and the wind power prediction precision is further improved.

Description

Technical field:

[0001] The invention relates to the field of wind power, in particular to a wind power prediction method and system in a wind farm. Background technique:

[0002] With the vigorous development of wind power and the expansion of the construction scale of wind farms, when analyzing the connection of wind farms to the power system, it is necessary to consider the characteristics of large fluctuations in the output power of wind farms. Wind energy has intermittent and random fluctuations. The change of wind speed directly leads to the change of active power and reactive power of the wind farm, and the output power is very unstable. When wind power penetrates full operation, it will have serious impacts, and it will also affect power quality and economic dispatch as well as power bidding. Therefore, it is of practical significance to actively carry out research work on wind power forecasting and improve the accuracy of forecasting for power grid dispatching, imp...

Examples

Embodiment 1

[0066] first, figure 1 It shows a flow chart of a wake effect-based wind power prediction method provided by an embodiment of the present invention; figure 1 As shown, Embodiment 1 provides a method for predicting wind power based on wake effects, including:

[0067] Step S1, through the pre-established wind speed model, calculate the wake velocity of the natural wind speed passing through the blades of the wind turbine according to the law of conservation of mass;

[0068] Step S2, according to the wake velocity, calculate the input wind speed of any wind turbine in the wind farm based on the law of conservation of momentum;

[0069] Step S3, performing wake correction on the input wind speed according to the input wind speed to obtain a corrected input wind speed;

[0070] Step S4, according to the corrected input wind speed, the predicted wind speed is obtained through the wind speed prediction model;

[0071] Step S5, according to the predicted wind speed, the wind powe...

Embodiment 2

[0172] Based on the wind power prediction method and system based on the wake effect in the first embodiment, the predicted wind power curve is monitored, and the abnormality of the curve can be monitored in real time through the monitoring of the curve, so that the wind turbine can be maintained and diagnosed in time . Based on this, this embodiment provides a method for abnormal diagnosis of the predicted wind power curve, the specific scheme is as follows:

[0173] Collect wind power data at different wind speeds;

[0174] Sort the collected data according to the wind speed, and calculate the power drift area under the unit accuracy. The calculation formula is:

[0175]

[0176] Among them, Δw is the difference of adjacent wind speed after sorting, Δw=w i+1 -w i ,

[0177] Δp is the power difference of adjacent wind speed points after sorting, Δp=p i+1 -p i ,

[0178] i is the data index number of wind speed and corresponding power after sorting, i=1, 2, 3...n;

...

Embodiment 3

[0201] In this embodiment, the wind power forecasting method and system based on the wake effect described in Embodiment 1 may be a double-blade wind turbine with the following specific structure. When analyzing the wake effect, for the Each impeller in the double-blade wind power generator executes the method steps in Embodiment 1 to obtain the analysis result of the wake effect of each impeller, so as to obtain the wind power prediction value of the impeller.

[0202] see Image 6 , 7 ,in Image 6 Schematic diagram of the structure of the dual-blade wind power generator provided in this embodiment, Figure 7 The principle diagram of the impeller speed combining mechanism provided for this embodiment.

[0203] In order to effectively utilize wind energy and increase power generation, the present embodiment provides the following wind generator, including: a first-stage impeller 1, a second-stage impeller 2, and an impeller speed combining mechanism; the impeller speed comb...

Technical field:

[0001] The invention relates to the field of wind power, in particular to a wind power prediction method and system in a wind farm. Background technique:

[0002] With the vigorous development of wind power and the expansion of the construction scale of wind farms, when analyzing the connection of wind farms to the power system, it is necessary to consider the characteristics of large fluctuations in the output power of wind farms. Wind energy has intermittent and random fluctuations. The change of wind speed directly leads to the change of active power and reactive power of the wind farm, and the output power is very unstable. When wind power penetrates full operation, it will have serious impacts, and it will also affect power quality and economic dispatch as well as power bidding. Therefore, it is of practical significance to actively carry out research work on wind power forecasting and improve the accuracy of forecasting for power grid dispatching, imp...

Examples

Embodiment 1

[0066] first, figure 1 It shows a flow chart of a wake effect-based wind power prediction method provided by an embodiment of the present invention; figure 1 As shown, Embodiment 1 provides a method for predicting wind power based on wake effects, including:

[0067] Step S1, through the pre-established wind speed model, calculate the wake velocity of the natural wind speed passing through the blades of the wind turbine according to the law of conservation of mass;

[0068] Step S2, according to the wake velocity, calculate the input wind speed of any wind turbine in the wind farm based on the law of conservation of momentum;

[0069] Step S3, performing wake correction on the input wind speed according to the input wind speed to obtain a corrected input wind speed;

[0070] Step S4, according to the corrected input wind speed, the predicted wind speed is obtained through the wind speed prediction model;

[0071] Step S5, according to the predicted wind speed, the wind powe...

Embodiment 2

[0172] Based on the wind power prediction method and system based on the wake effect in the first embodiment, the predicted wind power curve is monitored, and the abnormality of the curve can be monitored in real time through the monitoring of the curve, so that the wind turbine can be maintained and diagnosed in time . Based on this, this embodiment provides a method for abnormal diagnosis of the predicted wind power curve, the specific scheme is as follows:

[0173] Collect wind power data at different wind speeds;

[0174] Sort the collected data according to the wind speed, and calculate the power drift area under the unit accuracy. The calculation formula is:

[0175]

[0176] Among them, Δw is the difference of adjacent wind speed after sorting, Δw=w i+1 -w i ,

[0177] Δp is the power difference of adjacent wind speed points after sorting, Δp=p i+1 -p i ,

[0178] i is the data index number of wind speed and corresponding power after sorting, i=1, 2, 3...n;

...

Embodiment 3

[0201] In this embodiment, the wind power forecasting method and system based on the wake effect described in Embodiment 1 may be a double-blade wind turbine with the following specific structure. When analyzing the wake effect, for the Each impeller in the double-blade wind power generator executes the method steps in Embodiment 1 to obtain the analysis result of the wake effect of each impeller, so as to obtain the wind power prediction value of the impeller.

[0202] see Image 6 , 7 ,in Image 6 Schematic diagram of the structure of the dual-blade wind power generator provided in this embodiment, Figure 7 The principle diagram of the impeller speed combining mechanism provided for this embodiment.

[0203] In order to effectively utilize wind energy and increase power generation, the present embodiment provides the following wind generator, including: a first-stage impeller 1, a second-stage impeller 2, and an impeller speed combining mechanism; the impeller speed comb...

Images