CN105552970A - Method and apparatus for improving accuracy of predicting power of wind power station - Google Patents

Abstract

The invention provides a method and a device for improving the prediction accuracy of wind farm power. The method includes: obtaining the actual output value of the wind farm and the short-term power prediction curve of the wind farm; using linear extrapolation and moving smoothing methods to predict the predicted value of wind power output according to the actual output value of the wind farm; value and the short-term power prediction curve of the wind farm to generate the expected output value of the energy storage system; according to the remaining capacity of the energy storage system and the constraints of the SOC operation interval, the expected output value of the energy storage system is corrected. The present invention can configure a small amount of energy storage on the basis of good short-term power prediction accuracy to achieve the purpose of improving the prediction accuracy to an excellent level, thereby reducing wind farm assessment losses.

Description

A method and device for improving the accuracy of wind farm power prediction

technical field

The invention relates to the field of wind farm power generation, in particular to a method and device for improving the prediction accuracy of wind farm power.

Background technique

In the context of the rapid development of global wind power generation, limited by the huge investment in energy storage, the application of large-capacity energy storage at home and abroad is mainly in the demonstration stage, and the application scenarios of energy storage systems are also being explored. At present, the existing energy storage applications are divided into two types: energy storage used alone and used in conjunction with other power generation units. When used as an independent unit, it can be used to stabilize load peaks, peak loads, etc., participate in frequency regulation, and provide black start function , It can also be used for the transfer of users' energy demand peak hours, so as to reduce user expenditures by using the difference in electricity prices in the power market; it can improve power quality, enhance power supply reliability, etc. When energy storage is used in conjunction with other power generation units, one is to smooth the power output curve of the renewable energy generation unit for the intermittent and unpredictability of wind, solar and other renewable energy power generation; According to the impact of forecast deviation, energy storage and auxiliary output can improve the reliability of unit output according to the forecast situation. Due to the rapid development of wind power and photovoltaic power generation installed capacity, large-capacity energy storage systems have attracted attention and development due to their advantages of smoothing wind and wind fluctuations and adjusting wind and wind output power curves.

In most current studies, the control goal of the energy storage system is to smooth the output fluctuation of wind power or improve the power quality of new energy power generation, and it has not been applied in the assessment of the accuracy of short-term power prediction of wind farms.

Contents of the invention

The present invention proposes a method and device for improving the accuracy of wind farm power prediction. By configuring the wind farm with an energy storage system with a certain capacity, the accuracy and qualification rate of the short-term power prediction of the wind farm can be improved.

In order to achieve the above purpose, the embodiment of the present invention provides a method for improving the accuracy of wind farm power prediction, including: obtaining the actual output value of the wind farm and the short-term power prediction curve of the wind farm; Push and move smoothing methods to predict the predicted value of wind power output; generate the expected output value of the energy storage system according to the predicted value of wind power output and the short-term power forecast curve of the wind farm; Correct the expected output value of the energy storage system mentioned above.

Further, in one embodiment, obtaining the actual output value of the wind farm and the short-term power prediction curve of the wind farm is specifically: obtaining the actual output value of the wind farm and the short-term power prediction curve of the wind farm from the existing power generation units of the wind farm .

Further, in one embodiment, according to the actual output value of the wind farm, the method of linear extrapolation and moving smoothing is used to predict and generate the predicted value of wind power output, which specifically includes: according to the time m-1 and m-2 For the actual output value, the wind power output value at time m is recursively obtained by linear extrapolation method; the moving average is performed on the wind power output value at time m by moving smoothing method.

Further, in an embodiment, generating the expected output value of the energy storage system according to the predicted wind power output value and the short-term power forecast curve of the wind farm further includes: performing cubic spline interpolation processing on the short-term power forecast curve of the wind farm .

Further, in an embodiment, according to the remaining capacity of the energy storage system and the constraints of the SOC operating range, the expected output value of the energy storage system is corrected, including: setting the rated power output SOC range to [10%, 90% ], set the maximum power output SOC range as [40%, 60%] to judge whether the remaining capacity of the energy storage system meets the expected output value of the energy storage system, and if so, output according to the expected value of the energy storage system , if it is not satisfied, output according to the remaining capacity of the energy storage system.

In order to achieve the above object, an embodiment of the present invention also provides a device for improving the accuracy of wind farm power prediction, including: an acquisition unit for obtaining the actual output value of the wind farm and the short-term power prediction curve of the wind farm; a wind power output prediction value generating unit , used to predict the predicted value of wind power output based on the actual output value of the wind farm by using linear extrapolation and moving smoothing methods; the expected output value generation unit of the energy storage system is used to predict the wind power output based on the predicted value of wind power output and the short-term The power prediction curve is used to generate the expected output value of the energy storage system; the correction unit is used to correct the expected output value of the energy storage system according to the remaining capacity of the energy storage system and the constraints of the SOC operation range.

Further, in an embodiment, the acquiring unit is configured to acquire the actual output value of the wind farm and the short-term power prediction curve of the wind farm from an existing power generation unit of the wind farm.

Further, in one embodiment, the wind power output prediction value generation unit specifically includes: a linear extrapolation module, used to recursively deduce the wind power output by using a linear extrapolation method according to the actual output values at the time m-1 and m-2. The wind power output value at time m is obtained; the smoothing output module is used to perform sliding average processing on the wind power output value at time m by adopting a moving smoothing method.

Further, in an embodiment, the expected output value generation unit of the energy storage system includes: an interpolation processing module, configured to perform cubic spline interpolation processing on the short-term power prediction curve of the wind farm.

Further, in an embodiment, the correction unit is specifically configured to: set the rated power output SOC range to [10%, 90%], and set the maximum power output SOC range to [40%, 60%] , to judge whether the remaining capacity of the energy storage system satisfies the expected output value of the energy storage system, and if so, output according to the expected value of the energy storage system, and if not, output according to the remaining capacity of the energy storage system.

The method and device for improving the accuracy of wind farm power prediction in the embodiments of the present invention aim to improve the accuracy and pass rate of short-term power prediction of wind farms, by configuring an energy storage system with a certain capacity for the wind farm, and comprehensively applying the linear extrapolation method and moving smoothing method to quickly predict the real-time output of the wind farm, while considering the safe working range of the energy storage system and the output capability in different SOC intervals to control the output of the energy storage system, that is, the wind farm can be based on good short-term power prediction accuracy, Configure a small amount of energy storage to achieve the purpose of improving the prediction accuracy to an excellent level, so as to reduce the loss of wind farm assessment.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only These are some embodiments of the present invention. For those skilled in the art, other drawings can also be obtained according to these drawings on the premise of not paying creative efforts.

Fig. 1 is the processing flowchart of the method for improving the wind farm power prediction accuracy of the embodiment of the present invention;

Fig. 2 is a flow chart of a method for designing an expected value output of an energy storage system according to an embodiment of the present invention;

Fig. 3 is a schematic diagram of operating parameters of an energy storage system according to an embodiment of the present invention;

Fig. 4 is a processing flow chart of energy storage system output capability feedback according to an embodiment of the present invention;

5 is a schematic structural diagram of a device for improving the accuracy of wind farm power prediction according to an embodiment of the present invention;

Fig. 6 is a schematic structural diagram of the wind power output forecast value generation unit 102 according to the embodiment of the present invention.

detailed description

The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

At present, the factors affecting the accuracy of short-term power prediction of wind farms are mainly the accuracy of numerical weather prediction and the accuracy of prediction algorithms. This invention assumes that the prediction accuracy that the algorithm can achieve has been determined. On this basis, by adding an energy storage device to further improve the prediction accuracy. Among them, the calculation of the accuracy rate of short-term power forecasting of wind farms refers to the assessment indicators of wind farm output power forecasting and forecasting in the State Grid Enterprise Standard "Interim Measures for the Management of Wind Farm Power Forecasting and Forecasting". The daily wind power forecasting accuracy rate is:

$\mathrm{<span\; class="notranslate">\; t</span>}<span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; \%</span>}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; =</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; -</span>\sqrt{\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; N</span>}}\underset{\mathrm{<span\; class="notranslate">\; K</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; N</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{<span\; class="notranslate">\; (</span>\frac{{\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; m</span>}\mathrm{<span\; class="notranslate">\; k</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; p</span>}}_{\mathrm{<span\; class="notranslate">\; p</span>}\mathrm{<span\; class="notranslate">\; k</span>}}}{\mathrm{<span\; class="notranslate">\; C</span>}\mathrm{<span\; class="notranslate">\; a</span>}\mathrm{<span\; class="notranslate">\; p</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; \&times;</span>\mathrm{<span\; class="notranslate">\; 100</span>}\mathrm{<span\; class="notranslate">\; \%</span>}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; )</span>$

Among them: p _Mk is the actual average power at time k, p _pk is the predicted average power at time k, N is the total number of forecast data, the general calculation cycle is 24 hours, and the forecast frequency is 15 minutes per point, a total of 96 points, Cap is the operating installed capacity of the wind farm.

The principle that the present invention is based on is: the input is the actual output of the wind farm and the short-term power prediction curve of the wind farm, and the method of linear extrapolation and moving average is used to predict the wind power output power at the next moment (second level), and the short-term power prediction value is calculated. In order to obtain the expected output value of the energy storage system, consider the remaining capacity of the energy storage system and the limitation of the SOC operating range, and synthesize and output the output command of the energy storage system, that is, to compensate the accuracy of the short-term predicted power of the wind farm through the energy storage system, so as to improve the efficiency of the wind farm. Accuracy of short-term power forecasting.

Therefore, based on the above basic principles, in the present invention, the key step is to accurately calculate the expected output of the energy storage system, and to constrain the expected output value according to the output capacity of the energy storage system.

Fig. 1 is a processing flowchart of a method for improving the accuracy of wind farm power prediction according to an embodiment of the present invention. As shown in Figure 1, the method of this embodiment includes: step S101, obtaining the actual output value of the wind farm and the short-term power prediction curve of the wind farm; step S102, using linear extrapolation and moving smoothing according to the actual output value of the wind farm The method is to predict the predicted value of wind power output; step S103, generate the expected output value of the energy storage system according to the predicted value of wind power output and the short-term power forecast curve of the wind farm; step S104, according to the remaining capacity of the energy storage system and the constraints of the SOC operation interval The expected output value of the energy storage system is corrected.

In this embodiment, in step S101, the actual output value of the wind farm and the short-term power prediction curve of the wind farm may be obtained from existing power generation units of the wind farm.

In step S102, this step is to predict the wind power output at the next moment based on the real-time output history value of the wind farm. The present invention predicts using linear extrapolation and optimizes using moving smoothing.

Linear extrapolation refers to using the historical trend of the curve to infer the future trend. The present invention uses the measured power at the time m-1 and m-2 in the historical wind power operation curve to form a straight line, calculates the slope of the straight line, and uses the slope to recursively deduce the wind power output at the time m. . According to formulas (2) and (3), the slope k _m-1,m-2 of the line composed of the measured power at time m-1 and m-2 can be calculated.

y _m ＝y _m-1 +k _m-1,m-2 ×Δt(2)

${\mathrm{<span\; class="notranslate">\; k</span>}}_{\mathrm{<span\; class="notranslate">\; m</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}<span\; class="notranslate">\; ,</span>\mathrm{<span\; class="notranslate">\; m</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 2</span>}}<span\; class="notranslate">\; =</span>\frac{{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; m</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; -</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; m</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; 2</span>}}}{\mathrm{<span\; class="notranslate">\; \&Delta;</span>}\mathrm{<span\; class="notranslate">\; t</span>}}<span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 3</span>}<span\; class="notranslate">\; )</span>$

Among them, Δt can be taken as the minimum time interval for real-time collection of wind power output; y _m-1 and y _m-2 are the measured output power of the wind farm at time m-1 and m-2, respectively.

Using the linear extrapolation method to predict the data at the next moment has a high accuracy rate, which can meet engineering applications. However, when the data fluctuates greatly or the change trend changes from rising to falling or falling to rising, it will lead to recursive prediction. Data delays and mutations. Therefore, the present invention carries out sliding average processing to the real-time data of linear extrapolation prediction, as formula (4), calculates the average value of N historical data before the predicted output power y _m of wind power m obtained through linear extrapolation calculation and y _m , the obtained result y _m ′ is used as the optimal value of y _m to replace y _m .

${\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; m</span>}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; N</span>}}<span\; class="notranslate">\; (</span>\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; N</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; m</span>}<span\; class="notranslate">\; -</span>\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; +</span>{{\mathrm{<span\; class="notranslate">\; the\; y</span>}}^{<span\; class="notranslate">\; \&prime;</span>}}_{\mathrm{<span\; class="notranslate">\; m</span>}}<span\; class="notranslate">\; )</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; -</span><span\; class="notranslate">\; (</span>\mathrm{<span\; class="notranslate">\; 4</span>}<span\; class="notranslate">\; )</span>$

Among them, N is the number of historical real-time data obtained after linear extrapolation prediction and moving average, y _mi , i=0,1,..., N is the historical real-time data obtained after linear extrapolation prediction and moving average, The selection of N will affect the prediction accuracy of y _m ′.

The present invention adopts a statistical method to calculate multi-day forecast data in the research on the selection of the moving average window length. The result proves that when the sliding window length N=3, the prediction accuracy is the highest. Table 1 below lists the calculation results for any three days.

Table 1 The influence of the moving average window length on the accuracy rate

Moreover, since the short-term power prediction curve of a general wind farm is a point of 15 minutes, it needs to be processed into the same curve as the real-time wind power output data sampling. Considering that the short-term prediction curve is relatively smooth, cubic spline interpolation is used to process the short-term power of wind farms forecast curve.

According to the above method, the flow chart of the method for designing the expected value output of the energy storage system is shown in Figure 2:

Step S201, obtaining real-time output data of wind power;

Step S202, read the two nearest points P _m-2 and P _m-1 of the wind power real-time output data;

Step S203, seeking the slope k formed by the two points;

Step S204, using the slope k to linearly extrapolate the wind power output P _m at the next moment;

Step S205, update the predicted value by using the predicted value P _m and the sliding average of historical data. In this embodiment, the length of the sliding window is 3, that is, the average value P _m of P _m-2 , P _m-1 , and P _m is calculated. ';

Step S206, obtaining the wind power short-term power forecast curve;

Step S207, performing cubic spline interpolation processing on the wind power short-term power prediction curve;

Step S208, read the predicted value P _a of wind power output at time m;

In step S209, the difference between the updated predicted wind power output value P _m ' and the predicted value P _a of the point corresponding to the short-term power forecast is used as the expected output value of the energy storage system P _bat , that is, P _bat =P _m '-P _a .

Of course, in this embodiment, the order of steps S206-S208 does not mean that both steps can be performed simultaneously after steps S201-S205, or that the order of steps S206-S208 is before steps S201-S205.

In step S104 of the embodiment shown in Fig. 1, the expected output value of the energy storage system is corrected according to the remaining capacity of the energy storage system and the constraints of the SOC operating range, including: setting the rated power output SOC range to [10% , 90%], set the maximum power output SOC range as [40%, 60%] to judge whether the remaining capacity of the energy storage system meets the expected output value of the energy storage system, and if so, press the energy storage system The expected value of the system will be output, and if it is not met, the output will be based on the remaining capacity of the energy storage system.

The present invention divides the SOC operation range into more detailed segments when considering the output constraint of the energy storage system. That is: the SOC interval is divided into the maximum power output interval, the rated power output interval and the unsafe output interval. The rated power, rated capacity and SOC operating range of the energy storage system are considered in each interval.

The operating parameters of the energy storage system designed in the present invention are shown in Figure 3. The energy storage system output rated power P _N , and its corresponding rated capacity is Q _N ; the maximum output power (generally limited by the converter) P _max , its The corresponding rated capacity is Q _max ; in order to protect the battery and prolong the service life of the energy storage system, and avoid the energy storage system working at both ends of the SOC, set the rated power output SOC range to [10%, 90%], the maximum power output SOC range Set to [40%, 60%].

Fig. 4 is a flow chart of processing output capability feedback of an energy storage system according to an embodiment of the present invention. As shown in Figure 4:

Step S401, setting the initial state of the energy storage system;

Step S402, judging the SOC at time m-1;

Step S403, according to the current SOC state of the energy storage system, judge whether the energy storage system is in the SOC safe operation range [10%, 90%], if it is running in the safe range [10%, 90%], go to step S405, if not In the safe interval [10%, 90%], enter step S404;

Step S404, beyond the safe range, the output P _b of the energy storage system is 0, and wait for the next charging and discharging transition time to judge again;

Step S405, judging whether it is in the operating range [40%, 60%] that allows 1.5 times the rated power output, if yes, then enter step S406, if not, then enter step S409;

Step S406, judging whether the remaining capacity P _max meets the expected energy storage output value P _bk , that is, if P _bk ≥ P _max , go to step S407, and if P _bk ≤ P _max , go to step S408;

Step S407, exert power according to the remaining capacity P _max , that is, P _b =P _max ;

Step S408, exert power according to the expected value P _bk , that is, P _b =P _bk ;

Step S409, if it exceeds the operating range [40%, 60%], but is in the safe range [10%, 90%], and if the energy storage expected output value P _bk ≥ 0, then enter step S410 and step S411 respectively;

Step S410, when the SOC is near 0.1, judge whether the current output lower limit of the energy storage capacity of the energy storage system is greater than the expected energy storage output P _bk , and if so, enter step S412, and output power according to the expected energy storage output value P _bk , that is, P _b = P _bk , if not, go to step S413 and output power according to the energy storage capacity of the energy storage system, namely $P_b=\frac{({\mathrm{SOC}}_{K-1}-0.1)Q}{t};$

Step S411, when the SOC is near 0.9, judge whether the current output lower limit of the energy storage capacity of the energy storage system is greater than the expected energy storage output P _bk , if so, enter step S414, and output power according to the expected energy storage output value P _bk , that is, P _b = P _bk , if not, go to step S415 and output power according to the energy storage capacity of the energy storage system, namely $P_b=\frac{(0.9-{\mathrm{SOC}}_{K-1})Q}{t}.$

In the SOC boundary area, it may appear that the remaining capacity cannot maintain the rated power output for the next second, so the present invention also considers whether the remaining capacity can satisfy the energy storage system to continue outputting at the expected value.

Based on the same idea, an embodiment of the present invention also provides a device for improving the accuracy of wind farm power prediction, as shown in Figure 5, including: an acquisition unit 101, used to acquire the actual output value of the wind farm and the short-term power prediction curve of the wind farm; The wind power output forecast value generation unit 102 is used to predict the wind power output forecast value according to the actual output value of the wind farm by using linear extrapolation and moving smoothing methods; the energy storage system expected output value generation unit 103 is used to predict the wind power output value according to the The wind power output forecast value and the short-term power forecast curve of the wind farm generate the expected output value of the energy storage system; the correction unit 104 is used to correct the expected output value of the energy storage system according to the remaining capacity of the energy storage system and the constraints of the SOC operation range.

Specifically, the acquiring unit 101 is configured to acquire the actual output value of the wind farm and the short-term power prediction curve of the wind farm from existing power generation units of the wind farm.

Specifically, as shown in FIG. 6, the wind power output prediction value generation unit 102 specifically includes: a linear extrapolation module 1021, which is used to adopt a linear extrapolation method according to the actual output values at the time m-1 and m-2 The wind power output value at time m is obtained by recursion; the smoothing output module 1022 is configured to perform sliding average processing on the wind power output value at time m by adopting a moving smoothing method.

Specifically, the generation unit of the expected output value 103 of the energy storage system includes: an interpolation processing module, configured to perform cubic spline interpolation processing on the short-term power prediction curve of the wind farm.

Specifically, the correction unit 104 is specifically configured to: set the rated power output SOC range to [10%, 90%], set the maximum power output SOC range to [40%, 60%], to determine the Whether the remaining capacity of the energy storage system satisfies the expected output value of the energy storage system, if so, output according to the expected value of the energy storage system, and if not, output according to the remaining capacity of the energy storage system.

The invention aims at improving the accuracy rate and qualification rate of short-term power prediction of wind farms, and studies the output control strategy of the energy storage system by configuring a certain capacity energy storage system for the wind farm. Comprehensive application of linear extrapolation method and moving smoothing method to quickly predict the real-time output of wind farms, while considering the safe working range of the energy storage system and the output capacity in different SOC intervals, controlling the output of the energy storage system can ensure that the energy storage system works in a safe working area , and does not exceed the upper limit of output in different SOC intervals. At the same time, it can improve the accuracy and pass rate of short-term power prediction of wind farms, and reduce the loss of wind farm assessment.

Those skilled in the art should understand that the embodiments of the present invention may be provided as methods, systems, or computer program products. Accordingly, the present invention can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each procedure and/or block in the flowchart and/or block diagram, and a combination of procedures and/or blocks in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions may be provided to a general purpose computer, special purpose computer, embedded processor, or processor of other programmable data processing equipment to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing equipment produce a An apparatus for realizing the functions specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means, the instructions The device realizes the function specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions can also be loaded onto a computer or other programmable data processing device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, thereby The instructions provide steps for implementing the functions specified in the flow chart or blocks of the flowchart and/or the block or blocks of the block diagrams.

In the present invention, specific examples have been applied to explain the principles and implementation methods of the present invention, and the descriptions of the above examples are only used to help understand the method of the present invention and its core idea; meanwhile, for those of ordinary skill in the art, according to this The idea of the invention will have changes in the specific implementation and scope of application. To sum up, the contents of this specification should not be construed as limiting the present invention.

Claims (10)

1. improve a method for wind farm power prediction accuracy, it is characterized in that, comprising:

Obtain wind energy turbine set actual go out force value and wind energy turbine set short term power prediction curve;

According to described wind energy turbine set actual go out force value, adopt the method for linear extrapolation and gliding smoothing, prediction wind power output predicted value;

According to described wind power output predicted value and wind energy turbine set short term power prediction curve, generate energy-storage system and expect force value;

According to energy-storage system residual capacity and the constraint of SOC traffic coverage, expect force value correction to described energy-storage system.

2. the method for raising wind farm power prediction accuracy according to claim 1, is characterized in that, obtain wind energy turbine set actual go out force value and wind energy turbine set short term power prediction curve, be specially:

Obtain from the existing generator unit of wind energy turbine set described wind energy turbine set actual go out force value and wind energy turbine set short term power prediction curve.

3. the method for raising wind farm power prediction accuracy according to claim 1, is characterized in that, according to described wind energy turbine set actual go out force value, adopt the method for linear extrapolation and gliding smoothing, prediction generates wind power output predicted value, specifically comprises:

According to described m-1 and the m-2 moment actual go out force value, adopt linear extrapolation recursion to obtain the wind power output value in m moment;

Adopt the method for gliding smoothing, moving average process is carried out to the wind power output value in described m moment.

4. the method for raising wind farm power prediction accuracy according to claim 3, is characterized in that, according to described wind power output predicted value and wind energy turbine set short term power prediction curve, generates energy-storage system and expects force value, also comprise:

Cubic spline interpolation process is carried out to described wind energy turbine set short term power prediction curve.

5. the method for raising wind farm power prediction accuracy according to claim 1, is characterized in that, according to energy-storage system residual capacity and the constraint of SOC traffic coverage, expects force value correction, comprising described energy-storage system:

SOC range set of being exerted oneself by rated power is [10%, 90%], SOC range set of maximum power being exerted oneself is [40%, 60%], to judge whether described energy-storage system residual capacity meets described energy-storage system and expect force value, as meet then by as described in energy-storage system desired value exert oneself, if meet then according to as described in energy-storage system residual capacity exert oneself.

6. improve a device for wind farm power prediction accuracy, it is characterized in that, comprising:

Acquiring unit, for obtain wind energy turbine set actual go out force value and wind energy turbine set short term power prediction curve;

Wind power output predicted value generating means, for according to described wind energy turbine set actual go out force value, adopt the method for linear extrapolation and gliding smoothing, prediction wind power output predicted value;

Energy-storage system is expected force value generation unit, for according to described wind power output predicted value and wind energy turbine set short term power prediction curve, generates energy-storage system and expects force value;

Amending unit, for according to energy-storage system residual capacity and the constraint of SOC traffic coverage, expects force value correction to described energy-storage system.

7. the device of raising wind farm power prediction accuracy according to claim 6, is characterized in that, described acquiring unit be used for obtain from the existing generator unit of wind energy turbine set described wind energy turbine set actual go out force value and wind energy turbine set short term power prediction curve.

8. the device of raising wind farm power prediction accuracy according to claim 6, is characterized in that, described wind power output predicted value generating means specifically comprises:

Linear extrapolation module, for according to described m-1 and the m-2 moment actual go out force value, adopt linear extrapolation recursion to obtain the wind power output value in m moment;

Smoothly exerting oneself module, for adopting the method for gliding smoothing, moving average process being carried out to the wind power output value in described m moment.

9. the device of raising wind farm power prediction accuracy according to claim 8, is characterized in that, described energy-storage system expects that force value generation unit comprises:

Interpolation processing module, for carrying out cubic spline interpolation process to described wind energy turbine set short term power prediction curve.

10. the device of raising wind farm power prediction accuracy according to claim 6, is characterized in that, described amending unit specifically for:

SOC range set of being exerted oneself by rated power is [10%, 90%], SOC range set of maximum power being exerted oneself is [40%, 60%], to judge whether described energy-storage system residual capacity meets described energy-storage system and expect force value, as meet then by as described in energy-storage system desired value exert oneself, if meet then according to as described in energy-storage system residual capacity exert oneself.