Wind power disorder index and prediction effect evaluation method based on information entropy theory

Abstract

The present invention belongs to the technical field of electric power system, and in particular, relates to a wind power disorder index and prediction effect evaluation method based on information entropy theory. The present invention comprises the following steps: step 1. obtaining the random component of wind power output; step 2. calculating the probability corresponding to the first random component; step 3. respectively calculating the entropy value of wind power output prediction and the entropy value of actual wind power output, and obtaining the absolute value of the difference between the two; step 4. determining the disorder simulation effect of the prediction method. The evaluation method for the stability and disorder of wind power prediction results of the present invention uses the information entropy theory to evaluate the stability and disorder of the prediction method, so that the scientificity and comprehensiveness of the prediction evaluation method can be significantly improved, and the accuracy and stability of wind power prediction can also be improved. At the same time, the average value and distribution standard of the wind power prediction error of the present invention are more comprehensive and accurate, which plays a more important role in the stable frequency regulation of the power grid.

Description

Technical Field

[0001] The present invention belongs to the technical field of electric power systems, and in particular relates to a wind power disorder index and a prediction effect evaluation method based on information entropy theory. Background Art

[0002] Wind power forecasting mainly refers to the forecast of wind farm output. The wind power forecasting results can be used for short-term and ultra-short-term forecasts of power generation output by power grid dispatching departments, and are an important basis for power grid dispatching to make day-ahead plans. Improving the accuracy of wind power forecasting can improve the safety and stability of the power grid and promote the development and utilization of renewable energy.

[0003] Since wind power output is highly random and volatile, it is very important for wind power forecasting to predict the randomness and disorder of output. Disorder reflects the degree of difference in the error values ​​of all sample points. Whether the disorder can be accurately simulated is an important aspect of the prediction method's ability. The disorder of wind power output is directly related to the fluctuation range of wind power, which is very important for the stable frequency regulation of the power grid.

[0004] At present, the evaluation of prediction methods mainly involves the calculation of relative error and root mean square error, as well as the probability density estimation of wind power error. These two methods are now mature and are based on probability theory. They use probability distribution models such as "Gaussian-parameter" to describe the mean value and distribution standard deviation of wind power prediction errors. Summary of the invention

[0005] In view of the shortcomings of the above-mentioned prior art, the present invention provides a wind power disorder index and prediction effect evaluation method based on information entropy theory. Its purpose is to realize an evaluation method for the stability and disorder of wind power prediction results, and to use information entropy theory to evaluate the stability and disorder of the prediction method, so that the scientificity and comprehensiveness of the prediction evaluation method can be significantly improved.

[0006] The technical solution adopted by the present invention to achieve the above-mentioned purpose is:

[0007] The wind power disorder index and prediction effect evaluation method based on information entropy theory includes the following steps:

[0008] Step 1. Obtain the random component of wind power output;

[0009] Step 2. Calculate the probability corresponding to the random component;

[0010] Step 3. Calculate the entropy value of the wind power output prediction and the entropy value of the actual wind power output respectively, and obtain the absolute value of the difference between the two;

[0011] Step 4. Determine how well the prediction method simulates disorder.

[0012] Furthermore, the random component of wind power output is obtained including:

[0013] The calculation formula of the random component of wind power output is expressed as:

[0014] S(i)=C(i)+ε(i)

[0015] Among them: S(i) represents the original sequence of wind power output, C(i) represents the components after different fundamental wave transformation, and ε(i) represents the random component of error after signal decomposition.

[0016] Furthermore, the curve for obtaining wind power output is decomposed by using a signal decomposition method, and the obtained random components are normalized to obtain the entropy value.

[0017] Furthermore, the random component is obtained in other ways to calculate the entropy value of wind power.

[0018] Furthermore, the calculation of the probability corresponding to the ith random component refers to the calculation of the probability p(Δx i ).

[0019] Furthermore, the entropy value of the wind power output prediction and the entropy value of the actual wind power output are calculated respectively, and the absolute value of the difference between the two is obtained. The calculation formula is as follows:

[0020]

[0021]

[0022] Where: H pridict Represents the entropy value of wind power output prediction; H real represents the entropy value of actual wind power output, and ΔH represents wind power output.

[0023] Furthermore, the disorder simulation effect of the determination prediction method includes:

[0024] The judgment criterion is that the closer the entropy of the wind power output forecast value is to the entropy of the actual wind power value, the better the prediction method simulates the randomness and disorder of the original sequence.

[0025] Furthermore, there are three prediction methods for the disorder simulation effect of the judgment prediction method:

[0026] ΔH1>ΔH2>ΔH3, then the disorder simulation effect of method 3 is the best;

[0027] The expected results are as follows:

[0028] The information entropy theory is introduced, and based on the analysis of the information entropy of the prediction results, the disorder index of the prediction results is obtained, so as to select the prediction method that simulates the original sequence better.

[0029] A computer storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of the wind power disorder index and prediction effect evaluation method based on information entropy theory are implemented.

[0030] The present invention has the following beneficial effects and advantages:

[0031] The present invention can evaluate the stability and disorder of wind power prediction results by using the information entropy theory to evaluate the stability and disorder of the prediction method, so that the scientificity and comprehensiveness of the prediction evaluation method can be significantly improved.

[0032] The present invention proves that by introducing the information entropy theory, the disorder index of the prediction result can be obtained based on the analysis of the information entropy of the prediction result, so as to select the prediction method with better simulation effect of the original sequence and improve the accuracy and stability of wind power prediction.

[0033] The average value and distribution standard of the wind power prediction error of the present invention are more comprehensive and more accurate, and can play an important role in stabilizing the frequency regulation of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0035] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0036] In order to more clearly understand the above-mentioned objectives, features and advantages of the present invention, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict.

[0037] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0038] Refer to the following Figure 1 The technical solutions of some embodiments of the present invention are described.

[0039] Example 1

[0040] The present invention is a wind power disorder index and prediction effect evaluation method based on information entropy theory, such as Figure 1 As shown, Figure 1 The figure is a flow chart of the method of the present invention.

[0041] According to the theory of information theory, information is a measure of the orderliness of a system, and entropy is a measure of the disorderliness of a system. In order to solve the problem of quantitative measurement of information, C.E. Shannon proposed the concept of information entropy in 1948 and defined it as the probability of occurrence of discrete random events.

[0042] The calculation formula of information entropy is:

[0043]

[0044] Where: p(x i ) represents the probability of variable x appearing, x i is a random variable.

[0045] The entropy method is a classic method for evaluating the disorder of information: for a certain information, the smaller the entropy value, the greater the degree of information variation, and the worse the stability of the sample sequence; conversely, the larger the entropy value, the better the stability.

[0046] In the evaluation of the effect of wind power prediction, the present invention introduces the idea of ​​information entropy to evaluate the degree of disorder of wind power output, which is called the entropy value of wind power. After the result of wind power prediction appears, the entropy value calculation result of the random component is used to evaluate the stability of the wind power prediction method.

[0047] The specific operation steps of the present invention are as follows:

[0048] Step 1. Obtain the random component of wind power output.

[0049] The calculation formula of the random component of wind power output can be expressed as:

[0050] S(i)=C(i)+ε(i)

[0051] Among them: S(i) represents the original sequence of wind power output, C(i) represents the components after different fundamental wave transformation, and ε(i) represents the random component of error after signal decomposition.

[0052] For example, a signal decomposition method may be used to decompose the wind power output curve, and the obtained random components may be normalized to obtain the entropy value. Other methods may also be used to obtain random components to calculate the entropy value of wind power.

[0053] Step 2. Calculate the probability p(Δx i ).

[0054] Step 3. Calculate the entropy value of the predicted wind power output and the entropy value of the actual wind power output respectively, and find the absolute value of the difference between the two. The calculation formula is as follows:

[0055]

[0056]

[0057] Where: H pridict Represents the entropy value of wind power output prediction; H real represents the entropy value of actual wind power output, ΔH represents wind power output, p(Δx i )=Δx i x — Random variable in the system.

[0058] Step 4. Determine how well the prediction method simulates disorder.

[0059] The judgment criterion is that the closer the entropy of the wind power output forecast value is to the entropy of the actual wind power value, the better the prediction method is in simulating the randomness and disorder of the original sequence.

[0060] For example, if there are three existing prediction methods ΔH1>ΔH2>ΔH3, it means that method 3 has the best disorder simulation effect.

[0061] The expected results are as follows:

[0062] By introducing the information entropy theory, we can derive the disorder index of the prediction results based on the analysis of the information entropy of the prediction results, so as to select the prediction method that simulates the original sequence better and improve the accuracy and stability of wind power prediction.

[0063] Example 2

[0064] Based on the same inventive concept, an embodiment of the present invention further provides a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for evaluating the wind power disorder index and prediction effect based on information entropy theory described in Example 1 are implemented.

[0065] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0066] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0067] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0068] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0069] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. The wind power disorder index and prediction effect evaluation method based on information entropy theory is characterized by: The following steps are involved: Step 1. Obtain the random component of wind power output, including the calculation formula of the random component of wind power output is expressed as: S(i)=C(i)+ε(i), where: S(i) represents the original sequence of wind power output, C(i) represents the components after different fundamental wave transformation, and ε(i) represents the error random component after signal decomposition; Step 2. Calculate the probability corresponding to the random component; Step 3. Calculate the entropy value of the predicted wind power output and the entropy value of the actual wind power output respectively, and find the absolute value of the difference between the two. The calculation formula is as follows: Where: H pridict Represents the entropy value of wind power output prediction; H real represents the entropy value of actual wind power output, ΔH represents wind power output; Step 4. Determine how well the prediction method simulates disorder.

2. The wind power disorder index and prediction effect evaluation method based on information entropy theory according to claim 1 is characterized by: The random component of wind power output is obtained by decomposing the wind power output curve using a signal decomposition method, and then obtaining an entropy value after normalizing the obtained random component.

3. The wind power disorder index and prediction effect evaluation method based on information entropy theory according to claim 1 is characterized by: The calculation of the probability corresponding to the random component refers to the calculation of the probability p(Δx i ).

4. The wind power disorder index and prediction effect evaluation method based on information entropy theory according to claim 1 is characterized by: The disorder simulation effect of the determination prediction method includes: The judgment criterion is that the closer the entropy of the wind power output forecast value is to the entropy of the actual wind power value, the better the prediction method simulates the randomness and disorder of the original sequence.

5. The wind power disorder index and prediction effect evaluation method based on information entropy theory according to claim 1 is characterized by: The disorder simulation effect of the judgment prediction method has 3 prediction methods ΔH1>ΔH2>ΔH3, then the disorder simulation effect of method 3 is the best; The expected results are as follows: The information entropy theory is introduced, and based on the analysis of the information entropy of the prediction results, the disorder index of the prediction results is obtained, so as to select the prediction method that simulates the original sequence better.

6. A computer storage medium, characterized in that: The computer storage medium stores a computer program, and when the computer program is executed by the processor, the steps of the method for evaluating the disorder index and prediction effect of wind power based on information entropy theory according to any one of claims 1 to 5 are implemented.

Images