A short-term load forecasting method for microgrid based on ridgelet support vector machine

Abstract

The present invention discloses a microgrid short-term load forecasting method based on ridge wave support vector machine, comprising the following steps: step 1, obtaining historical load data and meteorological factor data of the microgrid, and performing data preprocessing, dividing the preprocessed data into a training set and a prediction set; step 2, using the data in the training set to train a microgrid short-term load forecasting model based on ridge wave support vector machine, and saving the trained prediction model; step 3, inputting the data in the prediction set into the trained prediction model, and outputting the load value of the microgrid at the time to be predicted. The prediction method disclosed by the present invention can effectively improve the prediction accuracy and meet the actual scheduling prediction requirements.

Description

Technical Field

[0001] The present invention relates to the field of microgrid load technology, and in particular to a microgrid short-term load forecasting method based on ridgelet support vector machine. Background Art

[0002] A microgrid is a group of micro systems consisting of distributed power sources, loads, energy storage systems and control devices. For a large power grid, it appears as a single controllable unit that can achieve highly reliable supply of loads in various forms of energy (electricity, heat, etc.). The power sources in a microgrid are mostly small-capacity distributed power sources, mainly photovoltaic cells, small wind turbines, micro gas turbines, fuel cells, batteries and other energy storage devices, which have the characteristics of low cost, low voltage and low pollution.

[0003] Load forecasting is an important part of the microgrid energy management system. It is the basis for optimizing the dispatch of distributed power sources, such as wind power, photovoltaics, micro gas turbines, diesel engines and energy storage. The forecast results will directly affect the microgrid operation strategy and power trading. Compared with the large power grid environment, it is more difficult for microgrids to conduct short-term load forecasting. This is mainly due to the strong randomness of the load, the low similarity of historical load curves, the limited user capacity, the small mutual smoothing effect of load characteristics between users, and the large overall load fluctuation.

[0004] In order to improve the accuracy of load forecasting, many scholars have conducted extensive research and proposed a series of forecasting methods, such as BP-NN forecasting method and conventional GRU neural network forecasting method. However, these methods still have the problem of insufficient forecasting accuracy. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides a microgrid short-term load forecasting method based on ridgelet support vector machine, so as to effectively improve the prediction accuracy and meet the actual scheduling prediction requirements.

[0006] To achieve the above object, the technical solution of the present invention is as follows:

[0007] A microgrid short-term load forecasting method based on ridgelet support vector machine includes the following steps:

[0008] Step 1: Obtain historical load data and meteorological factor data of the microgrid, perform data preprocessing, and divide the preprocessed data into a training set and a prediction set;

[0009] Step 2: Use the data in the training set to train the microgrid short-term load forecasting model based on the ridgelet support vector machine, and save the trained forecasting model;

[0010] Step three: input the data in the prediction set into the trained prediction model and output the load value of the microgrid at the time to be predicted.

[0011] In the above scheme, the microgrid short-term load forecasting model based on ridgelet support vector machine is as follows:

[0012]

[0013] Among them, the ridgelet kernel function ψ γ (x i ) is expressed as follows:

[0014]

[0015] In the formula, γ is the parameter space, that is:

[0016] γ=(a j ,u j ,g j );a j ,g j ∈R; a j >0;u j ∈S d-1

[0017] In the formula, α j , is the Lagrange multiplier of the jth ridgelet kernel function, i is the sample number, i = 1, 2, 3…l, l is the sample size, b is a constant; a j represents the scale vector of the jth ridgelet kernel function; u j represents the direction vector of the jth ridgelet kernel function; g j represents the position vector of the jth ridgelet kernel function, j = 1, 2, 3…m, m is the number of ridgelet kernel functions, and m>l; S d-1 Represented as d-1 dimensional space; x i represents the input vector of the i-th sample of the ridgelet kernel function, and y is the output of the microgrid short-term load forecasting model based on the ridgelet support vector machine, that is, the predicted short-term load.

[0018] In a further technical solution, the data in the training set is used to train the microgrid short-term load forecasting model based on the ridgelet support vector machine, and the Lagrange multiplier α of the jth ridgelet kernel function after training is obtained. j , and the scale vector a of the jth ridgelet kernel function j , direction vector u j and position vector g j .

[0019] Through the above technical solution, the microgrid short-term load forecasting method based on ridgelet support vector machine provided by the present invention has the following beneficial effects:

[0020] The present invention constructs a microgrid short-term load forecasting model based on ridge wave support vector machine. The kernel function of the ridge wave support vector machine adopts the ridge wave kernel function, which can effectively characterize the directional singular features in the signal and enhance the generalization ability and prediction performance of the prediction model. Through the prediction simulation and test of the actual microgrid load, it is confirmed that the proposed prediction model can effectively improve the prediction accuracy and meet the actual scheduling prediction requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below.

[0022] Figure 1 A schematic flow chart of a method for short-term load forecasting of a microgrid based on a ridgelet support vector machine disclosed in an embodiment of the present invention;

[0023] Figure 2 Schematic diagram of microgrid short-term load forecasting model based on ridgelet support vector machine. DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0025] The present invention provides a microgrid short-term load forecasting method based on ridgelet support vector machine, such as Figure 1 As shown, the following steps are included:

[0026] Step 1: Obtain historical load data and meteorological factor data of the microgrid, perform data preprocessing, and divide the preprocessed data into a training set and a prediction set;

[0027] Step 2: Use the data in the training set to train the microgrid short-term load forecasting model based on the ridgelet support vector machine, and save the trained forecasting model;

[0028] like Figure 2 As shown in the figure, the microgrid short-term load forecasting model based on ridgelet support vector machine is as follows:

[0029]

[0030] Among them, the ridgelet kernel function ψ γ (x i ) is expressed as follows:

[0031]

[0032] In the formula, γ is the parameter space, that is:

[0033] γ=(a j ,u j ,g j );a j ,g j ∈R; a j >0;u j ∈S d-1

[0034] In the formula, α j , is the Lagrange multiplier of the jth ridgelet kernel function, i is the sample number, i = 1, 2, 3…l, l is the sample size, b is a constant; a j represents the scale vector of the jth ridgelet kernel function; u j represents the direction vector of the jth ridgelet kernel function; g j represents the position vector of the jth ridgelet kernel function, j = 1, 2, 3…m, m is the number of ridgelet kernel functions, and m>l; S d-1 Represented as d-1 dimensional space; x i represents the input vector of the i-th sample of the ridgelet kernel function, and y is the output of the microgrid short-term load forecasting model based on the ridgelet support vector machine, that is, the predicted short-term load.

[0035] The microgrid short-term load forecasting model based on ridgelet support vector machine is trained using the data in the training set to obtain the Lagrange multiplier α of the jth ridgelet kernel function after training. j , and the scale vector a of the jth ridgelet kernel function j , direction vector u j and position vector g j .

[0036] Step three: input the data in the prediction set into the trained prediction model and output the load value of the microgrid at the time to be predicted.

[0037] In order to verify the effectiveness of the microgrid short-term load forecasting model based on ridgelet support vector machine (Model I) proposed in this invention, it is compared with the microgrid short-term load forecasting model based on conventional support vector machine (Model II) and the microgrid short-term load forecasting model based on BP neural network (Model III). The three models are used to predict the load of the microgrid at 24 o'clock on a certain day. The comparison of the prediction errors of the three models is shown in Table 1.

[0038] Table 1 Comparison of prediction errors of three prediction models

[0039]

[0040] As can be seen from Table 1, the average absolute error of the traditional prediction model based on BP neural network is 9.86%, and the maximum relative error is 19.27%. The average absolute error of the prediction model based on conventional support vector machine is reduced by 2.11% compared with the prediction model based on BP neural network, and the maximum relative error is reduced by 2.77%. The prediction model based on ridge wave support vector machine proposed in the present invention is adopted, and the average absolute error is reduced by 5.15% compared with the prediction model based on BP neural network, and the maximum relative error is reduced by 7.79%; the average absolute error is reduced by 3.04% compared with the prediction model based on conventional support vector machine, and the maximum relative error is reduced by 5.02%. This shows that the microgrid short-term load prediction model based on ridge wave support vector machine proposed in the present invention can effectively improve the prediction accuracy and meet the actual scheduling prediction requirements.

[0041] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A microgrid short-term load forecasting method based on ridgelet support vector machine, characterized in that: The steps include: Step 1: Obtain historical load data and meteorological factor data of the microgrid, perform data preprocessing, and divide the preprocessed data into a training set and a prediction set; Step 2: Use the data in the training set to train the microgrid short-term load forecasting model based on the ridgelet support vector machine, and save the trained forecasting model; Step 3: Input the data in the prediction set into the trained prediction model and output the load value of the microgrid at the time to be predicted; The microgrid short-term load forecasting model based on ridgelet support vector machine is as follows: ； Among them, the ridgelet kernel function The expression is as follows: ； In the formula, is the parameter space, that is: ； In the formula, is the Lagrange multiplier of the jth ridgelet kernel function, i is the sample number, i=1,2,3…l, l is the sample size, is a constant; Represents the scale vector of the jth ridgelet kernel function; Represents the direction vector of the jth ridgelet kernel function; represents the position vector of the jth ridgelet kernel function, j=1,2,3…m, m is the number of ridgelet kernel functions, and m>l; Represented as d-1 dimensional space; represents the input vector of the ith sample of the ridgelet kernel function, It is the output of the microgrid short-term load forecasting model based on ridgelet support vector machine, that is, the predicted short-term load.

2. A microgrid short-term load forecasting method based on ridgelet support vector machine according to claim 1, characterized in that: The microgrid short-term load forecasting model based on ridgelet support vector machine is trained using the data in the training set to obtain the Lagrange multiplier of the jth ridgelet kernel function after training. , and the scale vector of the jth ridgelet kernel function , direction vector and the position vector .

Images