Photovoltaic generating capacity control method, readable storage medium and equipment

Abstract

The invention discloses a photovoltaic power generation capacity control method, a readable storage medium and equipment, and belongs to the technical field of photovoltaic power generation. Based on the real-time power generation capacity of power generation equipment, the power generation capacity of the power generation equipment at a target time node is accurately predicted by adopting a pre-selected and trained power generation capacity prediction model; and determining an influence factor which affects the load consumption of the power utilization equipment at the target time node, inputting the influence factor into a pre-constructed load consumption quantity prediction model to obtain predicted load consumption at the target time node, and obtaining a power generation quantity error at the target time node through the predicted power generation quantity and the predicted load consumption at the target time node. Finally, the output power of the power generation equipment is controlled and the power generation amount is adjusted through the power generation amount error, thereby facilitating reasonable distribution of the power generation amount by a factory according to the production condition, ensuring the stability of the power generation equipment and a related grid-connected system, and solving the problem of power supply interruption caused by power grid fluctuation of a current factory roof photovoltaic power generation system.

Description

Technical Field

[0001] The invention relates to a photovoltaic power generation control method, a readable storage medium and a device, and belongs to the technical field of photovoltaic power generation. Background Art

[0002] At present, photovoltaic power generation systems on factory roofs are faced with problems including grid fluctuations, shocks, and incompatibility with the production environment. These problems not only affect the stability of power supply, but may also interfere with the operation of high-precision equipment, leading to reduced production efficiency and product quality problems. For example, grid fluctuations may cause voltage instability, affecting the precise control of precision equipment; and the instability of photovoltaic power generation systems may cause power supply interruptions, affecting the continuous operation of the production line. Summary of the invention

[0003] The purpose of the present invention is to overcome the deficiencies in the prior art and to provide a photovoltaic power generation control method, a readable storage medium and a device, which can accurately predict the power generation at a target time node based on the real-time power generation of the power generation equipment, which is beneficial for the factory to reasonably allocate the power generation according to the production situation, ensure the stability of the power generation equipment and related grid-connected systems, and solve the problem that the current factory roof photovoltaic power generation system is prone to power grid fluctuations leading to power supply interruptions.

[0004] In order to achieve the above purpose / solve the above technical problems, the present invention is implemented by adopting the following technical solutions: In one aspect, the present invention provides a photovoltaic power generation control method, comprising: Obtain real-time power generation of power generation equipment; Input the real-time power generation of the power generation equipment into the pre-trained power generation prediction model to determine the predicted power generation of the power generation equipment at the target time node; Determine the influencing factors that affect the load consumption of the power equipment at the target time node based on the power consumption characteristics of the power equipment at the target time node obtained in advance; Input the influencing factors into the pre-built load absorption prediction model to determine the predicted load absorption at the target time node; Based on the predicted power generation and the predicted load consumption at the target time node, determining the power generation error at the target time node; The output power of the power generation equipment is controlled according to the power generation error to adjust the power generation.

[0005] Furthermore, the training of the pre-trained power generation prediction model includes: Obtain chronologically ordered photovoltaic power generation time series data; According to the photovoltaic power generation time series data, determine the order of the model's autoregressive term and the order of the moving average term; Based on the model's autoregressive term order and moving average term order, a target power generation prediction model is constructed; The preprocessed historical photovoltaic power generation data set is used to train the target power generation prediction model, the optimal model parameters of the target power generation prediction model are determined, and the trained power generation prediction model is obtained.

[0006] Furthermore, the step of determining the order of the autoregressive term and the order of the moving average term of the model according to the photovoltaic power generation time series data includes: Perform ADF test on photovoltaic power generation time series data; If the photovoltaic power generation time series data is stable, then the autocorrelation function graph and the partial autocorrelation function graph are drawn based on the stable photovoltaic power generation time series data; According to the autocorrelation function graph and partial autocorrelation function graph, determine the order of the model autoregressive term and the order of the moving average term.

[0007] Furthermore, an ADF test is performed on the photovoltaic power generation time series data. If the photovoltaic power generation time series data is not stable, the photovoltaic power generation time series data is differentially processed to obtain stable photovoltaic power generation time series data.

[0008] Furthermore, the target power generation prediction model is constructed based on the model autoregressive term order and the moving average term order, including: The target power generation prediction model is expressed by the following formula: ; in: Indicates at time node t of power generation, Indicates at time node of power generation, p represents the autoregressive term, Indicates i autoregressive parameters, represents the white noise error term, q represents the moving average term, Indicates j Moving average parameters, c Represents a constant.

[0009] Furthermore, the method of using the preprocessed historical photovoltaic power generation data set to train the target power generation prediction model, determining the optimal model parameters of the target power generation prediction model, and obtaining the trained power generation prediction model includes: According to the loss function, the autoregressive parameters and moving average parameters of the target power generation prediction model are adjusted within the preset training rounds until the function loss value meets the threshold, thereby obtaining the optimal autoregressive parameters and moving average parameters; The loss function is expressed as follows: ; in: represents the loss value, represents the number of samples selected from the historical photovoltaic power generation data set, Indicates at time node t The actual photovoltaic power generation, Indicates at time node t The predicted power generation;

[0010] Based on the optimal autoregressive parameters and moving average parameters, a trained power generation prediction model is obtained.

[0011] Furthermore, the electricity consumption characteristics include historical electricity consumption, peak electricity consumption periods and weather conditions.

[0012] Furthermore, the pre-built load absorption capacity prediction model includes: The load absorption capacity prediction model is expressed by the following formula: ; in: Indicates that the power equipment is at the target time node t The load absorption capacity, Indicates that at the target time node t No. k The factors that affect the load consumption of power equipment are: Indicates that at the target time node t The number of impact factors, represents the regression coefficient, represents the intercept term, Represents the absorption error.

[0013] Another aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the photovoltaic power generation control method as described above is implemented.

[0014] The present invention also provides a computer device, comprising: A memory for storing instructions; The processor is used to execute the instructions so that the device implements the photovoltaic power generation control method as described above.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention is based on the real-time power generation of power generation equipment, and adopts a pre-selected and trained power generation prediction model to accurately predict the power generation of the power generation equipment at the target time node, and determines the influencing factors that affect the load absorption of the power consumption equipment at the target time node, and inputs the influencing factors into the pre-constructed load absorption prediction model to obtain the predicted load absorption at the target time node. The power generation error at the target time node can be obtained through the predicted power generation and predicted load absorption at the target time node. Finally, the output power of the power generation equipment is controlled by the power generation error, and the power generation is adjusted, which is beneficial for the factory to reasonably allocate the power generation according to the production situation, ensure the stability of the power generation equipment and the related grid-connected system, and solve the problem that the current factory roof photovoltaic power generation system is prone to power grid fluctuations and causes power supply interruptions.

[0016] 2. The present invention determines the order of the model autoregressive term and the order of the moving average term according to the photovoltaic power generation time series data arranged in chronological order, and constructs a target power generation prediction model based on the order of the model autoregressive term and the order of the moving average term. It only requires endogenous variables between the photovoltaic power generation time series data without the need for other exogenous variables, thereby reducing the complexity and calculation amount of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 is a flow chart of a photovoltaic power generation control method provided by an embodiment of the present invention; Figure 2 The present invention provides a flow chart of training a photovoltaic power generation prediction model for a photovoltaic power generation control method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the protection scope of the present invention. Example

[0019] like Figure 1 As shown, a photovoltaic power generation control method includes: Obtain real-time power generation of power generation equipment; Input the real-time power generation of the power generation equipment into the pre-trained power generation prediction model to determine the predicted power generation of the power generation equipment at the target time node; like Figure 2 As shown, the training of the pre-trained power generation prediction model includes: Obtain chronologically ordered photovoltaic power generation time series data; According to the photovoltaic power generation time series data, the order of the model autoregressive term and the order of the moving average term are determined, specifically: Perform ADF test on photovoltaic power generation time series data: If the photovoltaic power generation time series data is not stable, the photovoltaic power generation time series data is differentially processed to obtain stable photovoltaic power generation time series data; If the photovoltaic power generation time series data is stable, then based on the stable photovoltaic power generation time series data, the autocorrelation function diagram and the partial autocorrelation function diagram are drawn, and the order of the model autoregressive term and the order of the moving average term are determined according to the autocorrelation function diagram and the partial autocorrelation function diagram; Based on the order of the model autoregressive term and the order of the moving average term, a target power generation prediction model is constructed. The target power generation prediction model is expressed as follows: ; Indicates at time node t of power generation, Indicates at time node of power generation, p represents the autoregressive term, Indicates i autoregressive parameters, represents the white noise error term, q represents the moving average term, Indicates j Moving average parameters, c represents a constant; The preprocessed historical photovoltaic power generation data set is used to train the target power generation prediction model, determine the optimal model parameters of the target power generation prediction model, and obtain the trained power generation prediction model. Specifically: According to the loss function, the autoregressive parameters and moving average parameters of the target power generation prediction model are adjusted within the preset training rounds until the function loss value meets the threshold, thereby obtaining the optimal autoregressive parameters and moving average parameters; The loss function is expressed as follows: ; in: represents the loss value, represents the number of samples selected from the historical photovoltaic power generation data set, Indicates at time node t The actual photovoltaic power generation, Indicates at time node t The predicted power generation; Based on the optimal autoregressive parameters and moving average parameters, a trained power generation prediction model is obtained.

[0020] Determine the influencing factors that affect the load absorption of the power equipment at the target time node based on the power consumption characteristics of the power equipment at the target time node, where the power consumption characteristics include historical power consumption, peak power consumption period and weather conditions; The influencing factors are input into the pre-built load absorption prediction model to determine the predicted load absorption at the target time node, where the load absorption prediction model is expressed by the following formula: ; in: Indicates that the power equipment is at the target time node t The load absorption capacity, Indicates that at the target time node t No. k The factors that affect the load consumption of power equipment are: Indicates that at the target time node t The number of impact factors, represents the regression coefficient, represents the intercept term, represents the elimination error; and Determine from Table 1: Table 1

[0021] If the historical power consumption of the power-consuming equipment at the target time node is in the range of 0-500 kwh, then The value is 1; According to the condition, if the target time node meets condition 1 or condition 2, then , if both conditions 1 and 2 are met, then ,and ; If the historical power consumption of the power-consuming equipment at the target time node is between 500-1000 kwh, then The value is 1.5; According to the condition, if the target time node meets condition 1 or condition 2, then , if both conditions 1 and 2 are met, then ,and ; If the historical power consumption of the power-consuming equipment at the target time node is greater than 1000 kwh, then The value is 3; According to the condition, if the target time node meets condition 1 or condition 2, then , if both conditions 1 and 2 are met, then ,and .

[0022] Based on the predicted power generation and the predicted load consumption at the target time node, determining the power generation error at the target time node; The output power of the power generation equipment is controlled according to the power generation error to adjust the power generation.

[0023] Example 3 A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the following method: Obtain real-time power generation of power generation equipment; Input the real-time power generation of the power generation equipment into the pre-trained power generation prediction model to determine the predicted power generation of the power generation equipment at the target time node; According to the power consumption characteristics of the power-consuming equipment at the target time node, determine the influencing factors that affect the load consumption of the power-consuming equipment at the target time node; Input the influencing factors into the pre-built load absorption prediction model to determine the predicted load absorption at the target time node; Based on the predicted power generation and the predicted load consumption at the target time node, determining the power generation error at the target time node; The output power of the power generation equipment is controlled according to the power generation error to adjust the power generation.

[0024] Example 4 A computer device comprising: A memory for storing instructions; The processor is used to execute instructions so that the device performs the steps of implementing the following method: Obtain real-time power generation of power generation equipment; Input the real-time power generation of the power generation equipment into the pre-trained power generation prediction model to determine the predicted power generation of the power generation equipment at the target time node; According to the power consumption characteristics of the power-consuming equipment at the target time node, determine the influencing factors that affect the load consumption of the power-consuming equipment at the target time node; Input the influencing factors into the pre-built load absorption prediction model to determine the predicted load absorption at the target time node; Based on the predicted power generation and the predicted load consumption at the target time node, determining the power generation error at the target time node; The output power of the power generation equipment is controlled according to the power generation error to adjust the power generation.

[0025] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A photovoltaic power generation control method, characterized in that: include: Obtain real-time power generation of power generation equipment; Input the real-time power generation of the power generation equipment into the pre-trained power generation prediction model to determine the predicted power generation of the power generation equipment at the target time node; Determine the influencing factors that affect the load consumption of the power equipment at the target time node based on the power consumption characteristics of the power equipment at the target time node obtained in advance; Input the influencing factors into the pre-built load absorption prediction model to determine the predicted load absorption at the target time node; Based on the predicted power generation and the predicted load consumption at the target time node, determining the power generation error at the target time node; The output power of the power generation equipment is controlled according to the power generation error to adjust the power generation.

2. The photovoltaic power generation control method according to claim 1, characterized in that: The training of the pre-trained power generation prediction model includes: Obtain chronologically ordered photovoltaic power generation time series data; According to the photovoltaic power generation time series data, the order of the model autoregressive term and the order of the moving average term are determined; Based on the model's autoregressive term order and moving average term order, a target power generation prediction model is constructed; The preprocessed historical photovoltaic power generation data set is used to train the target power generation prediction model, the optimal model parameters of the target power generation prediction model are determined, and the trained power generation prediction model is obtained.

3. The photovoltaic power generation control method according to claim 2, characterized in that: Determining the order of the autoregressive term and the order of the moving average term of the model according to the photovoltaic power generation time series data includes: Perform ADF test on photovoltaic power generation time series data; If the photovoltaic power generation time series data is stable, then the autocorrelation function graph and the partial autocorrelation function graph are drawn based on the stable photovoltaic power generation time series data; According to the autocorrelation function graph and partial autocorrelation function graph, determine the order of the model's autoregressive term and moving average term.

4. The photovoltaic power generation control method according to claim 3, characterized in that: Perform ADF test on photovoltaic power generation time series data. If the photovoltaic power generation time series data is not stable, perform differential processing on the photovoltaic power generation time series data to obtain stable photovoltaic power generation time series data.

5. The photovoltaic power generation control method according to claim 2, characterized in that: The target power generation prediction model is constructed based on the model autoregressive term order and the moving average term order, including: The target power generation prediction model is expressed by the following formula: ； in: Indicates at time node t of power generation, Indicates at time node of power generation, p represents the autoregressive term, Indicates i autoregressive parameters, represents the white noise error term, q represents the moving average term, Indicates j Moving average parameters, c Represents a constant.

6. The photovoltaic power generation control method according to claim 5, characterized in that: The method of using the preprocessed historical photovoltaic power generation data set to train the target power generation prediction model, determining the optimal model parameters of the target power generation prediction model, and obtaining the trained power generation prediction model includes: According to the loss function, the autoregressive parameters and moving average parameters of the target power generation prediction model are adjusted within the preset training rounds until the function loss value meets the threshold, thereby obtaining the optimal autoregressive parameters and moving average parameters; The loss function is expressed as follows: ； in: represents the loss value, represents the number of samples selected from the historical photovoltaic power generation data set, Indicates at time node t The actual photovoltaic power generation, Indicates at time node t The predicted power generation; Based on the optimal autoregressive parameters and moving average parameters, a trained power generation prediction model is obtained.

7. The photovoltaic power generation control method according to claim 1, characterized in that: The electricity consumption characteristics include historical electricity consumption, peak electricity consumption periods and weather conditions.

8. The photovoltaic power generation control method according to claim 7, characterized in that: The pre-built load absorption capacity prediction model includes: The load absorption capacity prediction model is expressed by the following formula: ； in: Indicates that the power equipment is at the target time node t The load absorption capacity, Indicates that at the target time node t No. k The factors that affect the load consumption of power equipment are: Indicates that at the target time node t The number of impact factors, represents the regression coefficient, represents the intercept term, Represents the absorption error.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the photovoltaic power generation control method according to any one of claims 1 to 8 is implemented.

10. A computer device, characterized in that: include: A memory for storing instructions; A processor is used to execute the instruction so that the device implements the photovoltaic power generation control method as described in any one of claims 1 to 8.

Images