Balcony photovoltaic micro-inverter system and control method thereof

By obtaining the trend information distribution coefficient and floating free coefficient of the photovoltaic power generation voltage accumulation sequence, the gray prediction model is improved, and the problem of insufficient prediction accuracy in the photovoltaic power generation system is solved, and the precise control and maximum conversion of the micro-inverse system are realized. power.

CN118432089BActive Publication Date: 2024-11-15SHENZHEN LEIMING TECH DEV CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410891263.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-04
Publication Date
2024-11-15
Estimated Expiration
2044-07-04

AI Technical Summary

Technical Problem

In the photovoltaic power generation system, the gray prediction model cannot fully reflect the photovoltaic power generation state under different environmental factors because it assumes that all data have the same weight and importance, resulting in inaccurate prediction accuracy, which affects the regulation of the micro-inverse system.

Method used

By obtaining the trend information distribution coefficient and floating free coefficient of the photovoltaic power generation voltage accumulation sequence, combining the sequence decomposition algorithm and gray prediction model, the voltage and current prediction values ​​at the next moment are obtained, and used for the control of the micro-inverse system, the gray prediction model is improved to Consider the local fluctuation characteristics of the data.

Benefits of technology

The prediction accuracy of photovoltaic power generation state data is improved, the sensitivity of the prediction model to the dynamic characteristics of time is enhanced, and more accurate regulation of the micro-inverse system is achieved to achieve maximum conversion power.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118432089B_ABST
    Figure CN118432089B_ABST
Patent Text Reader

Abstract

The present application relates to the technical field of current conversion control, and specifically to a balcony photovoltaic micro-inverter system and a control method thereof, the method comprising: collecting photovoltaic power generation state data within a certain time range, and obtaining a cumulative sequence of photovoltaic power generation state data; analyzing the trend of local data distribution of elements in the cumulative sequence of photovoltaic power generation state data, and constructing a trend information distribution coefficient; further, analyzing the trend change characteristics, and constructing a floating free coefficient; calculating the deviation coefficient and neighbor weight value of photovoltaic power generation state data through the floating free coefficient, and using a grayscale prediction algorithm to predict the photovoltaic power generation state. Thus, the micro-inverter control system can be more accurately regulated to achieve the maximum conversion power.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of current conversion control, and in particular to a balcony photovoltaic micro-inverter system and a control method thereof. Background Art

[0002] In recent years, with the increasing awareness of sustainable energy and environmental protection, renewable energy technology has received widespread attention. Photovoltaic power generation systems have the advantages of modularity, high flexibility, and low environmental impact. They allow electricity to be generated directly at or near the point of use, thereby reducing transmission losses and improving energy efficiency. In distributed power generation systems, microinverters convert the DC power generated by individual photovoltaic panels into AC power for household use.

[0003] Grey prediction model is often used for prediction and control in photovoltaic power generation system to optimize the micro-inverter system. The characteristic of grey prediction model is that it makes predictions based on historical photovoltaic power generation status data, but it assumes that all data have the same weight and importance. In photovoltaic power generation system, due to changes in environmental factors such as different lighting conditions and temperature, there are certain differences in photovoltaic power generation status in historical data. If all data are regarded as having the same weight and importance, it may not fully reflect the actual situation in the current environment, thus affecting the prediction accuracy of photovoltaic power generation status data. This impact may cause the grey prediction model to predict the photovoltaic power generation status inaccurately, thereby affecting the regulation of micro-inverter system. Summary of the invention

[0004] In view of the above, it is necessary to provide a balcony photovoltaic micro-inverter system and a control method thereof to improve the prediction accuracy of photovoltaic power generation status data, accurately regulate the micro-inverter system, and achieve maximum conversion power.

[0005] The first aspect of the present application provides a balcony photovoltaic micro-inverter system control method, the method comprising:

[0006] Recording the sequences composed of the current and voltage data of photovoltaic power generation of a preset duration as photovoltaic power generation current sequence and photovoltaic power generation voltage sequence respectively;

[0007] Based on the photovoltaic power generation voltage data, the grey prediction model is used to obtain the photovoltaic power generation voltage accumulation sequence;

[0008] Based on the local numerical variation characteristics of all elements in the photovoltaic power generation voltage accumulation sequence, combined with the sequence decomposition algorithm, the trend information distribution coefficient sequence is obtained;

[0009] Based on the change characteristics and correlation characteristics of the elements in the trend information distribution coefficient sequence, the voltage prediction value at the next moment is obtained;

[0010] The current prediction value at the next moment is obtained by adopting the same method as the voltage prediction value; the voltage and current prediction values ​​at the next moment are used as inputs of the micro-inversion system to realize the control of the micro-inversion system.

[0011] In one embodiment, the step of acquiring the trend information distribution coefficient sequence is:

[0012] According to the local data distribution of each element of the photovoltaic power generation voltage accumulation sequence, combined with the sequence decomposition algorithm, the trend sequence and residual sequence of each element of the photovoltaic power generation voltage accumulation sequence are obtained;

[0013] According to the data distribution of the residual sequence of each element of the photovoltaic power generation voltage accumulation sequence, the data distribution index of each element of the photovoltaic power generation voltage accumulation sequence is obtained;

[0014] According to the variation characteristics of the residual sequence of each element of the photovoltaic power generation voltage accumulation sequence, combined with the data distribution index, the trend distribution factor of each element of the photovoltaic power generation voltage accumulation sequence is obtained;

[0015] The trend sequence of each element of the photovoltaic power generation voltage accumulation sequence is fitted to obtain a trend curve, and the slope of each trend item of the trend sequence in the trend curve is obtained, and the standard deviation of all the slopes of the trend sequence of each element is calculated and recorded as the information distribution factor of each element of the photovoltaic power generation voltage accumulation sequence; the product of the trend distribution factor of each element of the photovoltaic power generation voltage accumulation sequence and the information distribution factor is used as the trend information distribution coefficient of each element of the photovoltaic power generation voltage accumulation sequence; the sequence composed of the trend information distribution coefficients of all elements of the photovoltaic power generation voltage accumulation sequence is recorded as the trend information distribution coefficient sequence.

[0016] In one embodiment, the step of obtaining the trend sequence and residual sequence of each element of the photovoltaic power generation voltage accumulation sequence is specifically as follows:

[0017] Taking each element in the photovoltaic power generation voltage accumulation sequence as the center, the sequence composed of all elements in the preset window is recorded as the power generation voltage distribution sequence of each element, and the sequence decomposition algorithm is used to obtain the trend sequence and residual sequence of each element.

[0018] In one embodiment, the data distribution index of each element of the photovoltaic power generation voltage accumulation sequence is obtained as follows:

[0019] The extreme value of the trend sequence of each element is calculated; the data distribution index of each element of the photovoltaic power generation voltage accumulation sequence has a consistent change trend with the extreme value and an opposite change trend with the number of elements of the residual sequence.

[0020] In one embodiment, the step of obtaining the trend distribution factor of each element of the photovoltaic power generation voltage accumulation sequence includes:

[0021] The absolute value of the difference between each residual value in the residual sequence of each element of the photovoltaic power generation voltage accumulation sequence and the previous residual value is recorded as each residual difference; the absolute value of the difference between each residual difference and the corresponding data distribution index is calculated to obtain the distribution difference of each residual difference; the cumulative sum of all the distribution differences of each element is used as the trend distribution factor of each element of the photovoltaic power generation voltage accumulation sequence.

[0022] In one embodiment, the step of obtaining the voltage prediction value at the next moment includes:

[0023] A local window is preset with each element of the trend information distribution coefficient sequence as the center;

[0024] According to the local fluctuation characteristics of each element of the trend information distribution coefficient sequence, the floating variables of each element of the trend information distribution coefficient sequence are obtained;

[0025] According to the numerical characteristics of the local window of each element of the trend information distribution coefficient sequence, combined with the distribution characteristics of the floating variable, a floating free coefficient sequence is obtained;

[0026] According to the difference of adjacent values ​​of the floating free coefficient sequence, the neighbor weight value of each element of the photovoltaic power generation voltage accumulation sequence is obtained;

[0027] The photovoltaic power generation voltage sequence is used as the input of the grayscale prediction model, and the neighbor weight values ​​of all elements of the photovoltaic power generation voltage accumulation sequence are combined to output the voltage prediction value at the next moment.

[0028] In one embodiment, the floating variables of each element of the trend information distribution coefficient sequence are obtained as follows:

[0029] For the trend information distribution coefficient sequence, the difference between any value and the minimum value in the local window of each element is recorded as the first selection factor of each element; the difference between the maximum value and any value in the local window of each element is recorded as the second selection factor of each element; the minimum value of the first selection factor and the second selection factor of each element is taken as the floating eigenvalue of each element;

[0030] The floating variable of each element of the trend information distribution coefficient sequence has a consistent change trend with the floating characteristic value and an opposite change trend with the extreme value in the local window.

[0031] In one embodiment, the floating free coefficient sequence is obtained as follows:

[0032] The sequence composed of floating variables of all elements of the trend information distribution coefficient sequence is used as a floating variable sequence; the difference between the median of the floating variable sequence and the median of the local window of each element of the trend information distribution coefficient sequence is used as the denominator of the free factor of each element of the trend information distribution coefficient sequence; the difference between the element mean and the element standard deviation of the floating variable sequence is used as the numerator of the free factor of each element of the trend information distribution coefficient sequence;

[0033] The floating free coefficient of each element of the trend information distribution coefficient sequence has a consistent change trend with the free factor and the median of the floating variable sequence;

[0034] The sequence composed of the floating free coefficients of all elements of the trend information distribution coefficient sequence is taken as the floating free coefficient sequence.

[0035] In one embodiment, the step of obtaining the neighbor weight value of each element of the photovoltaic power generation voltage accumulation sequence includes:

[0036] For the photovoltaic power generation voltage accumulation sequence, the ratio of each element to the corresponding floating free coefficient of the previous element is used as the third selection factor of each element; the reciprocal of the third selection factor is used as the fourth selection factor of each element; the minimum value of the third selection factor and the fourth selection factor of each element is used as the deviation factor of each element, and the product of the deviation factor of each element and the weight value of the neighboring data in the original grayscale prediction model is used as the deviation coefficient of each element;

[0037] The difference between 1 and the deviation coefficient of each element of the photovoltaic power generation voltage accumulation sequence is used as the neighbor weight value of each element of the photovoltaic power generation voltage accumulation sequence.

[0038] A second aspect of the present application provides a balcony photovoltaic micro-inverter system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of any one of the above methods when executing the computer program.

[0039] This application has at least the following beneficial effects:

[0040] The present application proposes a balcony photovoltaic micro-inverter system and a control method thereof: obtaining a photovoltaic power generation current sequence and a photovoltaic power generation voltage sequence to provide a data basis for the control of the micro-inverter system, and the control of the micro-inverter system requires an accurate prediction of the photovoltaic power generation state at the next moment; when using a gray prediction model for sequence prediction, obtaining a photovoltaic power generation voltage accumulation sequence, eliminating random fluctuations and nonlinear trends in the original data, and making the data more regular and predictable; constructing a trend information distribution coefficient of photovoltaic power generation voltage accumulation sequence elements, which can more accurately capture and reflect the time dynamic characteristics of the data and quantify the time dynamic characteristics; constructing a floating free coefficient, which can capture the local fluctuations and abnormal changes of the sequence elements and enhance the sensitivity of the prediction model to subtle time dynamics; obtaining a deviation coefficient and a neighbor weight value, and improving the gray prediction model through the deviation coefficient and the neighbor weight value. The improved gray prediction model takes into account the local fluctuation characteristics of the data, and can more accurately capture the key features of the data, thereby improving the reliability of the prediction results, and more accurately regulates the micro-inverter control system through the prediction value to achieve the maximum conversion power. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A flowchart of a balcony photovoltaic micro-inverter system control method provided in one embodiment of the present application;

[0042] Figure 2 A schematic diagram of a photovoltaic power generation voltage sequence is provided for one embodiment of the present application;

[0043] Figure 3 A schematic diagram of a photovoltaic power generation voltage accumulation sequence provided by an embodiment of the present application;

[0044] Figure 4 A schematic diagram of a STL decomposition of a power generation voltage distribution sequence provided by an embodiment of the present application;

[0045] Figure 5 A flow chart for obtaining a trend information distribution sequence provided by one embodiment of the present application;

[0046] Figure 6 A flowchart for obtaining a predicted current value at the next moment provided by one embodiment of the present application. DETAILED DESCRIPTION

[0047] In the description of the embodiments of the present application, words such as "exemplary", "or", "for example" and the like are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "or", "for example" and the like is intended to present related concepts in a concrete manner.

[0048] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art in the present application. The terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application.

[0049] It should also be noted that the terms "first" and "second" in this application and the accompanying drawings are used to distinguish similar objects, rather than to describe a specific order or sequence. The method disclosed in the embodiments of the present application or the method shown in the flow chart includes one or more steps for implementing the method. Without departing from the scope of protection of the present application, the execution order of multiple steps can be interchanged with each other, and some steps can also be deleted.

[0050] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0051] The specific scheme of the balcony photovoltaic micro-inverter system and its control method provided by the present application is described in detail below with reference to the accompanying drawings.

[0052] See also Figure 1 , which shows a flow chart of the steps of a balcony photovoltaic micro-inverter system control method provided by an embodiment of the present application, the method comprising the following steps:

[0053] S1: Recording the sequences consisting of the current and voltage data of photovoltaic power generation of a preset duration as photovoltaic power generation current sequence and photovoltaic power generation voltage sequence respectively.

[0054] This application mainly predicts and adjusts photovoltaic power generation current and voltage data to ensure the stable operation of the micro-inverter system and maximize energy utilization.

[0055] First, according to the database of the photovoltaic micro-inverter control system, the current and voltage data of the historical photovoltaic power generation of the preset time length are obtained. In some embodiments of the present application, the data collection time interval is 1s, and the preset time length is 2min.

[0056] Due to various factors, the data collected may be missing. In some embodiments of this application, the mean interpolation method is used to complete the missing data in each initial sequence. Since the photovoltaic panels are installed outdoors, the collected data may be noisy. In some embodiments of this application, mean filtering is used to denoise the data. Since both mean interpolation and mean filtering are well-known technologies, the specific calculation process will not be repeated. In addition, the implementer can choose other methods to process the data, and this application does not limit this.

[0057] At this point, the sequences composed of the processed photovoltaic power generation current and voltage data are recorded as photovoltaic power generation current sequence and photovoltaic power generation voltage sequence respectively.

[0058] S2: Based on the photovoltaic power generation voltage data, a grey prediction model is used to obtain the photovoltaic power generation voltage accumulation sequence.

[0059] In order to ensure the micro-inverter system tracks the maximum power, it is necessary to accurately predict the photovoltaic power generation state at the next moment. Since the analysis of the photovoltaic power generation current sequence and the photovoltaic power generation voltage sequence is the same, this application takes the photovoltaic power generation voltage sequence as an example for analysis:

[0060] The grey prediction GM (1, 1) model is used to obtain the photovoltaic power generation voltage accumulation sequence according to the photovoltaic power generation voltage sequence; the photovoltaic power generation voltage accumulation sequence can help eliminate the randomness and volatility in the photovoltaic power generation voltage sequence, thereby better reflecting the development trend of the sequence.

[0061] Among them, the schematic diagram of photovoltaic power generation voltage sequence is as follows: Figure 2 As shown; Schematic diagram of photovoltaic power generation voltage accumulation sequence, as shown Figure 3 The horizontal axes of these two figures are all time points. Figure 2 The vertical axis is the photovoltaic power generation voltage, Figure 3 The vertical axis is the accumulated value of photovoltaic power generation voltage;

[0062] S3: Based on the local numerical variation characteristics of all elements of the photovoltaic power generation voltage accumulation sequence, combined with the sequence decomposition algorithm, the trend information distribution coefficient sequence is obtained.

[0063] When the grey prediction GM (1, 1) model obtains the photovoltaic power generation voltage cumulative sequence to construct a close-to-mean sequence, when the voltage data has a high trend, it means that there is a strong dependence between the data values ​​at each time point in the sequence.

[0064] The efficiency and output of photovoltaic power generation are affected by many factors, including the angle of the sun, the intensity of sunlight, weather conditions, and the movement of clouds. These factors directly affect the efficiency of photovoltaic panels in absorbing solar energy and the power generation status of photovoltaic systems, and also have a strong impact on the prediction results of data in different states. When modeling, data points need to be given relatively uniform weights to reflect the impact of the entire trend, so that the predicted voltage data is more accurate.

[0065] S301: According to the local data distribution of each element of the photovoltaic power generation voltage accumulation sequence, in combination with the sequence decomposition algorithm, the trend sequence and residual sequence of each element of the photovoltaic power generation voltage accumulation sequence are obtained.

[0066] In order to further analyze the local changes of the photovoltaic power generation voltage accumulation sequence, the sequence composed of all elements in the preset window is recorded as the power generation voltage distribution sequence of the i-th element, with the i-th element in the photovoltaic power generation voltage accumulation sequence as the center; in some embodiments of the present application, the preset window size is The implementer can flexibly adjust the window; it should be noted that for the elements whose window length cannot be obtained at both ends of the sequence, the mean interpolation method is used to complete them. Based on this, each element of the photovoltaic power generation voltage accumulation sequence has a corresponding power generation voltage distribution sequence. The power generation voltage distribution sequence facilitates the subsequent analysis of the local characteristics of the photovoltaic voltage accumulation sequence and reflects the local changes of the photovoltaic voltage accumulation sequence.

[0067] For the photovoltaic power generation voltage accumulation sequence, the sequence decomposition algorithm is used for the power generation voltage distribution sequence of each element to obtain the trend sequence, season sequence and residual sequence of the power generation voltage distribution sequence of each element.

[0068] In some embodiments of the present application, the sequence decomposition algorithm selects the STL (Seasonal and Trend decomposition using Loess) algorithm; the implementer can select the sequence decomposition algorithm according to the actual situation, and the present application does not impose any restrictions on this.

[0069] Among them, the STL decomposition diagram of the power generation voltage distribution sequence is as follows: Figure 4 shown.

[0070] S302: Obtaining a data distribution index of each element of the photovoltaic power generation voltage accumulation sequence according to the data distribution of the residual sequence of each element of the photovoltaic power generation voltage accumulation sequence.

[0071] The extreme value of the residual sequence of each element is calculated; the data distribution index of each element of the photovoltaic power generation voltage accumulation sequence has a consistent change trend with the extreme value and an opposite change trend with the number of elements of the residual sequence.

[0072] It should be noted that the consistent change trend is specifically manifested as as one variable increases or decreases, another variable also increases or decreases; conversely, the opposite change trend is formed; based on the unchanged trend relationship, the implementer can choose a suitable method to determine the variable, and this application does not impose any restrictions on this.

[0073] In some embodiments of the present application, the ratio of the extreme value to the number of elements in the residual sequence minus 1 is used as the data distribution index of each element of the photovoltaic power generation voltage accumulation sequence. The data distribution index is used to describe the discreteness of the power generation voltage distribution sequence data and reflects the degree of data fluctuation.

[0074] S303: Obtaining a trend distribution factor of each element of the photovoltaic power generation voltage accumulation sequence according to a variation characteristic of the residual sequence of each element of the photovoltaic power generation voltage accumulation sequence and combining the data distribution index.

[0075] The absolute value of the difference between each residual value in the residual sequence of each element of the photovoltaic power generation voltage accumulation sequence and the previous residual value is recorded as each residual difference; the absolute value of the difference between each residual difference and the corresponding data distribution index is calculated to obtain the distribution difference of each residual difference; the cumulative sum of all the distribution differences of each element is obtained and recorded as the trend distribution factor of each element. The trend distribution factor is used to describe the distribution trend of the data in the power generation voltage distribution sequence and reflect the trend change of the data.

[0076] S304: Obtain a trend information distribution coefficient sequence according to the change characteristics of the trend sequence of each element of the photovoltaic power generation voltage accumulation sequence and the trend distribution factor.

[0077] The trend sequence of each element of the photovoltaic power generation voltage accumulation sequence is fitted to obtain a trend curve, and the slope of each trend item of the trend sequence in the trend curve is obtained, and the standard deviation of all the slopes of the trend sequence of each element is calculated, which is recorded as the information distribution factor of each element of the photovoltaic power generation voltage accumulation sequence; it should be noted that, considering that all the slopes in the trend curve may be the same, the corresponding information distribution factor is 0 at this time, so the information distribution factor is corrected by adding a preset parameter adjustment factor greater than zero. In some embodiments of the present application, the parameter adjustment factor is 1; the implementer can flexibly adjust it according to the actual situation, and the present application does not limit this.

[0078] The trend information distribution coefficient of each element of the photovoltaic power generation voltage accumulation sequence is in a consistent trend relationship with the trend distribution factor and the information distribution factor.

[0079] In some embodiments of the present application, the product of the trend distribution factor and the information distribution factor of each element of the photovoltaic power generation voltage accumulation sequence is used as the trend information distribution coefficient of each element. The sequence composed of the trend information distribution coefficients of all elements of the photovoltaic power generation voltage accumulation sequence is recorded as the trend information distribution coefficient sequence.

[0080] Among them, the flow chart of obtaining the trend information distribution sequence is as follows: Figure 5 shown.

[0081] It should be noted that when there is a strong correlation between the values ​​of the power generation voltage distribution sequence, the smaller the value of the trend distribution factor of the photovoltaic power generation voltage accumulation sequence element; at the same time, the smaller the value of the element's information distribution factor, the smaller the value of the trend information distribution coefficient of the photovoltaic power generation voltage accumulation sequence element, indicating that the volatility of the voltage data is smaller, the trend is more consistent, and the possibility of strong correlation is greater. When the prediction module of the photovoltaic inverter predicts the data, the GM (1, 1) model relies more on adjacent data to ensure that the predicted data is more accurate, and can make the output voltage value reach the best state when controlling the micro-inverter system and achieve the best power.

[0082] Since each element of the photovoltaic power generation voltage accumulation sequence has a trend information distribution coefficient, the local volatility of the trend information distribution coefficient reflects the degree of connection. When the local volatility is smaller, the connection between the data is stronger. When calculating the prediction, the data weights should be closer to make the predicted value more accurate and the conversion effect of the micro-inversion system better.

[0083] S4: Based on the change characteristics and correlation characteristics of the elements in the trend information distribution coefficient sequence, the voltage prediction value at the next moment is obtained.

[0084] When the trend information distribution coefficient of each element of the photovoltaic power generation voltage accumulation sequence has a small fluctuation pattern in the trend information distribution coefficient sequence, it means that the data have a strong correlation.

[0085] S401: Obtaining floating variables of each element of the trend information distribution coefficient sequence according to the local fluctuation characteristics of each element of the trend information distribution coefficient sequence.

[0086] Take the jth element in the trend information distribution coefficient sequence as an example: take the jth element as the center and obtain a local window; in some embodiments of the present application, the local window is The implementer can flexibly adjust the window according to the actual situation. It should be noted that for the elements whose window length cannot be obtained at both ends of the sequence, the mean interpolation method is used to complete them. Based on this, each element in the trend information distribution coefficient sequence has a local window, which is convenient for subsequent analysis.

[0087] For the j-th element of the trend information distribution coefficient sequence, the difference between any numerical value and the minimum value in the local window of the j-th element is recorded as the first selection factor of the j-th element; the difference between the maximum value and any numerical value in the local window of the j-th element is recorded as the second selection factor of the j-th element; the minimum value of the first selection factor and the second selection factor of the j-th element is taken as the floating eigenvalue of the j-th element; the floating variables of each element of the trend information distribution coefficient sequence have a consistent changing trend with the floating eigenvalue and an opposite changing trend with the extreme value in the local window.

[0088] In some embodiments of the present application, the ratio of the floating characteristic value of the jth element to the numerical extreme difference value in the corresponding local window is used as the floating variable of the jth element of the trend information distribution coefficient sequence. The floating variable measures the change characteristics of the trend information distribution coefficient, that is, the degree of fluctuation of the change trend of the photovoltaic power generation voltage data.

[0089] S402: Obtain a floating free coefficient sequence according to the numerical characteristics of the local window of each element of the trend information distribution coefficient sequence and the distribution characteristics of the floating variable.

[0090] The sequence composed of floating variables of all elements of the trend information distribution coefficient sequence is taken as a floating variable sequence; the difference between the median of the floating variable sequence and the median of the local window of the j-th element of the trend information distribution coefficient sequence is taken as the denominator of the free factor of the j-th element; the difference between the element mean and the element standard deviation of the floating variable sequence is taken as the numerator of the free factor of the j-th element; it should be noted that in order to prevent the denominator from being 0 and the free factor from being meaningless, when the denominator is 0, the numerator is taken as the free factor of the j-th element.

[0091] The floating free coefficient of the jth element of the trend information distribution coefficient sequence has a consistent change trend with the free factor and the median of the floating variable sequence. In some embodiments of the present application, the product of the free factor and the median of the floating variable sequence is used as the floating free coefficient of the jth element of the trend information distribution coefficient sequence.

[0092] The sequence composed of the floating free coefficients of all elements in the trend information distribution coefficient sequence is taken as the floating free coefficient sequence.

[0093] The closer the data between the floating free coefficient sequences are, the higher the correlation between the data is. The closer the weights assigned to the data during prediction are, the better the prediction effect of the data can be. The higher the prediction effect, the more accurate the control of the micro-inversion system and the better the conversion effect.

[0094] S403: Obtaining the neighbor weight value of each element of the photovoltaic power generation voltage accumulation sequence according to the difference of adjacent values ​​of the floating free coefficient sequence.

[0095] It should be noted that, since the trend information distribution coefficient sequence corresponds one-to-one with each element of the photovoltaic power generation voltage accumulation sequence, and the trend information distribution sequence corresponds one-to-one with each element of the floating free coefficient sequence, the photovoltaic power generation voltage accumulation sequence corresponds one-to-one with each element of the floating free coefficient sequence.

[0096] For the photovoltaic power generation voltage accumulation sequence, the ratio of each element to the corresponding floating free coefficient of the previous element is used as the third selection factor of each element; the reciprocal of the third selection factor is used as the fourth selection factor of each element; the minimum value of the third selection factor and the fourth selection factor of each element is used as the deviation factor of each element, and the product of the deviation factor of each element and the weight value of the neighboring data in the original grayscale prediction GM (1, 1) model is used as the deviation coefficient of each element. In some embodiments of the present application, the weight value of the neighboring data is 0.5.

[0097] The neighbor weight value is in an opposite trend relationship to the deviation coefficient. In some embodiments of the present application, the difference between 1 and the deviation coefficient of each element of the photovoltaic power generation voltage accumulation sequence is used as the neighbor weight value of each element of the photovoltaic power generation voltage accumulation sequence.

[0098] The neighbor weight value and deviation coefficient can make the data predicted by the grayscale prediction GM (1, 1) model more accurate, providing a basis for the subsequent regulation of the micro-inversion system.

[0099] S404: A grayscale prediction model is used according to the neighbor weight values ​​of all elements of the photovoltaic power generation voltage accumulation sequence to obtain a voltage prediction value at the next moment.

[0100] The neighbor weight value and the deviation coefficient are used as the weights for generating the neighbor mean of the grayscale prediction GM (1, 1) model, and the generation of the neighbor mean generation sequence of the grayscale prediction GM (1, 1) model is improved. The photovoltaic power generation voltage sequence is used as the input of the grayscale prediction GM (1, 1) model, and the output result is the voltage prediction value at the next moment.

[0101] Among them, the flow chart for obtaining the current prediction value at the next moment is as follows: Figure 6 shown.

[0102] S5: using the same method as the voltage prediction value to obtain the current prediction value at the next moment; using the voltage and current prediction values ​​at the next moment as inputs of the micro-inverter system to achieve control of the micro-inverter system.

[0103] The voltage prediction value and current prediction value of photovoltaic power generation are used as the input of the micro-inverter system, and the output results are the adjusted current and voltage values, which realize the control of the micro-inverter, ensure the stable operation of the micro-inverter system and maximize energy utilization.

[0104] Based on the same inventive concept as the above method, an embodiment of the present application also provides a balcony photovoltaic micro-inverter system, including a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, the steps of any one of the above-mentioned balcony photovoltaic micro-inverter system control methods are implemented.

[0105] In summary, the embodiment of the present application proposes a balcony photovoltaic micro-inverter system and a control method thereof: obtaining a photovoltaic power generation current sequence and a photovoltaic power generation voltage sequence to provide a data basis for the control of the micro-inverter system, and the control of the micro-inverter system requires an accurate prediction of the photovoltaic power generation state at the next moment; when using a gray prediction model for sequence prediction, obtaining a photovoltaic power generation voltage accumulation sequence, eliminating random fluctuations and nonlinear trends in the original data, making the data more regular and predictable; constructing a trend information distribution coefficient of the photovoltaic power generation voltage accumulation sequence elements, which can more accurately capture and reflect the time dynamic characteristics of the data and quantify the time dynamic characteristics; constructing a floating free coefficient, which can capture the local fluctuations and abnormal changes of the sequence elements and enhance the sensitivity of the prediction model to subtle time dynamics; obtaining a deviation coefficient and a neighbor weight value, and improving the gray prediction model through the deviation coefficient and the neighbor weight value. The improved gray prediction model takes into account the local fluctuation characteristics of the data, and can more accurately capture the key features of the data, thereby improving the reliability of the prediction results, and more accurately regulates the micro-inverter control system through the prediction value to achieve the maximum conversion power.

[0106] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

[0107] For those skilled in the art, it is obvious that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the basic features of the present application. Therefore, no matter from which point of view, the above embodiments of the present application should be regarded as exemplary and non-restrictive; the technical solutions recorded in the above embodiments are modified, or some of the technical features are replaced by equivalents, which does not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. Balcony photovoltaic micro-inverter system control method, It is characterized in that The method comprises the following steps: Recording the sequences composed of the current and voltage data of photovoltaic power generation of a preset duration as photovoltaic power generation current sequence and photovoltaic power generation voltage sequence respectively; Based on the photovoltaic power generation voltage data, the grey prediction model is used to obtain the photovoltaic power generation voltage accumulation sequence; Based on the local numerical variation characteristics of all elements in the photovoltaic power generation voltage accumulation sequence, combined with the sequence decomposition algorithm, the trend information distribution coefficient sequence is obtained; Based on the change characteristics and correlation characteristics of the elements in the trend information distribution coefficient sequence, the voltage prediction value at the next moment is obtained; The current prediction value at the next moment is obtained by using the same method as the voltage prediction value; the voltage and current prediction values ​​at the next moment are used as inputs of the micro-inversion system to realize control of the micro-inversion system; The steps for obtaining the trend information distribution coefficient sequence are: According to the local data distribution of each element of the photovoltaic power generation voltage accumulation sequence, combined with the sequence decomposition algorithm, the trend sequence and residual sequence of each element of the photovoltaic power generation voltage accumulation sequence are obtained; According to the data distribution of the residual sequence of each element of the photovoltaic power generation voltage accumulation sequence, the data distribution index of each element of the photovoltaic power generation voltage accumulation sequence is obtained; According to the variation characteristics of the residual sequence of each element of the photovoltaic power generation voltage accumulation sequence, combined with the data distribution index, the trend distribution factor of each element of the photovoltaic power generation voltage accumulation sequence is obtained; The trend sequence of each element of the photovoltaic power generation voltage accumulation sequence is fitted to obtain a trend curve, and the slope of each trend item of the trend sequence in the trend curve is obtained, and the standard deviation of all the slopes of the trend sequence of each element is calculated, which is recorded as the information distribution factor of each element of the photovoltaic power generation voltage accumulation sequence; the product of the trend distribution factor of each element of the photovoltaic power generation voltage accumulation sequence and the information distribution factor is used as the trend information distribution coefficient of each element of the photovoltaic power generation voltage accumulation sequence; the sequence composed of the trend information distribution coefficients of all elements of the photovoltaic power generation voltage accumulation sequence is recorded as the trend information distribution coefficient sequence; The step of obtaining the voltage prediction value at the next moment includes: A local window is preset with each element of the trend information distribution coefficient sequence as the center; According to the local fluctuation characteristics of each element of the trend information distribution coefficient sequence, the floating variables of each element of the trend information distribution coefficient sequence are obtained; According to the numerical characteristics of the local window of each element of the trend information distribution coefficient sequence, combined with the distribution characteristics of the floating variable, a floating free coefficient sequence is obtained; According to the difference of adjacent values ​​of the floating free coefficient sequence, the neighbor weight value of each element of the photovoltaic power generation voltage accumulation sequence is obtained; The photovoltaic power generation voltage sequence is used as the input of the grayscale prediction model, and the neighbor weight values ​​of all elements of the photovoltaic power generation voltage accumulation sequence are combined to output the voltage prediction value at the next moment; The floating variables of each element of the trend information distribution coefficient sequence are specifically: For the trend information distribution coefficient sequence, the difference between any value and the minimum value in the local window of each element is recorded as the first selection factor of each element; the difference between the maximum value and any value in the local window of each element is recorded as the second selection factor of each element; the minimum value of the first selection factor and the second selection factor of each element is taken as the floating eigenvalue of each element; The floating variable of each element of the trend information distribution coefficient sequence has a consistent change trend with the floating characteristic value and an opposite change trend with the extreme value in the local window.

2. The balcony photovoltaic micro-inverter system control method according to claim 1, It is characterized in that The step of obtaining the trend sequence and residual sequence of each element of the photovoltaic power generation voltage accumulation sequence is specifically as follows: Taking each element in the photovoltaic power generation voltage accumulation sequence as the center, the sequence composed of all elements in the preset window is recorded as the power generation voltage distribution sequence of each element, and the sequence decomposition algorithm is used to obtain the trend sequence and residual sequence of each element.

3. The balcony photovoltaic micro-inverter system control method according to claim 1, It is characterized in that The data distribution index of each element of the photovoltaic power generation voltage accumulation sequence is obtained as follows: The extreme value of the trend sequence of each element is calculated; the data distribution index of each element of the photovoltaic power generation voltage accumulation sequence has a consistent change trend with the extreme value and an opposite change trend with the number of elements of the residual sequence.

4. The balcony photovoltaic micro-inverter system control method according to claim 1, It is characterized in that The step of obtaining the trend distribution factor of each element of the photovoltaic power generation voltage accumulation sequence includes: The absolute value of the difference between each residual value in the residual sequence of each element of the photovoltaic power generation voltage accumulation sequence and the previous residual value is recorded as each residual difference; the absolute value of the difference between each residual difference and the corresponding data distribution index is calculated to obtain the distribution difference of each residual difference; the cumulative sum of all the distribution differences of each element is used as the trend distribution factor of each element of the photovoltaic power generation voltage accumulation sequence.

5. The balcony photovoltaic micro-inverter system control method according to claim 1, It is characterized in that The obtained floating free coefficient sequence is specifically: The sequence composed of floating variables of all elements of the trend information distribution coefficient sequence is used as a floating variable sequence; the difference between the median of the floating variable sequence and the median of the local window of each element of the trend information distribution coefficient sequence is used as the denominator of the free factor of each element of the trend information distribution coefficient sequence; the difference between the element mean and the element standard deviation of the floating variable sequence is used as the numerator of the free factor of each element of the trend information distribution coefficient sequence; The floating free coefficient of each element of the trend information distribution coefficient sequence has a consistent change trend with the free factor and the median of the floating variable sequence; The sequence composed of the floating free coefficients of all elements of the trend information distribution coefficient sequence is taken as the floating free coefficient sequence.

6. The balcony photovoltaic micro-inverter system control method according to claim 1, It is characterized in that The method of obtaining the neighbor weight value of each element of the photovoltaic power generation voltage accumulation sequence includes: For the photovoltaic power generation voltage accumulation sequence, the ratio of each element to the corresponding floating free coefficient of the previous element is used as the third selection factor of each element; the reciprocal of the third selection factor is used as the fourth selection factor of each element; the minimum value of the third selection factor and the fourth selection factor of each element is used as the deviation factor of each element, and the product of the deviation factor of each element and the weight value of the neighboring data in the original grayscale prediction model is used as the deviation coefficient of each element; The difference between 1 and the deviation coefficient of each element of the photovoltaic power generation voltage accumulation sequence is used as the neighbor weight value of each element of the photovoltaic power generation voltage accumulation sequence.

7. A balcony photovoltaic micro-inverter system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.