Method, system and equipment for calculating short-circuit current of power distribution network containing distributed power supply based on grid-connected point voltage prediction, and storage medium

Abstract

The invention discloses a grid-connected point voltage prediction-based short-circuit current calculation method, system and device for a power distribution network containing a distributed power supply, and a storage medium, and relates to the technical field of power system short-circuit current calculation, and the method comprises the steps: collecting the historical data of the power distribution network, and cleaning the historical data; performing standardization processing on the cleaned data to select feature data influencing node voltage; constructing a training set data training model and evaluating performance; predicting the voltage of each node after short circuit by using the model; determining the output current of the distributed power supply according to the predicted node voltage value; and outputting the short-circuit current of the fault point. According to the grid-connected point voltage prediction-based distributed power supply-containing power distribution network short-circuit current calculation method provided by the invention, the short-circuit current is calculated through an iteration method, the accuracy of short-circuit current calculation is improved, the calculation time and complexity are reduced, the uncertainty of a distributed power supply is adapted, and the calculation efficiency is improved. Therefore, the dynamic analysis capability and the operation reliability of the power distribution network are enhanced, and the requirements of protection equipment selection and configuration are met.

Description

Technical Field

[0001] The present invention relates to the technical field of short-circuit current calculation of power systems, and in particular to a method, system, device and storage medium for calculating short-circuit current of a distribution network containing distributed power sources based on grid connection point voltage prediction. Background Art

[0002] With the rapid development of renewable energy and the widespread application of distributed power sources (such as solar photovoltaics, wind power generation, etc.) in distribution networks, modern distribution networks are gradually transforming into "active distribution networks". This transformation has improved energy efficiency and reduced environmental pollution, but it has also made the operation of distribution networks more complicated. It is mainly manifested in: the complexity of the grid topology has increased, and the decentralized access of distributed power sources has changed the traditional unidirectional power flow; the dynamic operation of the grid has increased, the output of distributed power sources is affected by weather and time, and the operation status of the grid has changed frequently; the short-circuit current characteristics have changed, and the access of distributed power sources will significantly change the short-circuit current level and characteristics of the distribution network. Therefore, accurately predicting the voltage at the grid connection point and calculating the short-circuit current are crucial to the stable operation of the distribution network and the selection of protection equipment.

[0003] However, the existing short-circuit current calculation methods are usually based on the steady-state model of the network, which makes it difficult to accurately reflect the impact of the access of distributed power sources. Traditional methods ignore the volatility of distributed power output and the dynamic changes in voltage, resulting in insufficient accuracy in short-circuit current calculation. In addition, for complex distribution network structures, traditional methods have high computational complexity and difficulty in real-time calculation. Faced with these challenges, methods based on data-driven and prediction technologies have become a research hotspot. In particular, machine learning algorithms such as support vector machines have shown significant advantages in voltage prediction and short-circuit current calculation. Using SVM for voltage prediction can effectively capture the dynamic changes in voltage of distribution networks containing distributed power sources, and combined with a dynamic short-circuit current calculation model, it can more accurately reflect the impact of distributed power sources on short-circuit current.

[0004] The present invention proposes a new method for predicting the grid connection point voltage based on the SVM model and calculating the short-circuit current through an iterative method, aiming to improve the accuracy of short-circuit current calculation, reduce the calculation time and complexity, adapt to the uncertainty of distributed power sources, thereby enhancing the dynamic analysis capability and operational reliability of the distribution network, meeting the requirements of protection equipment selection and configuration, and ensuring the safe and stable operation of the power grid. Summary of the invention

[0005] In view of the above-mentioned problems, the present invention is proposed.

[0006] Therefore, the technical problem solved by the present invention is that the existing short-circuit current calculation has the following optimization problems: it is difficult to accurately reflect the impact of the access of distributed power sources, the short-circuit current calculation accuracy is insufficient, and the real-time calculation is difficult.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions: a method for calculating short-circuit current of a distribution network containing distributed power sources based on grid connection point voltage prediction, comprising:

[0008] Collect historical data of the distribution network and clean the historical data;

[0009] Standardize the cleaned data to select characteristic data that affect node voltage;

[0010] Build training set data to train the model and evaluate the performance;

[0011] Use the model to predict the voltage at each node after a short circuit;

[0012] Determine the output current of the distributed power source according to the predicted node voltage value;

[0013] Output the short-circuit current of the fault point.

[0014] As a preferred solution of the method for calculating short-circuit current of a distribution network containing distributed power sources based on grid connection point voltage prediction described in the present invention, the historical data of the distribution network includes load size, short-circuit type, short-circuit location, system topology, line impedance, and transformer capacity.

[0015] As a preferred solution of the method for calculating short-circuit current of a distribution network containing distributed power sources based on grid connection point voltage prediction according to the present invention, the cleaning of historical data includes identifying and deleting abnormal values ​​in the historical data using the interquartile range method IQR. The specific formula is as follows:

[0016] IQR=Q 3 -Q 1

[0017] Among them, IQR represents the spread of the middle 50% in the historical data set, Q represents the value at the 25% position in the historical data, 3 Indicates the value at the 75% position in the historical data.

[0018] As a preferred solution of the method for calculating short-circuit current of a distribution network containing distributed power sources based on grid connection point voltage prediction according to the present invention, wherein: the standardization of the cleaned data includes adopting a zero-mean standardization method, which is expressed as:

[0019]

[0020] Among them, x represents the historical data after cleaning, u represents the mean of the data after cleaning, δ represents the standard deviation of the data after cleaning, and z represents the standardized data.

[0021] As a preferred solution of the method for calculating short-circuit current of a distribution network containing distributed power sources based on grid connection point voltage prediction described in the present invention, the characteristic data of the node voltage includes short-circuit location, short-circuit type, line impedance, and transformer capacity.

[0022] As a preferred solution of the method for calculating short-circuit current of a distribution network containing distributed power sources based on grid connection point voltage prediction according to the present invention, wherein: the construction of a training set data training model includes that the adopted training set data includes 80% of the standardized data;

[0023] A support vector machine (SVM) variant and a radial basis function (RBF) kernel are selected, and grid search and cross-validation methods are used to output the optimal penalty parameter C, kernel function parameter γ, and insensitive loss function parameter ε.

[0024] As a preferred solution of the method for calculating short-circuit current of a distribution network containing distributed power sources based on grid connection point voltage prediction according to the present invention, wherein: the performance evaluation includes using the determination coefficient R 2 The performance of the model is evaluated as follows:

[0025]

[0026] Among them, R 2 represents the coefficient of determination, SSR is the calculation of the residual sum of squares, and SST represents the calculation of the total sum of squares.

[0027] As a preferred solution of the method for calculating short-circuit current of a distribution network containing distributed power sources based on grid connection point voltage prediction described in the present invention, the method uses a model to predict the voltage of each node after a short circuit, including inputting new data that affects the node voltage, and dividing the new data into feature sets and target variables and inputting them into the model to predict the voltage of each node.

[0028] As a preferred solution of the method for calculating short-circuit current of a distribution network containing distributed power sources based on grid connection point voltage prediction according to the present invention, wherein: the output current of the distributed power source is determined according to the predicted node voltage value, including:

[0029] The voltage of the distributed generation grid connection point is extracted from the predicted node voltages, and the initial value of the output current of the distributed generation is given according to the predicted value of the grid connection point voltage.

[0030] As a preferred solution of the method for calculating short-circuit current of a distribution network containing distributed power sources based on grid connection point voltage prediction described in the present invention, the short-circuit current of the output fault point includes:

[0031] According to the value of the output current of the distributed power supply, the initial value of the short-circuit current is output, and the subsequent calculation is performed using an iterative method.

[0032] Another object of the present invention is to provide a short-circuit current calculation system for a distribution network containing distributed power sources based on grid connection point voltage prediction, which can determine the output current of the distributed power source according to the predicted node voltage value, thereby solving the problem of insufficient short-circuit current calculation accuracy in existing short-circuit current calculation methods.

[0033] To solve the above technical problems, the present invention provides the following technical solutions: a short-circuit current calculation system for a distribution network containing distributed power sources based on grid-connected point voltage prediction, comprising: a data acquisition module, a model evaluation module and a short-circuit current output module; the data acquisition module is used to collect historical data of the distribution network and clean it; the model evaluation module is used to use a training set data model through voltage feature data and evaluate the performance of the model; the short-circuit current output module is used to determine the output current of the distributed power source according to the predicted node voltage value, and output the short-circuit current of the fault point.

[0034] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the method for calculating short-circuit current of a distribution network containing distributed power sources based on grid connection point voltage prediction as described above are implemented.

[0035] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for calculating short-circuit current of a distribution network containing distributed power sources based on grid connection point voltage prediction as described above.

[0036] Beneficial effects of the present invention: The method for calculating short-circuit current of a distribution network containing distributed power sources based on grid connection point voltage prediction provided by the present invention improves data quality by cleaning historical data, identifies and deletes outliers through the interquartile range method IQR, and reduces the impact of noise and erroneous data on model performance. The cleaned data is more reliable, which helps to improve the robustness and prediction accuracy of the model. Standardization of the cleaned data facilitates comparison and model training between different features. Standardized data helps the algorithm converge faster and improves training efficiency. By selecting key features (such as short-circuit location, short-circuit type, etc.), unnecessary data dimensions are reduced and the efficiency and accuracy of model training are improved. Focusing on features that have a significant impact on node voltage makes model predictions more accurate. Selecting a suitable support vector machine SVM variant, such as the radial basis function RBF kernel, can better capture nonlinear relationships in the data. The optimal penalty parameter C, kernel function parameter γ, and insensitive loss function parameter ε are found through grid search and cross-validation to improve the generalization ability of the model. To evaluate the performance of the model, the determination coefficient R is used 2 Evaluate model performance, R 2 The closer the value is to 1, the more accurate the model prediction is. 2Adjust model parameters or collect data again to optimize model performance. Use the trained model to predict node voltages under new data and provide necessary input for short-circuit current calculation. The model can respond quickly to new data inputs to provide support for real-time monitoring and fault response of the distribution network. Determining the output current of distributed power sources based on the predicted value of the grid connection point voltage helps optimize power management and improve grid stability. The output of distributed power sources can be dynamically adjusted according to the state of the grid to improve the flexibility and reliability of the grid. The short-circuit current at the fault point is calculated through an iterative method to improve the accuracy and efficiency of fault analysis. Accurate short-circuit current calculation is crucial for the selection of protection equipment and the safe and stable operation of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0038] Figure 1 An overall flow chart of a method for calculating short-circuit current in a distribution network containing distributed power sources based on grid connection point voltage prediction provided by an embodiment of the present invention.

[0039] Figure 2 An overall flow chart of a method for calculating short-circuit current in a distribution network containing distributed power sources based on grid connection point voltage prediction provided by an embodiment of the present invention.

[0040] Figure 3 An overall flow chart of a method for calculating short-circuit current in a distribution network containing distributed power sources based on grid connection point voltage prediction provided by an embodiment of the present invention.

[0041] Figure 4 An overall flow chart of a method for calculating short-circuit current in a distribution network containing distributed power sources based on grid connection point voltage prediction provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0042] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0043] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0044] Example 1, reference Figure 1 , which is an embodiment of the present invention, provides a method for calculating short-circuit current of a distribution network containing distributed power sources based on grid connection point voltage prediction, comprising:

[0045] Collect historical data of the distribution network and clean the historical data;

[0046] Standardize the cleaned data to select characteristic data that affect node voltage;

[0047] Build training set data to train the model and evaluate the performance;

[0048] Use the model to predict the voltage at each node after a short circuit;

[0049] Determine the output current of the distributed power source according to the predicted node voltage value;

[0050] Output the short-circuit current of the fault point.

[0051] The historical data of the distribution network obtained includes load size, short circuit type, short circuit location, system topology, line impedance, transformer capacity, etc.

[0052] The method used to clean the historical data is the interquartile range method, and the specific formula is as follows:

[0053] IQR=Q 3 -Q 1

[0054] Where IQR is the spread of the middle 50% of the historical data set, Q 1 is the value at the 25% position in the historical data, Q 3 It is the value at the 75% position in the historical data, which is lower than Q 1 -1.5*IQR or higher than Q 3 Values ​​of +1.5*IQR were considered outliers and deleted.

[0055] The method used for standardizing the cleaned data is the zero-mean standardization method, and the specific formula is as follows:

[0056]

[0057] Among them, x is the historical data after cleaning; u is the mean of the cleaned data; δ is the standard deviation of the cleaned data, and z is the standardized data. By using this method, the mean of the processed data is 0, and after standardization, the data is distributed on a similar scale, which helps the algorithm converge faster.

[0058] The characteristic data affecting the node voltage are selected, including short circuit location, short circuit type, line impedance, and transformer capacity.

[0059] The method of using the training set data to train a suitable model includes selecting a suitable support vector machine SVM variant, such as a radial basis function RBF kernel, and using grid search and cross-validation methods to find the best penalty parameter C, kernel function parameter γ, and insensitive loss function parameter ε. C is a regularization parameter in SVM. A larger C will increase the model complexity and the risk of overfitting, while a smaller C will increase the classification error. γ defines the influence range of a single training sample. A too large γ will lead to overfitting, while a too small γ will fail to capture the complex relationships in the data. ε is used to define the error range between the predicted value and the true value. A too large ε will lead to an inaccurate model, while a too small ε will easily increase the complexity of the model.

[0060] The performance of the model was evaluated using the coefficient of determination R 2 Evaluate the performance of the model. The specific formula is as follows:

[0061]

[0062] Among them, R 2 is the coefficient of determination; SSR is the residual sum of squares; SST is the total sum of squares, R 2 The closer the value is to 1, the better the performance of the model is. 2 The closer the value is to 0, the worse the performance of the model. 2 If the value is not appropriate, you can repeat the above steps to collect more data and adjust the model parameters.

[0063] The method of using the model to predict the voltage of each node after a short circuit includes inputting new data that affects the node voltage, and dividing the new data into a feature set and a target variable and inputting the new data into the model to predict the voltage of each node.

[0064] The method of determining the output current of the distributed power source according to the predicted node voltage value includes extracting the voltage of the distributed power source grid connection point from the predicted node voltages, and providing an initial value of the output current of the distributed power source according to the predicted value of the grid connection point voltage.

[0065] The method of solving the short-circuit current at the fault point includes solving the initial value of the short-circuit current according to the initial value of the output current of the distributed power source, and performing subsequent calculations using an iterative method to improve the accuracy of the short-circuit current calculation.

[0066] Embodiment 2, as Figure 2 , which is an embodiment of the present invention, provides a short-circuit current calculation system for a distribution network containing distributed power sources based on grid connection point voltage prediction, comprising:

[0067] Data acquisition module, model evaluation module and short-circuit current output module;

[0068] The data acquisition module is used to collect historical data of the distribution network and clean it;

[0069] The model evaluation module is used to use the training set data model through the characteristic data of voltage and evaluate the performance of the model;

[0070] The short-circuit current output module is used to determine the output current of the distributed power supply according to the predicted node voltage value and output the short-circuit current of the fault point.

[0071] Embodiment 3, an embodiment of the present invention, is different from the first two embodiments in that:

[0072] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0073] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0074] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0075] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0076] Embodiment 4, as Figure 3 - Figure 4 , which is an embodiment of the present invention, provides a method for calculating short-circuit current of a distribution network containing distributed power sources based on grid connection point voltage prediction. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0077] The calculation accuracy of the present invention is kept at a high level even when the number of nodes increases. 2 The value may also remain above 0.9, showing good prediction performance. The calculation accuracy of the existing iterative calculation method decreases slightly with the increase of the number of nodes.2 The value gradually decreases from 0.85, indicating that the prediction performance is affected by the increase in the number of nodes. Under all node numbers, the calculation accuracy of the present invention is higher than that of the prior art, indicating that the present invention can more accurately predict the short-circuit current. As the number of nodes increases, the accuracy difference between the two technologies may become more obvious, further highlighting the advantages of the present invention.

[0078] The computing time used by the method of the present invention increases slightly with the increase in the number of nodes, but since the present invention adopts a more efficient algorithm, the increase may be relatively gentle. The computing time used by the existing iterative method increases significantly with the increase in the number of nodes, because the existing technology is inefficient when processing large-scale data. When the number of nodes is small, the performance difference between the two technologies is not obvious. As the number of nodes increases, the computing time of the present invention increases more slowly than the existing technology, showing better scalability. The efficiency advantage of the present invention may be more obvious when the number of nodes is large, which is particularly important for power grid systems that need to process large amounts of data.

[0079] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for calculating short-circuit current of a distribution network containing distributed power sources based on grid connection point voltage prediction, characterized in that: include: Collect historical data of the distribution network and clean the historical data; Standardize the cleaned data to select characteristic data that affect node voltage; Build training set data to train the model and evaluate the performance; Use the model to predict the voltage at each node after a short circuit; Determine the output current of the distributed power source according to the predicted node voltage value; Output the short-circuit current of the fault point.

2. The method for calculating short-circuit current of a distribution network containing distributed power sources based on grid connection point voltage prediction according to claim 1, characterized in that: The historical data of the distribution network includes load size, short circuit type, short circuit location, system topology, line impedance, and transformer capacity.

3. The method for calculating short-circuit current of a distribution network containing distributed power sources based on grid connection point voltage prediction according to claim 1 or 2, characterized in that: The cleaning of historical data includes identifying and deleting outliers in the historical data using the interquartile range method IQR. The specific formula is as follows: IQR=Q3-Q1 Among them, IQR represents the spread of the middle 50% in the historical data set, represents the value at the 25% position in the historical data, and Q3 represents the value at the 75% position in the historical data.

4. The method for calculating short-circuit current of a distribution network containing distributed power sources based on grid connection point voltage prediction according to claim 3, characterized in that: The standardization of the cleaned data includes adopting a zero-mean standardization method, which is expressed as: Among them, x represents the historical data after cleaning, u represents the mean of the data after cleaning, δ represents the standard deviation of the data after cleaning, and z represents the standardized data.

5. The method for calculating short-circuit current of a distribution network containing distributed power sources based on grid connection point voltage prediction according to claim 4, characterized in that: The characteristic data of the node voltage includes short circuit location, short circuit type, line impedance, and transformer capacity.

6. The method for calculating short-circuit current of a distribution network containing distributed power sources based on grid connection point voltage prediction according to claim 1 or 2, characterized in that: The constructing of the training set data training model includes using the training set data including 80% of the standardized data; A support vector machine (SVM) variant and a radial basis function (RBF) kernel are selected, and grid search and cross-validation methods are used to output the optimal penalty parameter C, kernel function parameter γ, and insensitive loss function parameter ε.

7. The method for calculating short-circuit current of a distribution network containing distributed power sources based on grid connection point voltage prediction according to claim 5, characterized in that: The performance evaluation includes using the coefficient of determination R 2 The performance of the model is evaluated as follows: Among them, R 2 represents the coefficient of determination, SSR is the calculation of the residual sum of squares, and SST represents the calculation of the total sum of squares.

8. The method for calculating short-circuit current of a distribution network containing distributed power sources based on grid connection point voltage prediction according to claim 1 or 2, characterized in that: The method of using the model to predict the voltage of each node after a short circuit includes inputting new data that affects the node voltage, and dividing the new data into a feature set and a target variable and inputting the feature set and the target variable into the model to predict the voltage of each node.

9. The method for calculating short-circuit current of a distribution network containing distributed power sources based on grid connection point voltage prediction according to claim 1 or 8, characterized in that: The step of determining the output current of the distributed power supply according to the predicted node voltage value includes: The voltage of the distributed generation grid connection point is extracted from the predicted node voltages, and the initial value of the output current of the distributed generation is given according to the predicted value of the grid connection point voltage.

10. The method for calculating short-circuit current of a distribution network containing distributed power sources based on grid connection point voltage prediction according to claim 1 or 2, characterized in that: The short-circuit current of the output fault point includes: According to the value of the output current of the distributed power supply, the initial value of the short-circuit current is output, and the subsequent calculation is performed using an iterative method.

11. A system for calculating short-circuit current of a distribution network containing distributed power sources based on grid connection point voltage prediction, characterized in that: include, A data collection module (100), used to collect and clean historical data of the distribution network; A model evaluation module (200) for using a training set data model through voltage feature data and evaluating the performance of the model; and The short-circuit current output module (300) is used to determine the output current of the distributed power source according to the predicted node voltage value, and output the short-circuit current of the fault point.

12. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method for calculating the short-circuit current of the distribution network containing distributed power sources based on the grid connection point voltage prediction are implemented.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the steps of the method for calculating the short-circuit current of the distribution network containing distributed power sources based on the grid connection point voltage prediction are implemented.

Images