A method and system for predicting the operation status of a distribution network

Abstract

The present invention discloses a method and system for predicting the operation state of a distribution network, which relates to the technical field of intelligent prediction. The method includes the following steps: constructing an open-loop equation, inputting interference quantities and input quantities into the open-loop equation to obtain corresponding output quantities, analyzing to obtain the periodic characteristics and probability characteristics of each interference quantity, and outputting the interference quantities and the corresponding probabilities. By analyzing the periodic and probability characteristics in historical data, the present invention can more accurately predict the influence of interference quantities on the operation state of the distribution network, takes into account various interference quantities and their dynamic changes, can better cope with uncertainties and complex working conditions, predicts the occurrence probability of interference quantities in advance, reasonably arranges maintenance and resource allocation, improves the operation efficiency, provides data support for distribution network operation management personnel, helps them make more scientific decisions, and can update the feature analysis in real time through the sliding window technology to adapt to the dynamic changes of the distribution network operation state.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent prediction, and particularly relates to a method and system for predicting the operation state of a distribution network. Background Technique

[0002] In recent years, data technology has become an important support for predicting the operation state of a distribution network. By collecting and analyzing a large amount of operation data, including information such as voltage, current, power, and temperature, functions such as load prediction, fault prediction, and energy management are realized. The application of big data technology not only improves the accuracy and practicability of prediction but also provides a scientific basis for the operation and maintenance of the power system. Driven by emerging technologies such as big data, artificial intelligence, and digital twin, the technology for predicting the operation state of a distribution network has made remarkable progress, but it still needs to be continuously optimized and innovated to meet the development needs of future power systems.

[0003] Currently, in the Chinese invention patent with the publication number CN117277266A, a method for predicting the operation state of a distribution network based on an improved firefly algorithm to optimize the RBF neural network is disclosed. This method constructs a prediction model for the operation state of the distribution network; inputs the divided training set into the prediction model for the operation state of the distribution network for training, and uses the mean absolute error and root mean square error as prediction evaluation indicators; compares the predicted voltage value with the actual voltage change amount of each node. If the voltage difference amount is less than the threshold, it is considered that the operation state of the distribution network is normal; if the voltage difference amount is greater than the threshold, the operation state of the distribution network is unstable. However, in the related technology, the relevant data of the power grid are not predicted based on historical data, lacking the scientific nature of prediction, and the prediction results are not optimized and output according to the probability and frequency of the occurrence of interference amounts, which easily leads to misleading predictions and is not conducive to the inclusiveness and accuracy of prediction. Summary of the Invention

[0004] The technical problem solved by the present invention is that in the related technology, the relevant data of the power grid are not predicted based on historical data, lacking the scientific nature of prediction, and the prediction results are not optimized and output according to the probability and frequency of the occurrence of interference amounts, which easily leads to misleading predictions and is not conducive to the inclusiveness and accuracy of prediction.

[0005] To solve the above technical problem, the present invention provides the following technical solutions: In the first aspect, a method for predicting the operation state of a distribution network includes the following steps:

[0006] Step S100, obtain the input quantity, output quantity, and interference quantity according to historical operation data, construct an open-loop equation based on the input quantity, output quantity, and interference quantity, and obtain the corresponding output quantity by inputting the interference quantity and input quantity into the open-loop equation;

[0007] Step S200: Set a time window, slide the interference amount according to the time window to obtain interference quantum data segments, analyze the sub-data segments, and obtain the periodic characteristics and probability characteristics of each interference amount.

[0008] Step S300: Obtain the current time point, match the corresponding interference amount according to the periodic characteristics of the interference amount, match the probability of the occurrence of the interference amount according to the probability characteristics, and output the interference amount and the corresponding probability.

[0009] As a preferred solution of a power distribution network operation state prediction method according to the present invention, wherein: the historical operation data includes input power, ambient temperature, ambient humidity, ambient wind speed, output power, cable aging degree, and transformer power conversion efficiency.

[0010] The reference value of the response speed of the cable transmission power is a first value, and the calculation method of the cable aging degree includes:

[0011] Calculate the difference between the response speed of the cable transmission power and the first value, denoted as the first difference, calculate the ratio of the first difference to the first value, and set the ratio of the first difference to the first value as the cable aging degree.

[0012] The transformer power conversion efficiency is expressed as the ratio of the transformer output power to the transformer input power.

[0013] As a preferred solution of a power distribution network operation state prediction method according to the present invention, wherein: set the input power as the input quantity, set the ambient temperature, ambient humidity, ambient wind speed, cable aging degree, and transformer power conversion efficiency as the interference amounts, set the output power as the output quantity, and the input quantity, output quantity, and interference amounts are time-domain signals that change with time.

[0014] As a preferred solution of a power distribution network operation state prediction method according to the present invention, wherein: the calculation method of the open-loop equation includes:

[0015] Through discrete Fourier transform, convert the input quantity, output quantity, and interference amounts from time-domain signals to frequency-domain signals, ignore the interference amounts, construct an open-loop transfer function according to the converted input quantity and output quantity, add the interference amounts, and convert the open-loop transfer function into an open-loop equation.

[0016] As a preferred solution of a power distribution network operation state prediction method according to the present invention, wherein: the calculation expression of the open-loop equation is:

[0017] ;

[0018] Wherein, is the output quantity, is the input quantity, , , , and are all interference quantities, and are respectively the ambient temperature, ambient humidity, ambient wind speed, cable aging degree, and transformer power conversion efficiency. is the open-loop transfer function. , , , and are the influence coefficients corresponding to each interference quantity, and the influence coefficients are obtained through experimental calculations.

[0019] As a preferred solution of a method for predicting the operation state of a distribution network according to the present invention, wherein: the first time length is set as the time window length, and the second value is set as the time step;

[0020] The interference quantities are sorted into a time series format. Through the sliding window technique, starting from the beginning of the time series, the window is continuously moved, and each time the length of the second value is moved, the data segments in each window are extracted, and the data segments are set as interference sub-data segments.

[0021] Analyze the sub-data segments to obtain the periodic characteristics and probability characteristics of each interference quantity.

[0022] As a preferred solution of a method for predicting the operation state of a distribution network according to the present invention, wherein: perform a discrete Fourier transform on each sub-data segment, convert the time-domain data into frequency-domain data, calculate the power spectral density of the interference quantity after the transformation, set the third value as the reference value of the power spectral density, compare each power spectral density with the third value, select the power spectral density segments greater than or equal to the third value, calculate the time interval between the end point of the previous segment and the starting point of the next adjacent power spectral density segment, traverse each time interval, calculate the average value of the time intervals, set the average value of the time intervals as the periodic characteristic of the corresponding interference quantity, and establish a first mapping relationship between the interference quantity and the periodic characteristic.

[0023] As a preferred solution of a method for predicting the operation state of a distribution network according to the present invention, wherein: count the total number of sub-data segments, count the number of times each interference quantity appears in the sub-data segments, denoted as the first number, calculate the ratio of the first number to the total number of sub-data segments, set it as the probability characteristic of the corresponding interference quantity, and establish a second mapping relationship between the interference quantity and the probability characteristic.

[0024] As a preferred solution of a method for predicting the operation state of a distribution network according to the present invention, the following steps are included: Obtain the current time point, calculate the time interval from the current time point to the end point of the previous sub-data segment, denoted as the first interval, calculate the difference between the first interval and the periodic characteristics corresponding to each interference quantity, select the difference between the first interval with the smallest absolute value and the periodic characteristics corresponding to each interference quantity, denoted as the target difference, and set the interference quantity corresponding to the target difference as the predicted interference quantity;

[0025] Input the predicted interference quantity into the second mapping relationship to match the corresponding probability;

[0026] Output the interference quantity and the corresponding probability.

[0027] In a second aspect, a system for predicting the operation state of a distribution network includes an analysis module, a calculation module, and a mapping module;

[0028] The analysis module is used to obtain the input quantity, output quantity, and interference quantity according to historical operation data, construct an open-loop equation based on the input quantity, output quantity, and interference quantity, and obtain the corresponding output quantity by inputting the interference quantity and input quantity into the open-loop equation;

[0029] The calculation module is used to set a time window, slide the interference quantity according to the time window to obtain sub-data segments of the interference quantity, analyze the sub-data segments to obtain the periodic characteristics and probability characteristics of each interference quantity;

[0030] The mapping module is used to obtain the current time point, match the corresponding interference quantity according to the periodic characteristics of the interference quantity, match the probability of the occurrence of the interference quantity according to the probability characteristics, and output the interference quantity and the corresponding probability.

[0031] The beneficial effects of the present invention: By analyzing the periodic and probability characteristics in historical data, it is possible to more accurately predict the impact of interference quantities on the operation state of the distribution network, consider various interference quantities and their dynamic changes, better cope with uncertainties and complex working conditions, predict the occurrence probability of interference quantities in advance, reasonably arrange maintenance and resource allocation, improve operation efficiency, provide data support for distribution network operation management personnel, help them make more scientific decisions, and through the sliding window technology, it is possible to update the feature analysis in real time to adapt to the dynamic changes of the distribution network operation state. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a schematic diagram of the basic process of a method for predicting the operation state of a distribution network provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0033] To make the above objects, features, and advantages of the present invention more apparent and understandable, the following provides a detailed description of the specific embodiments of the present invention in conjunction with the accompanying drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all embodiments.

[0034] Example, referring to Figure 1 , which is an embodiment of the present invention, provides a method for predicting the operating state of a distribution network, including the following steps:

[0035] Step S100: Obtain the input quantity, output quantity, and interference quantity according to historical operation data, construct an open-loop equation based on the input quantity, output quantity, and interference quantity, and obtain the corresponding output quantity by inputting the interference quantity and input quantity into the open-loop equation;

[0036] Step S200: Set a time window, slide the interference quantity according to the time window to obtain interference quantity sub-data segments, analyze the sub-data segments, and obtain the periodic characteristics and probability characteristics of each interference quantity;

[0037] Step S300: Obtain the current time point, match the corresponding interference quantity according to the periodic characteristics of the interference quantity, match the probability of the occurrence of the interference quantity according to the probability characteristics, and output the interference quantity and the corresponding probability.

[0038] By analyzing the periodic and probability characteristics in historical data, the present invention can more accurately predict the impact of interference quantities on the operating state of the distribution network, takes into account various interference quantities and their dynamic changes, can better cope with uncertainties and complex working conditions, predict the occurrence probability of interference quantities in advance, reasonably arrange maintenance and resource allocation, improve operating efficiency, provide data support for distribution network operation management personnel, and help them make more scientific decisions. Through the sliding window technology, the feature analysis can be updated in real time to adapt to the dynamic changes of the distribution network operating state.

[0039] The historical operation data includes input power, ambient temperature, ambient humidity, ambient wind speed, output power, cable aging degree, and transformer power conversion efficiency;

[0040] The reference value of the response speed of cable transmission power is the first value, and the calculation method of the cable aging degree includes:

[0041] Calculate the difference between the response speed of cable transmission power and the first value, denoted as the first difference, calculate the ratio of the first difference to the first value, and set the ratio of the first difference to the first value as the cable aging degree;

[0042] The transformer power conversion efficiency is expressed as the ratio of the transformer output power to the transformer input power.

[0043] In specific implementation, by analyzing the periodic and probabilistic characteristics in historical data, the impact of interference quantity on the operation state of the distribution network can be predicted more accurately. Through the dynamic monitoring of cable aging degree and transformer efficiency, potential problems can be detected in advance, and sudden failures can be reduced. The historical operation data is as follows: input power: 100 kW, output power: 95 kW, ambient temperature: 30 °C, ambient humidity: 70%, ambient wind speed: 5 m / s, cable aging degree: 0.1, transformer efficiency: 95%. For the cable aging degree, assuming the response speed is 0.9 and the reference value is 1.0, an aging degree of 0.1 indicates that the cable aging is relatively light. The transformer efficiency of 95% indicates that the transformer is in good operation state.

[0044] Set the input power as the input quantity, set the ambient temperature, ambient humidity, ambient wind speed, cable aging degree, and transformer power conversion efficiency as interference quantities, and set the output power as the output quantity. The input quantity, output quantity, and interference quantity are time-domain signals and change with time.

[0045] In specific implementation, through frequency-domain signal analysis, the dynamic changes of the input quantity and interference quantity can be captured, and the accuracy of output power prediction can be improved. The extraction of periodic characteristics and probabilistic characteristics enables the model to better adapt to complex operation environments. The sliding window technique allows the model to be updated in real time to adapt to the dynamic changes of the distribution network operation state. By predicting the changes in output power, potential problems can be detected in advance, and maintenance and resource allocation can be reasonably arranged.

[0046] The calculation method of the open-loop equation includes:

[0047] Through discrete Fourier transform, convert the input quantity, output quantity, and interference quantity from time-domain signals to frequency-domain signals. Ignore the interference quantity, construct an open-loop transfer function according to the converted input quantity and output quantity, and then add the interference quantity to convert the open-loop transfer function into an open-loop equation.

[0048] The calculation expression of the open-loop equation is:

[0049] ;

[0050] Where, is the output quantity, is the input quantity, , , , , and are all interference quantities, and are respectively the ambient temperature, ambient humidity, ambient wind speed, cable aging degree, and transformer power conversion efficiency, is the open-loop transfer function, , , , and They are influence coefficients corresponding to respective interference quantities, and the influence coefficients are obtained through experimental calculation.

[0051] In specific implementation, through frequency-domain analysis, the influences of input quantities and interference quantities on output quantities can be captured more effectively, thereby improving prediction accuracy. The introduction of the open-loop transfer function and the interference transfer function enables the system to analyze stability more intuitively in the frequency domain. Frequency-domain analysis provides a theoretical basis for the design and optimization of control systems, helps formulate more effective control strategies, and uses FFT for frequency-domain conversion, significantly reducing the computational complexity and improving the computational efficiency.

[0052] Set the first time length as the time-window length and set the second value as the time step;

[0053] Arrange the interference quantities in a time-series format. Through the sliding-window technique, starting from the beginning of the time series, continuously move the window, each time moving a length of the second value, extract the data segments in each window, and set the data segments as sub-data segments of the interference quantities;

[0054] Analyze the sub-data segments to obtain the periodic characteristics and probability characteristics of respective interference quantities.

[0055] Perform discrete Fourier transform on each sub-data segment to convert the time-domain data into frequency-domain data, calculate the power spectral density of the interference quantity after transformation, set the third value as the reference value of the power spectral density, compare each power spectral density with the third value, select the power spectral density segments greater than or equal to the third value, calculate the time interval between the end point of the previous segment and the start point of the next adjacent power spectral density segment, traverse each time interval, calculate the average value of the time intervals, set the average value of the time intervals as the periodic characteristic of the corresponding interference quantity, and establish the first mapping relationship between the interference quantity and the periodic characteristic.

[0056] Count the total number of sub-data segments, count the number of times each interference quantity appears in the sub-data segments, denoted as the first count, calculate the ratio of the first count to the total number of sub-data segments, set it as the probability characteristic of the corresponding interference quantity, and establish the second mapping relationship between the interference quantity and the probability characteristic.

[0057] Obtain the current time point, calculate the time interval from the current time point to the end point of the previous sub-data segment, denoted as the first interval, calculate the difference between the first interval and the periodic characteristics of respective interference quantities, select the difference between the first interval and the periodic characteristics of respective interference quantities with the smallest absolute value, denoted as the target difference, and set the interference quantity corresponding to the target difference as the predicted interference quantity;

[0058] Input the predicted interference quantity into the second mapping relationship to match the corresponding probability;

[0059] Output the interference amount and the corresponding probability.

[0060] In specific implementation, the extraction of periodic features helps to identify potential interference patterns in advance, thereby optimizing the system operation strategy and enhancing stability. Through statistical analysis, the occurrence probability of the interference amount can be estimated more accurately, thereby improving the prediction accuracy of the output power. The extraction of probability features helps to identify potential interference patterns in advance, thereby optimizing the system operation strategy and enhancing stability.

[0061] By analyzing the periodic and probability features in historical data, the present invention can more accurately predict the impact of the interference amount on the operation state of the distribution network. Considering various interference amounts and their dynamic changes, it can better cope with uncertainties and complex working conditions, predict the occurrence probability of the interference amount in advance, reasonably arrange maintenance and resource allocation, improve operation efficiency, provide data support for distribution network operation management personnel, and help them make more scientific decisions. Through the sliding window technology, the feature analysis can be updated in real time to adapt to the dynamic changes of the distribution network operation state.

[0062] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code. Among them, the storage medium is implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, abbreviated as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, abbreviated as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, abbreviated as EPROM), programmable read-only memory (Programmable Red-Only Memory, abbreviated as PROM), read-only memory (Read-Only Memory, abbreviated as ROM), magnetic memory, flash memory, magnetic disk or optical disc. These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions specified in one process Figure 1 one process or multiple processes and / or blocks Figure 1 or multiple blocks specified in the block.

[0063] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that modifications or equivalent replacements can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

Claims

1. A distribution network operation status prediction method, characterized in that: The following steps are involved: Step S100, obtaining input quantity, output quantity and interference quantity according to historical operation data, constructing an open-loop equation according to the input quantity, output quantity and interference quantity, and obtaining the corresponding output quantity by inputting the interference quantity and input quantity into the open-loop equation; Step S200, setting a time window, sliding the interference amount according to the time window, obtaining interference sub-data segments, analyzing the sub-data segments, and obtaining periodic characteristics and probability characteristics of each interference amount; Step S300, obtaining the current time point, matching the corresponding interference amount according to the periodic characteristics of the interference amount, matching the probability of occurrence of the interference amount according to the probability characteristics, and outputting the interference amount and the corresponding probability; The input power is set as the input quantity, the ambient temperature, ambient humidity, ambient wind speed, cable aging degree and transformer power conversion efficiency are set as the interference quantity, and the output power is set as the output quantity, wherein the input quantity, output quantity and interference quantity are time domain signals and change according to the change of time; Obtain the current time point, calculate the time interval from the current time point to the end point of the previous sub-data segment, record it as the first interval, calculate the difference between the first interval and the periodic characteristics corresponding to each interference amount, select the difference between the first interval and the periodic characteristics corresponding to each interference amount with the smallest absolute value, record it as the target difference, and set the interference amount corresponding to the target difference as the predicted interference amount; Inputting the predicted interference amount into the second mapping relationship to match the corresponding probability; The interference amount and the corresponding probability are output.

2. A distribution network operation status prediction method according to claim 1, characterized in that: The historical operation data includes input power, ambient temperature, ambient humidity, ambient wind speed, output power, cable aging and transformer power conversion efficiency; The reference value of the response speed of the cable transmission power is a first value, and the calculation method of the cable aging degree includes: Calculate the difference between the response speed of the cable transmission power and the first value, record it as the first difference, calculate the ratio of the first difference to the first value, and set the ratio of the first difference to the first value as the cable aging degree; The transformer power conversion efficiency is expressed as the ratio of the transformer output power to the transformer input power.

3. A distribution network operation status prediction method according to claim 1, characterized in that: The calculation method of the open-loop equation includes: Through discrete Fourier transform, the input, output and interference are converted from time domain signals to frequency domain signals, the interference is ignored, an open-loop transfer function is constructed based on the converted input and output, the interference is added, and the open-loop transfer function is converted into an open-loop equation.

4. A distribution network operation status prediction method according to claim 3, characterized in that: The calculation expression of the open-loop equation is: ； in, is the output, is the input quantity, , , , and are interference quantities, and are respectively ambient temperature, ambient humidity, ambient wind speed, cable aging degree and transformer power conversion efficiency. is the open-loop transfer function, , , , and is the influence coefficient corresponding to each interference quantity, and the influence coefficient is obtained through experimental calculation.

5. A distribution network operation status prediction method according to claim 1, characterized in that: The first time length is set as the time window length, and the second value is set as the time step length; Arrange the interference quantity into a time series format, and use a sliding window technique to continuously move the window from the starting point of the time series, each time moving the length of the second value, extract data fragments from each window, and set the data fragments as interference quantum data fragments; The sub-data segments are analyzed to obtain the periodic characteristics and probability characteristics of each interference quantity.

6. A distribution network operation status prediction method according to claim 5, characterized in that: Perform a discrete Fourier transform on each sub-data segment, convert the time domain data into frequency domain data, calculate the power spectrum density of the transformed interference amount, set the third value as a reference value of the power spectrum density, compare each power spectrum density with the third value, select a power spectrum density segment that is greater than or equal to the third value, calculate the time interval between the end point of the previous segment and the initial point of the next segment of adjacent power spectrum density segments, traverse each time interval, calculate the average value of the time interval, set the average value of the time interval as the periodic characteristic of the corresponding interference amount, and establish a first mapping relationship between the interference amount and the periodic characteristic.

7. A distribution network operation status prediction method according to claim 5, characterized in that: Count the total number of sub-data segments, count the number of times each interference amount appears in the sub-data segment, record it as the first number, calculate the ratio of the first number to the total number of sub-data segments, set it as the probability feature of the corresponding interference amount, and establish a second mapping relationship between the interference amount and the probability feature.

8. A distribution network operation status prediction system, the system is used to execute the distribution network operation status prediction method according to claim 1, characterized in that: It includes an analysis module, a calculation module and a mapping module; The analysis module is used to obtain input quantity, output quantity and interference quantity according to historical operation data, construct an open-loop equation according to the input quantity, output quantity and interference quantity, and obtain the corresponding output quantity by inputting the interference quantity and input quantity into the open-loop equation; The calculation module is used to set a time window, slide the interference amount according to the time window, obtain interference quantum data fragments, analyze the sub-data fragments, and obtain the periodic characteristics and probability characteristics of each interference amount; The mapping module is used to obtain the current time point, match the corresponding interference amount according to the periodic characteristics of the interference amount, match the probability of occurrence of the interference amount according to the probability characteristics, and output the interference amount and the corresponding probability; The input power is set as the input quantity, the ambient temperature, ambient humidity, ambient wind speed, cable aging degree and transformer power conversion efficiency are set as the interference quantity, and the output power is set as the output quantity, wherein the input quantity, output quantity and interference quantity are time domain signals and change according to the change of time; Obtain the current time point, calculate the time interval from the current time point to the end point of the previous sub-data segment, record it as the first interval, calculate the difference between the first interval and the periodic characteristics corresponding to each interference amount, select the difference between the first interval and the periodic characteristics corresponding to each interference amount with the smallest absolute value, record it as the target difference, and set the interference amount corresponding to the target difference as the predicted interference amount; Inputting the predicted interference amount into the second mapping relationship to match the corresponding probability; The interference amount and the corresponding probability are output.

Images