A method and system for monitoring carbon emissions of a substation

Abstract

The application discloses a kind of carbon emission monitoring method and system of transformer substation, method includes: with preset time window on direction angle value sequence sliding, direction angle value is vector synthesis in each time window and the amplitude of synthesis vector is extracted as direction consistency index, obtain direction consistency time sequence;Determine the deviation degree value of each direction consistency index and statistical center in direction consistency time sequence, obtain mean deviation sequence;Positive value element and negative value element in mean deviation sequence are respectively composed into positive and negative deviation point set, and the target distance between the centroid of two deviation point sets is calculated;When target distance is greater than preset distance threshold, generate carbon emission monitoring abnormal signal.Power time series data is used to detect abnormality using time series structure, which eliminates the interference of load fluctuation on metering drift monitoring, improves the sensitivity and reliability of carbon emission monitoring.

Description

Technical Field

[0001] This invention belongs to the field of carbon emission monitoring technology in power systems, and particularly relates to a carbon emission monitoring method and system for substations. Background Technology

[0002] As the core hub for power transmission and distribution in the power system, substations experience significant carbon emissions due to energy losses during their operation and maintenance. Accurate monitoring of substation carbon emissions is crucial for achieving carbon reduction targets and optimizing power grid operation strategies. Currently, substation carbon emission monitoring commonly employs indirect monitoring methods based on electricity metering data. This involves calculating energy losses using power time-series data collected from various electricity metering nodes, and then multiplying this by a carbon emission factor to obtain the carbon emission amount.

[0003] However, during long-term operation, electricity metering devices are affected by factors such as changes in ambient temperature and humidity, electromagnetic interference, and component aging, causing their measurement errors to gradually drift. When metering drift occurs at a certain electricity metering node, the carbon emissions calculated based on the power measurement value of that node will deviate from the true value. Existing technologies typically use methods to directly analyze the time-domain characteristics (such as mean, variance, and extreme values) or frequency-domain characteristics (such as spectrum and harmonics) of the power signal to detect metering anomalies. However, power signals are significantly affected by load fluctuations, and metering drift signals are easily overwhelmed by load fluctuations, resulting in low detection sensitivity and a high false alarm rate. Therefore, there is an urgent need for a technical solution that can extract stable features from the power signal that are independent of load fluctuations to detect metering drift. Summary of the Invention

[0004] The purpose of this invention is to provide a carbon emission monitoring method and system for substations, aiming to solve the technical problems of low sensitivity and high false alarm rate of meter drift detection caused by load fluctuations in the existing technology.

[0005] In a first aspect, the present invention provides a method for monitoring carbon emissions from a substation, comprising: The power time series data of the target substation during the operation and maintenance phase is obtained for a preset continuous time period. The power time series data includes the power measurement values ​​at each sampling time. Multiple power tuples are constructed using the power measurements at each sampling time. Calculate the relative orientation angle between the position of a certain power binary pair on a two-dimensional plane and a preset reference point to obtain a certain orientation angle value corresponding to the certain power binary pair. The orientation angle values ​​corresponding to all power binary pairs constitute an orientation angle value sequence. Slide the direction angle value sequence with a preset time window, convert each direction angle value in a certain time window into a vector on the unit circle according to a preset vector synthesis strategy, and synthesize each vector to obtain a certain synthesized vector of the certain time window. Extract the magnitude of the certain synthesized vector as a certain direction consistency index of the certain time window. The direction consistency indices of all time windows constitute a direction consistency time series. The deviation values ​​of the directional consistency index of each time window in the directional consistency time series from the statistical center of the directional consistency time series are determined, the deviation values ​​of each time window are obtained, and the deviation values ​​of all time windows are used to form a mean deviation series. The positive deviation point set is formed by combining all positive elements in the mean deviation sequence, and the negative deviation point set is formed by combining the absolute values ​​of all negative elements. The target distance between the first centroid position of the positive deviation point set and the second centroid position of the negative deviation point set is calculated, and it is determined whether the target distance is greater than a preset distance threshold. If the target distance is greater than the preset distance threshold, an abnormal carbon emission monitoring signal for the target substation is generated within the preset continuous time period.

[0006] Secondly, the present invention provides a carbon emission monitoring system for a substation, comprising: The acquisition module is configured to acquire power time-series data of the target substation during a preset continuous time period in the operation and maintenance phase, wherein the power time-series data includes the power measurement values ​​at each sampling time. The module is configured to construct multiple power tuples based on the power measurements at each sampling time. The calculation module is configured to calculate the relative orientation angle between the position of a certain power binary on a two-dimensional plane and a preset reference point, and obtain a certain orientation angle value corresponding to the certain power binary. The orientation angle values ​​corresponding to all power binary constitute an orientation angle value sequence. The extraction module is configured to slide on the direction angle value sequence with a preset time window, convert each direction angle value within a certain time window into a vector on the unit circle according to a preset vector synthesis strategy, and synthesize each vector to obtain a certain synthesized vector of the certain time window, and extract the magnitude of the certain synthesized vector as a certain direction consistency index of the certain time window. The direction consistency indices of all time windows constitute a direction consistency time series. The determination module is configured to determine the deviation value between the directional consistency index of each time window in the directional consistency time series and the statistical center of the directional consistency time series, obtain the deviation value of each time window, and construct a mean deviation sequence from the deviation values ​​of all time windows. The judgment module is configured to form a positive deviation point set by combining all positive elements in the mean deviation sequence, form a negative deviation point set by combining the absolute values ​​of all negative elements, calculate the target distance between the first centroid position of the positive deviation point set and the second centroid position of the negative deviation point set, and determine whether the target distance is greater than a preset distance threshold. The generation module is configured to generate a carbon emission monitoring anomaly signal for the target substation within the preset continuous time period if the target distance is greater than the preset distance threshold.

[0007] Thirdly, an electronic device is provided, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the steps of the substation carbon emission monitoring method according to any embodiment of the present invention.

[0008] Fourthly, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor performs the steps of the substation carbon emission monitoring method according to any embodiment of the present invention.

[0009] The carbon emission monitoring method and system for substations disclosed in this application acquires power time-series data of the target substation over a preset continuous time period; constructs multiple power pairs using power measurements at each sampling time; calculates the relative directional angle between the position of each power pair on a two-dimensional plane and a preset reference point, obtaining a sequence of directional angle values; slides a preset time window across the directional angle value sequence, performs vector synthesis on the directional angle values ​​within each time window, and extracts the amplitude of the synthesized vector as a directional consistency index, obtaining a directional consistency time series; determines the deviation of each directional consistency index from the statistical center in the directional consistency time series, obtaining a mean deviation sequence; combines the positive and negative elements in the mean deviation sequence into positive and negative deviation point sets, respectively, and calculates the target distance between the centroids of the two deviation point sets; when the target distance exceeds a preset distance threshold, a carbon emission monitoring anomaly signal is generated; and utilizes the time-series structure of the power time-series data for anomaly detection, eliminating the interference of load fluctuations on metering drift monitoring and improving the sensitivity and reliability of carbon emission monitoring. Attached Figure Description

[0010] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0011] Figure 1 A flowchart illustrating a carbon emission monitoring method for a substation, as provided in an embodiment of the present invention; Figure 2 This is a structural block diagram of a carbon emission monitoring system for a substation provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0012] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0013] Please see Figure 1 The diagram shows a flowchart of a carbon emission monitoring method for a substation according to this application.

[0014] like Figure 1 As shown, the carbon emission monitoring method for substations specifically includes the following steps: Step S101: Obtain power time-series data of the target substation during a preset continuous time period in the operation and maintenance phase. The power time-series data includes the power measurement values ​​at each sampling time.

[0015] In this step, the power time-series data consists of power measurements continuously collected by various energy metering nodes in the target substation during the operation and maintenance phase at a preset sampling frequency. These energy metering nodes include, but are not limited to: incoming energy meters for each voltage level bus, energy meters for each feeder branch, energy meters for station service transformers, and energy meters for reactive power compensation devices. Each energy metering node synchronously collects power measurements according to a unified sampling clock. The sampling frequency can be determined based on the data acquisition capabilities of the target substation and actual application requirements.

[0016] Step S102: Construct multiple power tuples using the power measurement values ​​at each sampling time.

[0017] In this step, the power measurement value at the i-th sampling time in the power time series data is taken as the first element of the i-th tuple, and the power measurement value at the (i+1)-th sampling time is taken as the second element of the i-th tuple. i starts from 1 and takes values ​​sequentially up to N-1 to obtain N-1 power tuples, where N is the total number of sampling times in the power time series data, and the time corresponding to the first element and the time corresponding to the second element in each power tuple are adjacent sampling times.

[0018] In one specific embodiment, the power measurement value at the first sampling time in the power time series data is used as the first element of the first binary tuple, and the power measurement value at the second sampling time is used as the second element of the first binary tuple to obtain the first power binary tuple; the power measurement value at the second sampling time is used as the first element of the second binary tuple, and the power measurement value at the third sampling time is used as the second element of the second binary tuple to obtain the second power binary tuple; and so on, until the power measurement value at the (N-1)th sampling time is used as the first element of the (N-1)th binary tuple, and the power measurement value at the Nth sampling time is used as the second element of the (N-1)th binary tuple to obtain the (N-1)th power binary tuple. The time corresponding to the first element and the time corresponding to the second element in each power binary tuple are adjacent sampling times, representing the power change relationship between adjacent times. The number of power binary tuples is equal to the total number of sampling times of the power time series data minus one.

[0019] Step S103: Calculate the relative direction angle between the position of a certain power binary on the two-dimensional plane and the preset reference point, and obtain a certain direction angle value corresponding to the certain power binary. The direction angle values ​​corresponding to all power binary constitute a direction angle value sequence.

[0020] In this step, each power tuple is mapped to a data point on a two-dimensional plane by using the power value at the first time point as the x-axis and the power value at the second time point as the y-axis. Taking the i-th power tuple as an example, the power measurement value at the i-th sampling time in the tuple is used as the x-axis value, and the power measurement value at the (i+1)-th sampling time is used as the y-axis value to determine the i-th data point on the two-dimensional plane. All data points are arranged in the time order of the corresponding power tuples to obtain a data point sequence. The x-axis value of each data point corresponds to the power change relationship between adjacent times in the original power time series data as time progresses.

[0021] The original orientation angle of the first data point in the data point sequence is taken as the orientation angle value of the first data point, wherein the original orientation angle is the angle between the direction of the line connecting the first data point and the origin of the two-dimensional plane coordinate system and the positive direction of the horizontal axis of the two-dimensional plane.

[0022] Taking the coordinates of the first data point in the data point sequence as the starting point, and the coordinates of each data point in the data point sequence other than the first data point as the target point, a first vector pointing from the starting point to the target point is calculated to obtain the first vector corresponding to each target point. The direction of this vector represents the cumulative displacement direction of the current data point relative to the starting point of the sequence.

[0023] Using the geometric center of the coordinate set of a preset number of adjacent data points in the data point sequence as the local center point, a second vector pointing from the local center point to the target point is calculated to obtain the second vector corresponding to each target point. The direction of this vector represents the instantaneous movement direction of the current data point in its local neighborhood. For preceding data points in the data point sequence that are insufficient to form a preset number of adjacent data points, the geometric center of the coordinate set of all existing preceding data points is used as the local center point. In a specific embodiment, the preset number is set to 10 data points. If the current target data point is the 5th data point and its preceding data points are less than 10, then the geometric center of the coordinate set of all 4 preceding data points is used as the local center point.

[0024] Calculate the angle between the direction of the first vector and the direction of the second vector corresponding to each target point, and use the angle value as the direction angle value corresponding to each target point. This angle value reflects the degree of deviation between the cumulative displacement direction of the current data point relative to the starting point of the entire data point sequence and the instantaneous motion direction in its local neighborhood.

[0025] The orientation angle value of the first data point and the orientation angle values ​​corresponding to each target point are arranged in the order of the data points in the data point sequence to form the orientation angle value sequence.

[0026] In summary, by mapping power pairs to data points on a two-dimensional plane, the original power amplitude information is transformed into directional information in geometric space. The directional angle of each data point reflects the relative orientation of the power change at that moment in the overall evolution of the data point sequence. Compared with directly analyzing power amplitude changes, the directional angle value only focuses on the direction of power change rather than the magnitude of the change, thereby eliminating the direct impact of load fluctuation amplitude on subsequent metering drift detection. This allows subsequent analysis to focus on the consistency characteristics of the power change direction, providing a stable data foundation for identifying systematic directional shifts caused by metering drift.

[0027] Step S104: Slide a preset time window on the direction angle value sequence, convert each direction angle value within a certain time window into a vector on the unit circle according to a preset vector synthesis strategy, and synthesize each vector to obtain a certain synthesized vector of the certain time window. Extract the magnitude of the certain synthesized vector as a certain direction consistency index of the certain time window. The direction consistency indices of all time windows constitute a direction consistency time series.

[0028] In this step, a fixed-length time window is slid across the direction angle value sequence point by point. At a certain time window position, the direction angle value falling within the certain time window is extracted to obtain the direction angle sequence of a certain window of the certain time window. Arrange the direction angle values ​​in the direction angle sequence of a certain window in ascending order according to their numerical values ​​to obtain a sorted direction angle sequence. Calculate the difference between two adjacent direction angle values ​​in the sorted direction angle sequence to obtain a certain angle gap sequence. The maximum value in the certain angle gap sequence is taken as the maximum angle gap, and the arithmetic mean of all angle gaps in the certain angle gap sequence except for the maximum angle gap is calculated as the mean of the remaining angle gaps. Calculate the difference between the maximum angular gap and the average of the remaining angular gaps, divide the difference by the maximum angular gap to obtain the gap deviation of a certain time window, and use the gap deviation as a certain amplitude value of a certain composite vector. The gap deviation is used to characterize the degree of clustering of the directional angle values ​​in the directional angle sequence of a certain window on the circumference. Each direction angle value in the certain window direction angle sequence is taken as the polar angle, and the polar radius is 1. The unit vector corresponding to each direction angle value is determined in the polar coordinate system. Vector summation is performed on each unit vector to obtain the resultant vector. The resultant vector is decomposed into a first component along the positive polar axis in the polar coordinate system and a second component perpendicular to the positive polar axis. The target angle between the resultant vector and the positive polar axis is determined according to the first component and the second component. The target angle is taken as a certain direction angle of the certain composite vector. A composite vector is formed by a certain amplitude and a certain direction angle within a certain time window.

[0029] In one specific embodiment, a fixed-length time window is slid across the direction angle value sequence point by point. At a certain time window position, the direction angle value falling within the certain time window is extracted to obtain a certain window direction angle sequence of the certain time window.

[0030] For amplitude calculation: The direction angle values ​​in a certain window direction angle sequence are sorted in ascending order of numerical value to obtain a sorted direction angle sequence. Taking a certain window direction angle sequence within a certain time window as an example, this sequence contains 50 direction angle values. These values ​​are rearranged in ascending order of angle size to obtain a sorted direction angle sequence. The difference between two adjacent direction angle values ​​in the sorted direction angle sequence is calculated sequentially to obtain 49 angle gap values. The difference between adjacent angles reflects the interval distribution of each direction angle value on the circumference. The sum of the gap values ​​in the angle gap sequence equals 360°. The maximum value in the angle gap sequence is taken as the maximum angle gap. The gap corresponds to the largest blank area of ​​the directional angle distribution on the circumference; the arithmetic mean of all directional gaps except the largest directional gap in the directional gap sequence is calculated as the mean of the remaining directional gaps; the difference between the largest directional gap and the mean of the remaining directional gaps is calculated, and the difference is divided by the largest directional gap to obtain the gap deviation of the time window. The gap deviation range is [0,1]. When the largest directional gap is much larger than the mean of the remaining gaps, the gap deviation is close to 1, indicating that the directional angle values ​​are concentrated in a few intervals; when the largest directional gap is close to the mean of the remaining gaps, the gap deviation is close to 0, indicating that the directional angle values ​​are evenly distributed throughout the circumference. The gap deviation is used as the amplitude of the composite vector.

[0031] For direction angle calculation: Each direction angle value in the direction angle sequence of a certain window is taken as the polar angle, and the polar radius is 1. The unit vector corresponding to each direction angle value is determined in the polar coordinate system. For each direction angle value θ in the direction angle sequence of the window, the rectangular coordinates of the corresponding unit vector are represented as (cosθ, sin θ). Vector summation is performed on all unit vectors within the time window to obtain the resultant vector. The resultant vector is decomposed into a first component along the positive polar axis direction (i.e., the 0° direction) and a second component perpendicular to the positive polar axis direction (i.e., the 90° direction). The value of the first component is equal to the projection of the resultant vector in the polar axis direction, and the value of the second component is equal to the projection of the resultant vector in the vertical direction. Based on the first and second components, the target angle of the resultant vector relative to the positive polar axis direction is determined by the arctangent function in the four quadrants. This target angle is the average direction of all direction angle values ​​within the window. This target angle is taken as the direction angle of the composite vector. The composite vector of the time window is composed of the magnitude and the direction angle.

[0032] Iterate through all window positions to obtain the composite vector corresponding to each window position.

[0033] In summary, by analyzing the angular gaps to calculate the amplitude of the synthesized vector, the concentration of directional angle values ​​within the window is quantified into a continuous value between 0 and 1. A value closer to 1 indicates a more concentrated concentration of directional angle values ​​within the window, signifying higher directional consistency; a value closer to 0 indicates a more dispersed distribution of directional angle values, resulting in lower directional consistency. This amplitude depends only on the relative intervals between directional angle values, not on the specific numerical value of the directional angle, thus eliminating the influence of overall translation of directional angle values ​​on consistency judgment and exhibiting rotation invariance. The amplitude calculation is based on the angular interval distribution on a circle, naturally adapting to the periodic characteristics of directional angles, requiring no special angle normalization processing. Simultaneously, the direction angle of the synthesized vector is calculated through unit vector synthesis in polar coordinates. The direction angle represents the average direction of the directional angle values ​​within the window, providing traceable dimensional information for subsequent anomaly type identification. The amplitude and direction angle together constitute the synthesized vector, completely preserving the distribution information of directional angle values ​​on the circle within the window.

[0034] Step S105: Determine the deviation value between the directional consistency index of each time window in the directional consistency time series and the statistical center of the directional consistency time series, obtain the deviation value of each time window, and construct a mean deviation series from the deviation values ​​of all time windows.

[0035] In this step, the values ​​of all directional consistency indicators in the directional consistency time series are obtained, the arithmetic mean of all directional consistency indicators is calculated, and the arithmetic mean is used as the statistical center of the directional consistency time series. For each directional consistency index in the directional consistency time series, the difference between the directional consistency index and the statistical center is calculated to obtain the deviation value corresponding to the directional consistency index. Arrange all deviation values ​​in chronological order according to the corresponding time window to obtain the mean deviation sequence.

[0036] The method in this embodiment uses the overall average level of the directional consistency time series as the statistical center and calculates the deviation value of the directional consistency index from the statistical center for each time window. This achieves the separation of the overall trend and individual fluctuations in the directional consistency time series. The sign of the deviation value directly reflects the direction of deviation of each time window relative to the overall average level, providing a clear classification basis for subsequent separation of positive and negative deviation point sets. This ensures that the mean deviation sequence retains the temporal information of each window on the time axis, corresponding one-to-one with the original window position, maintaining the integrity of the time sequence. This process does not rely on any external preset thresholds and is entirely based on the statistical characteristics of the data itself for adaptive deviation quantification, avoiding the uncertainty caused by manually setting thresholds. The mean deviation sequence, as an intermediate result, transforms the directional consistency index from the absolute numerical domain to the relative deviation domain relative to the overall average level, providing a data foundation for subsequent anomaly detection based on the symmetry of the deviation distribution.

[0037] Step S106: Form a positive deviation point set by combining all positive elements in the mean deviation sequence, form a negative deviation point set by combining the absolute values ​​of all negative elements, calculate the target distance between the first centroid position of the positive deviation point set and the second centroid position of the negative deviation point set, and determine whether the target distance is greater than a preset distance threshold.

[0038] In this step, the values ​​of each element in the mean deviation sequence are obtained, elements with values ​​greater than zero are marked as positive elements, all positive elements form the positive deviation point set, elements with values ​​less than zero are marked as negative elements, and the absolute values ​​of each negative element are taken to form the negative deviation point set. Calculate the first arithmetic mean of all elements in the positive deviation point set, and use the first arithmetic mean as the first centroid value of the positive deviation point set; Calculate the second arithmetic mean of all elements in the negative deviation point set, and use the second arithmetic mean as the second centroid value of the negative deviation point set; Calculate the absolute value of the difference between the first centroid value and the second centroid value, and use the absolute value of the difference as the target distance.

[0039] Taking a specific embodiment as an example, the mean deviation sequence contains 100 values, of which 45 are positive, 50 are negative, and 5 are zero. The positive values ​​form a set of positive deviation points, containing 45 positive deviation values; the negative values, after taking their absolute values, form a set of negative deviation points, containing the absolute values ​​of 50 negative deviation values.

[0040] Calculate the arithmetic mean of all elements in the positive deviation point set, and use this arithmetic mean as the first centroid value of the positive deviation point set. This first centroid value reflects the distribution center position of the positive deviation set on the numerical axis, i.e., the typical level of deviation for each window above the average level. Calculate the arithmetic mean of all elements in the negative deviation point set, and use this arithmetic mean as the second centroid value of the negative deviation point set. This second centroid value reflects the distribution center position of the negative deviation set on the numerical axis, i.e., the typical level of deviation for each window below the average level. Both the first and second centroid values ​​are non-negative numbers, and their magnitudes reflect the average levels of positive and negative deviations on the numerical axis, respectively.

[0041] The absolute value of the difference between the first centroid value and the second centroid value is calculated, and this absolute value is taken as the target distance. This target distance reflects the degree of separation between the positive deviation set and the negative deviation set on the numerical axis, that is, the degree of asymmetry in the numerical magnitude of the positive and negative deviations of the directional consistency index.

[0042] The target distance is compared with a preset distance threshold to determine whether the target distance is greater than the preset distance threshold.

[0043] If the deviation is not greater than the preset distance threshold, it indicates that the magnitudes of the positive and negative deviations are basically symmetrical, the distribution of each element in the mean deviation sequence on both sides is balanced, and the overall distribution of the directional consistency time series has not undergone significant structural changes. In this case, it is determined that the power change direction characteristics of the target substation remain stable during the operation and maintenance phase, and no systematic directional shift caused by metering drift has occurred.

[0044] Step S107: If the target distance is greater than the preset distance threshold, then generate a carbon emission monitoring anomaly signal for the target substation within the preset continuous time period.

[0045] In this step, if the target distance is greater than the preset distance threshold, the direction angle of the synthesized vector corresponding to each time window is obtained, and the direction angle time series is obtained by arranging them in chronological order. Perform linear trend fitting on the orientation angle time series to obtain the fitting slope of the orientation angle time series; When the fitting slope is greater than zero, a first type of carbon emission monitoring anomaly signal is generated. The first type of carbon emission monitoring anomaly signal is used to indicate that the target substation has a positive power change direction drift within the preset continuous time period. When the fitting slope is less than zero, a second type of carbon emission monitoring anomaly signal is generated. The second type of carbon emission monitoring anomaly signal is used to indicate that the target substation has a negative power change direction drift within the preset continuous time period. When the fitting slope is equal to zero, a third type of carbon emission monitoring anomaly signal is generated. The third type of carbon emission monitoring anomaly signal is used to indicate that there is an abnormal power change in the target substation within the preset continuous time period.

[0046] The method implemented here directly reflects the overall direction of change of the azimuth angle over time by the fitting slope of the azimuth angle time series. A fitting slope greater than zero corresponds to a positive drift anomaly, a fitting slope less than zero corresponds to a negative drift anomaly, and a fitting slope equal to zero corresponds to a non-directional anomaly. This provides maintenance personnel with a clear direction for fault location. Compared with monitoring methods that only provide a single abnormal signal, this method can distinguish the drift direction of power change and can more accurately locate the anomaly type, making it easier for maintenance personnel to take differentiated troubleshooting measures for different types of anomalies.

[0047] In summary, the method of this application acquires power time-series data of the target substation over a preset continuous time period; constructs multiple power tuples using power measurements at each sampling time; calculates the relative directional angle between the position of each power tuple on the two-dimensional plane and a preset reference point, obtaining a directional angle value sequence; slides a preset time window across the directional angle value sequence, performs vector synthesis on the directional angle values ​​within each time window, and extracts the amplitude of the synthesized vector as a directional consistency index, obtaining a directional consistency time series; determines the deviation of each directional consistency index from the statistical center in the directional consistency time series, obtaining a mean deviation sequence; forms positive and negative deviation point sets from the positive and negative elements in the mean deviation sequence, respectively, and calculates the target distance between the centroids of the two deviation point sets; when the target distance is greater than a preset distance threshold, a carbon emission monitoring anomaly signal is generated; and utilizes the time-series structure of the power time-series data for anomaly detection, eliminating the interference of load fluctuations on metering drift monitoring and improving the sensitivity and reliability of carbon emission monitoring.

[0048] Please see Figure 2 The diagram shows a structural block diagram of a carbon emission monitoring system for a substation according to this application.

[0049] like Figure 2 As shown, the carbon emission monitoring system 200 includes an acquisition module 210, a construction module 220, a calculation module 230, an extraction module 240, a determination module 250, a judgment module 260, and a generation module 270.

[0050] The system includes: an acquisition module 210, configured to acquire power time-series data of a target substation over a preset continuous time period during its operation and maintenance phase, the power time-series data including power measurement values ​​at each sampling time; a construction module 220, configured to construct multiple power pairs using the power measurement values ​​at each sampling time; a calculation module 230, configured to calculate the relative direction angle between the position of a power pair on a two-dimensional plane and a preset reference point, obtaining a direction angle value corresponding to the power pair, and the direction angle values ​​corresponding to all power pairs constitute a direction angle value sequence; and an extraction module 240, configured to slide a preset time window on the direction angle value sequence, convert each direction angle value within a time window into a vector on a unit circle according to a preset vector synthesis strategy, synthesize each vector to obtain a synthesized vector for the time window, and extract the amplitude of the synthesized vector as a certain value of the time window. A directional consistency index is defined, and the directional consistency indices of all time windows constitute a directional consistency time series. A determination module 250 is configured to determine the deviation value between the directional consistency index of each time window and the statistical center of the directional consistency time series, obtaining the deviation value of each time window, and constructing a mean deviation sequence from the deviation values ​​of all time windows. A judgment module 260 is configured to form a positive deviation point set from all positive elements in the mean deviation sequence, form a negative deviation point set from the absolute values ​​of all negative elements, calculate the target distance between the first centroid position of the positive deviation point set and the second centroid position of the negative deviation point set, and determine whether the target distance is greater than a preset distance threshold. A generation module 270 is configured to generate a carbon emission monitoring anomaly signal for the target substation within the preset continuous time period if the target distance is greater than the preset distance threshold.

[0051] It should be understood that Figure 2 The modules and references described in the document Figure 1 The steps described in the text correspond to those in the method described above. Therefore, the operations, features, and corresponding technical effects described above also apply to the method described in the text. Figure 2 The various modules in the document will not be described in detail here.

[0052] In other embodiments, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor performs the substation carbon emission monitoring method in any of the above method embodiments. In one embodiment, the computer-readable storage medium of the present invention stores computer-executable instructions, which are configured as follows: The power time series data of the target substation during the operation and maintenance phase is obtained for a preset continuous time period. The power time series data includes the power measurement values ​​at each sampling time. Multiple power tuples are constructed using the power measurements at each sampling time. Calculate the relative orientation angle between the position of a certain power binary pair on a two-dimensional plane and a preset reference point to obtain a certain orientation angle value corresponding to the certain power binary pair. The orientation angle values ​​corresponding to all power binary pairs constitute an orientation angle value sequence. Slide the direction angle value sequence with a preset time window, convert each direction angle value in a certain time window into a vector on the unit circle according to a preset vector synthesis strategy, and synthesize each vector to obtain a certain synthesized vector of the certain time window. Extract the magnitude of the certain synthesized vector as a certain direction consistency index of the certain time window. The direction consistency indices of all time windows constitute a direction consistency time series. The deviation values ​​of the directional consistency index of each time window in the directional consistency time series from the statistical center of the directional consistency time series are determined, the deviation values ​​of each time window are obtained, and the deviation values ​​of all time windows are used to form a mean deviation series. The positive deviation point set is formed by combining all positive elements in the mean deviation sequence, and the negative deviation point set is formed by combining the absolute values ​​of all negative elements. The target distance between the first centroid position of the positive deviation point set and the second centroid position of the negative deviation point set is calculated, and it is determined whether the target distance is greater than a preset distance threshold. If the target distance is greater than the preset distance threshold, an abnormal carbon emission monitoring signal for the target substation is generated within the preset continuous time period.

[0053] Computer-readable storage media may include a stored program area and a stored data area, wherein the stored program area may store an operating system and an application program required for at least one function; the stored data area may store data created based on the use of the substation's carbon emission monitoring system, etc. Furthermore, the computer-readable storage medium may include high-speed random access memory, and may also include memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer-readable storage medium may optionally include memory remotely configured relative to a processor, which can be connected to the substation's carbon emission monitoring system via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0054] Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiment of the present invention, such as... Figure 3 As shown, the device includes a processor 310 and a memory 320. The electronic device may also include an input device 330 and an output device 340. The processor 310, memory 320, input device 330, and output device 340 can be connected via a bus or other means. Figure 3 Taking a bus connection as an example, the memory 320 is the computer-readable storage medium described above. The processor 310 executes various server functions and data processing by running non-volatile software programs, instructions, and modules stored in the memory 320, thereby implementing the substation carbon emission monitoring method described in the above embodiment. The input device 330 can receive input digital or character information and generate key signal inputs related to user settings and function control of the substation's carbon emission monitoring system. The output device 340 may include a display screen or other display device.

[0055] The aforementioned electronic device can execute the method provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. Technical details not described in detail in this embodiment can be found in the method provided in the embodiments of the present invention.

[0056] In one implementation, the above-described electronic device is applied to a carbon emission monitoring system in a substation for a client application, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to: The power time series data of the target substation during the operation and maintenance phase is obtained for a preset continuous time period. The power time series data includes the power measurement values ​​at each sampling time. Multiple power tuples are constructed using the power measurements at each sampling time. Calculate the relative orientation angle between the position of a certain power binary pair on a two-dimensional plane and a preset reference point to obtain a certain orientation angle value corresponding to the certain power binary pair. The orientation angle values ​​corresponding to all power binary pairs constitute an orientation angle value sequence. Slide the direction angle value sequence with a preset time window, convert each direction angle value in a certain time window into a vector on the unit circle according to a preset vector synthesis strategy, and synthesize each vector to obtain a certain synthesized vector of the certain time window. Extract the magnitude of the certain synthesized vector as a certain direction consistency index of the certain time window. The direction consistency indices of all time windows constitute a direction consistency time series. The deviation values ​​of the directional consistency index of each time window in the directional consistency time series from the statistical center of the directional consistency time series are determined, the deviation values ​​of each time window are obtained, and the deviation values ​​of all time windows are used to form a mean deviation series. The positive deviation point set is formed by combining all positive elements in the mean deviation sequence, and the negative deviation point set is formed by combining the absolute values ​​of all negative elements. The target distance between the first centroid position of the positive deviation point set and the second centroid position of the negative deviation point set is calculated, and it is determined whether the target distance is greater than a preset distance threshold. If the target distance is greater than the preset distance threshold, an abnormal carbon emission monitoring signal for the target substation is generated within the preset continuous time period.

[0057] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., including several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods of various embodiments or some parts of embodiments.

[0058] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for monitoring carbon emissions from a substation, characterized in that, include: The power time series data of the target substation during the operation and maintenance phase is obtained for a preset continuous time period. The power time series data includes the power measurement values ​​at each sampling time. Multiple power tuples are constructed using the power measurements at each sampling time. Calculate the relative orientation angle between the position of a certain power binary pair on a two-dimensional plane and a preset reference point to obtain a certain orientation angle value corresponding to the certain power binary pair. The orientation angle values ​​corresponding to all power binary pairs constitute an orientation angle value sequence. Slide the direction angle value sequence with a preset time window, convert each direction angle value in a certain time window into a vector on the unit circle according to a preset vector synthesis strategy, and synthesize each vector to obtain a certain synthesized vector of the certain time window. Extract the magnitude of the certain synthesized vector as a certain direction consistency index of the certain time window. The direction consistency indices of all time windows constitute a direction consistency time series. The deviation values ​​of the directional consistency index of each time window in the directional consistency time series from the statistical center of the directional consistency time series are determined, the deviation values ​​of each time window are obtained, and the deviation values ​​of all time windows are used to form a mean deviation series. The positive deviation point set is formed by combining all positive elements in the mean deviation sequence, and the negative deviation point set is formed by combining the absolute values ​​of all negative elements. The target distance between the first centroid position of the positive deviation point set and the second centroid position of the negative deviation point set is calculated, and it is determined whether the target distance is greater than a preset distance threshold. If the target distance is greater than the preset distance threshold, an abnormal carbon emission monitoring signal for the target substation is generated within the preset continuous time period.

2. The carbon emission monitoring method for a substation according to claim 1, characterized in that, The construction of multiple power tuples based on power measurements at each sampling time includes: The power measurement value at the i-th sampling time in the power time series data is taken as the first element of the i-th tuple, and the power measurement value at the (i+1)-th sampling time is taken as the second element of the i-th tuple. i is taken sequentially from 1 to N-1 to obtain N-1 power tuples, where N is the total number of sampling times of the power time series data, and the time corresponding to the first element and the time corresponding to the second element in each power tuple are adjacent sampling times.

3. The carbon emission monitoring method for a substation according to claim 1, characterized in that, The calculation of the relative orientation angle between the position of a power binary pair on the two-dimensional plane and a preset reference point yields a specific orientation angle value corresponding to the power binary pair. The orientation angle values ​​corresponding to all power binary pairs constitute an orientation angle value sequence, including: Using the power value at the first time point in each power pair as the horizontal axis and the power value at the second time point as the vertical axis, each power pair is mapped to a data point on a two-dimensional plane, and the time sequence corresponding to each power pair is used as the arrangement order of each data point to obtain a data point sequence. The original orientation angle of the first data point in the data point sequence is taken as the orientation angle value of the first data point, wherein the original orientation angle is the angle between the direction of the line connecting the first data point and the origin of the two-dimensional plane coordinate system and the positive direction of the horizontal axis of the two-dimensional plane. Taking the coordinates of the first data point in the data point sequence as the starting point, and taking the coordinates of each data point in the data point sequence other than the first data point as the target point, calculate the first vector from the starting point to the target point to obtain the first vector corresponding to each target point; Using the geometric center of the coordinate set of a preset number of data points adjacent to each target point in the data point sequence as the local center point, calculate the second vector pointing from the local center point to the target point, and obtain the second vector corresponding to each target point; Calculate the angle between the direction of the first vector and the direction of the second vector corresponding to each target point, and use the angle value as the direction angle value corresponding to each target point; The orientation angle value of the first data point and the orientation angle values ​​corresponding to each target point are arranged in the order of the data points in the data point sequence to form the orientation angle value sequence.

4. The carbon emission monitoring method for a substation according to claim 1, characterized in that, The step of sliding along the direction angle value sequence within a preset time window, converting each direction angle value within a certain time window into a vector on the unit circle according to a preset vector synthesis strategy, and synthesizing the vectors to obtain a synthesized vector for the certain time window includes: Slide the sampling points on the orientation angle value sequence with a fixed-length time window, and extract the orientation angle value that falls within the time window at a certain time window position to obtain the orientation angle sequence of a certain window of the time window; Arrange the direction angle values ​​in the direction angle sequence of a certain window in ascending order according to their numerical values ​​to obtain a sorted direction angle sequence. Calculate the difference between two adjacent direction angle values ​​in the sorted direction angle sequence to obtain a certain angle gap sequence. The maximum value in the certain angle gap sequence is taken as the maximum angle gap, and the arithmetic mean of all angle gaps in the certain angle gap sequence except for the maximum angle gap is calculated as the mean of the remaining angle gaps. Calculate the difference between the maximum angular gap and the average of the remaining angular gaps, divide the difference by the maximum angular gap to obtain the gap deviation of a certain time window, and use the gap deviation as a certain amplitude value of a certain composite vector. The gap deviation is used to characterize the degree of clustering of the directional angle values ​​in the directional angle sequence of a certain window on the circumference. Each direction angle value in the certain window direction angle sequence is taken as the polar angle, and the polar radius is 1. The unit vector corresponding to each direction angle value is determined in the polar coordinate system. Vector summation is performed on each unit vector to obtain the resultant vector. The resultant vector is decomposed into a first component along the positive polar axis in the polar coordinate system and a second component perpendicular to the positive polar axis. The target angle between the resultant vector and the positive polar axis is determined according to the first component and the second component. The target angle is taken as a certain direction angle of the certain composite vector. A composite vector is formed by a certain amplitude and a certain direction angle within a certain time window.

5. The carbon emission monitoring method for a substation according to claim 1, characterized in that, The process of determining the deviation value of the directional consistency index of each time window in the directional consistency time series from the statistical center of the directional consistency time series, obtaining the deviation value of each time window, and constructing a mean deviation series from the deviation values ​​of all time windows includes: Obtain the values ​​of all directional consistency indicators in the directional consistency time series, calculate the arithmetic mean of all directional consistency indicators, and use the arithmetic mean as the statistical center of the directional consistency time series. For each directional consistency index in the directional consistency time series, the difference between the directional consistency index and the statistical center is calculated to obtain the deviation value corresponding to the directional consistency index. Arrange all deviation values ​​in chronological order according to the corresponding time window to obtain the mean deviation sequence.

6. The carbon emission monitoring method for a substation according to claim 1, characterized in that, The step of forming a positive deviation point set from all positive elements in the mean deviation sequence, forming a negative deviation point set from the absolute values ​​of all negative elements, and calculating the target distance between the first centroid value of the positive deviation point set and the second centroid value of the negative deviation point set includes: Obtain the value of each element in the mean deviation sequence, mark the elements with values ​​greater than zero as positive elements, and form the positive deviation point set by all positive elements. Mark the elements with values ​​less than zero as negative elements, and form the negative deviation point set by taking the absolute value of each negative element. Calculate the first arithmetic mean of all elements in the positive deviation point set, and use the first arithmetic mean as the first centroid value of the positive deviation point set; Calculate the second arithmetic mean of all elements in the negative deviation point set, and use the second arithmetic mean as the second centroid value of the negative deviation point set; Calculate the absolute value of the difference between the first centroid value and the second centroid value, and use the absolute value of the difference as the target distance.

7. The carbon emission monitoring method for a substation according to claim 4, characterized in that, If the target distance is greater than the preset distance threshold, generating an abnormal carbon emission monitoring signal for the target substation within the preset continuous time period includes: If the target distance is greater than the preset distance threshold, the direction angle of the synthesized vector corresponding to each time window is obtained, and the direction angle time series is obtained by arranging them in chronological order. Perform linear trend fitting on the orientation angle time series to obtain the fitting slope of the orientation angle time series; When the fitting slope is greater than zero, a first type of carbon emission monitoring anomaly signal is generated. The first type of carbon emission monitoring anomaly signal is used to indicate that the target substation has a positive power change direction drift within the preset continuous time period. When the fitting slope is less than zero, a second type of carbon emission monitoring anomaly signal is generated. The second type of carbon emission monitoring anomaly signal is used to indicate that the target substation has a negative power change direction drift within the preset continuous time period. When the fitting slope is equal to zero, a third type of carbon emission monitoring anomaly signal is generated. The third type of carbon emission monitoring anomaly signal is used to indicate that there is an abnormal power change in the target substation within the preset continuous time period.

8. A carbon emission monitoring system for a substation, characterized in that, include: The acquisition module is configured to acquire power time-series data of the target substation during a preset continuous time period in the operation and maintenance phase, wherein the power time-series data includes the power measurement values ​​at each sampling time. The module is configured to construct multiple power tuples based on the power measurements at each sampling time. The calculation module is configured to calculate the relative orientation angle between the position of a certain power binary on a two-dimensional plane and a preset reference point, and obtain a certain orientation angle value corresponding to the certain power binary. The orientation angle values ​​corresponding to all power binary constitute an orientation angle value sequence. The extraction module is configured to slide on the direction angle value sequence with a preset time window, convert each direction angle value within a certain time window into a vector on the unit circle according to a preset vector synthesis strategy, and synthesize each vector to obtain a certain synthesized vector of the certain time window, and extract the magnitude of the certain synthesized vector as a certain direction consistency index of the certain time window. The direction consistency indices of all time windows constitute a direction consistency time series. The determination module is configured to determine the deviation value between the directional consistency index of each time window in the directional consistency time series and the statistical center of the directional consistency time series, obtain the deviation value of each time window, and construct a mean deviation sequence from the deviation values ​​of all time windows. The judgment module is configured to form a positive deviation point set by combining all positive elements in the mean deviation sequence, form a negative deviation point set by combining the absolute values ​​of all negative elements, calculate the target distance between the first centroid position of the positive deviation point set and the second centroid position of the negative deviation point set, and determine whether the target distance is greater than a preset distance threshold. The generation module is configured to generate a carbon emission monitoring anomaly signal for the target substation within the preset continuous time period if the target distance is greater than the preset distance threshold.

9. An electronic device, characterized in that, include: At least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method according to any one of claims 1 to 7.

Images