Smart grid line loss detection system based on the Internet of Things

Through the Internet of Things-based smart grid line loss detection system, the grid line loss detection is performed using smart electricity meters and distributed fiber optic sensors, which solves the problems of incomplete detection and inaccurate calculations in the existing technology, and realizes the precise management of grid line loss , improves the operating efficiency of the power grid.

CN118625037BActive Publication Date: 2024-11-05山东鲁冠电气有限公司
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202411080802.8
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-08
Publication Date
2024-11-05
Estimated Expiration
2044-08-08

AI Technical Summary

Technical Problem

The existing power grid line loss detection is incomplete and the calculation is inaccurate, making it difficult to optimize and adjust the power grid in a targeted manner, reducing the overall operating efficiency of the power grid.

Method used

Adopt the smart grid wire loss detection system based on the Internet of Things, including information interaction module, sensor distribution module, data acquisition module, first line loss calculation module, second line loss calculation module and management module, and monitor through smart meter and distributed fiber optic sensor Data, perform interval correlation reconstruction and line loss calculation to achieve comprehensive and accurate line loss detection and management.

Benefits of technology

It realizes comprehensive and precise detection and management of power grid line losses, significantly improves the overall operating efficiency of the power grid, and ensures efficient and stable operation of the power grid.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118625037B_ABST
    Figure CN118625037B_ABST
Patent Text Reader

Abstract

The present invention discloses a smart grid line loss detection system based on the Internet of Things, which relates to the field of power grid monitoring technology. The system includes: an information interaction module for obtaining the layout data of the smart grid; a sensor distribution module for distributing monitoring sensors; a data acquisition module for receiving monitoring data sets and establishing correlation coefficients of monitoring intervals; a first line loss calculation module for calling smart meter monitoring data to generate independent line loss calculation results; a second line loss calculation module for generating associated line loss calculation results; and a management module for line loss detection and management of smart grids. The present invention solves the technical problems in the prior art that line loss detection is not comprehensive and line loss calculation is inaccurate, which makes it difficult to optimize and adjust the power grid in a targeted manner, resulting in low overall operation efficiency of the power grid, and achieves the technical effect of realizing comprehensive and accurate line loss detection and calculation, and significantly improving the overall operation efficiency of the power grid.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of power grid monitoring, and in particular to a smart grid line loss detection system based on the Internet of Things. Background Art

[0002] While providing strong power guarantee for economic and social development, the State Grid has put forward higher requirements for energy conservation and loss reduction of the power grid. The line loss rate index comprehensively reflects the losses in various links of the power grid operation. Although there are power statistics and line loss management systems, in the face of rapidly growing power demand and complex power grid architecture, there are still technical problems such as incomplete line loss detection and inaccurate line loss calculation, which makes it difficult to optimize and adjust the power grid in a targeted manner, resulting in low overall power grid operation efficiency. Summary of the invention

[0003] The present application provides an intelligent grid line loss detection system based on the Internet of Things, which is used to solve the technical problems in the prior art that line loss detection is incomplete and line loss calculation is inaccurate, making it difficult to optimize and adjust the grid in a targeted manner, resulting in low overall operating efficiency of the grid.

[0004] In view of the above problems, the present application provides a smart grid line loss detection system based on the Internet of Things.

[0005] The present application provides a smart grid line loss detection system based on the Internet of Things, the system comprising:

[0006] An information interaction module is used to obtain the layout data of the smart grid, wherein the layout data includes the distribution data of the power grid line, the structural data of the power grid line and the line load data; a sensor distribution module is used to distribute the monitoring sensors, wherein the monitoring sensors include smart meters and distributed optical fiber sensors, and the monitoring sensors are distributed through preset interval identifiers, wherein the preset interval identifiers are identifiers after the intervals are clustered based on the layout data; a data acquisition module is used to receive the monitoring data set of the monitoring sensor, and synchronously obtain the transmission task of the power grid line, perform interval association reconstruction according to the transmission task and the preset interval identifier, and establish the association coefficient of the monitoring interval; a first line loss A calculation module is used to call the smart meter monitoring data in the monitoring data set, perform line loss calculation in an independent monitoring interval according to the smart meter monitoring data, and generate an independent line loss calculation result; a second line loss calculation module is used to call the distributed optical fiber sensor monitoring data in the monitoring data set, perform an abnormality authentication in the interval on the distributed optical fiber sensor monitoring data, generate a first abnormal authentication result, perform line loss calculation in an associated monitoring interval according to the first abnormal authentication result, the smart meter monitoring data, and the correlation coefficient, and generate an associated line loss calculation result; a management module is used to perform line loss detection management of the smart grid according to the independent line loss calculation result and the associated line loss calculation result.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] The information interaction module is used to obtain the layout data of the smart grid; the sensor distribution module is used to distribute the monitoring sensors, and the monitoring sensors are distributed through preset interval identification; the data acquisition module is used to receive the monitoring data set of the monitoring sensor, and synchronously obtain the transmission task of the power grid line, and establish the correlation coefficient of the monitoring interval; the first line loss calculation module is used to call the smart meter monitoring data in the monitoring data set to generate an independent line loss calculation result; the second line loss calculation module is used to call the distributed optical fiber sensor monitoring data in the monitoring data set, perform anomaly authentication within the interval, and generate the first anomaly authentication result; the management module is used to perform line loss detection and management of the smart grid according to the independent line loss calculation result and the associated line loss calculation result. The technical effect of realizing comprehensive and accurate line loss detection and calculation and significantly improving the overall operation efficiency of the power grid has been achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 A schematic diagram of the structure of a smart grid line loss detection system based on the Internet of Things provided in an embodiment of the present application.

[0011] Explanation of the reference numerals: information interaction module 10 , sensor distribution module 20 , data acquisition module 30 , first line loss calculation module 40 , second line loss calculation module 50 , management module 60 . DETAILED DESCRIPTION

[0012] The present application provides an intelligent grid line loss detection system based on the Internet of Things, which is used to solve the technical problems in the prior art that line loss detection is incomplete and line loss calculation is inaccurate, making it difficult to optimize and adjust the grid in a targeted manner, resulting in low overall operating efficiency of the grid.

[0013] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0014] Embodiment 1, as Figure 1 As shown, the present application provides a smart grid line loss detection system based on the Internet of Things, the system comprising:

[0015] The information interaction module 10 is used to obtain the layout data of the smart grid, wherein the layout data includes the distribution data of the grid lines, the structural data of the grid lines and the line load data.

[0016] Specifically, the information interaction module 10 undertakes the key data acquisition task. It focuses on collecting various important layout data of the smart grid. Among them, the distribution data of the power grid line describes in detail the layout of the power grid line in the geographical space, such as the starting point, end point, and path of the line, which helps to understand the overall architecture of the power grid. The structural data of the power grid line covers the constituent elements of the line, such as the material of the line (such as copper, aluminum, etc.), the thickness of the line, and the type of line (overhead line, cable, etc.). This information is crucial for evaluating the performance and carrying capacity of the line. The line load data reflects the size of the power load borne by the line in a specific time period, which is of great significance for analyzing the operating status of the power grid and predicting potential overload risks. This module provides basic and key data support for the subsequent analysis, calculation and management of the entire system through effective data collection and integration methods, which helps to plan and optimize the architecture of the power grid and improve the operating efficiency of the power grid.

[0017] The sensor distribution module 20 is used to distribute monitoring sensors, the monitoring sensors include smart meters and distributed optical fiber sensors, and the monitoring sensors are distributed by preset interval identifiers, and the preset interval identifiers are identifiers obtained by performing interval clustering based on the deployment data.

[0018] Specifically, the sensor distribution module 20 undertakes the important task of arranging the location of monitoring sensors in the smart grid. The monitoring sensors include two types: smart meters and distributed optical fiber sensors. Smart meters are mainly used to measure the amount of electricity used and related parameters, while distributed optical fiber sensors can detect physical parameters such as temperature and strain of the line, so as to monitor the operation status of the power grid more comprehensively. These monitoring sensors are not randomly distributed, but their positions are determined by preset interval identifiers. This preset interval identifier is not set randomly, but is based on the previously acquired smart grid layout data, and is obtained after interval clustering. The layout data contains key information such as the distribution, structure and load of the power grid line. By analyzing and processing these data, the entire power grid is divided into different intervals, and then, according to the characteristics and requirements of these intervals, specific identifiers are set for each interval. The monitoring sensors are distributed according to these preset interval identifiers. This distribution method is highly targeted and scientific, and can ensure that the layout of the sensors in the power grid matches the actual situation of the power grid, making the monitoring more accurate and comprehensive, and can more effectively discover possible problems in the power grid, providing strong support for the stable operation and optimized management of the smart grid.

[0019] The data acquisition module 30 is used to receive the monitoring data set of the monitoring sensor, and synchronously obtain the transmission task of the power grid line, perform interval association reconstruction according to the transmission task and the preset interval identifier, and establish the association coefficient of the monitoring interval.

[0020] Specifically, the data acquisition module 30 plays a key role in data reception and processing. First, it is responsible for receiving monitoring data sets generated by monitoring sensors (such as smart meters and distributed optical fiber sensors), which contain real-time status information of various aspects of the power grid. At the same time, the module will synchronously obtain the transmission tasks of the power grid lines. These transmission tasks may include specific work requirements related to the operation of the power grid, such as power distribution and dispatching instructions. Then, according to the transmission tasks and preset interval identifiers, the data is reconstructed for interval association, that is, it will reorganize and combine the received data according to the transmission tasks and preset interval identifiers to establish the association between different monitoring intervals. Through this association reconstruction, the correlation coefficient of the monitoring interval is finally established. This correlation coefficient describes the mutual relationship and influence degree between each monitoring interval. For example, how much impact the power change in one interval may have on the adjacent interval, or how the synergy of different intervals under a specific transmission task is. With this correlation coefficient, subsequent line loss calculation, power grid management and optimization can more accurately take into account the mutual relationship between different intervals, so as to make more scientific and reasonable decisions, promote the collaborative work of power grid monitoring and management, improve the stability and reliability of power grid operation, and reduce the risk of failure.

[0021] The first line loss calculation module 40 is used to call the smart meter monitoring data in the monitoring data set, perform line loss calculation in an independent monitoring interval according to the smart meter monitoring data, and generate an independent line loss calculation result.

[0022] Specifically, the first line loss calculation module 40 mainly focuses on processing the smart meter monitoring data from the monitoring data set, extracting the relevant data collected by the smart meter from the monitoring data set, and then calculating the line loss specifically for the independent monitoring interval based on these smart meter monitoring data. An independent monitoring interval refers to an area that is divided out in the power grid, relatively independent and has specific characteristics. By analyzing and calculating the relevant data in this interval, an independent line loss calculation result is finally generated. This result can clearly reflect the specific situation of the line loss in the independent monitoring interval, such as the numerical value of the line loss, the changing trend of the line loss, etc. This helps to more accurately understand and evaluate the energy loss of the power grid lines in a specific independent interval, and provides an important basis for subsequent power grid optimization, maintenance and management. It provides data support for the refined management of the power grid, so that resources can be more accurately allocated to independent intervals that need to be improved, thereby improving the efficiency of power grid operation.

[0023] The second line loss calculation module 50 is used to call the distributed optical fiber sensor monitoring data in the monitoring data set, perform an abnormality authentication within the interval of the distributed optical fiber sensor monitoring data, generate a first abnormality authentication result, perform line loss calculation within the associated monitoring interval based on the first abnormality authentication result, the smart meter monitoring data, and the correlation coefficient, and generate an associated line loss calculation result.

[0024] Specifically, the second line loss calculation module 50 is mainly responsible for calling the distributed optical fiber sensor monitoring data in the monitoring data set, and performing an abnormal authentication on these data within the interval, and judging whether there is an abnormal situation by analyzing the characteristics and patterns of the data or comparing with the preset normal range, so as to generate a first abnormal authentication result. The line loss calculation within the associated monitoring interval will be performed based on the first abnormal authentication result, the smart meter monitoring data and the previously established correlation coefficient, and finally the associated line loss calculation result will be generated. In this process, the smart meter monitoring data provides information about the amount of electricity, etc., and the correlation coefficient reflects the correlation between different monitoring intervals. Combining this information, the line loss situation within the associated monitoring interval can be more comprehensively and accurately evaluated. Exemplarily, the distributed optical fiber sensor monitors abnormal changes in current, voltage or other related parameters within a certain interval, and the first abnormal authentication result will point out these abnormalities. Then, combined with the electricity data of the interval and the associated interval monitored by the smart meter, and considering the correlation coefficient between each interval (the correlation coefficient can represent, for example, the load relationship between different lines, electrical distance, etc.), complex calculations and analyses are performed to obtain the line loss calculation result within the associated monitoring interval. It can more accurately detect and evaluate line loss problems, especially those that may be affected by multiple intervals. It not only considers the anomalies of a single interval, but also integrates the information of multiple related intervals, thereby providing more valuable data support for power grid optimization, fault diagnosis and management, and helping to take targeted measures in a timely manner to reduce line losses and improve the efficiency and stability of power grid operation.

[0025] The management module 60 is used to perform line loss detection management of the smart grid according to the independent line loss calculation result and the associated line loss calculation result.

[0026] Specifically, the management module 60 will obtain the independent line loss calculation results output by the first line loss calculation module and the associated line loss calculation results output by the second line loss calculation module in real time, and it will store these results in a special data storage area for easy access and analysis at any time. These results will be compared and integrated in detail, not only will the line loss of each independent monitoring interval be analyzed separately, but also the mutual influence of line loss between associated monitoring intervals will be considered comprehensively. For example, for an independent monitoring interval, if its line loss continues to be high for a period of time, the management module will deeply explore whether it is caused by equipment aging, load imbalance, etc. within the interval, or by abnormal conditions of adjacent associated monitoring intervals. Specific management strategies are formulated based on the analysis results. If it is found that it is a problem with individual equipment, a maintenance or replacement plan will be arranged; if the line loss is too high due to unreasonable line layout, a line transformation plan will be planned; if there is a large area of ​​abnormal line loss fluctuations, the operation mode of the entire power grid may be adjusted or the load may be redistributed. At the same time, the management module 60 will continue to monitor the changes in line loss, establish a line loss database, record historical line loss data, and prepare preventive measures or optimization plans in advance. In addition, it will also interact and share data with other related power grid management systems. The results of line loss detection and management are provided to the dispatching department so that they can make more reasonable decisions when distributing electricity; the information of abnormal line loss areas is provided to the maintenance department to guide them to conduct targeted inspections and maintenance work. The management module 60 makes full use of the independent line loss calculation results and the associated line loss calculation results to achieve comprehensive, precise and dynamic detection and management of smart grid line losses, ensuring efficient and stable operation of the power grid.

[0027] In a possible implementation, the data acquisition module 30 further includes:

[0028] The correlation coefficient is established as follows:

[0029] .

[0030] .

[0031] .

[0032] .

[0033] in, Characterization monitoring interval and monitoring interval The correlation coefficient, For monitoring interval and monitoring interval physical distance, , , For monitoring interval The coordinates of , , For monitoring interval The coordinates of Characterization monitoring interval and monitoring interval The structural similarity of For monitoring interval and monitoring interval The structural differences Characterization monitoring interval and monitoring interval The load similarity of For monitoring interval The active power, For monitoring interval The active power, For monitoring interval and monitoring interval The load power covariance, and The monitoring intervals are and monitoring interval The standard deviation of load power, , , are the weight coefficients of physical distance, structural similarity, and load similarity respectively.

[0034] Specifically, To calculate the monitoring interval and monitoring interval The correlation coefficient of For monitoring interval and monitoring interval physical distance, ( )and( These are the coordinates of the two monitoring intervals. The closer the physical distance is, the higher the degree of correlation between the two. Characterization monitoring interval and monitoring interval The structural similarity of For monitoring interval and monitoring interval The structural differences between the two monitoring intervals are shown in Table 1. The structural similarity reflects the similarity of the monitoring between the two monitoring intervals. The smaller the structural difference, the closer the structure is and the stronger the correlation is. Characterization monitoring interval and monitoring interval The load similarity takes into account the covariance of active power and load power and the standard deviation of load power in the two monitoring intervals. For monitoring interval The active power, For monitoring interval The active power, For monitoring interval and monitoring interval The load power covariance, and The monitoring intervals are and monitoring interval The load power standard deviation, the closer the active power is, the larger the covariance is, the smaller the standard deviation is, the higher the composite similarity is, and the greater the degree of association is; , , They are the weight coefficients of physical distance, structural similarity, and load similarity. By adjusting these weight coefficients, the influence of different factors on the correlation coefficient can be highlighted according to actual needs and priorities, so as to more accurately reflect the comprehensive correlation between the two monitoring intervals. The complex correlation characteristics between the monitoring intervals are expressed in a quantitative way, so that the relationship between different intervals can be clearly measured and compared. It integrates multiple key factors such as physical distance, structural similarity, and load similarity to fully reflect the correlation between intervals. The accuracy of line loss calculation is improved, and the mutual influence between different intervals is more accurately reflected, so that the line loss calculation results are closer to the actual situation, which helps to discover potential line loss problems and improve the efficiency of the power grid.

[0035] In a possible implementation, the management module 60 further includes:

[0036] Configure the comprehensive line loss rate calculation formula as follows:

[0037] .

[0038] in, is the comprehensive line loss rate, is the number of independent monitoring intervals, For the monitoring interval The number of associated monitoring intervals, Characterization monitoring interval The input power, Characterization monitoring interval The output power, is the sum of the line losses of the independent line loss calculation results, For the monitoring interval Associated monitoring interval The input power, For the monitoring interval Associated monitoring interval The output power, is the correlation coefficient The updated results, , is the weight coefficient of abnormal authentication, and Respectively represent the monitoring interval and monitoring interval The monitoring temperature, and For monitoring interval and monitoring interval The base temperature, and The monitoring intervals are and monitoring interval The standard deviation of temperature.

[0039] The comprehensive line loss rate is calculated, and line loss detection and management of the smart grid is performed based on the comprehensive line loss rate.

[0040] Specifically, It is the comprehensive line loss rate, which is a key indicator to measure the power loss of smart grid; Represents the number of independent monitoring intervals, which are the parts of the power grid that need to be analyzed for line losses separately For the monitoring interval The number of associated monitoring intervals, which have some association with specific independent monitoring intervals, and are associated with physical distance, structural similarity, load similarity, etc.; Characterization monitoring interval The input power, that is, the electric power flowing into the monitoring interval; Characterization monitoring interval The output power, that is, the electric power flowing out of the monitoring interval; The sum of the line losses of the independent line loss calculation results is obtained by summing the difference between the input power and the output power of each independent monitoring interval; For the monitoring interval Associated monitoring interval The input power, For the monitoring interval Associated monitoring interval The output power, is the correlation coefficient The updated result is used to quantify the correlation between the two monitoring intervals; , is the weight coefficient of abnormal authentication, which is used to adjust the impact of abnormal situations on line loss rate calculation. and Respectively characterize the monitoring interval and monitoring interval The monitoring temperature, and For monitoring interval and monitoring interval The base temperature is a reference temperature determined based on specific standards or historical data; and The monitoring intervals are and monitoring interval The temperature standard deviation reflects the degree of temperature dispersion; the calculation of the comprehensive line loss rate comprehensively considers the power conditions of the independent monitoring interval and the associated monitoring interval, as well as the correlation coefficient, abnormal authentication weight, temperature and other factors. The comprehensive line loss rate calculated by this formula can comprehensively and accurately reflect the line loss situation of the smart grid, thereby providing a basis for line loss detection and management. The specific calculation process requires obtaining the input power, output power, temperature and other data of each monitoring interval and the associated monitoring interval, as well as the values ​​of parameters such as the correlation coefficient and abnormal authentication weight, and then substituting them into the formula for calculation. In practical applications, it is necessary to use corresponding monitoring equipment and systems to collect and process these data to ensure the accuracy and real-time nature of the line loss rate calculation. At the same time, it is also necessary to reasonably set and adjust the various parameters in the formula according to the specific power grid conditions and management needs to make them more in line with the actual situation and management goals.

[0041] In a possible implementation, the smart grid line loss detection system based on the Internet of Things further includes an early warning module, which is used to:

[0042] Obtain historical abnormal reporting data of power grid lines.

[0043] A penalty feature of the monitoring interval is constructed based on the historical abnormal reporting data.

[0044] The independent line loss calculation result is compensated by using the penalty feature, and an abnormal warning is reported according to the compensated independent line loss calculation result.

[0045] Specifically, obtaining the historical abnormality reporting data of the power grid line refers to collecting the data generated and recorded when the power grid line has abnormal conditions in the past from the relevant database, monitoring system or record documents. These data usually contain the following types of information: the time and date of the abnormality, accurate to the specific moment, to determine the time pattern of the abnormality. The specific location of the abnormality, such as a specific transmission line, substation or a specific device. The type of abnormality, such as short circuit, overload, voltage fluctuation, power factor abnormality, etc. The severity of the abnormality, represented by some quantitative indicators, such as the deviation value of current or voltage, the size of power loss, etc. The equipment parameters and operating status information related to the abnormality, such as the model of the equipment, the age, the load conditions at that time, etc. The treatment measures and treatment results taken for the abnormality, including maintenance records, replaced parts, etc. The way to obtain these historical abnormality reporting data can be directly extracted from the power grid monitoring equipment through an automated data acquisition system, or it can be manually sorted and entered into relevant paper or electronic records. Obtaining accurate and comprehensive historical abnormality reporting data is of great significance for subsequent analysis of the operating status of the power grid line, prediction of potential abnormalities, and optimization of power grid management strategies.

[0046] Conduct an in-depth analysis of historical abnormal reporting data, classify and organize the data according to the monitoring interval, and count the frequency, type, severity and other information of abnormalities in each monitoring interval. Then, determine the key indicators of the penalty feature based on the statistical results. For example, if the frequency of abnormal occurrence in a certain monitoring interval is high, it can be used as an important penalty feature indicator; or, if the type of abnormality in a certain interval is more serious (such as short circuit) and the number of times is large, it is also included in the key indicators. Set weights for these key indicators. The weight setting can be determined based on the degree of impact of the abnormality on the operation of the power grid, the size of the loss caused, etc. The indicators with higher weights have greater influence in subsequent calculations and analyses. Further, consider all key indicators and their weights comprehensively, and construct a penalty feature value that can reflect the severity of the abnormal situation in each monitoring interval. This value can be a comprehensive score or a specific mathematical expression. For example, for monitoring interval A, the frequency of abnormal occurrence is 3 times per month, the average loss caused by each abnormality is large, and serious short circuit abnormalities have occurred. By setting the corresponding weights and calculation methods, a higher penalty feature value is constructed for monitoring interval A, indicating that there is a higher abnormal risk in this interval. The penalty features constructed in this way can be used to carry out targeted processing and attention on different monitoring intervals in subsequent work such as line loss calculation and abnormal warning, so as to improve the stability and reliability of power grid operation.

[0047] First, the penalty features that have been constructed reflect the risk level of anomalies in each monitoring interval. These penalty features may be derived based on various factors in the historical anomaly reporting data, such as the high frequency of anomalies in a monitoring interval, the more serious the anomaly type, or the more likely anomalies to occur under certain conditions.

[0048] Then, when performing independent line loss calculations, the corresponding penalty characteristic value is applied to the calculation process to compensate the original line loss calculation result. The compensation method can be to increase or decrease a certain amount of line loss according to the size of the penalty characteristic value. For example, if the penalty characteristic value of a monitoring interval is high, it means that it has a higher abnormal risk, then a larger compensation amount may be added to its original line loss calculation result; conversely, if the penalty characteristic value is low, a smaller compensation amount may be added or no compensation may be performed.

[0049] The independent line loss calculation result after compensation can better reflect the actual situation of the monitoring interval. Next, the compensated result is compared with the preset threshold or normal range. If the compensated line loss calculation result exceeds the threshold or is not within the normal range, an abnormal warning will be reported. For example, assuming that the penalty characteristic value of monitoring interval A is 0.8 (this is a relatively high value, indicating that the interval has a high abnormal risk), the original line loss calculation result is 5%. According to the set compensation rules, the compensation amount may be determined to be 1% (the specific size of the compensation amount can be set according to actual conditions and experience). Then the compensated line loss calculation result is 5%+1%×0.8=5.8%. If the preset line loss threshold is 5.5%, an abnormal warning will be reported at this time, indicating that there is an abnormal situation in monitoring interval A, which requires further attention and inspection. In this way, those monitoring intervals with higher abnormal risks can be discovered more timely and accurately, so that corresponding measures can be taken to investigate and deal with them, prevent potential problems or failures, and thus improve the operational stability and reliability of the power grid. At the same time, the continuous accumulation and updating of historical abnormal reporting data can further optimize the construction of penalty features and compensation rules, making line loss calculation and abnormal warning more accurate and effective.

[0050] In a possible implementation, the smart grid line loss detection system based on the Internet of Things further includes a timing verification module, and the timing verification module is used to:

[0051] A timing verification window is matched based on the abnormal warning.

[0052] The time series verification window is used to perform continuous data collection in the monitoring interval for reporting abnormal warnings, and a time series data set is established.

[0053] Taking the starting point of the time series data set as the benchmark data, perform fluctuation loss analysis at each time node, and generate additional warning information based on the fluctuation loss analysis results.

[0054] The abnormal warning is updated through the additional warning information.

[0055] Specifically, the process of matching the timing verification window based on the abnormal warning is to conduct a deeper analysis and confirmation of the monitoring interval where abnormalities may exist. When an abnormal warning is received, a suitable timing verification window needs to be determined. The length and time range of this window will be set according to the specific situation, such as considering the possible duration of the abnormality, the frequency of data collection, the characteristics of the system and other factors. After determining the timing verification window, continuous data collection of the monitoring interval that reports the abnormal warning can be performed according to the window, so as to establish a time series data set containing the data in the window. Then, the starting point of the time series data set is used as the benchmark data to perform fluctuation loss analysis at each time node. This step aims to evaluate the fluctuation of line loss by comparing the difference between the data at each time point and the data at the starting point. There are many specific fluctuation loss analysis methods, such as the moving average method, which expands the reference time point and uses the periodic data of multiple time points for smoothing to obtain the relative value of the indicator at the current moment. Its advantage is that it excludes the influence caused by the abnormality of the same period to identify the pattern and trend in the data; or the absolute value threshold method is set. By setting a certain threshold, when the indicator is lower or higher than the threshold, the indicator fluctuation is considered to be abnormal. Based on the results of the fluctuation loss analysis, additional warning information can be generated, which can provide more details and characteristics about the anomaly, such as the amplitude of the fluctuation, the change in trend, whether there is a specific pattern, etc. Finally, the previous abnormal warning is updated with the additional warning information. Updating the abnormal warning by matching the timing verification window, performing fluctuation loss analysis, and generating additional warning information can provide deeper insights and more accurate judgments, which helps to respond to various abnormal situations in a timely and effective manner.

[0056] When the abnormal warning is triggered, the monitoring interval that reports the abnormal warning is continuously collected according to the time range and data collection frequency of the pre-set timing verification window. For example, if the timing verification window is set to 1 hour and the collection frequency is once per minute, 60 data points will be collected within this 1 hour. The collected data will be sorted and stored in chronological order to establish a time series data set containing timestamps and corresponding monitoring data. Assuming that the monitored data is line loss power, each row in this time series data set may contain the specific time of collection (such as 15:30 on July 2, 2024) and the corresponding line loss power value (such as 50 watts). By establishing such a time series data set, the changes in the data in the monitoring interval within a specific time period can be observed more comprehensively and in detail, providing a data basis for subsequent fluctuation loss analysis.

[0057] The starting point data of the time series data set is determined as the benchmark data. Then, for the data of each subsequent time node, the difference between it and the benchmark data is calculated. This difference can be a numerical difference, a change in proportion, or other measures that can reflect the degree of fluctuation. By comparing the difference between each time node and the benchmark data, the fluctuation loss situation is evaluated. If at a certain time node, the fluctuation of the data exceeds the preset threshold or shows an obvious abnormal pattern, additional warning information is generated based on these analysis results. For example, if the set threshold is that the fluctuation amplitude exceeds 20% of the benchmark data, when the fluctuation amplitude of the data at a certain time node reaches or exceeds this threshold, additional warning information such as "At a specific time, the line loss fluctuation amplitude exceeds the benchmark by 20%, and special attention should be paid" is generated. Alternatively, if it is observed that the fluctuation of the data shows a trend of continuous increase or decrease, corresponding additional warning information describing the trend can also be generated, such as "From the start time to the current time, the line loss fluctuation continues to increase, and there may be a risk of potential fault aggravation". The generated additional warning information can provide more detailed and targeted prompts to help relevant personnel understand the development of abnormalities more timely and accurately, so as to take more effective countermeasures.

[0058] Evaluate the content and importance of the additional warning information, for example, determine the severity of the fluctuation loss, the stability of the trend, and the possible impact on the operation of the power grid. Then, integrate the key data and conclusions in the additional warning information into the original abnormal warning. This includes updating the description of the abnormality, supplementing the specific values ​​and trend information about the fluctuation loss, and a more detailed assessment of potential risks. For example, if the original abnormal warning simply points out that there is an abnormal line loss in the monitoring interval, and the additional warning information shows that the line loss fluctuation continues to increase within a specific time and exceeds a certain amplitude, the updated abnormal warning can be described as "the line loss in the monitoring interval is abnormal, and the fluctuation continues to increase within a specific time period, the amplitude exceeds a specific value, and there is a serious failure risk." In addition, the level of the abnormal warning may be adjusted according to the additional warning information. If the additional warning information indicates that the situation is more critical, the warning level may be raised from "general" to "serious". The updated abnormal warning can provide more comprehensive, accurate and timely information to relevant personnel so that they can make more appropriate decisions and take more effective countermeasures to ensure the safe and stable operation of the power grid.

[0059] In a possible implementation, the sensor distribution module 20 further includes a clustering submodule, and the clustering submodule is used to:

[0060] The line characteristics of the power grid line are extracted based on the layout data.

[0061] Conduct line evaluation on power grid lines and establish the importance weights of line features in layout data.

[0062] The interval similarity analysis of the power grid line is performed through the line characteristics, and the interval clustering division is completed after weighted calculation of the interval similarity analysis results based on important weights.

[0063] Specifically, it is necessary to obtain the layout data related to the power grid lines. These data include various parameters of the lines, equipment information, operating status data, etc. From the layout data, features that can describe the characteristics of the power grid lines are extracted, such as the voltage level, current size, power factor, line length, conductor model, tower type, insulator status, equipment aging degree, etc. These features can reflect the electrical characteristics, physical structure and operating status of the lines.

[0064] Clarify the objectives and standards of line evaluation. This may include evaluating the safety, reliability, economy, stability and other aspects of the line. Then, analyze each line feature in the layout data and consider its impact on the line evaluation objectives. For example, for safety, the insulation performance and current carrying capacity of the line may be of high importance; for reliability, the failure rate and maintenance history of the equipment may be more critical; for economy, the construction cost and operating loss of the line need to be focused on. Next, a variety of methods can be used to determine the important weights. Common methods include the analytic hierarchy process (AHP), the Delphi method, and the principal component analysis method. Taking the principal component analysis method as an example, the original line feature data is mathematically transformed to extract the main components, and the weights are determined according to the contribution rate of the components. In the process of determining the weights, the results need to be checked for consistency or analyzed for rationality to ensure the accuracy and reliability of the weights. For example, suppose that after evaluation, it is believed that the current carrying capacity of the line has a weight of 0.3 for safety, the failure rate of the equipment has a weight of 0.4 for reliability, and the construction cost has a weight of 0.5 for economy. By establishing such important weights, the actual role and importance of each line characteristic in the power grid line evaluation can be more accurately reflected, providing strong support for subsequent analysis and decision-making.

[0065] The steps of similarity analysis, weighted calculation and interval clustering of power line intervals are performed to determine the line characteristics. First, various characteristics of the power line have been extracted through the previous steps; interval similarity analysis, using appropriate similarity measurement methods to compare line characteristics of different intervals. Common methods can be to calculate the distance or similarity between feature vectors. For example, methods such as Euclidean distance and cosine similarity can be used. For each line interval, its characteristics are represented as a vector, and then the similarity between vectors of different intervals is calculated; important weight application, according to the previously established line feature important weights, the results of interval similarity analysis are weighted. The important weights reflect the relative importance of each line feature in the evaluation. By multiplying the similarity measurement results with the weights of the corresponding features, the important features can have a greater influence in the clustering process; interval clustering, based on the weighted similarity results, interval clustering is performed. Common clustering algorithms can be used, such as K-Means clustering algorithm. The goal of the clustering algorithm is to divide similar intervals into the same cluster, and dissimilar intervals into different clusters. Take the K-Means clustering algorithm as an example: (1) Initialization: Select the number of clusters K and randomly initialize K cluster centers. (2) Assign intervals: For each line interval, calculate its weighted distance to each cluster center (using the weighted similarity measure). Assign the interval to the cluster with the smallest weighted distance. (3) Update cluster center: Recalculate the feature average of all intervals in each cluster as the new cluster center. (4) Repeat steps (2) and (3): Repeat the process of assigning intervals and updating cluster centers until the change in cluster center is less than a certain threshold or the specified number of iterations is reached. Through this process, the interval clustering division is completed. The clustering results obtained will divide the intervals of the power grid line into different clusters. The intervals within each cluster have high similarity, while the intervals between different clusters have large differences. Such clustering division can help better understand the structure and characteristic distribution of power grid lines, and facilitate targeted analysis, planning, operation and maintenance. For example, specific maintenance strategies and resource allocation plans can be formulated for lines in different clusters, or some line intervals with similar operating characteristics can be found for unified management and optimization.

[0066] In a possible implementation, the smart grid line loss detection system based on the Internet of Things further includes a dynamic early warning module, which is used to:

[0067] Conduct steady-state evaluation on power grid lines and establish steady-state evaluation results.

[0068] An adaptive moving window is matched based on the steady-state evaluation result.

[0069] A moving standard deviation is established through the adaptive moving window, and a dynamic threshold is configured through the moving standard deviation.

[0070] Dynamic early warning alarm is issued through the dynamic threshold and the smart meter monitoring data.

[0071] Specifically, data related to the steady-state operation of power grid lines are collected, such as voltage, current, power, power factor, load rate, etc. The equipment conditions of the lines are comprehensively considered, such as the aging degree of conductors and insulators, the failure rate of equipment, etc. The structure and topology of the power grid, such as the connection method of the lines, whether there is a single point failure risk, etc., must also be considered. Based on the above analysis and evaluation, a steady-state evaluation result can be established, and the evaluation result adopts a combination of quantitative indicators and qualitative descriptions. For example, quantitative indicators include specific values ​​of voltage deviation, percentage of current overload, specific value of power factor, etc. Qualitative descriptions can be "line voltage is stable, current load is reasonable, equipment is in good condition, and overall steady-state operation is good", or "some lines have voltage fluctuations, current is close to overload, and attention needs to be paid", etc. The steady-state evaluation results help to understand the operating status of power grid lines and provide a basis for subsequent maintenance, upgrades and optimization.

[0072] The adaptive moving window is a time window determined based on the steady-state evaluation results. The size of this window will be adjusted according to the characteristics of the line, historical data, and the specific situation of the steady-state evaluation. For example, if the line is running relatively stable, the window size may be relatively large; if the line has more fluctuations or changes, the window size may be reduced accordingly to reflect the changes in the line status more timely.

[0073] The steps to establish a moving standard deviation through an adaptive moving window and configure a dynamic threshold using the moving standard deviation are as follows: First, use an adaptive moving window to obtain the data in the window. Then, calculate the standard deviation of the data in the window, that is, the moving standard deviation, which reflects the degree of dispersion of the data. Next, use the moving standard deviation to configure the dynamic threshold according to the specific situation and needs. Common methods include: fixed multiple method, percentile method, etc.; taking the fixed multiple method as an example, the moving standard deviation is multiplied by a fixed multiple (such as 2 or 3), and a reference value (such as the mean) is added or subtracted to obtain the dynamic threshold. For example, the threshold can be set to mean ± k × moving standard deviation, where k is a constant. In practical applications, the setting of dynamic thresholds needs to take into account a variety of factors, such as data characteristics, business needs, tolerance for anomalies, etc. Continuously adjust and optimize the dynamic threshold to ensure that anomalies in the data can be accurately detected while minimizing false positives and false negatives.

[0074] When using dynamic thresholds and smart meter monitoring data for dynamic early warning alarms, first, the smart meter monitoring data is obtained in real time. These data may include various electrical parameters such as current, voltage, power, and electricity. Then, the acquired real-time monitoring data is compared with the pre-set dynamic threshold. If the monitoring data exceeds the upper limit of the dynamic threshold or is lower than the lower limit of the dynamic threshold, the early warning alarm mechanism is triggered. At the same time, in order to ensure the accuracy and reliability of the early warning, a certain delay or confirmation mechanism is set. For example, only when the monitoring data exceeds the threshold for multiple consecutive times or continues to exceed the threshold for a certain period of time, the early warning is actually reported to avoid false alarms due to short-term fluctuations or interference. For the reported early warning, a corresponding recording and tracking mechanism should be established so that it can be traced and referenced in subsequent analysis and handling of abnormal situations.

[0075] In a possible implementation, the dynamic warning module is further used to:

[0076] A feedback mechanism is established and triggered according to the reporting results of dynamic early warnings.

[0077] The dynamic threshold is updated based on the feedback mechanism trigger results.

[0078] Specifically, establishing such a feedback mechanism usually includes the following key steps: setting up feedback channels, determining the way to receive and feedback the results of dynamic early warning alarms, which can be through specific software systems, emails, text message notifications or online forms, etc.; clarifying feedback responsibilities, designating personnel or teams responsible for receiving and processing feedback, and ensuring that there are dedicated people to pay attention to and handle feedback information in a timely manner; designating feedback content, determining the information that the feedback recipient needs to provide, such as the accuracy of the warning (whether there is indeed an abnormality), a specific description of the abnormality, and suggestions for warning processing; setting trigger conditions, when the dynamic early warning alarm is issued, the feedback mechanism is activated, and it is set to require relevant personnel to provide feedback within a certain period of time after the alarm is issued (such as 24 hours); tracking and reminders, establishing a tracking system, recording the status of feedback (feedback received, not fed back), and sending reminder notifications for those who have not provided feedback in a timely manner to ensure the timeliness of feedback.

[0079] Collect relevant data and information after the feedback mechanism is triggered. This includes determining which warnings are accurate, which are false alarms, and what are the omissions. Then, analyze the collected feedback results. If a large number of feedbacks indicate that there are too many false alarms in the warning, that is, the actual situation is not abnormal but the warning is triggered, this means that the current dynamic threshold is set too low. In this case, the dynamic threshold can be appropriately increased. For example, a new moving standard deviation is calculated and the threshold is adjusted based on this multiplied by a slightly smaller coefficient, or a fixed value is added to the original threshold. On the contrary, if the feedback shows that there are many omissions, that is, an abnormality actually occurred but the warning was not triggered, this means that the dynamic threshold is set too high. In this case, the dynamic threshold should be lowered. For example, the calculated moving standard deviation is multiplied by a slightly larger coefficient, or a fixed value is subtracted from the original threshold. When updating the dynamic threshold, the operating characteristics and historical data of the power line should also be considered to ensure that the updated threshold can detect the real anomaly in a timely and accurate manner, and minimize the occurrence of false alarms and omissions. By continuously optimizing the dynamic threshold based on the feedback mechanism trigger results, the dynamic early warning system of the power line can be made more accurate and effective.

[0080] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0081] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0082] This specification and the drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. The smart grid line loss detection system based on the Internet of Things is characterized by: The system comprises: An information interaction module, used to obtain layout data of the smart grid, wherein the layout data includes distribution data of power grid lines, structural data of power grid lines, and line load data; A sensor distribution module, used for distributing monitoring sensors, wherein the monitoring sensors include smart meters and distributed optical fiber sensors, and the monitoring sensors are distributed by preset interval identifiers, wherein the preset interval identifiers are identifiers obtained by performing interval clustering based on the deployment data; A data acquisition module is used to receive the monitoring data set of the monitoring sensor, and synchronously obtain the transmission task of the power grid line, perform interval association reconstruction according to the transmission task and the preset interval identifier, and establish the association coefficient of the monitoring interval; A first line loss calculation module, used to call the smart meter monitoring data in the monitoring data set, perform line loss calculation within an independent monitoring interval according to the smart meter monitoring data, and generate an independent line loss calculation result; A second line loss calculation module is used to call the distributed optical fiber sensor monitoring data in the monitoring data set, perform an abnormality authentication within the interval on the distributed optical fiber sensor monitoring data, generate a first abnormality authentication result, perform line loss calculation within the associated monitoring interval according to the first abnormality authentication result, the smart meter monitoring data, and the correlation coefficient, and generate an associated line loss calculation result; A management module, used for performing line loss detection management of the smart grid according to the independent line loss calculation result and the associated line loss calculation result; Performing interval association reconstruction according to the transmission task and the preset interval identifier to establish the association coefficient of the monitoring interval also includes: The correlation coefficient is established as follows: Among them, Q ij Characterizes the correlation coefficient between monitoring interval i and monitoring interval j, D ij is the physical distance between monitoring interval i and monitoring interval j, x i ,y i 、z i is the coordinate of monitoring interval i, x j ,y j 、z j is the coordinate of monitoring interval j, S ij Characterizes the structural similarity between monitoring interval i and monitoring interval j, τ ij is the structural difference between monitoring interval i and monitoring interval j, L ij Characterizes the load similarity between monitoring interval i and monitoring interval j, P i is the active power of monitoring interval i, P j is the active power of monitoring interval j, Cov(P i ,P j ) is the load power covariance between monitoring interval i and monitoring interval j, and are the load power standard deviations of monitoring interval i and monitoring interval j, respectively; α, β, and γ are the weight coefficients of physical distance, structural similarity, and load similarity, respectively; Performing line loss detection management of the smart grid according to the independent line loss calculation result and the associated line loss calculation result also includes: Configure the comprehensive line loss rate calculation formula as follows: Where H is the comprehensive line loss rate, N is the number of independent monitoring intervals, M is the number of associated monitoring intervals with monitoring interval i, and P in,i Characterizes the input power of monitoring interval i, P out,i Characterizes the output power of monitoring interval i, is the sum of the line losses of the independent line loss calculation results, P in,ij is the input power of monitoring interval j associated with monitoring interval i, P out,ij is the output power of monitoring interval j associated with monitoring interval i, is the correlation coefficient Q ij The updated results, μ is the weight coefficient of abnormal authentication, T i and T j Respectively represent the monitoring temperature of monitoring interval i and monitoring interval j, T baseline,i and T baseline,j is the reference temperature of monitoring interval i and monitoring interval j, and are the temperature standard deviations of monitoring interval i and monitoring interval j respectively; The comprehensive line loss rate is calculated, and line loss detection and management of the smart grid is performed based on the comprehensive line loss rate.

2. The smart grid line loss detection system based on the Internet of Things according to claim 1, characterized in that: The system also includes an early warning module, which is used to: Obtain historical abnormal reporting data of power grid lines; Constructing penalty features for monitoring intervals based on the historical abnormal reporting data; The independent line loss calculation result is compensated by using the penalty feature, and an abnormal warning is reported according to the compensated independent line loss calculation result.

3. The smart grid line loss detection system based on the Internet of Things as claimed in claim 2, characterized in that: The system further includes a timing verification module, wherein the timing verification module is used to: Matching the timing verification window based on the abnormal warning; Continuous data collection of the monitoring interval for abnormal warning is performed in the time series verification window to establish a time series data set; Taking the starting point of the time series data set as the benchmark data, perform fluctuation loss analysis at each time node, and generate additional warning information based on the fluctuation loss analysis results; The abnormal warning is updated through the additional warning information.

4. The smart grid line loss detection system based on the Internet of Things as claimed in claim 1, characterized in that: The sensor distribution module further includes a clustering submodule, and the clustering submodule is used to: Extracting line characteristics of the power grid line based on the layout data; Conduct line evaluation on power grid lines and establish the importance weights of line features in layout data; The interval similarity analysis of the power grid line is performed through the line characteristics, and the interval clustering division is completed after weighted calculation of the interval similarity analysis results based on important weights.

5. The smart grid line loss detection system based on the Internet of Things as claimed in claim 1, characterized in that: The system also includes a dynamic early warning module, which is used to: Conduct steady-state evaluation on power grid lines and establish steady-state evaluation results; Matching an adaptive moving window based on the steady-state evaluation result; Establishing a moving standard deviation through the adaptive moving window, and configuring a dynamic threshold through the moving standard deviation; Dynamic early warning alarm is issued through the dynamic threshold and the smart meter monitoring data.

6. The smart grid line loss detection system based on the Internet of Things as claimed in claim 5, characterized in that: The dynamic early warning module is also used for: Establish a feedback mechanism and trigger it according to the reporting results of dynamic early warning; The dynamic threshold is updated based on the feedback mechanism trigger results.

Citation Information

Patent Citations

  • Smart power grid line loss detection method and system

    CN103869192A

  • Monitoring and locating method based on abnormal electricity consumption detection module

    CN106707099A

  • District line loss analysis monitoring system based on big data and analysis method thereof

    CN114139862A

  • Intelligent identification method for transformer-household relation of power supply transformer area

    CN115436840A

  • Power distribution network line loss anomaly detection method and system based on intelligent algorithm

    CN116298675A