Power supply and distribution system operation state monitoring system based on big data

Abstract

The invention discloses a power supply and distribution system operation state monitoring system based on big data, and relates to the technical field of big data. The state monitoring accuracy of the power supply and distribution system is effectively improved; the method comprises the following steps: acquiring historical time sequence data of a supply and distribution system through a historical construction unit and a real-time acquisition unit arranged on a data acquisition module; setting power distribution and utilization association, and constructing a power distribution and utilization data acquisition model by the historical time ordinal number through the power distribution and utilization association; real-time distribution data of the distribution system is acquired in real time through the distribution and utilization data acquisition model; analyzing the power distribution and utilization data to obtain abnormal power distribution and utilization data; obtaining an abnormal level of the abnormal power distribution and utilization data, and generating a corresponding abnormal level signal; and performing early warning on the abnormal power supply and distribution data according to the abnormal level signal.

Description

Technical Field

[0001] This invention relates to the field of big data technology, specifically a power supply and distribution system operation status monitoring system based on big data. Background Technology

[0002] With the deepening of smart grid construction and the rapid development of the energy internet, the power supply and distribution system, as the "last mile" of power transmission, directly affects social production and daily life through its operational stability and reliability. Traditional power supply and distribution monitoring systems rely heavily on manual inspections and fixed threshold alarms, which are significantly inadequate in processing massive amounts of heterogeneous data, assessing complex operating conditions, and providing early warnings of faults. Especially against the backdrop of drastic fluctuations in electricity load and the large-scale integration of distributed energy resources, the system's operating state exhibits highly nonlinear and time-varying characteristics, making it difficult for traditional methods to meet the demands for real-time, accurate, and intelligent monitoring. Big data technology offers a new path to solving this problem, but its in-depth application in the power supply and distribution field still faces core challenges such as model building, correlation analysis, and state classification. Peak electricity consumption data is highly valuable, but traditional methods simply pile up "historical electricity consumption time series" and "historical power distribution time series," ignoring the non-uniform matching between the two on a time scale (such as the contradiction between the periodicity of power distribution and the randomness of electricity consumption). The lack of effective mechanisms (such as segmenting based on "overlapping time points" and optimizing dynamic chain connections) to link fragmented time series data into an organic whole leads to insufficient data value mining. The correlation between anomalies in power distribution data and power consumption data has not been fully explored. Existing methods typically detect power distribution anomalies or power consumption anomalies in isolation, ignoring the "distribution-consumption" linkage (e.g., a fault at a specific power distribution point may trigger anomalies in data from related power consumption points). The lack of a joint analysis mechanism based on a power distribution-consumption coordination model makes it difficult to pinpoint root causes and accurately identify complex anomalies.

[0003] The early warning information lacks a tiered linkage mechanism. All anomalies trigger alarms at the same level, making it impossible to distinguish between minor fluctuations and precursors to major failures, leading to operator fatigue or delays in critical response. There is an urgent need to build a scientific tiered model based on anomaly deviation (e.g., level one to three anomalies) to drive differentiated early warning responses; the assessment of anomaly severity is too simplistic (e.g., binary "normal / abnormal"), failing to quantify risk levels and hindering the optimal allocation of operational resources. To address the aforementioned technical problems, this invention provides a power supply and distribution system operation status monitoring system based on big data. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention provides a power supply and distribution system operation status monitoring system based on big data; The objective of this invention can be achieved through the following technical solution: a power supply and distribution system operation status monitoring system based on big data, the system including a data acquisition module, a data analysis module, a level monitoring module, and an early warning module; The data acquisition module is equipped with a historical construction unit and a real-time acquisition unit; the historical construction unit is used to collect historical time-series data of the power supply and distribution system; and sets up power distribution and consumption association to construct a power distribution and consumption data acquisition model by using the historical time-series data; the real-time acquisition unit is used to collect real-time power distribution and consumption data of the power supply and distribution system through the power distribution and consumption data acquisition model. The data analysis module is used to analyze power distribution data and obtain abnormal power distribution data; The level monitoring module is used to obtain the abnormality level of abnormal power distribution data and generate the corresponding abnormality level signal; the early warning module is used to issue an early warning for abnormal power supply and distribution data based on the abnormality level signal.

[0005] Furthermore, the process by which the historical construction unit collects historical time-series data of the supply and distribution system includes: The power supply and distribution system includes a power supply system wirelessly connected to several power distribution terminals; it schedules the historical peak electricity consumption cycle of the power distribution terminals in the recent 24 hours, and collects the historical electricity consumption time sequence and historical power distribution time sequence of each power distribution terminal during the historical peak electricity consumption cycle; Obtain the same time points of historical power consumption and historical power distribution for each power distribution terminal, and mark them as overlapping time points. Use the overlapping time points as the dividing line to simultaneously segment the historical power consumption and historical power distribution time to obtain segmented historical time. The segmented historical time includes segmented historical power consumption time and segmented historical power distribution time.

[0006] Furthermore, the process of setting up power distribution and consumption associations and constructing a power distribution and consumption data acquisition model by linking historical time series data includes: Set up a power distribution optimization chain and associate the power distribution and consumption of the segmented historical time sequence from left to right; The power distribution association is used to obtain the number of power distribution time points in the segmented historical power distribution time sequence starting from the leftmost segmented historical time sequence, and mark them as the segmented power distribution quantity; and to perform segmented matching between the segmented historical power consumption time sequence and the segmented historical power distribution time sequence according to the segmented power distribution quantity.

[0007] Furthermore, if the number of segmented power distributions is 0, the minimum overlapping time point between adjacent segments of the historical power distribution time sequence is obtained and marked as a temporary power distribution time point; the temporary power distribution time point and the corresponding power consumption time point of the historical power consumption time sequence are connected sequentially through the power distribution optimization chain to generate a segmented power distribution and consumption data network. If the number of segmented power distributions is 1, then the power distribution time point and the corresponding power consumption time point of the segmented historical power consumption sequence are connected sequentially through the power distribution optimization chain to generate a segmented power distribution and consumption data network. If the number of segmented power distributions is greater than 1, then obtain the number m of the corresponding segmented historical power consumption time points, and use the formula... Obtain the number of units N of electricity consumption time points matched for each power distribution time point; where n represents the number of segmented power distributions; then connect the power distribution time points sequentially through the power distribution optimization chain to obtain the segmented power distribution and consumption data network corresponding to the number of units. The segmented power distribution and consumption data network is spliced ​​together by the power distribution time points and power consumption time points corresponding to the overlapping time points to generate a power distribution and consumption data acquisition model.

[0008] Furthermore, the process by which the real-time acquisition unit acquires the distribution data of the power supply and distribution system in real time through the power distribution data acquisition model includes: The power distribution and consumption data of the power distribution terminal are collected in real time through the power distribution collection time point and the power consumption collection time point of the power distribution data acquisition model. The power distribution and consumption data includes power distribution data and power consumption data.

[0009] Furthermore, the process by which the data analysis module analyzes power distribution data to obtain abnormal power distribution data includes: The segmented power distribution data network of the power distribution data acquisition model obtains the segmented historical time sequence corresponding to the power distribution data through the power distribution optimization chain; Power distribution data and corresponding power consumption data are obtained through segmented historical time series; threshold ranges for power distribution data and power consumption data are set. Compare the power distribution data and power consumption data with the corresponding power distribution data threshold range and power consumption data threshold range; If both the power distribution data and the power consumption data fall within the power distribution data threshold range and the power consumption data threshold range, then the corresponding power distribution data and power consumption data will be marked as normal power distribution data and normal power consumption data. Conversely, the corresponding power distribution data and power consumption data will be marked as abnormal power distribution data and abnormal power consumption data.

[0010] Furthermore, the process by which the level monitoring module acquires the abnormality level of abnormal power distribution data and generates a corresponding abnormality level signal includes: Set the highest abnormal value for abnormal power distribution data and abnormal power consumption data; obtain the ratio of abnormal power distribution and consumption to the highest abnormal value, and mark it as an abnormal data value; If the abnormal data value is less than 60%, the abnormality level will be marked as Level 1 abnormality. If the abnormal data value is greater than 60% but less than 90%, the abnormality level will be marked as Level 2. If the abnormal data value is greater than 90%, the abnormality level will be marked as Level 3. The first-level, second-level, and third-level anomaly levels will generate first-level, second-level, and third-level anomaly signals, respectively.

[0011] Furthermore, the process by which the early warning module issues early warnings for abnormal data based on the anomaly level signal includes: The abnormal level signal is sent to the preset management terminal for early warning, abnormal configuration data is obtained, and then processed.

[0012] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention collects historical time-series data of the power supply and distribution system through the historical construction unit and real-time acquisition unit set in the data acquisition module; sets up power distribution and consumption association, and constructs a power distribution and consumption data acquisition model through the power distribution and consumption association of historical time-series data; and collects real-time power distribution and consumption data of the power supply and distribution system in real time through the power distribution and consumption data acquisition model; then analyzes the power distribution and consumption data to obtain abnormal power distribution and consumption data; obtains the abnormality level of abnormal power distribution and consumption data, and generates corresponding abnormality level signals; and provides early warning for abnormal power supply and distribution data based on the abnormality level signals; effectively improving the accuracy of power supply and distribution system status monitoring. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0014] Figure 1 This is a schematic diagram of the present invention. Detailed Implementation

[0015] 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, and 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.

[0016] like Figure 1 As shown, a power supply and distribution system operation status monitoring system based on big data is disclosed. The system includes a data acquisition module, a data analysis module, a level monitoring module, and an early warning module. The data acquisition module is equipped with a historical construction unit and a real-time acquisition unit; the historical construction unit is used to collect historical time-series data of the power supply and distribution system; and sets up power distribution and consumption association to construct a power distribution and consumption data acquisition model by using the historical time-series data; the real-time acquisition unit is used to collect real-time power distribution and consumption data of the power supply and distribution system through the power distribution and consumption data acquisition model. The data analysis module is used to analyze power distribution data and obtain abnormal power distribution data; The level monitoring module is used to obtain the abnormality level of abnormal power distribution data and generate the corresponding abnormality level signal; the early warning module is used to issue an early warning for abnormal power supply and distribution data based on the abnormality level signal.

[0017] It should be further explained that the historical construction unit is used to collect historical time-series data of the power supply and distribution system; the process of setting up power distribution and consumption associations and constructing a power distribution and consumption data acquisition model by using historical time-series data through power distribution and consumption associations includes: The power supply and distribution system includes a power supply system wirelessly connected to several power distribution terminals; it schedules the historical peak electricity consumption cycle of the power distribution terminals in the recent 24 hours, and collects the historical electricity consumption time sequence and historical power distribution time sequence of each power distribution terminal during the historical peak electricity consumption cycle; Obtain the same time points of historical power consumption and historical power distribution for each power distribution terminal, and mark them as overlapping time points. Use the overlapping time points as the dividing line to simultaneously segment the historical power consumption and historical power distribution time to obtain segmented historical time. The segmented historical time includes segmented historical power consumption time and segmented historical power distribution time.

[0018] Set up a power distribution optimization chain and associate the power distribution and consumption of the segmented historical time sequence from left to right; The power distribution association is used to obtain the number of power distribution time points in the segmented historical power distribution time sequence starting from the leftmost segmented historical time sequence, and mark them as the segmented power distribution quantity; and to perform segmented matching between the segmented historical power consumption time sequence and the segmented historical power distribution time sequence according to the segmented power distribution quantity. If the number of segmented power distributions is 0, then obtain the minimum overlapping time point of the segmented historical power distribution time sequence and mark it as a temporary power distribution time point; connect the temporary power distribution time point with the corresponding power consumption time point of the segmented historical power consumption time sequence in sequence through the power distribution optimization chain to generate a segmented power distribution and consumption data network. If the number of segmented power distributions is 1, then the power distribution time point and the corresponding power consumption time point of the segmented historical power consumption sequence are connected sequentially through the power distribution optimization chain to generate a segmented power distribution and consumption data network. If the number of segmented power distributions is greater than 1, then obtain the number m of the corresponding segmented historical power consumption time points, and use the formula... Obtain the number of units N of electricity consumption time points matched for each power distribution time point; where n represents the number of segmented power distributions; then connect the power distribution time points sequentially through the power distribution optimization chain to obtain the segmented power distribution and consumption data network corresponding to the number of units. In the above embodiments, it should be further explained that when the number of segmented power distributions is greater than 1, the formula is used... What we get is the smallest integer that can be matched for the power distribution time point. However, since m and n are not divisible, the last power distribution time point may be greater than N. For example, when m is 7 and n is 5, then N is 1, which means that each power distribution time point matches one power consumption time point. After matching in order, there are two power consumption time points left, which are then connected to the last power distribution time point. This is equivalent to connecting the remainder to the last power distribution time point. The segmented power distribution and consumption data network is spliced ​​together with the power distribution time points and power consumption time points corresponding to the overlapping time points to generate a power distribution and consumption data acquisition model. In the above embodiments, it should be further explained that the electricity consumption time and duration of each distribution terminal are different. The same distribution time point and electricity consumption time point are marked as overlapping time points. These overlapping time points are the times when the electricity supply is most abundant during the historical peak electricity consumption cycle. Using the overlapping time points as dividing lines can better analyze the electricity consumption data and distribution data of the entire historical peak electricity consumption cycle. The distribution time point may be obtained from the distribution cycle, while the electricity consumption time point is not fixed. Therefore, by segmenting and matching the segmented historical electricity consumption time series with the segmented historical distribution time series to collect and analyze the distribution data for different electricity consumption times, the electricity consumption and distribution status of the distribution terminals can be better monitored. The distribution optimization chain is used to transmit distribution data.

[0019] It should be further explained that the process by which the real-time acquisition unit acquires the distribution data of the power supply and distribution system in real time through the power distribution data acquisition model includes: The power distribution and consumption data of the power distribution terminal are collected in real time through the power distribution collection time point and the power consumption collection time point of the power distribution data acquisition model. The power distribution and consumption data includes power distribution data and power consumption data. In the above embodiments, it should be further explained that the power distribution and power consumption data acquisition time points of the power distribution and consumption data acquisition model change over time. Because the historical peak electricity consumption cycles change, the current power distribution and power consumption data acquisition time points also change accordingly. Therefore, data is not collected based solely on a fixed acquisition time of the power distribution and consumption data acquisition model. For example, the current power distribution data acquisition time points of the power distribution and consumption data acquisition model are 12:30 and 15:02; the power consumption data acquisition time point is 9:20. If the timestamps are 10:52, 12:30, and 14:02, then data is collected based on the power distribution and power consumption collection time points. If the power distribution and power consumption collection time points change during the collection process, for example, if the power distribution collection time points are 15:02 and 16:20, and the power consumption collection time points are 11:52, 13:30, and 15:02, then the current time point is obtained. If the current time point is 13:06, then data collection continues based on the latest power distribution and power consumption collection time points, and so on.

[0020] It should be further explained that the process by which the data analysis module analyzes power distribution data to obtain abnormal power distribution data includes: The segmented power distribution data network of the power distribution data acquisition model obtains the segmented historical time sequence corresponding to the power distribution data through the power distribution optimization chain; Power distribution data and corresponding power consumption data are obtained through segmented historical time series; threshold ranges for power distribution data and power consumption data are set. Compare the power distribution data and power consumption data with the corresponding power distribution data threshold range and power consumption data threshold range; If both the power distribution data and the power consumption data fall within the power distribution data threshold range and the power consumption data threshold range, then the corresponding power distribution data and power consumption data will be marked as normal power distribution data and normal power consumption data. Conversely, the corresponding power distribution data and power consumption data will be marked as abnormal power distribution data and abnormal power consumption data.

[0021] It should be further explained that the process by which the level monitoring module acquires the abnormality level of abnormal power distribution data and generates the corresponding abnormality level signal includes: Set the highest abnormal value for abnormal power distribution data and abnormal power consumption data; obtain the ratio of abnormal power distribution and consumption to the highest abnormal value, and mark it as an abnormal data value; If the abnormal data value is less than 60%, the abnormality level will be marked as Level 1 abnormality. If the abnormal data value is greater than 60% but less than 90%, the abnormality level will be marked as Level 2. If the abnormal data value is greater than 90%, the abnormality level will be marked as Level 3. The first-level, second-level, and third-level anomaly levels will generate first-level, second-level, and third-level anomaly signals, respectively.

[0022] It should be further explained that the process by which the early warning module issues early warnings for abnormal data based on the abnormality level signal includes: The abnormal level signal is sent to the preset management terminal for early warning, abnormal configuration data is obtained, and then processed.

[0023] Working Principle: This invention collects historical time-series data of the power supply and distribution system through the historical construction unit and real-time acquisition unit set in the data acquisition module; sets up power distribution and consumption association, and constructs a power distribution and consumption data acquisition model through the power distribution and consumption association of historical time-series data; and collects real-time power distribution and consumption data of the power supply and distribution system in real time through the power distribution and consumption data acquisition model; then analyzes the power distribution and consumption data to obtain abnormal power distribution and consumption data; obtains the abnormality level of abnormal power distribution and consumption data, and generates corresponding abnormality level signals; and provides early warning for abnormal power supply and distribution data based on the abnormality level signals; effectively improving the accuracy of power supply and distribution system status monitoring.

[0024] The features and exemplary embodiments of various aspects of this application will be described in detail above. In order to make the purpose, technical solution and advantages of this application clearer, the application will be further described in detail above with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain this application and not to limit this application. For those skilled in the art, this application can be implemented without some of the details in these specific details. The above description of the embodiments is only to provide a better understanding of this application by showing examples of this application.

[0025] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. A power supply and distribution system operation status monitoring system based on big data, characterized in that, The system includes a data acquisition module, a data analysis module, a level monitoring module, and an early warning module; The data acquisition module is equipped with a historical construction unit and a real-time acquisition unit; the historical construction unit is used to collect historical time-series data of the power supply and distribution system; and sets up power distribution and consumption association to construct a power distribution and consumption data acquisition model by using the historical time-series data; the real-time acquisition unit is used to collect real-time power distribution and consumption data of the power supply and distribution system through the power distribution and consumption data acquisition model. The data analysis module is used to analyze power distribution data and obtain abnormal power distribution data; The level monitoring module is used to obtain the abnormality level of abnormal power distribution data and generate the corresponding abnormality level signal; The early warning module is used to issue early warnings for abnormal supply and distribution data based on the abnormality level signal.

2. The power supply and distribution system operation status monitoring system based on big data according to claim 1, characterized in that, The process of the historical construction unit collecting historical time-series data of the supply and distribution system includes: The power supply and distribution system includes a power supply system wirelessly connected to several power distribution terminals; it schedules the historical peak electricity consumption cycle of the power distribution terminals in the recent 24 hours, and collects the historical electricity consumption time sequence and historical power distribution time sequence of each power distribution terminal during the historical peak electricity consumption cycle; Obtain the same time points of historical power consumption and historical power distribution for each power distribution terminal, and mark them as overlapping time points. Use the overlapping time points as the dividing line to simultaneously segment the historical power consumption and historical power distribution time to obtain segmented historical time. The segmented historical time includes segmented historical power consumption time and segmented historical power distribution time.

3. The power supply and distribution system operation status monitoring system based on big data according to claim 2, characterized in that, The process of setting up power distribution and consumption associations and constructing a power distribution and consumption data acquisition model by using historical time series data through power distribution and consumption associations includes: Set up a power distribution optimization chain and associate the power distribution and consumption of the segmented historical time sequence from left to right; The power distribution association is used to obtain the number of power distribution time points in the segmented historical power distribution time sequence starting from the leftmost segmented historical time sequence, and mark them as the segmented power distribution quantity; and to perform segmented matching between the segmented historical power consumption time sequence and the segmented historical power distribution time sequence according to the segmented power distribution quantity.

4. The power supply and distribution system operation status monitoring system based on big data according to claim 3, characterized in that, If the number of segmented power distributions is 0, then obtain the minimum overlapping time point of the segmented historical power distribution time sequence and mark it as a temporary power distribution time point; connect the temporary power distribution time point with the corresponding power consumption time point of the segmented historical power consumption time sequence in sequence through the power distribution optimization chain to generate a segmented power distribution and consumption data network. If the number of segmented power distributions is 1, then the power distribution time point and the corresponding power consumption time point of the segmented historical power consumption sequence are connected sequentially through the power distribution optimization chain to generate a segmented power distribution and consumption data network. If the number of segmented power distributions is greater than 1, then obtain the number m of the corresponding segmented historical power consumption time points, and use the formula... Obtain the number of units N of electricity consumption time points matched for each power distribution time point; where n represents the number of segmented power distributions; then connect the power distribution time points sequentially through the power distribution optimization chain to obtain the segmented power distribution and consumption data network corresponding to the number of units. The segmented power distribution and consumption data network is spliced ​​together by the power distribution time points and power consumption time points corresponding to the overlapping time points to generate a power distribution and consumption data acquisition model.

5. The power supply and distribution system operation status monitoring system based on big data according to claim 4, characterized in that, The process by which the real-time acquisition unit acquires power distribution data in real time through the power distribution data acquisition model includes: The power distribution and consumption data of the power distribution terminal are collected in real time through the power distribution collection time point and the power consumption collection time point of the power distribution data acquisition model. The power distribution and consumption data includes power distribution data and power consumption data.

6. The power supply and distribution system operation status monitoring system based on big data according to claim 5, characterized in that, The process by which the data analysis module analyzes power distribution data to obtain abnormal power distribution data includes: The segmented power distribution data network of the power distribution data acquisition model obtains the segmented historical time sequence corresponding to the power distribution data through the power distribution optimization chain; Power distribution data and corresponding power consumption data are obtained through segmented historical time series; threshold ranges for power distribution data and power consumption data are set. Compare the power distribution data and power consumption data with the corresponding power distribution data threshold range and power consumption data threshold range; If both the power distribution data and the power consumption data fall within the power distribution data threshold range and the power consumption data threshold range, then the corresponding power distribution data and power consumption data will be marked as normal power distribution data and normal power consumption data. Conversely, the corresponding power distribution data and power consumption data will be marked as abnormal power distribution data and abnormal power consumption data.

7. The power supply and distribution system operation status monitoring system based on big data according to claim 6, characterized in that, The process by which the level monitoring module acquires the abnormality level of abnormal power distribution data and generates the corresponding abnormality level signal includes: Set the highest abnormal value for abnormal power distribution data and abnormal power consumption data; obtain the ratio of abnormal power distribution and consumption to the highest abnormal value, and mark it as an abnormal data value; If the abnormal data value is less than 60%, the abnormality level will be marked as Level 1 abnormality. If the abnormal data value is greater than 60% but less than 90%, the abnormality level will be marked as Level 2. If the abnormal data value is greater than 90%, the abnormality level will be marked as Level 3. The first-level, second-level, and third-level anomaly levels will generate first-level, second-level, and third-level anomaly signals, respectively.

8. A power supply and distribution system operation status monitoring system based on big data according to claim 7, characterized in that, The process by which the early warning module issues early warnings for abnormal data based on the anomaly level signal includes: The abnormal level signal is sent to the preset management terminal for early warning, abnormal configuration data is obtained, and then processed.

Images