An intelligent monitoring terminal for power grid distribution

Abstract

The present invention discloses an intelligent monitoring terminal for power grid distribution, including a regional data acquisition module, a distribution network data storage library, a distribution monitoring system and a distribution execution module, and the distribution monitoring system is composed of a data classification unit, a data analysis unit and an instruction transmission unit, and the present invention relates to the technical field of power grid distribution. The intelligent monitoring terminal for power grid distribution, by establishing an intelligent monitoring model, extracts historical data set data to realize the analysis of power consumption in various power consumption areas, transmits the analyzed results to the intelligent monitoring model for optimization, and then introduces the intelligent monitoring model in combination with real-time data set data to predict the subsequent power consumption in the power consumption area, generates corresponding results according to the power consumption, effectively predicts the power consumption anomaly in the power consumption area, realizes short-distance dispatch between substations, gives time to find abnormal conditions, and avoids fluctuations in power distribution, so as to realize comprehensive monitoring and management of power distribution in the monitoring area.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid distribution, and in particular to an intelligent monitoring terminal for power grid distribution. Background Art

[0002] With the rapid economic development, the demand for electricity continues to grow and the scale of the power grid continues to expand, which puts higher requirements on the operational safety and power supply stability of the power grid.

[0003] The reference patent name is: an intelligent power distribution monitoring system terminal based on wireless transmission ad hoc network (patent publication number: CN105119373A, patent publication date: 2015-12-02). The intelligent power distribution monitoring system terminal is composed of an intelligent circuit breaker control circuit, a wireless handheld programmer and a wireless communication module. It has an overload protection function for the intelligent circuit breaker, and a wireless communication function between the intelligent power distribution monitoring center and the terminals of multiple distribution stations. The intelligent power distribution monitoring system composed of multiple terminals located in different locations can reduce the installed capacity of the transformer and the number of line overloads while ensuring that the power supply capacity of the existing power grid meets the power demand of users, thereby achieving the good effect of shifting peaks and filling valleys and balancing loads, thereby greatly improving the energy utilization rate of the whole society.

[0004] Based on the description in the above-mentioned document, in the existing power distribution monitoring operation of the power grid, while monitoring multiple distribution areas, some of the distribution areas may have power distribution anomalies, that is, the power distribution is not enough to support the power consumption within the cycle, so that the load overload problem occurs. For the distribution network, even if the problem is discovered and timely power distribution is implemented, there is still a time delay that causes unstable power consumption and even regional power outages. For this reason, the present invention provides an intelligent monitoring terminal for power distribution in the power grid. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides an intelligent monitoring terminal for power grid distribution, which solves the problem that in the existing power grid distribution monitoring operation, while monitoring multiple distribution areas, some distribution areas will have power distribution anomalies, that is, the power distribution is not enough to support the power consumption within a cycle, so that load overload problems occur. For the distribution network, even if the problem is discovered and timely power distribution is implemented, there is still a time delay that causes unstable power consumption and even regional power outages.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent monitoring terminal for power grid distribution, comprising:

[0007] The regional data collection module is used to collect the power consumption data and corresponding power distribution parameter data of the monitored power consumption area;

[0008] The distribution network data repository completes the transmission of collected data through wireless communication technology, stores and saves it through the distribution network data repository, and extracts the historical power consumption data of the monitored power consumption area and the corresponding distribution parameter data;

[0009] The power distribution monitoring system realizes data classification and analysis operations and forms power distribution dispatching instructions, including:

[0010] The data classification unit filters the data to retain the required data and forms historical data sets and real-time data sets;

[0011] The data analysis unit establishes an intelligent monitoring model, extracts historical data sets to analyze the power consumption of various power consumption areas, transmits the analysis results to the intelligent monitoring model for optimization, and then introduces the intelligent monitoring model in combination with the real-time data set data to predict the subsequent power consumption of the power consumption area, and generates corresponding results based on the power consumption;

[0012] An instruction transmission unit generates corresponding instructions according to the analysis results and transmits them to the power distribution execution module;

[0013] The power distribution execution module implements power distribution scheduling operations according to instructions.

[0014] Preferably, the operations of forming the historical data set and the real-time data set in the data classification unit are:

[0015] A1. The required data type is formed into a data template labeled N, and then the collected and extracted data is mapped to the data template N;

[0016] A2. Compare the data content type collected and extracted with the data type in the data template N, and map the data content of the same type into the data template N, so as to extract the required data and eliminate the useless data;

[0017] A3. Finally, the corresponding collected data types in the data template N and the data types extracted based on the database are classified, and summarized into historical data sets and real-time data sets respectively.

[0018] Preferably, the data analysis unit extracts the historical data set data to implement the analysis operation of the power consumption situation of each power consumption area as follows:

[0019] B1. Extract the areas with abnormal conditions in the historical data set, and extract the periodic power consumption data set during power distribution in each power consumption area in sequence. The obtained multiple periodic power consumption data in a single area is marked as P. n ;

[0020] B2, then use the intelligent monitoring model to establish the curve coordinate axis, and convert the periodic power consumption data P nIntroduce a curve coordinate axis to form a change curve;

[0021] B3. Segment the change curve, obtain abnormal prediction points by calculating the power consumption, and determine whether there is an abnormal situation after the abnormal prediction point.

[0022] Preferably, the forming operation of the change curve in B2 is:

[0023] b21. Using the intelligent monitoring model, an X-axis is formed based on the cycle time of power distribution, and a Y-axis is formed based on the total power consumption in the corresponding cycle time, and the starting points of the X-axis and the Y-axis intersect;

[0024] b22, the power data P under the corresponding cycle n Curve coordinate axes are introduced as nodes in sequence, and the nodes are smoothly connected in a periodic time sequence to form a change curve.

[0025] Preferably, the operation of segmenting the change curve in B3 is:

[0026] b31. Calculate the average power distribution in each cycle, and then use a constant function corresponding to the average power distribution value as a dividing line to introduce the curve coordinate axis and intersect the change curve;

[0027] b32, and use the previous intersection point as the split point, and the coordinates are (x, Q 平 ), use the segmentation points to segment the changing curve;

[0028] b33. The curve before the split point is set as the normal curve, and the curve after the split point is set as the over-standard curve, and the total power consumption of the normal curve before the split point is calculated.

[0029] Preferably, the formula for calculating the average power distribution in b31 is:

[0030] Q 平 =(Q 1 +Q 2 +…+Q m ) / m;

[0031] Q 平 is the average power distribution value in a single cycle, (Q 1 +Q 2 +…+Q m ) is the total power distribution in m cycles;

[0032] And the calculation formula for the total power consumption of the normal curve before the split point in b33 is:

[0033] P 前 =Q 平 + (P1 +P 2 +…+P a );

[0034] P 前 is the total power consumption of the normal curve before the split point, a is the number of adjacent cycle nodes before the split point, (P 1 +P 2 +…+P a ) is the total power consumption at the corresponding cycle node before the split point.

[0035] Preferably, the operation of calculating the abnormal prediction point in B3 is:

[0036] C1. Sequentially extract the power consumption values ​​corresponding to the period nodes on the over-standard curve after the split point, and calculate the total power consumption before the corresponding period node;

[0037] C2, then calculate the numerical deviation between the total power consumption and the total power distribution at the current cycle node, and compare it with the power distribution at the subsequent adjacent cycle nodes based on the numerical deviation;

[0038] C3. The abnormal prediction point is determined based on the comparison result, and then the total power consumption at the adjacent cycle nodes after the abnormal prediction point and the total corresponding distribution power are calculated. If the total power consumption at the adjacent cycle nodes after the abnormal prediction point is greater than the total corresponding distribution power, the determined abnormal prediction point is used as the optimization data, otherwise the determined abnormal prediction point is invalid.

[0039] Preferably, the total power consumption before the C1 cycle node is calculated as follows:

[0040] P 后 =P 1 +P 2 +…+P a+1 ;

[0041] P 后 is the total power consumption at the corresponding cycle node after the split point, P a+1 It is the power consumption value corresponding to the adjacent cycle node (a+1) on the over-standard curve after the split point;

[0042] The calculation formula for the numerical deviation in C2 is:

[0043] S=(Q 1 +Q 2 +…+Q a+1 )-P 后 ;

[0044] S is the numerical deviation, and (Q 1 +Q 2 +…+Q a+1) is the total power distribution corresponding to the period node (a+1);

[0045] And the numerical deviation S is related to the power consumption value Q at the subsequent cycle node (a+2) a+2 The comparison produces the following results:

[0046] Result 1: S<Q a+2 , then the period node at (a+1) is the abnormal prediction point;

[0047] Result 2: S ≥ Q a+2 , then the period node at (a+1) is not an abnormal prediction point.

[0048] Preferably, the operation of introducing the intelligent monitoring model into the data analysis unit in combination with the real-time data set data to predict the subsequent power consumption of the power consumption area is:

[0049] D1. The real-time data set data is introduced into the optimized intelligent monitoring model, and a curve is formed synchronously for segmentation operation. The data before segmentation does not need to be analyzed, and the periodic nodes after segmentation implement analysis operations in sequence;

[0050] D2. And correspondingly find out the real-time abnormal prediction point, and when the abnormal prediction point occurs, it is necessary to generate a distribution dispatching instruction.

[0051] Preferably, the setting operation of the power distribution dispatching instruction in D2 is:

[0052] E1. Take the area where the abnormal prediction point currently exists as the center point, extract the distances between other distribution areas and the center point, and sort them in order from near to far;

[0053] E2, and determine whether there are abnormal prediction points in other distribution areas based on the results of the analysis, and extract areas without abnormal prediction points based on the E1 operation;

[0054] E3. Based on the E2 operation, determine whether the numerical deviation of the corresponding cycle node in other areas is greater than the sum of the power consumption value at the subsequent cycle node and the power consumption value at the subsequent cycle node of the area where the abnormal prediction point currently exists. If so, the area that is ranked first among the areas that simultaneously meet the E1 to E3 operations will perform a distribution transfer operation to the current abnormal area.

[0055] The present invention provides an intelligent monitoring terminal for power distribution in a power grid. Compared with the prior art, it has the following beneficial effects:

[0056] (1) The intelligent monitoring terminal for power distribution in the power grid establishes an intelligent monitoring model, extracts data from historical data sets to analyze the power consumption of each power consumption area, transmits the analysis results to the intelligent monitoring model for optimization, and then introduces the intelligent monitoring model in combination with the real-time data set data to predict the subsequent power consumption of the power consumption area. The corresponding results are generated based on the power consumption situation, effectively predicting the power consumption anomaly in the power consumption area, realizing short-distance scheduling between substations, giving time to find abnormal situations, and avoiding fluctuations in power distribution, thereby realizing comprehensive monitoring and management of power distribution in the monitoring area.

[0057] (2) The intelligent monitoring terminal for power distribution in the power grid extracts the areas with abnormal conditions from the historical data set, and then uses the intelligent monitoring model to establish the curve coordinate axis, and introduces the historical data to form a change curve. At the same time, the analysis operation after segmentation is performed according to the change curve to further optimize the intelligent monitoring model, thereby reducing the analysis time of irrelevant periodic nodes, improving the analysis efficiency and analysis accuracy, judging and determining the abnormal prediction points, and realizing the precise optimization of the intelligent monitoring model, so as to improve the accuracy of subsequent real-time data analysis.

[0058] (3) The intelligent monitoring terminal for power distribution of the power grid determines the distance between other distribution areas and the area where the abnormal prediction point currently exists, and then determines whether there are abnormal prediction points in other areas. Finally, it determines whether the value deviation at the corresponding cycle node in other areas is greater than the sum of the power consumption value at the subsequent cycle node and the power consumption value at the subsequent cycle node of the area where the abnormal prediction point currently exists. When the conditions are met, the first eligible area is selected to implement the distribution dispatching instruction, thereby reducing losses while solving abnormalities, giving time for maintenance and abnormality screening, and improving the fault tolerance rate, making the monitoring operation more comprehensive and safe. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 This is a functional block diagram of the power distribution monitoring system of the present invention;

[0060] Figure 2 is an operation flow chart of the data analysis unit of the present invention;

[0061] Figure 3 It is an operation flow chart of the power distribution dispatching instruction of the present invention;

[0062] Figure 4 It is a schematic diagram of the curve coordinate axis of the change curve of the present invention. DETAILED DESCRIPTION

[0063] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0064] See also Figure 1-Figure 4 , the present invention provides two technical solutions:

[0065] Example 1, please refer to Figure 1 , an intelligent monitoring terminal for power grid distribution, comprising:

[0066] The regional data collection module is used to collect the power consumption data and corresponding power distribution parameter data of the monitored power consumption area;

[0067] The distribution network data repository completes the transmission of collected data through wireless communication technology, stores and saves it through the distribution network data repository, and extracts the historical power consumption data of the monitored power consumption area and the corresponding distribution parameter data;

[0068] The power distribution monitoring system realizes data classification and analysis operations and forms power distribution dispatching instructions, including:

[0069] The data classification unit filters the data to retain the required data and forms historical data sets and real-time data sets;

[0070] The data analysis unit establishes an intelligent monitoring model, extracts historical data sets to analyze the power consumption of various power consumption areas, transmits the analysis results to the intelligent monitoring model for optimization, and then introduces the intelligent monitoring model in combination with the real-time data set data to predict the subsequent power consumption of the power consumption area, and generates corresponding results based on the power consumption;

[0071] An instruction transmission unit generates corresponding instructions according to the analysis results and transmits them to the power distribution execution module;

[0072] The power distribution execution module implements power distribution scheduling operations according to instructions.

[0073] Among them, by establishing an intelligent monitoring model and extracting data from historical data sets, the power consumption of each power consumption area is analyzed, and the results of the analysis are transmitted to the intelligent monitoring model for optimization. Then, the intelligent monitoring model is introduced in combination with the real-time data set data to predict the subsequent power consumption of the power consumption area. The corresponding results are generated according to the power consumption situation, and the power consumption anomalies in the power consumption area are effectively predicted, and short-distance scheduling between substations is realized, giving time to find abnormal situations and avoiding fluctuations in power distribution, so as to realize comprehensive monitoring and management of power distribution and power consumption in the monitoring area.

[0074] The power distribution execution module is composed of overhead lines, poles, cables, distribution transformers, switchgear, reactive compensation capacitors and other power distribution equipment and ancillary facilities. It mainly implements the operation of power distribution transmission according to instructions, and the specific implementation of power distribution is an existing mature technology and will not be elaborated in detail.

[0075] In the embodiment of the present invention, the operations of forming the historical data set and the real-time data set in the data classification unit are:

[0076] A1. The required data type is formed into a data template labeled N, and then the collected and extracted data is mapped to the data template N;

[0077] A2. Compare the data content type collected and extracted with the data type in the data template N, and map the data content of the same type into the data template N, so as to extract the required data and eliminate the useless data;

[0078] A3. Finally, the corresponding collected data types in the data template N and the data types extracted based on the database are classified, and summarized into historical data sets and real-time data sets respectively.

[0079] See also Figure 2 In the embodiment of the present invention, the data analysis unit extracts the historical data set data to implement the analysis operation of the power consumption situation of each power consumption area as follows:

[0080] B1. Extract the areas with abnormal conditions in the historical data set, and extract the periodic power consumption data set during power distribution in each power consumption area in sequence. The obtained multiple periodic power consumption data in a single area is marked as P. n ;

[0081] B2, then use the intelligent monitoring model to establish the curve coordinate axis, and convert the periodic power consumption data P n Introduce a curve coordinate axis to form a change curve;

[0082] B3. Segment the change curve, obtain abnormal prediction points by calculating the power consumption, and determine whether there is an abnormal situation after the abnormal prediction point.

[0083] See also Figure 4 In the embodiment of the present invention, the forming operation of the change curve in B2 is:

[0084] b21. Using the intelligent monitoring model, an X-axis is formed based on the cycle time of power distribution, and a Y-axis is formed based on the total power consumption in the corresponding cycle time, and the starting points of the X-axis and the Y-axis intersect;

[0085] b22, the power data P under the corresponding cycle nCurve coordinate axes are introduced as nodes in sequence, and the nodes are smoothly connected in a periodic time sequence to form a change curve.

[0086] In the embodiment of the present invention, the operation of segmenting the change curve in B3 is:

[0087] b31. Calculate the average power distribution in each cycle, and then use a constant function corresponding to the average power distribution value as a dividing line to introduce the curve coordinate axis and intersect the change curve;

[0088] b32, and use the previous intersection point as the split point, and the coordinates are (x, Q 平 ), use the segmentation points to segment the changing curve;

[0089] b33. The curve before the split point is set as the normal curve, and the curve after the split point is set as the over-standard curve, and the total power consumption of the normal curve before the split point is calculated.

[0090] In the embodiment of the present invention, the formula for calculating the average power distribution in b31 is:

[0091] Q 平 =(Q 1 +Q 2 +…+Q m ) / m;

[0092] Q 平 is the average power distribution value in a single cycle, (Q 1 +Q 2 +…+Q m ) is the total power distribution in m cycles;

[0093] And the calculation formula for the total power consumption of the normal curve before the split point in b33 is:

[0094] P 前 =Q 平 + (P 1 +P 2 +…+P a );

[0095] P 前 is the total power consumption of the normal curve before the split point, a is the number of adjacent cycle nodes before the split point, (P 1 +P 2 +…+P a ) is the total power consumption at the corresponding cycle node before the split point.

[0096] In the embodiment of the present invention, the operation of calculating the abnormal prediction point in B3 is:

[0097] C1. Sequentially extract the power consumption values ​​corresponding to the period nodes on the over-standard curve after the split point, and calculate the total power consumption before the corresponding period node;

[0098] C2, then calculate the numerical deviation between the total power consumption and the total power distribution at the current cycle node, and compare it with the power distribution at the subsequent adjacent cycle nodes based on the numerical deviation;

[0099] C3. The abnormal prediction point is determined based on the comparison result, and then the total power consumption at the adjacent cycle nodes after the abnormal prediction point and the total corresponding distribution power are calculated. If the total power consumption at the adjacent cycle nodes after the abnormal prediction point is greater than the total corresponding distribution power, the determined abnormal prediction point is used as the optimization data, otherwise the determined abnormal prediction point is invalid.

[0100] Among them, by extracting the areas with abnormal conditions in the historical data set, and then using the intelligent monitoring model to establish the curve coordinate axis, and introducing historical data to form a change curve, the analysis operation after segmentation is realized according to the change curve to further optimize the intelligent monitoring model, thereby reducing the analysis time of irrelevant periodic nodes, improving analysis efficiency and analysis accuracy, judging and determining abnormal prediction points, and realizing accurate optimization of the intelligent monitoring model, so as to improve the accuracy of subsequent real-time data analysis.

[0101] In the embodiment of the present invention, the total power consumption before the C1 period node is calculated as follows:

[0102] P 后 =P 1 +P 2 +…+P a+1 ;

[0103] P 后 is the total power consumption at the corresponding cycle node after the split point, P a+1 It is the power consumption value corresponding to the adjacent cycle node (a+1) on the over-standard curve after the split point;

[0104] The calculation formula for the numerical deviation in C2 is:

[0105] S=(Q 1 +Q 2 +…+Q a+1 )-P 后 ;

[0106] S is the numerical deviation, and (Q 1 +Q 2 +…+Q a+1 ) is the total power distribution corresponding to the period node (a+1);

[0107] And the numerical deviation S is related to the power consumption value Q at the subsequent cycle node (a+2)a+2 The comparison produces the following results:

[0108] Result 1: S<Q a+2 , then the period node at (a+1) is the abnormal prediction point;

[0109] Result 2: S ≥ Q a+2 , then the period node at (a+1) is not an abnormal prediction point.

[0110] In the embodiment of the present invention, the operation of introducing the intelligent monitoring model into the data analysis unit in combination with the real-time data set data to predict the subsequent power consumption of the power consumption area is:

[0111] D1. The real-time data set data is introduced into the optimized intelligent monitoring model, and a curve is formed synchronously for segmentation operation. The data before segmentation does not need to be analyzed, and the periodic nodes after segmentation implement analysis operations in sequence;

[0112] D2. And find out the real-time abnormal prediction point accordingly, and when the abnormal prediction point occurs, it is necessary to generate a distribution dispatch instruction.

[0113] See also Figure 3 In the embodiment of the present invention, the setting operation of the power distribution dispatching instruction in D2 is:

[0114] E1. Take the area where the abnormal prediction point currently exists as the center point, extract the distances between other distribution areas and the center point, and sort them in order from near to far;

[0115] E2, and determine whether there are abnormal prediction points in other distribution areas based on the results of the analysis, and extract areas without abnormal prediction points based on the E1 operation;

[0116] E3. Based on the E2 operation, determine whether the numerical deviation of the corresponding cycle node in other areas is greater than the sum of the power consumption value at the subsequent cycle node and the power consumption value at the subsequent cycle node of the area where the abnormal prediction point currently exists. If so, the area that is ranked first among the areas that simultaneously meet the E1 to E3 operations will perform a distribution transfer operation to the current abnormal area.

[0117] Among them, by determining the distance between other distribution areas and the current area with abnormal prediction points, and then determining whether there are abnormal prediction points in other areas, and finally determining whether the numerical deviation under the corresponding cycle node in other areas is greater than the sum of the power consumption values ​​under subsequent cycle nodes and the power consumption values ​​under subsequent cycle nodes of the area with the current abnormal prediction point, after the conditions are met, the first eligible area is selected to implement the distribution dispatching instruction, thereby reducing losses while solving anomalies, giving time for maintenance and anomaly screening, and improving the fault tolerance rate, making the monitoring operation more comprehensive and safe.

[0118] The difference between the second embodiment and the first embodiment is that the monitoring and management operation of the same power consumption area is realized by using the existing intelligent monitoring terminal for power grid distribution and the intelligent monitoring terminal for power grid distribution of the present invention, and the abnormal situation generated during the monitoring process is discovered, and the efficiency of discovering the abnormal situation is recorded. The specific results are shown in Table 1:

[0119] Table 1 Situation record table

[0120] Whether an exception occurs Abnormal situations Processing Existing intelligent monitoring terminals yes Generate an exception Power outage and timely repair Intelligent monitoring terminal of the present invention no Predicting anomalies No impact and repair

[0121] To sum up, by adopting the intelligent monitoring terminal for power grid distribution of the present invention to realize the monitoring and management operations of power consumption areas and distribution stations, it is possible to effectively predict abnormal situations, and send abnormal signals or instructions in advance to realize distribution scheduling and personnel repair and processing operations, thereby avoiding the occurrence of abnormalities, and making the distribution of power consumption areas balanced, realizing comprehensive monitoring and management operations.

[0122] Meanwhile, the contents not described in detail in this specification belong to the prior art known to those skilled in the art.

[0123] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0124] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent monitoring terminal for power distribution, characterized in that: include: The regional data collection module is used to collect the power consumption data and corresponding power distribution parameter data of the monitored power consumption area; The distribution network data repository completes the transmission of collected data through wireless communication technology, stores and saves it through the distribution network data repository, and extracts the historical power consumption data of the monitored power consumption area and the corresponding distribution parameter data; The power distribution monitoring system realizes data classification and analysis operations and forms power distribution dispatching instructions, including: The data classification unit filters the data to retain the required data and forms historical data sets and real-time data sets; The data analysis unit establishes an intelligent monitoring model, extracts historical data sets to analyze the power consumption of various power consumption areas, transmits the analysis results to the intelligent monitoring model for optimization, and then introduces the intelligent monitoring model in combination with the real-time data set data to predict the subsequent power consumption of the power consumption area, and generates corresponding results based on the power consumption; An instruction transmission unit generates corresponding instructions according to the analysis results and transmits them to the power distribution execution module; The power distribution execution module implements power distribution dispatching operations according to instructions; The data analysis unit extracts the historical data set data to implement the analysis operation of the power consumption situation of each power consumption area as follows: B1. Extract the areas with abnormal conditions in the historical data set, and extract the periodic power consumption data set during power distribution in each power consumption area in sequence. The obtained multiple periodic power consumption data in a single area is marked as P. n ; B2, then use the intelligent monitoring model to establish the curve coordinate axis, and convert the periodic power consumption data P n Introduce a curve coordinate axis to form a change curve; B3, segmenting the change curve, and obtaining the abnormal prediction point by calculating the power consumption, and determining whether there is an abnormal situation after the abnormal prediction point; The forming operation of the change curve in B2 is: b21. Using the intelligent monitoring model, an X-axis is formed based on the cycle time of power distribution, and a Y-axis is formed based on the total power consumption in the corresponding cycle time, and the starting points of the X-axis and the Y-axis intersect; b22, the power data P under the corresponding cycle n The curve coordinate axes are introduced as nodes in sequence, and the nodes are smoothly connected by curves in the order of periodic time to form a change curve; The operation of segmenting the change curve in B3 is: b31. Calculate the average power distribution in each cycle, and then use a constant function corresponding to the average power distribution value as a dividing line to introduce the curve coordinate axis and intersect the change curve; b32, and use the previous intersection point as the split point, and the coordinates are (x, Q 平 ), using segmentation points to segment the change curve; b33. The curve before the split point is set as the normal curve, and the curve after the split point is set as the over-standard curve, and the total power consumption of the normal curve before the split point is calculated; The operation of calculating the abnormal prediction point in B3 is: C1. Sequentially extract the power consumption values ​​corresponding to the period nodes on the over-standard curve after the split point, and calculate the total power consumption before the corresponding period node; C2, then calculate the numerical deviation between the total power consumption and the total power distribution at the current cycle node, and compare it with the power distribution at the subsequent adjacent cycle nodes based on the numerical deviation; C3. The abnormal prediction point is determined based on the comparison result, and then the total power consumption at the adjacent cycle nodes after the abnormal prediction point and the total corresponding distribution power are calculated. If the total power consumption at the adjacent cycle nodes after the abnormal prediction point is greater than the total corresponding distribution power, the determined abnormal prediction point is used as the optimization data, otherwise the determined abnormal prediction point is invalid.

2. The intelligent monitoring terminal for power distribution according to claim 1, characterized in that: The operations of forming the historical data set and the real-time data set in the data classification unit are: A1. The required data type is formed into a data template labeled N, and then the collected and extracted data is mapped to the data template N; A2. Compare the data content type collected and extracted with the data type in the data template N, and map the data content of the same type into the data template N, so as to extract the required data and eliminate the useless data; A3. Finally, the corresponding collected data types in the data template N and the data types extracted based on the database are classified, and summarized into historical data sets and real-time data sets respectively.

3. The intelligent monitoring terminal for power distribution according to claim 1, characterized in that: The formula for calculating the average power distribution in b31 is: Q 平 =(Q1+Q2+…+Q m ) / m; Q 平 is the average power distribution value in a single cycle, (Q1+Q2+…+Q m ) is the total power distribution in m cycles; And the calculation formula for the total power consumption of the normal curve before the split point in b33 is: P 前 =Q 平 +(P1+P2+…+P a ); P 前 is the total power consumption of the normal curve before the split point, a is the number of adjacent cycle nodes before the split point, (P1+P2+…+P a ) is the total power consumption at the corresponding cycle node before the split point.

4. The intelligent monitoring terminal for power distribution according to claim 1, characterized in that: The total power consumption before the C1 cycle node is calculated as follows: P 后 =P1+P2+…+P a+1 ; P 后 is the total power consumption at the corresponding cycle node after the split point, P a+1 It is the power consumption value corresponding to the adjacent period node (a+1) on the over-standard curve after the split point; The calculation formula for the numerical deviation in C2 is: S=(Q1+Q2+…+Q a+1 )-P 后 ; S is the numerical deviation, and (Q1+Q2+…+Q a+1 ) is the total power distribution corresponding to the period node (a+1); And the numerical deviation S is related to the power consumption value Q at the subsequent cycle node (a+2) a+2 The comparison produces the following results: Result 1: S<Q a+2 , then the period node at (a+1) is the abnormal prediction point; Result 2: S ≥ Q a+2 , then the period node at (a+1) is not an abnormal prediction point.

5. The intelligent monitoring terminal for power distribution in a power grid according to claim 1, characterized in that: The operation of the data analysis unit combining the real-time data set data with the intelligent monitoring model to predict the subsequent power consumption of the power consumption area is: D1. The real-time data set data is introduced into the optimized intelligent monitoring model, and a curve is formed synchronously for segmentation operation. The data before segmentation does not need to be analyzed, and the periodic nodes after segmentation implement analysis operations in sequence; D2. And find out the real-time abnormal prediction point accordingly, and when the abnormal prediction point occurs, it is necessary to generate a distribution dispatch instruction.

6. The intelligent monitoring terminal for power distribution in a power grid according to claim 5, characterized in that: The setting operation of the power distribution dispatching instruction in D2 is: E1. Take the area where the abnormal prediction point currently exists as the center point, extract the distances between other distribution areas and the center point, and sort them in order from near to far; E2, and determine whether there are abnormal prediction points in other distribution areas based on the results of the analysis, and extract areas without abnormal prediction points based on the E1 operation; E3. Based on the E2 operation, determine whether the numerical deviation of the corresponding cycle node in other areas is greater than the sum of the power consumption value at the subsequent cycle node and the power consumption value at the subsequent cycle node of the area where the abnormal prediction point currently exists. If so, the area that is ranked first among the areas that simultaneously meet the E1 to E3 operations will perform a distribution transfer operation to the current abnormal area.

Images