Power grid equipment monitoring and early warning method based on big data

Abstract

The invention provides a power grid equipment monitoring and early warning method based on big data, and the method comprises the steps: determining a grid region type corresponding to each grid region according to a target region type of each grid region in a target region; determining a grid feature vector corresponding to each grid region according to the electrical parameters of the plurality of electrical devices in each grid region; clustering the grid feature vectors corresponding to a plurality of grid regions with the same grid region type and the historical feature vectors to obtain a plurality of feature vector class groups; determining a target device state identifier of each grid feature vector according to a historical device state identifier of a historical feature vector included in each feature vector class group; and outputting the grid feature vector and alarm information corresponding to the target equipment state identifier representing that the power grid state is an abnormal state, so as to prompt a worker to carry out abnormity screening on the electrical equipment in the abnormal power grid state, and ensure the use safety of the electrical equipment in the target area.

Description

Background Art

[0002] Grid equipment is an electrical equipment connected to the power grid. Monitoring the power parameters of grid equipment is a means of verifying the safety of power consumption of grid equipment. Currently, the inspection results of the safe operation of grid equipment are achieved through real-time monitoring of various power parameters of each grid equipment. When the instantaneous value of a certain power parameter or multiple power parameters with a correlation or the detection value within a preset monitoring time period is not within the preset normal range, an alarm is sent to the control center of the grid equipment, and a corresponding emergency strategy is made to ensure that the abnormally operating grid equipment is powered off in time and does not hinder the operation of other grid equipment. However, this method of real-time monitoring of each power parameter will occupy a large amount of operating memory in the control center. The amount of data processed in real time is too large, which will affect the control center's processing of other data. Summary of the invention

[0003] In view of the above technical problems, the technical solution adopted by the present invention is:

[0004] According to one aspect of the present application, a method for monitoring and early warning of power grid equipment based on big data is provided, comprising the following steps:

[0005] Step S100, performing rasterization processing on the target area to obtain a plurality of raster areas corresponding to the target area;

[0006] Step S200, determining the grid area type corresponding to each grid area according to the target area type of each grid area in the target area;

[0007] Step S300, determining a grid feature vector corresponding to each grid area according to electrical parameters of a number of electrical devices in each grid area;

[0008] Step S400: clustering grid feature vectors corresponding to a plurality of grid regions of the same grid region type and historical feature vectors corresponding to the plurality of grid regions to obtain a plurality of feature vector clusters; the historical feature vectors are obtained based on electrical parameters of a plurality of electrical devices in the grid regions within a historical period; each historical feature vector corresponds to a historical device status identifier;

[0009] Step S500, determining the target device state identifier corresponding to each grid feature vector according to the historical device state identifier corresponding to the historical feature vector included in each feature vector group;

[0010] Step S600: outputting a grid feature vector corresponding to a target device state identifier representing that a power grid state of an electrical device in a grid area is in an abnormal state, and alarm information including an area identifier of the grid area corresponding to the grid feature vector.

[0011] In an exemplary embodiment of the present application, step S100 includes:

[0012] Step S110 , dividing the target area into grids according to a preset grid size to obtain a plurality of grid areas corresponding to the target area; wherein the size of each grid area is the preset grid size.

[0013] In an exemplary embodiment of the present application, step S200 includes:

[0014] Step S210: according to the target area types corresponding to the target area, the target area is divided into types to obtain a plurality of type sub-areas corresponding to the target area; each type sub-area corresponds to a unique target area type;

[0015] Step S220: Obtain the region identifier of each grid region to obtain a first region identifier list A=(A1, A2, ..., A i ,...,A j ), where i = 1, 2, ..., j, j is the number of grid regions, A i is the region identifier of the i-th grid region;

[0016] Step S230: Obtain the region identifier of each type of sub-region, and obtain a second region identifier list B=(B1, B2, ..., B p ,...,B q ), where p = 1, 2, ..., q, q is the number of sub-regions of the type; B p is the region identifier of the p-th type sub-region;

[0017] Step S240: traverse the first area identifier list A and the second area identifier list B. If B p The corresponding type sub-area is in A i The area in the corresponding grid area is i If the area ratio of the corresponding grid area is greater than a preset area ratio threshold, the target area type corresponding to the p-th type sub-area is determined as the grid area type corresponding to the i-th grid area;

[0018] Step S250: If all sub-areas of the same type are in A i The area in the corresponding grid area is i If the proportions of the areas of the corresponding grid regions are all less than or equal to the preset area ratio threshold, the preset key region type is determined as the grid region type corresponding to the i-th grid region.

[0019] In an exemplary embodiment of the present application, step S300 includes:

[0020] Step S310: Obtain parameter characteristics of electrical parameters of several electrical devices in each grid area, and obtain a grid feature vector group B = (B1, B2, ..., B i ,...,B j ), where B i is the grid feature vector corresponding to the i-th grid area;

[0021] B i =(B i1 ,B i2 ,...,B ir ,...,B is ), where r = 1, 2, ..., s, and s is the number of types of electrical equipment that are preset; B ir is a list of electrical parameters of the rth type of electrical equipment in the i-th grid area;

[0022] B ir =(B ir1 ,B ir2 ,...,B irt ,...,B iru ), wherein t = 1, 2, ..., u, and u is the number of preset electrical parameters; B irt is a parameter feature list of the tth electrical parameter of the rth type of electrical equipment in the i-th grid area;

[0023] B irt =(B irt1 ,B irt2 ,...,B irtv ,...,B irtw ); wherein v = 1, 2, ..., w; w is the number of parameter characteristics of the preset electrical parameters; B irtv is the vth parameter feature of the tth electrical parameter of the rth type electrical equipment in the ith grid area.

[0024] In an exemplary embodiment of the present application, step S400 includes:

[0025] Step S410: De-duplicate the grid region types corresponding to the plurality of grid regions to obtain a de-duplicate grid region type list C = (C1, C2, ..., C x ,...,C y ), wherein x = 1, 2, ..., y; y is the number of deduplicated grid region types obtained after deduplication of several grid region types; C x The type identifier of the xth deduplicated raster region type;

[0026] Step S420: Get the grid area type as C xThe grid feature vectors of several grid regions of the corresponding deduplicated grid region type are obtained to obtain the grid feature vector list D corresponding to the xth deduplicated grid region type x =(D x1 ,D x2 ,...,D xz ,...,D xh(x) ); where z = 1, 2, ..., h(x); h(x) is the grid region type of C x The number of grid regions of the corresponding grid region type after deduplication; D xz For grid area type C x The grid feature vector of the zth grid region of the corresponding deduplicated grid region type;

[0027] Step S430: Get the grid area type as C x The historical feature vectors of the corresponding grid region types after deduplication are obtained to obtain the historical feature vector list set E corresponding to the x-th grid region type after deduplication. x =(E x1 ,E x2 ,...,E xz ,...,E xh(x) ), where E xz For grid area type C x The list of historical feature vectors corresponding to the zth grid area of ​​the corresponding deduplicated grid area type;

[0028] E xz =(E xz1 ,E xz2 ,...,E xza ,...,E xzb(xz) ); where a=1,2,...,b(xz); b(xz) is the grid region type of C x The number of historical feature vectors corresponding to the zth grid area of ​​the corresponding deduplicated grid area type; E xza For grid area type C x The a-th historical feature vector of the z-th grid region of the corresponding deduplicated grid region type;

[0029] Step S440: Calculate the grid feature vector list D x A list of several grid feature vectors and historical feature vectors in E x Several historical feature vectors in are mixed and clustered to obtain several feature vector clusters.

[0030] In an exemplary embodiment of the present application, a number of historical feature vectors corresponding to the i-th grid area are determined by the following steps:

[0031] Step S001: Obtain parameter characteristics of electrical parameters of several electrical devices in the i-th grid area in several historical periods, and obtain a historical characteristic vector group F corresponding to the i-th grid area. i =(F i1 ,F i2 ,...,F im ,...,F in ), where m = 1, 2, ..., n, and n is the number of historical periods; F im is the historical feature vector corresponding to the i-th grid area in the m-th historical period;

[0032] F im =(F im1 ,F im2 ,...,F imr ,...,F ims ), where F imr is a list set of electrical parameters of the rth type of electrical equipment in the i-th grid area in the m-th historical period;

[0033] F imr =(F imr1 ,F imr2 ,...,F imrt ,...,F imru ), where F imrt is a parameter feature list of the tth electrical parameter of the rth type of electrical equipment in the i-th grid area in the m-th historical period;

[0034] F imrt =(F imrt1 ,F imrt2 ,...,F imrtv ,...,F imrtw ), where F imrtv is the vth parameter feature of the tth electrical parameter of the rth type of electrical equipment in the ith grid area in the mth historical period.

[0035] In an exemplary embodiment of the present application, the historical device state identifier of the historical feature vector is determined by the following steps:

[0036] Step S002: historical feature vector list set E x Clustering of several historical feature vectors in the grid to obtain the grid area type C x Several historical feature vector clusters corresponding to the raster regions of the corresponding deduplicated raster region types;

[0037] Step S003: Determine the device status identifier corresponding to each historical feature vector group according to the preset grid status judgment rule;

[0038] Step S004: Determine the device state identifier corresponding to each historical feature vector group as the historical device state identifier of each historical feature vector included in the historical feature vector group;

[0039] Wherein, when the historical device state identifier is a first state identifier, it is characterized that the power grid state of the electrical equipment in the grid area corresponding to the historical device state identifier during the historical period corresponding to the historical device state identifier is a normal state; when the historical device state identifier is a second state identifier, it is characterized that the power grid state of the electrical equipment in the grid area corresponding to the historical device state identifier during the historical period corresponding to the historical device state identifier is an abnormal state;

[0040] Step S005: If there is a historical feature vector that does not belong to any historical feature vector group, the historical device state identifier of the historical feature vector is determined as the second state identifier.

[0041] In an exemplary embodiment of the present application, step S500 includes:

[0042] Step S510: Get C x The number of abnormal historical feature vectors included in each feature vector cluster of the corresponding deduplicated grid region type to obtain the abnormal historical feature vector quantity list G x =(G x1 ,G x2 ,...,G xc ,...,G xd(x) ), where c = 1, 2, ..., d(x); d(x) is C x The number of feature vector clusters of the corresponding raster region type after deduplication; G xc C x The number of abnormal historical feature vectors included in the c-th feature vector class group of the corresponding deduplicated grid region type; wherein the abnormal historical feature vector is a historical feature vector whose historical device state identifier is the second state identifier;

[0043] Step S520: Get C x The total number of feature vectors included in each feature vector group of the corresponding deduplicated grid region type is obtained to obtain a feature vector quantity list H x =(H x1 ,H x2 ,...,H xc ,...,H xd(x) ), where H xc C xThe total number of feature vectors included in the cth feature vector group of the corresponding grid region type after deduplication; the total number of feature vectors included in the feature vector group is the sum of the number of grid feature vectors and historical feature vectors included in the feature vector group;

[0044] Step S530: If G xc / H xc If it is greater than the preset percentage threshold, C x The target device state identifier of the grid feature vector in the cth feature vector cluster of the corresponding grid region type after deduplication is determined as the second state identifier; otherwise, step S540 is executed;

[0045] Step S540: Get C x The number of normal historical feature vectors included in each feature vector group of the corresponding deduplicated grid region type to obtain a list of normal historical feature vectors Q x =(Q x1 ,Q x2 ,...,Q xc ,...,Q xd(x) ), where Q xc C x The number of normal historical feature vectors included in the cth feature vector class group of the corresponding deduplicated grid region type; wherein the normal historical feature vector is a historical feature vector whose historical device state identifier is the first state identifier;

[0046] Step S550: If Q xc / H xc If it is greater than the preset percentage threshold, C x The target device state identifier of the grid feature vector in the cth feature vector class group of the corresponding grid region type after deduplication is determined as the first state identifier;

[0047] Step S560: If there is a grid feature vector that does not belong to any feature vector group, the target device state identifier of the grid feature vector is determined as the second state identifier.

[0048] In an exemplary embodiment of the present application, step S550 further includes:

[0049] Step S551: If Q xc / H xc If the percentage is less than or equal to the preset threshold, C x The target device state identifier of the grid feature vector in the cth feature vector class group of the corresponding grid region type after deduplication is determined as the pending state identifier;

[0050] Step S552: inputting the grid feature vector with the target device state identified as the pending state identification into a preset precise analysis model to obtain a corresponding power grid state analysis result;

[0051] Step S553: ​​if the grid state analysis result indicates that the grid state is normal, the pending state identifier is determined as the first state identifier; if the grid state analysis result indicates that the grid state is abnormal, the pending state identifier is determined as the second state identifier.

[0052] In an exemplary embodiment of the present application, step S600 includes:

[0053] Step S610, traversing each grid feature vector, if the target device state identifier of any grid feature vector is the second state identifier, then determining the grid feature vector as an abnormal grid feature vector;

[0054] Step S620, determining the grid area corresponding to the abnormal grid feature vector as the abnormal grid area;

[0055] Step S630: output each abnormal grid feature vector and the alarm information of the region identification containing the abnormal grid region.

[0056] According to one aspect of the present application, a non-transitory computer-readable storage medium is provided, in which at least one instruction or at least one program is stored. The at least one instruction or the at least one program is loaded and executed by a processor to implement the aforementioned big data-based power grid equipment monitoring and early warning method.

[0057] According to one aspect of the present application, an electronic device is provided, including a processor and the aforementioned non-transitory computer-readable storage medium.

[0058] The present invention has at least the following beneficial effects:

[0059] The big data-based power grid equipment monitoring and early warning method of the present invention performs rasterization processing on the target area to obtain several grid areas corresponding to the target area, determines the grid area type corresponding to each grid area according to the target area type of each grid area in the target area, and then determines the grid feature vector corresponding to each grid area according to the electrical parameters of several electrical equipment in each grid area. The grid feature vector is used to represent the electrical parameter characteristics of the electrical equipment in the corresponding grid area, and clusters the grid feature vectors corresponding to several grid areas of the same grid area type and the historical feature vectors corresponding to the several grid areas to obtain several feature vector clusters. Since the electrical parameter characteristics of the electrical equipment corresponding to the several feature vectors in each feature vector cluster are similar, it can be considered that the grid states of the electrical equipment in the grid areas corresponding to the several feature vectors in the feature vector cluster are similar. Therefore, according to the historical equipment status identification corresponding to the historical feature vectors included in each feature vector group, the target equipment status identification corresponding to each grid feature vector is determined, and the grid feature vector corresponding to the target equipment status identification representing that the power grid state of the electrical equipment in the grid area is abnormal is output, and the alarm information including the area identification of the grid area corresponding to the grid feature vector is output. By grid-dividing the target area and collecting electrical parameters for each grid area, the corresponding grid feature vector is determined, and it is clustered with the historical feature vector to determine the target equipment status identification corresponding to the grid feature vector, and the staff is prompted to perform abnormal screening for abnormal electrical parameters on all electrical equipment in the grid area where the electrical equipment with abnormal power grid state is located, while reducing the processing amount of the electrical parameters of the electrical equipment, the safe use of the electrical equipment in the target area is ensured. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0061] Figure 1 A flowchart of a big data-based power grid equipment monitoring and early warning method provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0062] 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0063] This application proposes a big data-based power grid equipment monitoring and early warning method, such as Figure 1 As shown, the following steps are included:

[0064] Step S100, performing rasterization processing on the target area to obtain a plurality of raster areas corresponding to the target area;

[0065] The target area is the area where the power grid equipment is monitored, that is, the power grid equipment in the target area is monitored and warned to ensure the power safety of the power grid equipment in the target area.

[0066] Further, as a feasible embodiment, step S100 includes step S110:

[0067] Step S110, dividing the target area into grids according to a preset grid size to obtain a plurality of grid areas corresponding to the target area;

[0068] The size of each grid area is a preset grid size (eg, the area of ​​each grid area is one kilometer by one kilometer), and the method for dividing the target area into grids can adopt the existing grid processing method.

[0069] Step S200, determining the grid area type corresponding to each grid area according to the target area type of each grid area in the target area;

[0070] The target area type can be a residential area, a commercial area, an industrial area, a transportation area, etc. The target area type can be determined by the staff conducting a field survey of the target area, that is, the staff conducts a field survey of the target area in advance, determines the type sub-areas of each target area type in the target area, and then marks each type sub-area with the corresponding target area type.

[0071] Further, step S200 includes steps S210 to S250:

[0072] Step S210: classify the target area according to the target area types corresponding to the target area, so as to obtain a plurality of sub-areas of different types corresponding to the target area;

[0073] Each type of sub-area corresponds to a unique target area type. For example, if there are four type of sub-areas in the target area (A, B, C, and D respectively), then each type of sub-area corresponds to a unique target area type (for example, the target area type corresponding to type sub-area A is a residential area, the target area type corresponding to type sub-area B is an industrial area, the target area type corresponding to type sub-area C is a transportation area, and the target area type corresponding to type sub-area D is a commercial area).

[0074] Step S220: Obtain the region identifier of each grid region to obtain a first region identifier list A=(A1, A2, ..., A i ,...,A j ), where i = 1, 2, ..., j, j is the number of grid regions, A i is the region identifier of the i-th grid region;

[0075] Step S230: Obtain the region identifier of each type of sub-region, and obtain a second region identifier list B=(B1, B2, ..., B p ,...,B q ), where p = 1, 2, ..., q, q is the number of sub-regions of the type; B p is the region identifier of the p-th type sub-region;

[0076] Step S240: traverse the first area identifier list A and the second area identifier list B. If B p The corresponding type sub-area is in A i The area in the corresponding grid area is i If the area ratio of the corresponding grid area is greater than a preset area ratio threshold, the target area type corresponding to the p-th type sub-area is determined as the grid area type corresponding to the i-th grid area;

[0077] If B p The corresponding type sub-area is in A i The area in the corresponding grid area is i If the area ratio of the corresponding grid area is greater than the preset area ratio threshold (the preset area ratio threshold can be set to 90%), then A is considered i Most of the corresponding grid area belongs to B p The corresponding type sub-region, then the grid region type corresponding to the i-th grid region is determined to be B p The target region type of the corresponding type subregion.

[0078] Step S250: If all sub-areas of the same type are in A i The area in the corresponding grid area is iIf the proportions of the areas of the corresponding grid regions are all less than or equal to the preset area ratio threshold, the preset key region type is determined as the grid region type corresponding to the i-th grid region.

[0079] If all types of sub-areas are in A i The area in the corresponding grid area is i If the area ratio of the corresponding grid area is less than or equal to the preset area ratio threshold, it means that A i If the corresponding grid area is composed of boundary areas of multiple types of sub-areas, the preset key area type (such as the boundary area) can be determined as the grid area type corresponding to the i-th grid area.

[0080] Step S300, determining a grid feature vector corresponding to each grid area according to electrical parameters of a number of electrical devices in each grid area;

[0081] Further, as a feasible embodiment, step S300 includes step S310:

[0082] Step S310: Obtain parameter characteristics of electrical parameters of several electrical devices in each grid area, and obtain a grid feature vector group B = (B1, B2, ..., B i ,...,B j ), where B i is the grid feature vector corresponding to the i-th grid area;

[0083] B i =(B i1 ,B i2 ,...,B ir ,...,B is ), where r = 1, 2, ..., s, and s is the number of types of electrical equipment that are preset; B ir is a list of electrical parameters of the rth type of electrical equipment in the i-th grid area;

[0084] B ir =(B ir1 ,B ir2 ,...,B irt ,...,B iru ), wherein t = 1, 2, ..., u, and u is the number of preset electrical parameters; B irt is a parameter feature list of the tth electrical parameter of the rth type of electrical equipment in the i-th grid area;

[0085] B irt =(B irt1 ,B irt2 ,...,B irtv ,...,B irtw); wherein v = 1, 2, ..., w; w is the number of parameter characteristics of the preset electrical parameters; B irtv is the vth parameter feature of the tth electrical parameter of the rth type electrical equipment in the ith grid area.

[0086] The types of electrical equipment can be divided according to the power consumption (such as small-power electrical equipment, medium-power electrical equipment, and high-power electrical equipment), or according to the type of electricity consumption (such as household electrical equipment, factory electrical equipment, and commercial electrical equipment). The specific types of classification can be determined by the actual needs of the staff.

[0087] The electrical parameters of electrical equipment can be output power, operating voltage, operating current, power consumption frequency, power consumption time, etc.

[0088] The parameter characteristics of the electrical parameters of the electrical equipment may be the mean value, peak value, valley value, variance, etc. corresponding to the electrical parameters.

[0089] Step S400, clustering grid feature vectors corresponding to a plurality of grid regions of the same grid region type and historical feature vectors corresponding to the plurality of grid regions to obtain a plurality of feature vector clusters;

[0090] Clustering the grid feature vectors corresponding to several grid areas of the same grid area type and the historical feature vectors corresponding to the several grid areas can ensure the subsequent accurate judgment of the power usage status of the electrical equipment. Since the grid areas corresponding to the clustered feature vectors (including the grid feature vectors and the historical feature vectors) are of the same grid area type (such as residential areas), it can be considered that the power usage habits, power usage time, etc. of the electrical equipment in these grid areas are similar. Therefore, by clustering the grid feature vectors and the historical feature vectors of these grid areas, the judgment error of the power usage status of the electrical equipment can be reduced.

[0091] Further, step S400 includes step S410-step S440:

[0092] Step S410: De-duplicate the grid region types corresponding to the plurality of grid regions to obtain a de-duplicate grid region type list C = (C1, C2, ..., C x ,...,C y ), wherein x = 1, 2, ..., y; y is the number of deduplicated grid region types obtained after deduplication of several grid region types; C x The type identifier of the xth deduplicated raster region type;

[0093] Step S420: Get the grid area type as C xThe grid feature vectors of several grid regions of the corresponding deduplicated grid region type are obtained to obtain the grid feature vector list D corresponding to the xth deduplicated grid region type x =(D x1 ,D x2 ,...,D xz ,...,D xh(x) ); where z = 1, 2, ..., h(x); h(x) is the grid region type of C x The number of grid regions of the corresponding grid region type after deduplication; D xz For grid area type C x The grid feature vector of the zth grid region of the corresponding deduplicated grid region type;

[0094] Step S430: Get the grid area type as C x The historical feature vectors of the corresponding grid region types after deduplication are obtained to obtain the historical feature vector list set E corresponding to the x-th grid region type after deduplication. x =(E x1 ,E x2 ,...,E xz ,...,E xh(x) ), where E xz For grid area type C x The list of historical feature vectors corresponding to the zth grid area of ​​the corresponding deduplicated grid area type;

[0095] E xz =(E xz1 ,E xz2 ,...,E xza ,...,E xzb(xz) ); where a=1,2,...,b(xz); b(xz) is the grid region type of C x The number of historical feature vectors corresponding to the zth grid area of ​​the corresponding deduplicated grid area type; E xza For grid area type C x The a-th historical feature vector of the z-th grid region of the corresponding deduplicated grid region type;

[0096] Step S440: Calculate the grid feature vector list D x A list of several grid feature vectors and historical feature vectors in E x Several historical feature vectors in are mixed and clustered to obtain several feature vector clusters.

[0097] Several feature vectors in a feature vector group can be considered to have the same power usage status of the electrical equipment in the corresponding grid areas.

[0098] The historical feature vectors are obtained based on the electrical parameters of several electrical devices in the grid area within the historical period, wherein several historical feature vectors corresponding to the i-th grid area are determined by step S001:

[0099] Step S001: Obtain parameter characteristics of electrical parameters of several electrical devices in the i-th grid area in several historical periods, and obtain a historical characteristic vector group F corresponding to the i-th grid area. i =(F i1 ,F i2 ,...,F im ,...,F in ), where m = 1, 2, ..., n, and n is the number of historical periods; F im is the historical feature vector corresponding to the i-th grid area in the m-th historical period;

[0100] F im =(F im1 ,F im2 ,...,F imr ,...,F ims ), where F imr is a list set of electrical parameters of the rth type of electrical equipment in the i-th grid area in the m-th historical period;

[0101] F imr =(F imr1 ,F imr2 ,...,F imrt ,...,F imru ), where F imrt is a parameter feature list of the tth electrical parameter of the rth type of electrical equipment in the i-th grid area in the m-th historical period;

[0102] F imrt =(F imrt1 ,F imrt2 ,...,F imrtv ,...,F imrtw ), where F imrtv is the vth parameter feature of the tth electrical parameter of the rth type of electrical equipment in the ith grid area in the mth historical period.

[0103] The length and start and end time of the historical period can be set according to the needs of the staff.

[0104] Each historical feature vector corresponds to a historical device status identifier, and the historical device status identifier of the historical feature vector is determined through steps S002 to S005:

[0105] Step S002: historical feature vector list set Ex Clustering of several historical feature vectors in the grid to obtain the grid area type C x Several historical feature vector clusters corresponding to the raster regions of the corresponding deduplicated raster region types;

[0106] Step S003: Determine the device status identifier corresponding to each historical feature vector group according to the preset grid status judgment rule;

[0107] The grid status judgment rule is a judgment standard set by the staff. After obtaining several historical feature vector groups, the staff can judge the power consumption status of the electrical equipment in several grid areas corresponding to each historical feature vector group in the corresponding historical period to determine the equipment status of each historical feature vector group (for example, among the electrical equipment in several grid areas corresponding to the historical feature vector group, more than eighty percent of the electrical equipment has abnormal power consumption in the corresponding historical period, then the equipment power consumption status of the historical feature vector group is determined to be abnormal), and then establish an association relationship between the equipment status identifier corresponding to the equipment status of each historical feature vector group and the historical feature vector group.

[0108] Step S004: Determine the device state identifier corresponding to each historical feature vector group as the historical device state identifier of each historical feature vector included in the historical feature vector group;

[0109] Among them, when the historical device status identifier is the first status identifier, it is characterized by that the grid status of the electrical equipment in the grid area corresponding to the historical device status identifier during the historical period corresponding to the historical device status identifier is normal (the grid status is the equipment power consumption status of the electrical equipment).

[0110] When the historical device state identifier is the second state identifier, it is characterized that the power grid state of the electrical devices in the grid area corresponding to the historical device state identifier in the historical period corresponding to the historical device state identifier is abnormal.

[0111] Step S005: If there is a historical feature vector that does not belong to any historical feature vector group, the historical device state identifier of the historical feature vector is determined as the second state identifier.

[0112] The historical feature vectors that do not belong to any historical feature vector group, that is, the discrete points after clustering, are considered to have abnormal power grid status because their power consumption status of the electrical equipment corresponding to each historical feature vector group is different or dissimilar. Therefore, the staff shall reconfirm it to reduce the judgment error of the power grid status.

[0113] Step S500, determining the target device state identifier corresponding to each grid feature vector according to the historical device state identifier corresponding to the historical feature vector included in each feature vector group;

[0114] Further, step S500 includes steps S510 to S560:

[0115] Step S510: Get C x The number of abnormal historical feature vectors included in each feature vector cluster of the corresponding deduplicated grid region type to obtain the abnormal historical feature vector quantity list G x =(G x1 ,G x2 ,...,G xc ,...,G xd(x) ), where c = 1, 2, ..., d(x); d(x) is C x The number of feature vector clusters of the corresponding raster region type after deduplication; G xc C x The number of abnormal historical feature vectors included in the c-th feature vector class group of the corresponding deduplicated grid region type; wherein the abnormal historical feature vector is a historical feature vector whose historical device state identifier is the second state identifier;

[0116] Step S520: Get C x The total number of feature vectors included in each feature vector group of the corresponding deduplicated grid region type is obtained to obtain a feature vector quantity list H x =(H x1 ,H x2 ,...,H xc ,...,H xd(x) ), where H xc C x The total number of feature vectors included in the cth feature vector group of the corresponding grid region type after deduplication; the total number of feature vectors included in the feature vector group is the sum of the number of grid feature vectors and historical feature vectors included in the feature vector group;

[0117] Step S530: If G xc / H xc If it is greater than the preset percentage threshold, C x The target device state identifier of the grid feature vector in the cth feature vector cluster of the corresponding grid region type after deduplication is determined as the second state identifier; otherwise, step S540 is executed;

[0118] The preset percentage threshold can be eighty percent. If the ratio of the number of abnormal historical feature vectors included in the feature vector group to the total number of feature vectors included in the feature vector group is greater than the preset percentage threshold, and since the power usage states of the electrical equipment in the corresponding several grid areas in the feature vector group are similar, it can be considered that the power usage states of all feature vectors in the feature vector group are the same, and the target device state identifier of the grid feature vector in the feature vector group is determined as the second state identifier.

[0119] Step S540: Get C x The number of normal historical feature vectors included in each feature vector group of the corresponding deduplicated grid region type to obtain a list of normal historical feature vectors Q x =(Q x1 ,Q x2 ,...,Q xc ,...,Q xd(x) ), where Q xc C x The number of normal historical feature vectors included in the cth feature vector class group of the corresponding deduplicated grid region type; wherein the normal historical feature vector is a historical feature vector whose historical device state identifier is the first state identifier;

[0120] Step S550: If Q xc / H xc If it is greater than the preset percentage threshold, C x The target device state identifier of the grid feature vector in the cth feature vector class group of the corresponding grid region type after deduplication is determined as the first state identifier;

[0121] Step S551: If Q xc / H xc If the percentage is less than or equal to the preset threshold, C x The target device state identifier of the grid feature vector in the cth feature vector class group of the corresponding grid region type after deduplication is determined as the pending state identifier;

[0122] If the pending status identification, that is, the power consumption status of the electrical equipment in the grid area corresponding to the feature vector group, is too complex, further accurate judgment is required.

[0123] Step S552: inputting the grid feature vector with the target device state identified as the pending state identification into a preset precise analysis model to obtain a corresponding power grid state analysis result;

[0124] The preset precise analysis model can adopt the existing model for accurately judging the electrical parameters of electrical equipment. The precise analysis model analyzes the power grid status analysis results of the electrical equipment corresponding to the grid feature vector of the pending state identification through its own set judgment logic. The judgment logic is set by the developer of the precise analysis model.

[0125] Step S553: ​​If the power grid state analysis result indicates that the power grid state is normal, the pending state identifier is determined as the first state identifier;

[0126] If the power grid state analysis result indicates that the power grid state is abnormal, the pending state identifier is determined as the second state identifier.

[0127] Step S560: If there is a grid feature vector that does not belong to any feature vector group, the target device state identifier of the grid feature vector is determined as the second state identifier.

[0128] Step S600: outputting a grid feature vector corresponding to a target device state identifier representing that a power grid state of an electrical device in a grid area is in an abnormal state, and alarm information including an area identifier of the grid area corresponding to the grid feature vector.

[0129] Further, step S600 includes step S610-step S630:

[0130] Step S610, traversing each grid feature vector, if the target device state identifier of any grid feature vector is the second state identifier, then determining the grid feature vector as an abnormal grid feature vector;

[0131] Step S620, determining the grid area corresponding to the abnormal grid feature vector as the abnormal grid area;

[0132] Step S630: output each abnormal grid feature vector and the alarm information of the region identification containing the abnormal grid region.

[0133] Each abnormal grid feature vector and the alarm information containing the area identification of the abnormal grid area are output to the control center. After receiving the abnormal grid feature vector and the alarm information, the staff of the control center can conduct further accurate analysis of the electrical equipment in the abnormal grid area to find the cause of the abnormal grid state.

[0134] The power grid equipment monitoring and early warning method based on big data of the present invention performs rasterization processing on the target area to obtain a plurality of raster areas corresponding to the target area, determines the raster area type corresponding to each raster area according to the target area type of each raster area in the target area, and then determines the raster feature vector corresponding to each raster area according to the electrical parameters of a plurality of electrical equipment in each raster area, the raster feature vector is used to represent the electrical parameter characteristics of the electrical equipment in the corresponding raster area, and clusters the raster feature vectors corresponding to a plurality of raster areas of the same raster area type and the historical feature vectors corresponding to the plurality of raster areas to obtain a plurality of feature vector cluster groups, because the electrical equipment corresponding to the plurality of feature vectors in each feature vector cluster group The electrical parameter characteristics are similar, so it can be considered that the grid states of the electrical equipment in the grid area corresponding to several feature vectors in the feature vector group are similar. Therefore, according to the historical equipment state identification corresponding to the historical feature vector included in each feature vector group, the target equipment state identification corresponding to each grid feature vector is determined, and the grid feature vector corresponding to the target equipment state identification representing that the grid state of the electrical equipment in the grid area is abnormal and the alarm information including the area identification of the grid area corresponding to the raster feature vector are output, so as to prompt the staff to perform abnormal screening for abnormal electrical parameters on all electrical equipment in the grid area where the electrical equipment with abnormal grid state is located, so as to ensure the safe use of electrical equipment in the target area.

[0135] An embodiment of the present invention further provides a computer program product, which includes program code. When the program product is run on an electronic device, the program code is used to enable the electronic device to execute the steps of the method according to various exemplary embodiments of the present invention described above in this specification.

[0136] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0137] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0138] In an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0139] It will be appreciated by those skilled in the art that various aspects of the present invention may be implemented as a system, method or program product. Therefore, various aspects of the present invention may be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as a "circuit", "module" or "system".

[0140] The electronic device according to this embodiment of the present invention is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0141] The electronic device is presented in the form of a general-purpose computing device. The components of the electronic device may include, but are not limited to: the at least one processor mentioned above, the at least one storage device mentioned above, and a bus connecting different system components (including storage devices and processors).

[0142] The storage stores program codes, which can be executed by the processor, so that the processor executes the steps according to various exemplary embodiments of the present invention described in the above “Exemplary Method” section of this specification.

[0143] The memory may include readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory, and may further include read only memory (ROM).

[0144] The storage may also include a program / utility having a set (at least one) of program modules, such program modules including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include the implementation of a network environment.

[0145] The bus may represent one or more of several types of bus structures including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures.

[0146] The electronic device may also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device, and / or any device that enables the electronic device to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface. Furthermore, the electronic device may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter.

[0147] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible implementations, various aspects of the present invention can also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary embodiments of the present invention described in the above "Exemplary Method" section of the present specification.

[0148] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0149] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0150] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0151] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0152] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to an exemplary embodiment of the present invention, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0153] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0154] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A power grid equipment monitoring and early warning method based on big data, characterized in that: The method comprises the following steps: Step S100, performing rasterization processing on the target area to obtain a plurality of raster areas corresponding to the target area; Step S200, determining the grid area type corresponding to each of the grid areas according to the target area type of each of the grid areas in the target area; Step S300, determining a grid feature vector corresponding to each grid area according to electrical parameters of a plurality of electrical devices in each grid area; Step S400, clustering the grid feature vectors corresponding to a plurality of grid regions of the same grid region type and the historical feature vectors corresponding to the plurality of grid regions to obtain a plurality of feature vector clusters; the historical feature vectors are obtained based on electrical parameters of a plurality of electrical devices in the grid region within a historical period; each of the historical feature vectors corresponds to a historical device status identifier; Step S500, determining the target device state identifier corresponding to each of the grid feature vectors according to the historical device state identifiers corresponding to the historical feature vectors included in each of the feature vector groups; Step S600: outputting the grid feature vector corresponding to the target device state identifier indicating that the power grid state of the electrical equipment in the grid area is abnormal, and alarm information including the area identifier of the grid area corresponding to the grid feature vector.

2. The method according to claim 1, characterized in that The step S100 includes: Step S110: dividing the target area into grids according to a preset grid size to obtain a plurality of grid areas corresponding to the target area; wherein the size of each grid area is the preset grid size.

3. The method according to claim 2, characterized in that The step S200 includes: Step S210: according to the target area types corresponding to the target area, the target area is divided into types to obtain a plurality of type sub-areas corresponding to the target area; each type sub-area corresponds to a unique target area type; Step S220: Obtain the region identifier of each grid region to obtain a first region identifier list A=(A1, A2, ..., A i ,...,A j ), wherein i=1, 2, ..., j, j is the number of the grid regions; A i is the region identifier of the i-th grid region; Step S230: Obtain the region identifier of each sub-region of the type, and obtain a second region identifier list B=(B1, B2, ..., B p ,...,B q ), wherein p = 1, 2, ..., q, q is the number of sub-regions of the type; B p is the region identifier of the pth sub-region of the type; Step S240: traverse the first area identifier list A and the second area identifier list B. If B p The corresponding sub-area of ​​the type is in A i The area in the corresponding grid area is i If the proportion of the area of ​​the corresponding grid area is greater than a preset area ratio threshold, the target area type corresponding to the p-th sub-area of ​​the type is determined as the grid area type corresponding to the i-th grid area; Step S250: If all sub-areas of the type are in A i The area in the corresponding grid area is i If the proportions of the areas of the corresponding grid regions are all less than or equal to a preset area ratio threshold, the preset key region type is determined as the grid region type corresponding to the i-th grid region.

4. The method according to claim 3, characterized in that The step S300 includes: Step S310: Obtain parameter characteristics of electrical parameters of several electrical devices in each grid area to obtain a grid feature vector group B = (B1, B2, ..., B i ,...,B j ), where B i is the grid feature vector corresponding to the i-th grid area; B i =(B i1 ,B i2 ,...,B ir ,...,B is ), where r = 1, 2, ..., s, and s is the number of types of electrical equipment that are preset; B ir is a list set of electrical parameters of the rth type of electrical equipment in the i-th grid area; B ir =(B ir1 ,B ir2 ,...,B irt ,...,B iru ), wherein t = 1, 2, ..., u, and u is the number of preset electrical parameters; B irt is a parameter characteristic list of the tth electrical parameter of the rth type of electrical equipment in the i-th grid area; B irt =(B irt1 ,B irt2 ,...,B irtv ,...,B irtw ); wherein v = 1, 2, ..., w; w is the number of parameter characteristics of the preset electrical parameters; B irtv is the vth parameter feature of the tth electrical parameter of the rth type electrical equipment in the ith grid area.

5. The method according to claim 4, characterized in that The step S400 includes: Step S410: De-duplicate the grid region types corresponding to the plurality of grid regions to obtain a de-duplicated grid region type list C = (C1, C2, ..., C x ,...,C y ), wherein x = 1, 2, ..., y; y is the number of deduplicated grid region types obtained after deduplication of several grid region types; C x The type identifier of the xth deduplicated raster region type; Step S420: Get the grid area type as C x The grid feature vectors of the corresponding grid region types after deduplication, so as to obtain the grid feature vector list D corresponding to the xth grid region type after deduplication x =(D x1 ,D x2 ,...,D xz ,...,D xh(x) ); where z = 1, 2, ..., h(x); h(x) is the grid region type of C x The number of the grid regions of the corresponding deduplicated grid region type; D xz For grid area type C x The grid feature vector of the zth grid region of the corresponding deduplicated grid region type; Step S430: Get the grid area type as C x The historical feature vectors of the corresponding grid region types after deduplication are obtained to obtain the historical feature vector list set E corresponding to the x-th grid region type after deduplication. x =(E x1 ,E x2 ,...,E xz ,...,E xh(x) ), where E xz For grid area type C x A list of historical feature vectors corresponding to the zth grid area of ​​the corresponding deduplicated grid area type; E xz =(E xz1 ,E xz2 ,...,E xza ,...,E xzb(xz) ); where a=1,2,...,b(xz); b(xz) is the grid region type of C x The number of historical feature vectors corresponding to the zth grid area of ​​the corresponding deduplicated grid area type; E xza For grid area type C x The a-th historical feature vector of the z-th grid region of the corresponding deduplicated grid region type; Step S440: the grid feature vector list D x Several grid feature vectors and the historical feature vector list set E in x Several historical feature vectors in are mixed and clustered to obtain several feature vector clusters.

6. The method according to claim 5, characterized in that The historical feature vectors corresponding to the i-th grid area are determined by the following steps: Step S001: Obtain parameter characteristics of electrical parameters of several electrical devices in the i-th grid area in several historical periods, and obtain a historical feature vector group F corresponding to the i-th grid area. i =(F i1 ,F i2 ,...,F im ,...,F in ), where m = 1, 2, ..., n, and n is the number of historical periods; F im is the historical feature vector corresponding to the i-th grid area in the m-th historical period; F im =(F im1 ,F im2 ,...,F imr ,...,F ims ), where F imr is a list set of electrical parameters of the rth type of electrical equipment in the i-th grid area in the m-th historical period; F imr =(F imr1 ,F imr2 ,...,F imrt ,...,F imru ), where F imrt A parameter feature list of the tth electrical parameter of the rth type of electrical equipment in the mth historical period in the i-th grid area; F imrt =(F imrt1 ,F imrt2 ,...,F imrtv ,...,F imrtw ), where F imrtv It is the vth parameter feature of the tth electrical parameter of the rth type electrical equipment in the i-th grid area in the m-th historical period.

7. The method according to claim 6, characterized in that The historical device status identifier of the historical feature vector is determined by the following steps: Step S002: the historical feature vector list set E x Clustering of several historical feature vectors in the grid to obtain the grid area type C x A plurality of historical feature vector clusters corresponding to the grid area of ​​the corresponding deduplicated grid area type; Step S003: determining the device status identifier corresponding to each of the historical feature vector groups according to a preset grid status judgment rule; Step S004: Determine the device state identifier corresponding to each of the historical feature vector groups as the historical device state identifier of each of the historical feature vectors included in the historical feature vector group; Wherein, when the historical device state identifier is a first state identifier, it is characterized that the power grid state of the electrical equipment in the grid area corresponding to the historical device state identifier during the historical period corresponding to the historical device state identifier is in a normal state; when the historical device state identifier is a second state identifier, it is characterized that the power grid state of the electrical equipment in the grid area corresponding to the historical device state identifier during the historical period corresponding to the historical device state identifier is in an abnormal state; Step S005: If there is a historical feature vector that does not belong to any of the historical feature vector groups, the historical device state identifier of the historical feature vector is determined as the second state identifier.

8. The method according to claim 7, characterized in that The step S500 includes: Step S510: Get C x The number of abnormal historical feature vectors included in each feature vector cluster of the corresponding deduplicated grid region type to obtain the abnormal historical feature vector quantity list G x =(G x1 ,G x2 ,...,G xc ,...,G xd(x) ), where c = 1, 2, ..., d(x); d(x) is C x The number of feature vector clusters of the corresponding raster region type after deduplication; G xc C x The number of abnormal historical feature vectors included in the c-th feature vector class group of the corresponding deduplicated grid region type; wherein the abnormal historical feature vector is a historical feature vector whose historical device state identifier is the second state identifier; Step S520: Get C x The total number of feature vectors included in each feature vector group of the corresponding deduplicated grid region type is obtained to obtain a feature vector quantity list H x =(H x1 ,H x2 ,...,H xc ,...,H xd(x) ), where H xc C x The total number of feature vectors included in the cth feature vector group of the corresponding grid region type after deduplication; the total number of feature vectors included in the feature vector group is the sum of the number of grid feature vectors and historical feature vectors included in the feature vector group; Step S530: If G xc / H xc If it is greater than the preset percentage threshold, C x The target device state identifier of the grid feature vector in the cth feature vector cluster of the corresponding grid region type after deduplication is determined as the second state identifier; otherwise, step S540 is executed; Step S540: Get C x The number of normal historical feature vectors included in each feature vector group of the corresponding deduplicated grid region type to obtain a list of normal historical feature vectors Q x =(Q x1 ,Q x2 ,...,Q xc ,...,Q xd(x) ), where Q xc C x The number of normal historical feature vectors included in the cth feature vector class group of the corresponding deduplicated grid region type; wherein the normal historical feature vector is a historical feature vector whose historical device state identifier is the first state identifier; Step S550: If Q xc / H xc If it is greater than the preset percentage threshold, C x The target device state identifier of the grid feature vector in the cth feature vector class group of the corresponding grid region type after deduplication is determined as the first state identifier; Step S560: If there is a grid feature vector that does not belong to any of the feature vector groups, the target device state identifier of the grid feature vector is determined as the second state identifier.

9. The method according to claim 8, characterized in that The step S550 further includes: Step S551: If Q xc / H xc If the percentage is less than or equal to the preset threshold, C x The target device state identifier of the grid feature vector in the cth feature vector class group of the corresponding grid region type after deduplication is determined as the pending state identifier; Step S552: inputting the grid feature vector with the target device state identified as the pending state identification into a preset precise analysis model to obtain a corresponding power grid state analysis result; Step S553: ​​if the grid state analysis result indicates that the grid state is normal, the pending state identifier is determined as the first state identifier; if the grid state analysis result indicates that the grid state is abnormal, the pending state identifier is determined as the second state identifier.

10. The method according to claim 9, characterized in that The step S600 includes: Step S610, traversing each of the grid feature vectors, if the target device state identifier of any of the grid feature vectors is the second state identifier, determining the grid feature vector as an abnormal grid feature vector; Step S620, determining the grid area corresponding to the abnormal grid feature vector as the abnormal grid area; Step S630: output each abnormal grid feature vector and alarm information including the region identifier of the abnormal grid region.

Images