Regional power outage judgment method and system based on night light remote sensing and highway traffic network

Abstract

The application provides a regional night power failure judgment method and system based on night light remote sensing and a highway traffic network, and the method comprises the following steps: removing the night light remote sensing image of the date of "active power failure" from the obtained night light remote sensing image to obtain a pretreated night light remote sensing image set; downloading the latest road network data from the website of the traffic management department to which the target region belongs, and removing the non-light-emitting road network data from the latest road network data to obtain pretreated road network data; preparing a regional power failure judgment dynamic base map according to the pretreated night light remote sensing image set and the pretreated road network data; and comparing the night light remote sensing image of the date to be judged with the regional power failure judgment dynamic base map to realize the judgment of whether the date and time point is "passive power failure". The application can realize accurate judgment of "passive power failure" of the target region.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of regional power outage judgment, in particular to a regional night power outage judgment method and system based on night light remote sensing and highway traffic network. BACKGROUND

[0002] The continuity and stability of power supply is the basic guarantee of social livelihood. On the one hand, power outage needs to be monitored in real time: when regional power outage occurs, the power supply company needs to find out in the first time and make corresponding treatment to protect industrial production and social livelihood. On the other hand, power outage can be divided into "active power outage" and "passive power outage": active power outage is the planned power outage actively deployed by the power supply department when the region needs power maintenance or time-sharing power supply; passive power outage is defined as the power outage situation when an occasional event occurs: such as equipment failure caused by overload, short / short circuit of power line, etc. Therefore, when the power supply company statistically analyzes the past power supply data and power consumption data, the active power outage data is usually retained and recorded, while the passive power outage data is often not comprehensive, causing power consumption safety hazards.

[0003] At the same time, with the use of domestic night light remote sensing satellites such as Lijia No. 1, the resolution of night light data has been significantly improved, making it possible to determine whether there is regional power outage at a certain time point (time period) through night light remote sensing data. At the same time, in order to avoid the confusion of power outage area judgment in night light remote sensing data caused by street lamps (with backup power supply), car lights, etc., it is necessary to remove the influence of street lamps and car lights in the original night light remote sensing data. SUMMARY

[0004] The present application mainly aims at the judgment of night passive power outage data, and provides a regional night power outage judgment method based on night light remote sensing and highway traffic network, which analyzes the regional night light remote sensing data, and removes the influence of street lamps, car lights, etc. in the night light remote sensing image through the highway traffic network, finally judges whether there is power outage at the time point corresponding to the light remote sensing data, and realizes the accurate judgment of the "passive power outage" of the region through the "active power outage" data of the power supply center.

[0005] The above technical problems of the present application are mainly solved by the following technical scheme:

[0006] A regional night power outage judgment method based on night light remote sensing and highway traffic network, comprising the following steps:

[0007] Comprising the following steps:

[0008] Step one, night light remote sensing data preprocessing: obtain the time point of the target area to push back several days of night light remote sensing image, obtain the date of the target area night "active power failure" from the power supply department, remove the night light remote sensing image of the date of "active power failure" in the obtained night light remote sensing image, obtain the preprocessed night light remote sensing image set;

[0009] Step two, city traffic network data preprocessing: download the latest road network data from the website of the traffic management department of the target area, remove the non-light-emitting road network data from the latest road network data, and obtain the preprocessed road network data;

[0010] Step three, regional power failure research and judgment base map intelligent production: according to the preprocessed night light remote sensing image set in step one and the preprocessed road network data in step two, the regional power failure research and judgment dynamic base map is produced;

[0011] Step four, night light image pixel level power failure research: according to the regional power failure research and judgment dynamic base map produced in step three, the night light remote sensing image of the date to be researched is compared, and the research of whether the date is "passive power failure" is realized.

[0012] Further, step one specifically includes:

[0013] Step 1.1, at the time point needing to be researched, obtain the night light remote sensing image of the day, denoted as IMG data , data is the date of the night light remote sensing image; at the same time, push back in time sequence, take the night light remote sensing image of the previous 30 days, each image is numbered as IMG n , n = 1, 2, 3, …, 30;

[0014] Step 1.2, obtain the date of the night "active power failure" in the region from the power supply department, remove the night light remote sensing image of the day in IMG n data set, obtain the preprocessed night light remote sensing image set IMG m , wherein 0≤m≤30.

[0015] 7、Further, step two specifically includes:

[0016] Step 2.1, download the latest road network data from the website of the traffic management department of the target area;

[0017] Step 2.2, in ArcGIS, save the road network data as a separate layer, which is denoted as Layer R ;

[0018] Step 2.3, in the IMG m set processed in step 1.2, store each image in a separate layer in ArcGIS, which is denoted as IMGLayer m ;

[0019] Step 2.4, Layer R and m IMGLayer m Overlay, in Layer R Within the range of , the non-illuminated area is removed to obtain the preprocessed road network data.

[0020] Furthermore, step 2.4 specifically includes:

[0021] (1) In Layer R Within the range, find the latitude and longitude coordinates of each pixel point on the image, assuming there are n points in total;

[0022] (2) In IMGLayer m In each layer, calculate the grayscale values ​​of n points respectively, take the arithmetic mean of the m values ​​of each point, and get the grayscale value of n points as follows:

[0023]

[0024] Among them, Grey n Indicates the average gray value of the nth point in the m layers, g nm Represents the grayscale value of the nth point on the mth layer;

[0025] (3) Set the threshold to 20 to remove Grey n Points less than the threshold value of 20 are removed and recorded as Point left ;

[0026] (4) In Layer R Within the range, keep Point left The rest of the road network is from Layer R Remove the remaining road network data and store it in a new layer RL middle.

[0027] Furthermore, step three specifically includes:

[0028] Step 3.1: The night light remote sensing data adopts the 130-meter resolution of the Luojia-1 satellite, and the resolution of the regional power outage analysis dynamic base map is set to 130 meters;

[0029] Step 3.2, in IMGLayer m In the m layers, m images are superimposed at the same time. In the superimposed image, the grayscale value of each pixel is the arithmetic average of the grayscale values ​​of the pixels at the same position in the m images. The superimposed image is stored in the new layer BaseMap;

[0030] Step 3.3: Overlay the Layer on the BaseMap layerRL ;

[0031] Step 3.4, in the BaseMap layer, remove Layer RL , modify the BaseMap as the power outage research base map of the region.

[0032] Further, step four specifically includes:

[0033] Step 4.1, new layer, store IMG data data in the layer, the layer is called Layer judge ;

[0034] Step 4.2, compare the gray value of each pixel of the BaseMap base map layer and Layer judge image;

[0035] Step 4.3, set the gray value threshold 20, which means that all pixels greater than 20 are determined as light-emitting area, record all pixels in Layer judge whose gray value is less than 20 but greater than 20 in BaseMap;

[0036] Step 4.4, store all pixels meeting the conditions of step 4.3 in the newly created Layer result layer in the form of point elements;

[0037] Step 4.5, determine the area composed of point elements in Layer result , which is the pixel-level power outage research result of night light image.

[0038] Further, it also includes:

[0039] Step five, the research result generalization step based on reliable power supply data: combined with the power outage research of "time point" in step four and the change of regional power supply data of power supply department, realize the research result from "time point" to "time period" generalization, that is, realize the research of multiple power outage states in a long time period.

[0040] Further, step five specifically includes:

[0041] Step 5.1, for the result obtained in step four, that is, the area where the point elements in Layer result correspond to the time point of IMG data data, set the time point as T;

[0042] Step 5.2, calculate 1 hour forward and backward from the time point of IMG data data, then get the time interval [T-1, T+1];

[0043] Step 5.3, query the power supply department layer result The power supply data of the area where the midpoint element is located, recording the power supply data of each 1 minute of the area, a total of 120 data;

[0044] Step 5.4, analyze the change rate of 120 data, if the data is steadily increasing or decreasing, it is defined as the power supply data of the area has no significant change; indicating that the power supply in the geographic area is stable, and no large-scale power failure occurs during this period, then the power failure research result is generalized to the interval [T-1, T+1], wherein the change rate is realized by calculating the standard deviation or variance;

[0045] Step 5.5, on the contrary, it indicates that there may be power failure or power-on time in the interval, and the generalization interval is reduced to repeat the above steps;

[0046] Step 5.6, if the generalization interval is reduced to 1 minute, and there is still significant change in the power supply data in the interval, stop generalization, indicating that the "passive power failure" event monitored by the night light remote sensing image is quickly solved within 1 minute.

[0047] A regional night power failure research system based on night light remote sensing and highway traffic network, comprising:

[0048] A night light remote sensing data preprocessing module is configured to obtain night light remote sensing images of a target area for a plurality of days before a time point, obtain dates of "active power failure" in the target area from a power supply department, remove the night light remote sensing images of the dates of "active power failure" from the obtained night light remote sensing images, and obtain a set of preprocessed night light remote sensing images;

[0049] A city traffic network data preprocessing module is configured to download the latest road network data from a website of a traffic management department to which the target area belongs, and remove non-emitting road network data from the latest road network data to obtain preprocessed road network data;

[0050] A regional power failure research base map intelligent production module is configured to produce a regional power failure research dynamic base map based on the set of preprocessed night light remote sensing images and the preprocessed road network data;

[0051] A night light image pixel-level power failure research module is configured to compare a night light remote sensing image of a date to be researched with the produced regional power failure research dynamic base map to research whether the date is "passive power failure" or not.

[0052] Further, it further comprises:

[0053] The research and judgment result generalization module based on the trusted power supply data is used for combining the power failure research and judgment of the "time point" of the night light image pixel level power failure research and judgment module and the change of the regional power supply data of the power supply department, realizing the research and judgment result from "time point" to "time period", that is, realizing the research and judgment of multiple power failure states in a long time period.

[0054] The present application has the following beneficial effects:

[0055] 1. Combined with the highway network, the night light effect of the street lamp, the car lamp and the like is excluded from the regional power failure research and judgment range, and the judgment accuracy can be effectively improved.

[0056] 2. Based on the city night light remote sensing data, the research and judgment of the "passive power failure" event at a certain time point is realized.

[0057] 3. Combined with the regional power supply data (trusted data) of the power supply department, the generalization of the "time point" power failure research and judgment result on the "time period" is realized. BRIEF DESCRIPTION OF DRAWINGS

[0058] Figure 1 is a flowchart of a regional night power failure research and judgment method based on night light remote sensing and highway traffic network of the present application;

[0059] Figure 2 is a module block diagram of a regional night power failure research and judgment system based on night light remote sensing and highway traffic network of the present application. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0061] Please refer to Figure 1 The embodiments of the present application provide a regional night power failure research and judgment method based on night light remote sensing and highway traffic network, which comprises the following steps:

[0062] Step S1, night light remote sensing data preprocessing step: adopting Luo-Ga No.1 night light remote sensing data (Luo-Ga No.1 night light remote sensing satellite features: 130-meter resolution, can clearly identify roads and blocks, and receives data 4 times a day), pre-processing historical night light remote sensing image data of the same region, and the specific implementation steps are as follows:

[0063] Step 1.1, obtaining the night light remote sensing image of the day at the time point (date) to be researched, denoted as IMGdata , data is the date of the night light remote sensing image; at the same time, the previous 30 days of night light remote sensing images (one per day) are taken in chronological order, and each image is numbered as IMG n , n = 1, 2, 3, …, 30; if it is necessary to determine whether there is a night power outage in a certain area on December 31, 2023, the night light remote sensing image of the day is first obtained, which is denoted as IMG 20231231 , then the night light remote sensing image of December 30 is numbered as IMG1, the night light remote sensing image of December 29 is numbered as IMG2, and so on.

[0064] Step 1.2, obtain the date of the night “active power outage” in the area from the power supply department, and remove the night light remote sensing image of the day from the IMG n data set to obtain a new night light remote sensing image set IMG m , where 0≤m≤30, the size of m depends on how many images of “active power outage” dates are removed.

[0065] In particular, if m = 0, continue to count back 30 days until m > 0.

[0066] At this point, the night light remote sensing data preprocessing work is completed.

[0067] Step two, city traffic network data preprocessing step: realize the preprocessing of the highway traffic network data of the target area (the area to be judged for power outage), the specific implementation steps are as follows:

[0068] Step 2.1, download the latest road network data from the website of the traffic management department to which the target area belongs;

[0069] Step 2.2, in ArcGIS, save the road network data as a separate layer, which is denoted as Layer R ;

[0070] Step 2.3, in the IMG m set processed in step 1.2, store each image in a separate layer in ArcGIS, which is denoted as IMGLayer m ;

[0071] Step 2.4, superimpose Layer R and m IMGLayer m , remove the non-lighting (night light) area within the range of Layer R , and the specific steps are as follows:

[0072] (1) First, within the range of Layer R (area highway), the latitude and longitude coordinates of each pixel point on each image are obtained, assuming there are n points;

[0073] (2) In IMGLayer m In each layer, calculate the grayscale values ​​of n points respectively, take the arithmetic mean of the m values ​​of each point, and get the grayscale value of n points as follows:

[0074]

[0075] Among them, Grey n Indicates the average gray value of the nth point in the m layers, g nm Represents the grayscale value of the nth point on the mth layer;

[0076] (3) Set the threshold to 20 to remove Grey n Points less than the threshold value of 20 are removed and recorded as Point left ;

[0077] (4) In Layer R Within the range, keep Point left The rest of the road network is from Layer R Removed; for ease of description, the remaining road network data is stored in a new layer Layer RL middle;

[0078] The principle of this step can be summarized as follows: through image processing, the non-luminous (no street lights, less vehicle headlight data) road network data is removed.

[0079] At this point, the urban transportation network data preprocessing work is completed.

[0080] Step 3: Intelligent production of regional power outage analysis base map: Use the night light remote sensing data and traffic network data compiled in the previous steps to produce a regional power outage analysis dynamic base map. The specific implementation process is as follows:

[0081] Step 3.1: Since the night light remote sensing data with a resolution of 130 meters from the Luojia-1 satellite is used, the resolution of the base map is set to 130 meters;

[0082] Step 3.2, in IMGLayer m In the m layers, m images are superimposed at the same time. In the superimposed image, the grayscale value of each pixel is the arithmetic average of the grayscale values ​​of the pixels at the same position in the m images; the superimposed image is stored in the new layer BaseMap;

[0083] Step 3.3: Overlay the Layer on the BaseMap layer RL ;

[0084] Step 3.4, in the BaseMap layer, remove Layer RLThe contained area; the modified BaseMap is the area outage research base map involved in the present application;

[0085] The BaseMap constructed by the above steps is not constant, and the content of the base map needs to be adjusted in real time according to the date of the outage image to be researched; that is, the date needs to be reselected, and steps 1-3 are repeated to re-construct the BaseMap, in order to enhance the long-time change of the regional night light (such as the addition of a building in a certain area, or the completion of a new road with street lights).

[0086] Step four, night light image pixel-level outage research step: using the base map BaseMap constructed by the foregoing steps, comparing the night light remote sensing image of the date to be researched, realizing the research of whether the date time point is "passive power failure", the specific implementation steps are:

[0087] Step 4.1, create a new layer, store IMG data Data into the layer, the layer is called Layer judge ;

[0088] Step 4.2, compare the BaseMap base map layer and Layer judge , the gray value of each pixel of the image;

[0089] Step 4.3, set the gray value threshold 20 (indicating that greater than 20 is determined as a light-emitting area), record all the pixels in Layer judge whose gray value is less than 20 but greater than 20 in BaseMap;

[0090] Step 4.4, store all pixels that meet the conditions described in step 4.3 in the form of point elements in the newly created Layer result ;

[0091] Step 4.5, the area composed of point elements in Layer result is the pixel-level outage research result of the night light image.

[0092] Step five, research result generalization step based on reliable power supply data: since there are only 4 night light remote sensing images per day, it can only be determined whether "passive power failure" at the time point, and it cannot be determined whether the power failure state is long in a longer period of time; On the other hand, based on the regional power supply data of the power supply department, the change can be continuously monitored. Therefore, the outage research at the "time point" can be combined with the change of the regional power supply data of the power supply department to realize the expansion of the research result from the "time point" to the "time period". The specific implementation steps are:

[0093] Step 5.1, for the result (the area where the point elements in Layer result ) obtained in step four, the result corresponds to IMGdata data is T;

[0094] Step 5.2, calculate 1 hour forward and backward from the time point of IMG data data, and obtain the time interval [T-1, T+1];

[0095] Step 5.3, query the power supply data of the power supply department in the area (Layer result The midpoint element is in the area) power supply data, record the power supply data of each 1 minute in the area, a total of 120 data;

[0096] Step 5.4, analyze the change rate of 120 data (which can be realized by calculating standard deviation or variance), if the data is smoothly increased or decreased, it is defined as that the power supply data in the area has no significant change; it is shown that the power supply in the geographic area is stable, and no large-scale power failure occurs during this period, so the power failure research result can be generalized to the interval [T-1, T+1];

[0097] Step 5.5, on the contrary, it is shown that there may be power failure (incoming call) in the interval, which can reduce the generalization interval and repeat the above steps, such as IMG data data, calculate 30 minutes, 15 minutes and so on forward and backward from the time point;

[0098] Step 5.6, if the generalization interval is reduced to 1 minute, and there is still significant change in the power supply data in the interval, stop generalization, which shows that the "passive power failure" event monitored by the night light remote sensing image is quickly solved in 1 minute.

[0099] At this point, the description of the regional night power failure research method based on night light remote sensing and highway traffic network is completed.

[0100] As shown in Figure 2 , the embodiment of the present application provides a regional night power failure research system based on night light remote sensing and highway traffic network, comprising:

[0101] The night light remote sensing data preprocessing module 10. The main function of this module is to use the Luo Ga No. 1 night light remote sensing data (Luo Ga No. 1 night light remote sensing satellite features: 130-meter resolution, which can clearly identify roads and blocks, and receive data 4 times a day), and preprocess historical night light remote sensing image data in the same area. First, the time point (date) to be researched is obtained, and the night light remote sensing image of the day is recorded as IMG data , data is the date of the night light remote sensing image; at the same time, the time sequence is pushed back, and the night light remote sensing image of the previous 30 days (1 image per day) is taken, and each image is numbered as IMG n, n = 1, 2, 3, ..., 30; if it is necessary to determine whether there will be a nighttime power outage in a certain area on December 31, 2023, first obtain the nighttime light remote sensing image of that day, recorded as IMG 20231231 , then the night light remote sensing image number of December 30 is IMG1, the night light remote sensing image number of December 29 is IMG2, and so on. Then, obtain the date of "active power outage" in the area at night from the power supply department, and in IMG n Remove the night light remote sensing image of that day from the data set to obtain a new night light remote sensing image set IMG m , where 0≤m≤30, and the size of m depends on how many images of the "active power outage" date are removed; finally, the preprocessing of night light remote sensing data is completed.

[0102] Urban traffic network data preprocessing module 20. The main function of this module is to realize the highway traffic network data of the target area (the area to be judged for power outage). First, it is necessary to download the latest road network data from the website of the traffic management department of the target area; then, in ArcGIS, save the road network data as a separate layer, which is recorded as Layer R ; At the same time, IMG after module 10 processing m In the collection, each image is stored in a separate layer in ArcGIS, and the layer is recorded as IMGLayer m ; Next, Layer R and m IMGLayer m Overlay, in Layer R Within the range (regional highway), find the latitude and longitude coordinates of each pixel on the image, assuming there are n points in total; then, in IMGLayer m In each layer, calculate the gray value of n points respectively, take the arithmetic mean of the m values ​​of each point, and get the gray value calculation formula of n points; then, set the threshold value to 20 to remove the gray value. n Points less than the threshold value of 20 are removed and recorded as Point left , in Layer R Within the range, keep Point left The rest of the road network is from Layer R Finally, the urban traffic network data preprocessing work is completed.

[0103] Regional power outage analysis base map intelligent production module 30. First, set the base map resolution to 130 meters; then, in IMGLayer mof the m images, the gray value of each pixel in the superimposed image is the arithmetic mean of the gray values of the pixels at the same position in the m images; the superimposed image is stored in a newly created layer BaseMap; then, the layer Layer RL is superimposed on the BaseMap layer; further, in the BaseMap layer, the area contained in the Layer RL is removed; finally, the modified BaseMap is the area outage research base map involved in the present application.

[0104] The nighttime light image pixel-level outage research module 40. The main function of this module is to compare the night light remote sensing image of the date to be researched with the base map BaseMap constructed by the aforementioned module 30 to realize the research of whether the date and time point is "passive outage". First, a new layer is created, and the IMG data data is stored in the layer, which is denoted as Layer judge ; then, the gray values of each pixel of the images in the BaseMap base map layer and the Layer judge are compared pixel by pixel; then, a gray value threshold 20 is set (indicating that a value greater than 20 is determined to be a light-emitting area), and all pixels in the Layer judge whose gray value is less than 20 but greater than 20 in the BaseMap are recorded; then, all pixels satisfying the above conditions are stored in a newly created layer Layer result in the form of point elements; finally, the area composed of the point elements in the Layer result is the nighttime light image pixel-level outage research result.

[0105] The research result generalization module 50 based on reliable power supply data. The main function of this module is: first, for the result obtained by the module 40 (the area where the point elements in the Layer result are located), the result corresponds to the time point of the IMG data data, and the time point is denoted as T; then, 1 hour before and after the time point of the IMG data data is calculated, and the time interval [T-1, T+1] is obtained; at the same time, the power supply department of the area (Layer resultThe power supply data of the region where the midpoint element is located is recorded, and 120 data of each 1 minute of the region are recorded. Then, the change rate of the 120 data is analyzed (which can be realized by calculating the standard deviation or variance), if the data is steadily increased or decreased, it is defined that the power supply data of the region has no significant change; it indicates that the power supply in the geographical region is stable, and no large-scale power failure occurs during this period, and the power failure research result can be generalized to the interval [T-1, T+1]; otherwise, it indicates that there may be power failure (power supply) in the interval, the generalization interval can be reduced, and the above steps are repeated, such as IMG data The time point of the data is calculated forward and backward for 30 minutes, 15 minutes, etc.; finally, if the generalization interval is reduced to 1 minute, and there is still significant change of the power supply data in the interval, the generalization is stopped, which indicates that the "passive power failure" event monitored by the night light remote sensing image is quickly solved in 1 minute; finally, the regional night power failure research method based on night light remote sensing and highway traffic network is completed.

[0106] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer usable storage media containing computer usable program code (including but not limited to disk storage, CD-ROM, optical storage, etc.).

[0107] The present application is described with reference to flowcharts and / or block diagrams of the method, device (system), and computer program product according to the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device realize the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one or more flows and / or blocks. Figure 1 The functions specified in one or more flows and / or blocks.

[0108] These computer program instructions can also be stored in a computer readable storage medium which can guide the computer or other programmable data processing device to work in a specific way, so that the instructions stored in the computer readable storage medium produce a product including instruction devices, which realize the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one or more flows and / or blocks. Figure 1 The functions specified in one or more flows and / or blocks.

[0109] These computer program instructions can also be loaded into a computer or other programmable data processing devices, so that a series of operational steps are performed on the computer or other programmable data processing devices to generate computer-implemented processes, thus the instructions executed on the computer or other programmable data processing devices provide operational steps for implementing the functions of the flow Figure 1 One flow or multiple flows and / or the functions specified in the block Figure 1 One block or multiple blocks.

[0110] Finally, it should be noted that: the above examples are only used to illustrate the technical solutions of the present application, but not to limit it, although the above embodiments of the present application have been described in detail, those skilled in the art should understand: the specific embodiments of the present application can be modified or replaced by the same, without departing from the spirit and scope of the present application, any modification or equivalent replacement, which should be covered within the scope of protection of the claims of the present application.

Claims

1. A method for analyzing and judging regional nighttime power outages based on nighttime light remote sensing and highway traffic network, characterized in that: The steps include: Step 1: Preprocessing of nighttime light remote sensing data: Obtain nighttime light remote sensing images of the target area several days in advance. Obtain the dates of "voluntary power outages" in the target area from the power supply department. Remove the nighttime light remote sensing images on the dates of "voluntary power outages" from the acquired nighttime light remote sensing images to obtain a preprocessed nighttime light remote sensing image set. Step 2: Preprocessing urban traffic network data: Download the latest road network data from the website of the traffic management department of the target area, remove the non-luminous road network data from the latest road network data, and obtain the preprocessed road network data; Step 3: Intelligently create a regional power outage analysis base map: Based on the night light remote sensing image collection pre-processed in step 1 and the road network data pre-processed in step 2, exclude the night light effects in the pre-processed road network data from the regional power outage analysis range, and create a regional power outage analysis dynamic base map; Step 4. Pixel-level power outage assessment using nighttime light images: Based on the dynamic base map for regional power outage assessment produced in step 3, compare it with the nighttime light remote sensing imagery of the date to be assessed to determine whether there is a "passive power outage" at that date and time.

2. The method for analyzing and judging regional nighttime power outages based on nighttime light remote sensing and road traffic network according to claim 1, characterized in that: Step 1 specifically includes: Step 1.1: At the time point required for analysis, obtain the night light remote sensing image of the day, recorded as IMG data , data is the date of the night light remote sensing image; at the same time, we go back in time and take the night light remote sensing images of the previous 30 days, and each image number is recorded as IMG n , n=1,2,3,…,30; Step 1.2: Obtain the date of "active power outage" at night in the area from the power supply department, and n Remove the night light remote sensing image of that day from the data set to obtain the preprocessed night light remote sensing image set IMG m , where 0≤m≤30.

3. The method for analyzing and judging regional nighttime power outages based on nighttime light remote sensing and highway traffic network according to claim 2, characterized in that: Step 2 specifically includes: Step 2.

1. Download the latest road network data from the website of the traffic management department in the target area; Step 2.2: In ArcGIS, save the road network data as a separate layer, which is called Layer R ; Step 2.3, IMG after processing in step 1.2 m In the collection, each image is stored in a separate layer in ArcGIS, and the layer is recorded as IMGLayer m ; Step 2.4, Layer R and m IMGLayer m Overlay, in Layer R Within the range of , the non-illuminated area is removed to obtain the preprocessed road network data.

4. The method for analyzing and judging regional nighttime power outages based on nighttime light remote sensing and road traffic network according to claim 3 is characterized in that: Step 2.4 specifically includes: (1) In Layer R Within the range, find the latitude and longitude coordinates of each pixel point on the image, assuming there are n points in total; (2) In IMGLayer m In each layer, calculate the grayscale values ​​of n points respectively, take the arithmetic mean of the m values ​​of each point, and get the grayscale value of n points as follows: ； in, Indicates the average gray value of the nth point in the m layers, g nm Represents the grayscale value of the nth point on the mth layer; (3) Set the threshold to 20 and remove Points less than the threshold value of 20 are removed and recorded as Point left ; (4) In Layer R Within the range, keep Point left The rest of the road network is from Layer R Remove the remaining road network data and store it in a new layer RL middle.

5. The method for analyzing and judging regional nighttime power outages based on nighttime light remote sensing and road traffic network according to claim 4 is characterized in that: Step three specifically includes: Step 3.1: The night light remote sensing data adopts the 130-meter resolution of the Luojia-1 satellite, and the resolution of the regional power outage analysis dynamic base map is set to 130 meters; Step 3.2, in IMGLayer m In the m layers, m images are superimposed at the same time. In the superimposed image, the grayscale value of each pixel is the arithmetic average of the grayscale values ​​of the pixels at the same position in the m images. The superimposed image is stored in the new layer BaseMap; Step 3.3: Overlay the Layer on the BaseMap layer RL ; Step 3.4, in the BaseMap layer, remove Layer RL The modified BaseMap for the included area is the base map for power outage assessment in the said area.

6. The method for analyzing and judging regional nighttime power outages based on nighttime light remote sensing and road traffic network according to claim 5, characterized in that: Step 4 specifically includes: Step 4.1, create a new layer and put IMG data The data is stored in this layer, which is called Layer judge ; Step 4.2: Compare the BaseMap layer and the Layer pixel by pixel judge The gray value of each pixel in the image; Step 4.3, set the gray value threshold to 20, indicating that all values ​​greater than 20 are considered luminous areas, and record the Layer judge All pixels whose grayscale value is less than 20 in the image but greater than 20 in the BaseMap; Step 4.4: All pixels that meet the conditions in step 4.3 are stored as point features in the new layer. result middle; Step 4.5, determine the layer result The area formed by the midpoint elements is the pixel-level power outage assessment result of the night light image.

7. The method for analyzing and judging regional nighttime power outages based on nighttime light remote sensing and highway traffic network according to claim 6, characterized in that: Also includes: Step 5. Generalize the analysis results based on reliable power supply data: Combine the power outage analysis at the "time point" in step 4 and the changes in the power supply data of the power supply department's area to expand and generalize the analysis results from the "time point" to the "time period", that is, to achieve analysis of multiple power outage states over a longer period of time.

8. The method for analyzing and judging regional nighttime power outages based on nighttime light remote sensing and highway traffic network according to claim 7, characterized in that: Step 5 specifically includes: Step 5.1: For the result obtained in step 4, that is, Layer result The area where the midpoint element is located corresponds to IMG data The time point of the data, let this time point be T; Step 5.2, IMG data Calculate 1 hour forward and 1 hour backward at the time point of the data to get the time interval [T-1, T+1]; Step 5.3: Query the power supply department layer result The power supply data of the area where the midpoint element is located is recorded every 1 minute, for a total of 120 data points; Step 5.4: Analyze the rate of change of the 120 data points. If the data increases or decreases steadily, it is defined as no significant change in the power supply data for the region. This indicates that the power supply in the region is stable and no large-scale power outages occurred during this period. The power outage analysis results are then generalized to the interval [T-1, T+1]. The rate of change is calculated by calculating the standard deviation or variance. Step 5.5: On the contrary, it indicates that there may be power outage or power supply time in the interval. Reduce the generalization interval and repeat the above steps; Step 5.6: If the generalization interval is reduced to 1 minute and there are still significant changes in the power supply data within the interval, stop generalization, indicating that the "passive power outage" event monitored by the night light remote sensing image was quickly resolved within 1 minute.

9. A regional nighttime power outage analysis and judgment system based on nighttime light remote sensing and highway traffic network, characterized by: include: The nighttime light remote sensing data preprocessing module is used to obtain nighttime light remote sensing images of the target area several days in advance. The date of "active power outage" in the target area at night is obtained from the power supply department. The nighttime light remote sensing images on the "active power outage" date are removed from the acquired nighttime light remote sensing images to obtain a set of preprocessed nighttime light remote sensing images. The urban traffic network data preprocessing module is used to download the latest road network data from the website of the traffic management department of the target area, remove the non-luminous road network data from the latest road network data, and obtain the preprocessed road network data; The module for intelligently creating a regional power outage analysis base map is used to create a dynamic regional power outage analysis base map based on a pre-processed night light remote sensing image set and pre-processed road network data, excluding the night light effects in the pre-processed road network data from the regional power outage analysis range. The nighttime light image pixel-level power outage assessment module is used to compare the nighttime light remote sensing image of the date to be assessed with the prepared regional power outage assessment dynamic base map to determine whether there is a "passive power outage" at that date and time.

10. The regional nighttime power outage analysis and judgment system based on nighttime light remote sensing and highway traffic network as claimed in claim 9 is characterized in that: Also includes: The module for generalizing the analysis and judgment results based on trusted power supply data is used to combine the "time point" power outage analysis of the night light image pixel-level power outage analysis module with changes in regional power supply data from the power supply department. This allows the analysis and judgment results to be generalized from "time point" to "time period", that is, to enable the analysis and judgment of multiple power outage states over a longer period of time.

Images