A method and system for real-time power outage monitoring in residential areas based on mobile Internet traffic feedback

Abstract

The present invention provides a method and system for real-time power outage monitoring in residential areas based on mobile Internet traffic feedback, the method comprising: layering the power supply network data provided by the power supply company to form a multi-layer tree structure and displaying it on a map; when the background APP of the user's smart phone is always connected to the network and the background APP is disconnected after losing WIFI, the user is marked as an effective group user, and according to the divided multi-layer tree structure, all surface element areas in the bottom layer are independently marked as 1 geographic fence; the mobile traffic behavior characteristics of the effective group users entering a certain geographic fence in the target area are counted, and the collected mobile traffic behavior characteristics of the effective group users are sorted and stored; the power outage area is obtained by statistical analysis of the stored data and visualized on the map. The present invention not only does not require active feedback from residents, but can also accurately delineate the complete power outage area by coordinating with the power supply network.

Description

Technical Field

[0001] The present invention relates to the field of power outage monitoring, and in particular to a method and system for real-time power outage monitoring in residential areas based on mobile Internet traffic feedback. Background Art

[0002] Timely discovery of power outages can not only improve the service quality of power supply companies, but also quickly respond to and deal with potential safety hazards in electricity use. In my country, power customer groups can be roughly divided into industrial and residential electricity users. In the field of industrial electricity use, in order to ensure safe and efficient production, perfect power outage warning, prevention and response equipment are often available; while in the field of residential electricity use, users often cannot timely discover and accurately feedback the complete situation of power outages. At the same time, power companies from the power supply end cannot quickly locate the power outage area based on real-time power supply data. On the other hand, although residents' active feedback can notify the power supply department of power outages as soon as possible, regional power outages and large user bases can not only fail to accurately describe the entire power outage area, but also cause serious information congestion to limited feedback channels, which invisibly greatly increases the service costs of power supply companies. The lack of professional feedback information from users is more likely to cause incorrect judgments and evaluations of power outages. Furthermore, due to the popularity of UPS and power banks, some users use alternative power supplies and modems and routers to connect to the Internet through fiber optic cables. Therefore, power outages cannot be judged by simply judging whether there is a WIFI connection. Summary of the invention

[0003] In view of this, the present invention proposes an automated and intelligent method for real-time power outage monitoring in residential areas, which not only does not require active feedback from residents, but can also accurately define the entire power outage area by coordinating with the power supply network.

[0004] The above technical problems of the present invention are mainly solved by the following technical solutions:

[0005] A method for real-time power outage monitoring in residential areas based on mobile Internet traffic feedback comprises the following steps:

[0006] Step 1: Regional division based on power supply network: Layer the power supply network data provided by the power supply company to form a multi-layer tree structure and display it on the map;

[0007] Step 2: Statistics of user mobile traffic behavior characteristics: When the background APP of the user's smartphone is always connected to the network and the background APP is disconnected after losing WIFI, the user is marked as a valid group user. According to the multi-layer tree structure divided in step 1, all surface element areas in the bottom layer are independently marked as 1 geographic fence; statistics are collected on the mobile traffic behavior characteristics of the valid group users who enter a certain geographic fence in the target area, and the mobile traffic behavior characteristics include the duration of using WIFI or mobile network and the usage period;

[0008] Step 3: Building a user mobile traffic behavior database: sorting and storing the mobile traffic behavior characteristics of the effective group users collected in step 2;

[0009] Step 4: Power outage monitoring in residential areas: Through statistical analysis of the data stored in step 3, real-time monitoring of power outages in residential areas in the target area is achieved to determine the power outage area;

[0010] Step 5: Visualize the power outage area: Visualize the power outage area determined in real time in step 4 on the map.

[0011] Furthermore, step one specifically includes:

[0012] Step 1.1: In the residential electricity consumption area, the tree-structured distribution network is divided into multiple layers. The first layer is the root node distribution layer, which supplies electricity to the residents of the entire area. The second layer is forked into multiple branch nodes. The third layer is further branched from multiple nodes of the second layer. Assume that there are n layers in total.

[0013] Step 1.2: Load the default base map in ArcGIS software. The base map area is the target area that needs to be monitored for power outages.

[0014] Step 1.3, continue to load n layers: the first layer is the root node coverage area layer, which is stored as surface elements and the area is the entire target area;

[0015] Step 1.4, repeat the above steps to ensure that each of the n layers stores the area covered by the branch power grid as a surface element;

[0016] Step 1.5: Perform topology check: If a layer has multiple surface elements, each surface element should not intersect.

[0017] Furthermore, step 2 specifically includes:

[0018] Step 2.1, obtain the current network status through the APP installed on the smartphone;

[0019] Step 2.2: Agree on the conditions for obtaining user network status:

[0020] For current smartphones, there are usually three ways to manage the network: 1) Background apps are always connected to the network; 2) Apps are disconnected from the network immediately or after a delay after entering the background; 3) Background apps are disconnected from the network after losing WiFi;

[0021] For the first scenario, after using the power application, the user can obtain the user's network status at any time as long as the background is not forcibly cleaned up;

[0022] For the second scenario, users can monitor the network status only when using the power application;

[0023] For the third situation, the user's network status changes are monitored by whether the user is disconnected from the network: WIFI is lost or the background is forcibly cleared;

[0024] The users whose WIFI is lost in the first and third situations are considered as valid group users;

[0025] Step 2.3: According to the multi-layer tree structure divided in step 1, all the area elements in the bottom layer are independently marked as one geographic fence;

[0026] Step 2.4: When the effective group of users enters a certain geographic fence, the network status is monitored and the mobile traffic behavior characteristics of the users in the target area are counted.

[0027] Furthermore, step three specifically includes:

[0028] Step 3.1: Count all valid group users that appeared in the geo-fence one month before the current time point. Suppose that in the nth geo-fence, there were m valid group users that appeared in the previous month.

[0029] Step 3.2: Record the number of days the user appears in the geo-fence in a month and the duration of time the user spends in the geo-fence each day, respectively. nm , T nmk , where Data nm represents the number of days that the mth valid group user in the nth geo-fence appears, T nmk It indicates the duration of the mth valid group user in the nth geo-fence appearing on the kth day;

[0030] Step 3.3: Record the duration of the user's daily WIFI use in the geo-fence by time period, recorded as WIFITime nmkh ; and the duration of using the mobile network, recorded as MobileTime nmkh ; where h ranges from 0 to 24.

[0031] Furthermore, step four specifically includes:

[0032] Step 4.1: If at a certain time point, the number of users in a certain geographic fence area that exceeds the first preset threshold disappears from the WIFI network state, switches to the mobile data state or loses the connection at the same time, it is directly determined that the geographic fence area has a power outage, and the process directly jumps to step 5;

[0033] Step 4.2: Based on the user behavior library constructed in step 3, analyze the real-time data and monitor the power outage events based on the analysis of user behavior. The implementation method is as follows:

[0034] First, for a certain geo-fence, extract the real-time information of users in the geo-fence, including Data nm , T nmk 、WIFITime nmkr and MobileTime nmkr ;

[0035] Get real-time network status information of users in the geo-fence NET nm , indicating that the mth person in the nth geo-fence is connected to WIFI or mobile network at this time, taking Boolean value, 1 for WIFI connection, 0 for mobile network connection;

[0036] According to the current time, calculate the average duration of each user using WIFI and mobile network in the current period. The calculation formulas are:

[0037]

[0038] Where d is the day of the current month, and r indicates the time period at the current time point;

[0039] Filter the users currently in the geo-fence and keep the users who have "many days in the geo-fence each month" and "long time in the geo-fence on the current date". The filtering method is: Data nm >18 and T nmk >30 minutes; suppose that in the current geo-fence, after screening, there are s users left;

[0040] The average duration of the remaining s users using WIFI and mobile network in the current time period is:

[0041]

[0042] Calculate the ratio of the historical average WIFI usage time and mobile network usage time of s users in the time period at this time:

[0043]

[0044] Among them, if AverageMobile ns is 0, then R sTake a fixed value of 10;

[0045] NET defined previously nm After the above steps, it is now NET ns ;

[0046] For the current user, determine R s Size, if a user's R s If it is greater than the second preset threshold, the user's current NET ns The value indicates that the user has the habit of using WIFI for a long time during this period; suppose that among the s remaining users, R s The number of users greater than the threshold is t;

[0047] Construct the evaluation formula:

[0048]

[0049] A third preset threshold is set. If PJ is less than the third preset threshold, it indicates that among t users who have the habit of using WIFI for a long time during this period, there are users who use WIFI less than the third preset threshold at this time, and it is determined that there is a power outage in the geographical fence area.

[0050] A residential area real-time power outage monitoring device based on Internet traffic feedback, comprising:

[0051] The regional division module based on the power supply network is used to layer the power supply network data provided by the power supply company to form a multi-layer tree structure and display it on the map;

[0052] The user mobile traffic behavior feature statistics module is used to mark the user as a valid group user when the background APP of the user's smartphone is always connected to the network and the background APP is disconnected after losing WIFI. According to the multi-layer tree structure, all surface element areas in the bottom layer are independently marked as a geographic fence; the mobile traffic behavior features of the valid group users entering a certain geographic fence in the target area are counted, and the mobile traffic behavior features include the length of time and time period of using WIFI or mobile network;

[0053] A user mobile traffic behavior library construction module is used to organize and store the collected mobile traffic behavior characteristics of effective group users;

[0054] The residential area power outage monitoring module is used to realize real-time monitoring of power outages in residential areas of the target area through statistical analysis of the stored data, and then determine the power outage area;

[0055] The power outage area visualization module is used to visualize the power outage area determined in real time on the map.

[0056] Furthermore, the power supply network-based area division module is specifically used to:

[0057] In the residential electricity consumption area, the tree-structured distribution network is divided into multiple layers. The first layer is the root node distribution layer, which supplies electricity to the residents of the entire area. The second layer is forked into multiple branch nodes. The third layer is branched by multiple nodes in the second layer. Assume that there are n layers in total.

[0058] Load the default base map in ArcGIS software. The base map area is the target area that needs to be monitored for power outages.

[0059] Continue to load n layers: the first layer is the root node coverage area layer, which is stored as surface elements and the area is the entire target area;

[0060] Repeat the above steps to ensure that in each of the n layers, the area covered by the branch power grid is stored as a polygon element;

[0061] Perform a topology check: If a layer has multiple area features, each area feature should not intersect.

[0062] Furthermore, the user mobile traffic behavior feature statistics module is specifically used to:

[0063] Get the current network status through the APP installed on the smartphone;

[0064] Agreed conditions for obtaining user network status:

[0065] For current smartphones, there are usually three ways to manage the network: 1) Background apps are always connected to the network; 2) Apps are disconnected from the network immediately or after a delay after entering the background; 3) Background apps are disconnected from the network after losing WiFi;

[0066] For the first scenario, after using the power application, the user can obtain the user's network status at any time as long as the background is not forcibly cleaned up;

[0067] For the second scenario, users can monitor the network status only when using the power application;

[0068] For the third situation, the user's network status changes are monitored by whether the user is disconnected from the network: WIFI is lost or the background is forcibly cleared;

[0069] The users whose WIFI is lost in the first and third situations are considered as valid group users;

[0070] According to the divided multi-layer tree structure, all area elements in the bottom layer are independently marked as one geographic fence;

[0071] When a valid group of users enters a geographic fence, its network status is monitored and the mobile traffic behavior characteristics of users in the target area are counted.

[0072] Furthermore, the user mobile traffic behavior library construction module is specifically used to:

[0073] Count all valid group users that appeared in the geo-fence one month before the current time point. Suppose that in the nth geo-fence, there were m valid group users that appeared in the previous month.

[0074] Record the number of days the user appears in the geo-fence in a month and the duration of each day in the geo-fence, respectively. nm , T nmk , where Data nm represents the number of days that the mth valid group user in the nth geo-fence appears, T nmk It indicates the duration of the mth valid group user in the nth geo-fence appearing on the kth day;

[0075] Record the duration of the user's daily WIFI usage in the geo-fence by time period, recorded as WIFITime nmkh ; and the duration of using the mobile network, recorded as MobileTime nmkh ; where h ranges from 0 to 24.

[0076] Furthermore, the residential area power outage monitoring module is specifically used for:

[0077] If at a certain time point, the number of users in a certain geographic fence area that exceeds the first preset threshold disappears from the WIFI network state, switches to the mobile data state or loses the connection at the same time, it is directly determined that the geographic fence area has a power outage, and the process directly jumps to step 5;

[0078] Through the constructed user behavior library, real-time data is analyzed and power outage events are monitored based on the analysis of user behavior. The implementation method is as follows:

[0079] First, for a certain geo-fence, extract the real-time information of users in the geo-fence, including Data nm , T nmk 、WIFITime nmkr and MobileTime nmkr ;

[0080] Get real-time network status information of users in the geo-fence NET nm , indicating that the mth person in the nth geo-fence is connected to WIFI or mobile network at this time, taking Boolean value, 1 for WIFI connection, 0 for mobile network connection;

[0081] According to the current time, calculate the average duration of each user using WIFI and mobile network in the current period. The calculation formulas are:

[0082]

[0083] Where d is the day of the current month, and r indicates the time period at the current time point;

[0084] Filter the users currently in the geo-fence and keep the users who have "many days in the geo-fence each month" and "long time in the geo-fence on the current date". The filtering method is: Data nm >18 and T nmk >30 minutes; suppose that in the current geo-fence, after screening, there are s users left;

[0085] The average duration of the remaining s users using WIFI and mobile network in the current time period is:

[0086]

[0087] Calculate the ratio of the historical average WIFI usage time and mobile network usage time of s users in the time period at this time:

[0088]

[0089] Among them, if AverageMobile ns is 0, then R s Take a fixed value of 10;

[0090] NET defined previously nm After the above steps, it is now NET ns ;

[0091] For the current user, determine R s Size, if a user's R s If it is greater than the second preset threshold, the user's current NET ns The value indicates that the user has the habit of using WIFI for a long time during this period; suppose that among the s remaining users, R s The number of users greater than the threshold is t;

[0092] Construct the evaluation formula:

[0093]

[0094] Set a third preset threshold. If PJ is less than the third preset threshold, it indicates that in t users

[0095] The users have the habit of using WIFI for a long time during this period. At this time, the number of users using WIFI is less than the third preset threshold, and it is determined that there is a power outage in the geographical fence area.

[0096] The present invention mainly targets power outage events in residential areas, and provides a real-time power outage monitoring method and system for residential areas based on mobile Internet traffic feedback. It evaluates the behavioral habits of users' mobile phones in residential areas in two situations: "WIFI connection" and "mobile Internet connection", and realizes the discovery of power outage time when WIFI cannot be connected (power outage in residential areas). At the same time, combined with the characteristics of the power supply network, it realizes the delineation of the complete power outage area in the residential area, and generates a "real-time power outage map" in a visual form, effectively improving the service efficiency of the power supply service department. BRIEF DESCRIPTION OF THE DRAWINGS

[0097] Figure 1 It is a flow chart of a method for real-time power outage monitoring in residential areas based on mobile Internet traffic feedback according to an embodiment of the present invention;

[0098] Figure 2 It is a module block diagram of a residential area real-time power outage monitoring system based on mobile Internet traffic feedback according to an embodiment of the present invention. DETAILED DESCRIPTION

[0099] In order to make the purpose, technical solution and advantages of the embodiment of the present invention clearer, the technical solution in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all of the embodiments. Based on the embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. The entire system is implemented in software.

[0100] See also Figure 1 The embodiment of the present invention provides a method for real-time power outage monitoring in residential areas based on mobile Internet traffic feedback, comprising the following steps:

[0101] Step 1: Regional division based on power supply network: Layer the power supply network data provided by the power supply company to form a multi-layer tree structure and display it on the map. The specific implementation steps are:

[0102] Step 1.1: In the residential electricity consumption area, the most common distribution network structure is a tree structure. Therefore, the tree structure can be divided into multiple layers: the first layer is the root node distribution layer, which supplies electricity to the residents of the entire area. The second layer is forked into multiple branch nodes. The third layer is branched by multiple nodes of the second layer. Assume that there are n layers in total.

[0103] Step 1.2: In ArcGIS software, load the default base map, which is the target area for power outage monitoring;

[0104] Step 1.3, continue to load n layers: the first layer is the root node coverage area layer (equivalent to the regional distribution network bus), which is stored as a surface element, and the area is the entire target area;

[0105] Step 1.4, repeat the above steps to ensure that each of the n layers stores the area covered by the branch power grid as a surface element;

[0106] Step 1.5, perform topology check: If a layer has multiple surface elements, each surface element should not intersect (branch power distribution areas should not overlap).

[0107] At this point, the regional division according to the topological map of the power supply network and the visualization operation of the thematic map have been realized.

[0108] Step 2: Statistics of user mobile traffic behavior characteristics: When the background APP of the user's smartphone is always connected to the network and the background APP is disconnected after losing WIFI, the user is marked as a valid group user. According to the multi-layer tree structure divided in step 1, all surface element areas in the bottom layer are independently marked as a geographic fence; statistics are made on the mobile traffic behavior characteristics of the valid group users who enter a certain geographic fence in the target area, and the mobile traffic behavior characteristics include the duration and time period of using WIFI or mobile network. The specific implementation steps are:

[0109] Step 2.1: Since it is impossible to obtain the operator's data, it is impossible to obtain the overall situation of the user's mobile phone using the network. The current network status (including the background) can only be obtained through the power application (such as the "Online State Grid APP") (similar to the friend network status display in the QQ software): For example, for Android phones, the network type of the device can be obtained through the ConnectivityManager class during the development of the "Online State Grid APP";

[0110] Step 2.2: Agree on the conditions for obtaining user network status:

[0111] (a) For current smartphones, there are usually three network management methods: 1) Background apps are always connected to the network; 2) Apps are disconnected from the network immediately or after a delay after entering the background; 3) Background apps are disconnected from the network after losing WiFi;

[0112] (b) For the first situation, after using the "Online State Grid APP", the user can obtain the user's network status at any time as long as the background is not forcibly cleared;

[0113] (c) For the second situation, the user can only monitor the network status when using the "Online State Grid APP";

[0114] (d) For situation 3), the user's network status change can be monitored by whether the user is disconnected from the network: WIFI is lost or the background is forcibly cleared;

[0115] Therefore, only the "WIFI loss" in the first and third situations can be used as the target observation group for the subsequent user mobile traffic behavior, which is called the "effective group" in the present invention;

[0116] Optimized: Power supply companies can encourage users to open the "Online State Grid APP" and "actively" obtain users' network status through SMS and APP pop-up screens;

[0117] Step 2.3: To avoid collecting the user's specific location information for a long time (only obtaining the user's area information in the form of geo-fences), according to the multi-layer tree structure divided in step 1, all the surface element areas in the layer at the bottom layer (the leaf layer of the tree structure) are independently marked as 1 "geo-fence", that is, there are as many "geo-fences" as there are surface element areas;

[0118] Step 2.4: When a valid group of users enters a certain geographic fence, monitor its network status;

[0119] Step 2.5: After the effective group of users enters the geographic fence, there may be other reasons for the change of network status: for example, WIFI only covers the home, and the effective group of users walks out of the WIFI coverage area. Therefore, it is necessary to collect data for a long time to provide support for subsequent user behavior analysis.

[0120] Step 3: Building a user mobile traffic behavior database, which is used to organize the valid group user data collected in step 2 into the database, so as to facilitate the subsequent user behavior analysis and power outage monitoring based on data mining. The specific implementation steps are:

[0121] Step 3.1: As described in step 2.3, multiple geo-fences are formed by all the surface element areas in the bottom layer, and all valid group users who appeared in the geo-fences in the month before the current time point are counted. Suppose that in the nth geo-fence, a total of m valid group users appeared in the previous month;

[0122] Step 3.2: Record the number of days the user appears in the geo-fence in a month and the duration of time the user spends in the geo-fence each day, respectively. nm , T nmk , where Data nm represents the number of days that the mth valid group user in the nth geo-fence appears, T nmk It indicates the duration of the mth valid group user in the nth geo-fence appearing on the kth day;

[0123] Step 3.3: Record the duration of the user's daily WIFI use in the geo-fence by time period, recorded as WIFITime nmkh ; and the duration of using the mobile network, recorded as MobileTime nmkh ; where h ranges from 0 to 24, such as MobileTime 1234 It indicates the duration of mobile data usage by the second valid group of users in the first geo-fence at 4 o'clock on the third day, in minutes;

[0124] At this point, the construction of the user mobile traffic behavior library has been completed.

[0125] Furthermore, the accuracy of statistical data can be increased by adding statistics and analysis of time periods.

[0126] Step 4: Residential area power outage monitoring step: Through statistical analysis of the data stored in the previous steps, real-time monitoring of power outages in residential areas of the target area is achieved. The specific implementation steps are as follows:

[0127] Step 4.1: If at a certain time point, the number of users in a certain geographic fence area that exceeds a threshold (set as α) disappears from the WIFI network state at the same time, switches to the mobile data state or loses connection, it is directly determined that the geographic fence area has a power outage, and jumps directly to step 5;

[0128] For optimization, the threshold α needs to be dynamically set according to the time period: for example, during the day, when users are active, the value of α should be as large as possible, such as 0.8; at night, when users are less active, α can be smaller, such as 0.5;

[0129] Step 4.2: More generally, due to user regional activities, disconnection of APP connection, network disconnection during calls, etc., it is necessary to analyze real-time data based on the analysis of user behavior and monitor power outage events through the user behavior library built based on step 3. The implementation method is as follows:

[0130] a) First, for a certain geo-fence, extract the real-time (current) information of users in the geo-fence, including Data nm , T nmk 、WIFITime nmkr and MobileTime nmkr ;

[0131] b) Get real-time (current) network status information of users in the geo-fence NET nm , indicating that the mth person in the nth geo-fence is connected to WIFI or mobile network at this time, taking Boolean value, 1 for WIFI connection, 0 for mobile network connection;

[0132] c) According to the current time, calculate the average duration of each user using WIFI and mobile network in the current period. The calculation formulas are:

[0133]

[0134] Where d is the day of the current month, and r indicates the time period at the current time point;

[0135] d) Further filter the users currently in the geo-fence, and keep the users who are "in the geo-fence for many days per month" and "in the geo-fence for a long time on the current date (such as this day of last month)", and the filtering method is: Data nm

[0136] >18 and T nmk >30 minutes; suppose that in the current geo-fence, after screening, there are s users left;

[0137] e) The average duration of the remaining s users using WIFI and mobile network in the current time period is:

[0138]

[0139] f) Calculate the ratio of the historical average WIFI usage time and mobile network usage time of s users in the time period at this time:

[0140]

[0141] Among them, if AverageMobile ns is 0, then R s Take a fixed value of 10;

[0142] g) NET defined in b) nm , after screening in step d), it is now NET ns ;

[0143] h) For the current user, determine R s Size, if a user's R s If it is greater than the threshold (e.g. 5), the user's current NET ns Value; This indicates that the user has the habit of using WIFI for a long time during this period; Suppose that among the remaining s users, R s The number of users greater than the threshold is t;

[0144] i) Construct the evaluation formula:

[0145]

[0146] j) Set a threshold. If PJ is less than the threshold (0.1), it means that among t users (who have the habit of using WIFI for a long time during this period), only less than 0.1 (10%) users use WIFI at this time, and it is determined that there is a power outage in the geographical fence area; the remaining 10% WIFI users may be users of UPS and power bank routers (who can still use WIFI during a power outage).

[0147] Step 5: Visualizing the power outage area, which is used to visualize the power outage area (geo-fenced area) determined in real time on the map. The specific implementation steps are as follows:

[0148] Step 5.1, in the nth layer (the leaf layer of the tree structure described in step 1), fill the surface elements of the power outage area with a fixed color number, such as red (255,0,0) in the RGB color space;

[0149] Step 5.2, fill the surface element corresponding to the parent node (in the n-1 layer) of the power outage area (surface element) in the n layer with a fixed color number (255-255 / n,0,0);

[0150] Step 5.3: Follow the method in step 5.2. For example, in the n-2 layer element area, the fill color number is (255-2x255 / n,0,0);

[0151] Step 5.4, now the visualization of the thematic map of the power outage area is completed: the "darkest" red is displayed in the core power outage area; the "lighter" red is displayed in the upper level area of ​​the power outage area; and so on.

[0152] like Figure 2 As shown: A real-time power outage monitoring system for residential areas based on mobile Internet traffic feedback in an embodiment of the present invention includes the following functional modules:

[0153] A regional division module 10 based on the power supply network. The main function of this module is to layer the power supply network data provided by the power supply company and display it on the map. First, in the residential power consumption area, the most common distribution network structure is a tree structure. Therefore, the tree structure can be divided into multiple layers: the first layer is the root node distribution layer, which supplies electricity to the entire area of ​​residents, the second layer is forked into multiple branch nodes, and the third layer has multiple nodes of the second layer branched separately, assuming that there are n layers in total; then, in the ArcGIS software, load the default base map, the base map area is the target area that needs to monitor power outages, and at the same time, continue to load n layers: the first layer is the root node coverage area layer (equivalent to the regional distribution network bus), which is stored as a surface element, and the area is the entire target area; then, perform a topological check: if a layer has multiple surface elements, each surface element should not intersect (the branch distribution areas do not overlap); finally, the regional division and thematic map visualization operations according to the topological map of the power supply network are realized.

[0154] User mobile traffic behavior feature statistics module 20. The main function of this module is to count the mobile traffic behavior features of users in the target area, including: the duration of using different networks (WIFI or mobile network), usage time periods and other behavioral features. First, since it is impossible to obtain operator-side data, it is impossible to obtain the overall situation of the user's mobile phone using the network. The current network status (including the background) can only be obtained through the "Online State Grid APP" (similar to the network status display in QQ software); then, the user's network status acquisition conditions are agreed upon: a) For current smart phones, there are usually three network management methods: 1) The background APP is always disconnected; 2) The APP is disconnected immediately or delayed after entering the background; 3) The background APP is disconnected after losing WIFI; b) For the first case, after using the "Online State Grid APP", the user can obtain the user's network status at any time as long as the background is not forcibly cleaned; c) For the second case, the user can monitor the network status only when using the "Online State Grid APP"; d) For the third case, the user's network status can be monitored by whether the user is disconnected from the network Changes: WIFI is lost or the background is forcibly cleared; e) Only the "WIFI loss" in the first and third situations can be used as the target observation group for the subsequent user's mobile traffic behavior, which is called the "effective group" in the present invention; then, in order to avoid collecting the user's specific location information for a long time (only obtaining the user's area information in the form of a geographic fence), according to the multi-layer tree structure divided in step 1, all surface element areas in the layer at the bottom layer (the leaf layer of the tree structure) are independently marked as 1 "geo-fence", that is, there are as many "geo-fences" as there are surface element areas; finally, after the effective group users enter the geographic fence, there may be other reasons for the change of network status: for example, WIFI only covers the home, and the effective group users walk out of the WIFI coverage, so it is necessary to collect data for a long time to provide support for subsequent user behavior analysis.

[0155] The user mobile traffic behavior library construction module 30. The main function of this module is to organize the valid group user data collected by module 20 into the library, so as to facilitate the subsequent user behavior analysis and power outage monitoring based on data mining. First, as described in module 20, the multiple geographic fences formed by all the surface element areas in the lowest layer are counted, and all the valid group users who have appeared in the geographic fence one month before the current time point are counted. Suppose that in the nth geographic fence, there are m valid group users in the previous month; then, the number of days that the user appears in the geographic fence in one month and the daily duration in the geographic fence are recorded, which are recorded as Data nm , T nmk , where Data nm represents the number of days that the mth valid group user in the nth geo-fence appears, T nmkrepresents the duration of the mth valid group user in the nth geo-fence appearing on the kth day; finally, the duration of the user using WIFI in the geo-fence every day is recorded in different time periods, recorded as WIFITime nmkh ; and the duration of using the mobile network, recorded as MobileTime nmkh ; where h ranges from 0 to 24, such as MobileTime 1234 Indicates the duration of mobile data use by the second valid group of users in the first geo-fence at 4 o'clock on the third day, in minutes.

[0156] Residential area power outage monitoring module 40. The main function of this module is to achieve real-time monitoring of power outages in residential areas of the target area through statistical analysis of the data stored in the aforementioned modules. First, if at a certain time point, the existing effective group of users in a certain geographical fence area, the users exceeding the threshold ratio (set as α) disappear at the same time, the WIFI network status is converted to mobile data status or loses connection, then it is directly determined that there is a power outage in the geographical fence area, and jumps directly to module 50; then, in more general cases, due to user area activities, disconnection of APP connection, network disconnection during calls, etc., it is necessary to analyze real-time data based on the analysis of user behavior through the user behavior library constructed based on module 30 to monitor power outage events. This module needs to use all the data collected by module 30 and adopt a series of intelligent processes to implement it, as described in step 4.2.

[0157] Power outage area visualization module 50. The main function of this module is to visualize the power outage area (geographic fence area) determined in real time on the map. First, in the nth layer (the leaf layer of the tree structure described in step one), the surface element of the power outage area is filled with a fixed color number, such as red (255,0,0) in the RGB color space; then, the surface element corresponding to the parent node (in the n-1 layer) of the power outage area (surface element) in the nth layer is filled with a fixed color number (255-255 / n,0,0); by analogy with the method in step 5.2, such as in the n-2 layer element area, the fill color number is (255-2x255 / n,0,0); finally, the visualization display of the thematic map of the power outage area is completed: the "darkest" red is displayed in the core power outage area; the "lighter" red is displayed in the upper level area of ​​the power outage area; and so on.

[0158] The present invention aims at power outage events in residential areas and provides a real-time power outage monitoring method and system for residential areas based on mobile Internet traffic feedback. The method evaluates the behavioral habits of users' mobile phones in residential areas in two situations: "WIFI connection" and "mobile Internet connection". It can realize the discovery of power outage time when WIFI cannot be connected (power outage in residential areas). At the same time, it combines the characteristics of the power supply network to realize the delineation of the complete power outage area in the residential area, and generates a "real-time power outage map" in a visual form, effectively improving the service efficiency of the power supply service department.

[0159] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0160] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0161] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0162] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0163] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for real-time power outage monitoring in residential areas based on mobile Internet traffic feedback, characterized in that: The steps include: Step 1: Regional division based on power supply network: Layer the power supply network data provided by the power supply company to form a multi-layer tree structure and display it on the map; Step 2: Statistics of user mobile traffic behavior characteristics: When the background APP of the user's smartphone is always connected to the network and the background APP is disconnected after losing WIFI, the user is marked as a valid group user. According to the multi-layer tree structure divided in step 1, all the surface feature areas in the bottom layer are independently marked as 1 geographic fence; Counting the mobile traffic behavior characteristics of valid groups of users entering a certain geographic fence in the target area, wherein the mobile traffic behavior characteristics include the duration and time period of using WIFI or mobile network; Step 3: Building a user mobile traffic behavior database: sorting and storing the mobile traffic behavior characteristics of the effective group users collected in step 2; Step 4: Power outage monitoring in residential areas: Through statistical analysis of the data stored in step 3, real-time monitoring of power outages in residential areas in the target area is achieved to determine the power outage area; Step 5: Visualize the power outage area: Visualize the power outage area determined in real time in step 4 on the map.

2. The method for real-time power outage monitoring in residential areas based on mobile Internet traffic feedback as claimed in claim 1, characterized in that: Step 1 specifically includes: Step 1.1: In the residential electricity consumption area, the tree-structured distribution network is divided into multiple layers. The first layer is the root node distribution layer, which supplies electricity to the residents of the entire area. The second layer is forked into multiple branch nodes. The third layer is further branched from multiple nodes of the second layer. Assume that there are n layers in total. Step 1.2: Load the default base map in ArcGIS software. The base map area is the target area that needs to be monitored for power outages. Step 1.3, continue to load n layers: the first layer is the root node coverage area layer, which is stored as surface elements and the area is the entire target area; Step 1.4, repeat the above steps to ensure that each of the n layers stores the area covered by the branch power grid as a surface element; Step 1.5: Perform topology check: If a layer has multiple surface elements, each surface element should not intersect.

3. The method for real-time power outage monitoring in residential areas based on mobile Internet traffic feedback as claimed in claim 1, characterized in that: Step 2 specifically includes: Step 2.1, obtain the current network status through the APP installed on the smartphone; Step 2.2: Agree on the conditions for obtaining user network status: For current smartphones, there are usually three ways to manage the network: 1) Background apps are always connected to the network; 2) Apps are disconnected from the network immediately or after a delay after entering the background; 3) Background apps are disconnected from the network after losing WiFi; For the first scenario, after using the power application, the user can obtain the user's network status at any time as long as the background is not forcibly cleaned up; For the second scenario, users can monitor the network status only when using the power application; For the third situation, the user's network status changes can be monitored by whether the user is disconnected from the network: WIFI is lost or the background is forcibly cleared; The users whose WIFI is lost in the first and third situations are considered as valid group users; Step 2.3: According to the multi-layer tree structure divided in step 1, all the area elements in the bottom layer are independently marked as one geographic fence; Step 2.4: When the effective group of users enters a certain geographic fence, the network status is monitored and the mobile traffic behavior characteristics of the users in the target area are counted.

4. The method for real-time power outage monitoring in residential areas based on mobile Internet traffic feedback as claimed in claim 2, characterized in that: Step three specifically includes: Step 3.1: Count all valid group users that appeared in the geo-fence one month before the current time point. Suppose that in the nth geo-fence, there were m valid group users that appeared in the previous month. Step 3.2: Record the number of days the user appears in the geo-fence in a month and the duration of time the user spends in the geo-fence each day, respectively. nm , T nmk , where Data nm represents the number of days that the mth valid group user in the nth geo-fence appears, T nmk It indicates the duration of the mth valid group user in the nth geo-fence appearing on the kth day; Step 3.3: Record the duration of the user's daily WIFI use in the geo-fence by time period, recorded as WIFITime nmkh ; and the duration of using the mobile network, recorded as MobileTime nmkh ; where h ranges from 0 to 24.

5. The method for real-time power outage monitoring in residential areas based on mobile Internet traffic feedback as claimed in claim 4, characterized in that: Step 4 specifically includes: Step 4.1: If at a certain time point, the number of users in a certain geographic fence area that exceeds the first preset threshold disappears from the WIFI network state, switches to the mobile data state or loses the connection at the same time, it is directly determined that the geographic fence area has a power outage, and the process directly jumps to step 5; Step 4.2: Based on the user behavior library constructed in step 3, analyze the real-time data and monitor the power outage events based on the analysis of user behavior. The implementation method is as follows: First, for a certain geo-fence, extract the real-time information of users in the geo-fence, including Data nm , T nmk 、WIFITime nmkr and MobileTime nmkr ; Among them, r indicates the time period of the current time point; Get real-time network status information of users in the geo-fence NET nm , indicating that the mth person in the nth geo-fence is connected to WIFI or mobile network at this time, taking Boolean value, 1 for WIFI connection, 0 for mobile network connection; According to the current time, calculate the average duration of each user using WIFI and mobile network in the current period. The calculation formulas are: ； ； Where d is the day of the current month, and r indicates the time period at the current time point; Filter the users currently in the geo-fence and keep the users who "spend more days in the geo-fence each month" and "spend more time in the geo-fence on the current date". The filtering method is: Data nm >18 and T nmk >30 minutes; suppose that in the current geo-fence, after screening, there are s users left; The average duration of the remaining s users using WIFI and mobile network in the current time period is: ； ； Where n represents the nth geo-fence, s represents the sth valid users, k represents the duration of occurrence on the kth day, and r represents the current time period; Calculate the ratio of the historical average WIFI usage time and mobile network usage time of s users in the time period at this time: ； Among them, if If is 0, Take a fixed value of 10; NET defined previously nm After the above steps, it is now NET ns ; For the current user, determine Size, if a user's If it is greater than the second preset threshold, the user's current NET ns The value indicates that the user has the habit of using WIFI for a long time during this period; suppose that among the remaining s users, The number of users greater than the threshold is t; Construct the evaluation formula: ； A third preset threshold is set. If PJ is less than the third preset threshold, it indicates that among t users who have the habit of using WIFI for a long time during this period, there are users who use WIFI less than the third preset threshold at this time, and it is determined that there is a power outage in the geographical fence area.

6. A real-time power outage monitoring device for residential areas based on mobile Internet traffic feedback, characterized in that: include: The regional division module based on the power supply network is used to layer the power supply network data provided by the power supply company to form a multi-layer tree structure and display it on the map; The user mobile traffic behavior feature statistics module is used to mark the user as a valid group user when the background APP of the user's smartphone is always connected to the network and the background APP is disconnected after losing WIFI. According to the multi-layer tree structure, all the surface feature areas in the bottom layer are independently marked as a geographic fence; Counting the mobile traffic behavior characteristics of valid groups of users entering a certain geographic fence in the target area, wherein the mobile traffic behavior characteristics include the duration and time period of using WIFI or mobile network; A user mobile traffic behavior library construction module is used to organize and store the collected mobile traffic behavior characteristics of effective group users; The residential area power outage monitoring module is used to realize real-time monitoring of power outages in residential areas of the target area through statistical analysis of the stored data, and then determine the power outage area; The power outage area visualization module is used to visualize the power outage area determined in real time on the map.

7. The device for real-time power outage monitoring in residential areas based on mobile Internet traffic feedback as claimed in claim 6, characterized in that: The power supply network-based area division module is specifically used for: In the residential electricity consumption area, the tree-structured distribution network is divided into multiple layers. The first layer is the root node distribution layer, which supplies electricity to the residents of the entire area. The second layer is forked into multiple branch nodes. The third layer is branched by multiple nodes in the second layer. Assume that there are n layers in total. Load the default base map in ArcGIS software. The base map area is the target area that needs to be monitored for power outages. Continue to load n layers: the first layer is the root node coverage area layer, which is stored as surface elements and the area is the entire target area; Repeat the above steps to ensure that in each of the n layers, the area covered by the branch power grid is stored as a polygon element; Perform a topology check: If a layer has multiple area features, each area feature should not intersect.

8. The device for real-time power outage monitoring in residential areas based on mobile Internet traffic feedback as claimed in claim 6, characterized in that: The user mobile traffic behavior feature statistics module is specifically used to: Get the current network status through the APP installed on the smartphone; Agreed conditions for obtaining user network status: For current smartphones, there are usually three ways to manage the network: 1) Background apps are always connected to the network; 2) Apps are disconnected from the network immediately or after a delay after entering the background; 3) Background apps are disconnected from the network after losing WiFi; For the first scenario, after using the power application, the user can obtain the user's network status at any time as long as the background is not forcibly cleaned up; For the second scenario, users can monitor the network status only when using the power application; For the third situation, the user's network status changes can be monitored by whether the user is disconnected from the network: WIFI is lost or the background is forcibly cleared; The users whose WIFI is lost in the first and third situations are considered as valid group users; According to the divided multi-layer tree structure, all area elements in the bottom layer are independently marked as one geographic fence; When a valid group of users enters a geographic fence, its network status is monitored and the mobile traffic behavior characteristics of users in the target area are counted.

9. The device for real-time power outage monitoring in residential areas based on mobile Internet traffic feedback as claimed in claim 7, characterized in that: The user mobile traffic behavior library construction module is specifically used to: Count all valid group users that appeared in the geo-fence one month before the current time point. Suppose that in the nth geo-fence, there were m valid group users that appeared in the previous month. Record the number of days the user appears in the geo-fence in a month and the duration of each day in the geo-fence, respectively. nm , T nmk , where Data nm represents the number of days that the mth valid group user in the nth geo-fence appears, T nmk It indicates the duration of the mth valid group user in the nth geo-fence appearing on the kth day; Record the duration of the user's daily WIFI usage in the geo-fence by time period, recorded as WIFITime nmkh ; and the duration of using the mobile network, recorded as MobileTime nmkh ; where h ranges from 0 to 24.

10. The device for real-time power outage monitoring in residential areas based on mobile Internet traffic feedback according to claim 9, characterized in that: The residential area power outage monitoring module is specifically used for: If at a certain time point, the number of users in a valid group in a certain geographical fence area that exceeds a first preset threshold disappears from the WIFI network state, switches to the mobile data state or loses the connection at the same time, it is directly determined that there is a power outage in the geographical fence area, and the determined power outage area is visualized on the map; Through the constructed user behavior library, real-time data is analyzed and power outage events are monitored based on the analysis of user behavior. The implementation method is as follows: First, for a certain geo-fence, extract the real-time information of users in the geo-fence, including Data nm , T nmk 、WIFITime nmkr and MobileTime nmkr ; Get real-time network status information of users in the geo-fence NET nm , indicating that the mth person in the nth geo-fence is connected to WIFI or mobile network at this time, taking Boolean value, 1 for WIFI connection, 0 for mobile network connection; According to the current time, calculate the average duration of each user using WIFI and mobile network in the current period. The calculation formulas are: ； ； Where d is the day of the current month, and r indicates the time period at the current time point; Filter the users currently in the geo-fence and keep the users who "spend more days in the geo-fence each month" and "spend more time in the geo-fence on the current date". The filtering method is: Data nm >18 and T nmk >30 minutes; suppose that in the current geo-fence, after screening, there are s users left; The average duration of the remaining s users using WIFI and mobile network in the current time period is: ； ； Calculate the ratio of the historical average WIFI usage time and mobile network usage time of s users in the time period at this time: ； Among them, if If is 0, Take a fixed value of 10; NET defined previously nm After the above steps, it is now NET ns ; For the current user, determine Size, if a user's If it is greater than the second preset threshold, the user's current NET ns The value indicates that the user has the habit of using WIFI for a long time during this period; suppose that among the remaining s users, The number of users greater than the threshold is t; Construct the evaluation formula: ； A third preset threshold is set. If PJ is less than the third preset threshold, it indicates that among t users who have the habit of using WIFI for a long time during this period, there are users who use WIFI less than the third preset threshold at this time, and it is determined that there is a power outage in the geographical fence area.

Images