A photovoltaic power theft monitoring method based on Beidou communication

Abstract

The present invention relates to the field of photovoltaic electricity theft monitoring technology, and discloses a photovoltaic electricity theft monitoring method based on Beidou communication. The method comprises the following steps: Step 1: monitoring the current data of each branch of a photovoltaic string using a sensor, and determining whether the current of each branch is abnormal by analyzing the current data; if a branch with abnormal current exists, collecting the current and voltage data of each branch in real time and converting the data into the algebraic sum of the branch power generation; Step 2: calculating and obtaining a predicted power generation value of the photovoltaic string based on photovoltaic power generation environment data and photovoltaic module parameter data; and dynamically analyzing the predicted power generation value and the algebraic sum of the power generation of each branch to determine the risk of electricity theft. By integrating dynamic power generation analysis with environmental data, the present invention improves the accuracy of electricity theft identification and avoids misjudgments caused by meteorological interference.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic electricity theft monitoring, and in particular to a photovoltaic electricity theft monitoring method based on Beidou communication. Background Art

[0002] Photovoltaic power generation, a technology that directly converts solar energy into electricity using the photovoltaic effect of semiconductor materials, has become a key option for global energy transition. With the rapid growth of photovoltaic installed capacity, power plant operations and management face numerous challenges, particularly electricity theft.

[0003] To address the issue of photovoltaic power theft, existing technologies mainly use prevention and control measures based on current monitoring and manual inspections. However, these methods have significant limitations in application. Traditional current monitoring systems find it difficult to distinguish between power generation anomalies caused by meteorological and environmental influences that result in actual power theft. Moreover, manual inspections are inefficient and cannot cover large-scale power stations, especially in remote areas with weak communication infrastructure. The existing technology system makes it difficult to build a complete closed loop of monitoring, positioning, and evidence collection technology, resulting in power station operators facing multiple difficulties in their anti-power theft work. Summary of the Invention

[0004] The purpose of this invention is to provide a method for monitoring photovoltaic power theft based on Beidou communication to solve the above technical problems:

[0005] The purpose of the present invention can be achieved through the following technical solutions:

[0006] A method for monitoring photovoltaic power theft based on Beidou communication includes the following steps:

[0007] Step 1: Use sensors to monitor the current data of each branch of the photovoltaic string. By analyzing the current data, determine whether the current of each branch is abnormal. If there is an abnormal current branch, collect the current and voltage data of each branch in real time and convert the data into the algebraic sum of the branch power generation;

[0008] Step 2: Calculate and obtain the power generation forecast value of the photovoltaic string based on the photovoltaic power generation environment data and photovoltaic module parameter data; dynamically analyze the power generation forecast value and the algebraic sum of the power generation of each branch to determine the risk of power theft;

[0009] Step 3: When it is determined that there is a risk of electricity theft, the Beidou timing function is used to synchronize the timestamps of all sensors to locate the location information of the photovoltaic string with the abnormal current branch; and a drone inspection strategy is established based on the location information and photovoltaic power generation environment data;

[0010] Step 4: Implement the drone inspection strategy and collect evidence of electricity theft through drone inspections.

[0011] As a further technical solution, photovoltaic power generation environment data includes: irradiance data collected by the radiometer and meteorological data of the photovoltaic power station obtained by the weather station; photovoltaic module parameter data includes: conversion efficiency of the photovoltaic module, actual temperature of the photovoltaic module, standard test temperature of the photovoltaic module, and power temperature coefficient of the photovoltaic module.

[0012] As a further technical solution, the process of analyzing the current data to determine whether the current of each branch is abnormal includes:

[0013] Collect branch current and corresponding timestamps, and convert real-time current data into a current-time curve;

[0014] The current change curve is compared and analyzed with the standard change curve of the current in the current environment in the preset interval. The comparison and analysis result is indicated as the current anomaly coefficient. By controlling and analyzing the threshold value of the current anomaly coefficient, it is determined whether the branch current is abnormal.

[0015] As a further technical solution, the process of determining the risk of electricity theft includes:

[0016] By formula Calculate the algebraic sum of the power generation of each branch ;

[0017] By formula Calculate and obtain the predicted power generation value of the photovoltaic string ;in is the conversion efficiency of the photovoltaic module, is the total area of ​​the string, is the irradiance, is the actual temperature of the PV module, is the standard test temperature for photovoltaic modules. is the power temperature coefficient of the photovoltaic module;

[0018] By algebraically summing multiple groups of power generation and the predicted power generation value of the corresponding PV string The risk coefficient of electricity theft is obtained by difference analysis.

[0019] As a further technical solution, the algebraic sum of multiple groups of power generation and the predicted power generation value of the corresponding PV string The difference analysis process includes:

[0020] During the preset monitoring phase, extract Algebraic sum of group power generation Power generation forecast value relative to timestamp ;

[0021] By formula Calculate the risk factor of electricity theft ;in, 、 is the preset weight coefficient;

[0022] The risk factor of electricity theft is compared with the preset threshold For comparison:

[0023] like , then it is judged that there is no risk of electricity theft in the corresponding PV string, and the drone inspection strategy is not implemented;

[0024] like , it is judged that the corresponding PV string has the risk of electricity theft, and the drone inspection strategy is established based on the location information of the PV strings in the abnormal current branch and the PV power generation environment data.

[0025] As a further technical solution, the process of establishing a drone inspection strategy includes:

[0026] Obtain meteorological data in the photovoltaic power plant area through the weather station, including wind speed, rainfall, humidity and visibility;

[0027] Normalize the acquired meteorological data to obtain the corresponding meteorological normalization index, perform weighted sum calculation on each meteorological normalization index according to the preset weight, and output the calculation result to indicate the navigation feasibility parameter;

[0028] Based on the navigation feasibility parameters, it is determined whether to dispatch a drone to inspect the photovoltaic power station area.

[0029] As a further technical solution, the process of establishing a drone inspection strategy also includes:

[0030] If the navigation feasibility parameters do not exceed the preset range, a comprehensive analysis is performed on the location information of the photovoltaic strings with abnormal current branches and the power theft risk coefficient of the corresponding photovoltaic strings, and the unmanned planned route is obtained based on the comprehensive analysis results.

[0031] As a further technical solution, the process of comprehensively analyzing the location information of PV strings with abnormal current branches and the power theft risk coefficient of the corresponding PV strings includes:

[0032] Obtain the location information of the drone base station and the three-dimensional model of the photovoltaic power plant, establish a spatial coordinate system in the three-dimensional model, and convert the location information of the photovoltaic strings with current anomalies into the spatial coordinates of the detection points. The location coordinates of the drone base station and the spatial coordinates of the detection points are used as navigation nodes.

[0033] Before the drone is about to fly to the next node, the formula Calculate the priority index of each remaining node , select the node corresponding to the maximum priority index as the next target node;

[0034] in, 、 is the preset weight, is the electricity theft risk coefficient of the PV string, is the preset threshold corresponding to the electricity theft risk factor; is the route distance from the remaining nodes to the node where the drone is currently located; The preset detection time of the detection point.

[0035] Beneficial effects of the present invention:

[0036] (1) This invention improves the accuracy of electricity theft identification by integrating dynamic power generation analysis with environmental data, avoiding misjudgments caused by meteorological interference. Secondly, the Beidou timing and positioning function breaks through the limitations of communication infrastructure and realizes the rapid location of abnormal strings in remote areas. In addition, drone intelligent inspections replace manual inspections and can more accurately detect abnormal strings, forming a closed-loop anti-electricity theft system covering monitoring, abnormal point location, key detection and evidence collection, which is particularly suitable for the automated supervision of large-scale photovoltaic power stations.

[0037] (2) The UAV inspection route planning process provided by the present invention establishes a three-dimensional spatial coordinate system of the photovoltaic power station, maps the current abnormal branch position and the UAV base station into navigation nodes, and designs a dynamic priority index formula. It comprehensively considers the risk factor of electricity theft, route distance and detection time, calculates the priority index of the remaining nodes in real time during each flight decision, and selects the highest value as the next target node, thereby achieving flexible response to new detection points during the inspection process, ensuring priority detection of high-risk targets, optimizing flight path efficiency, and solving the response delay and insufficient coverage problems caused by traditional fixed routes. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The present invention will be further described below with reference to the accompanying drawings.

[0039] Figure 1 A flowchart of a method for monitoring photovoltaic power theft based on Beidou communication provided by the present invention;

[0040] Figure 2 This is a process diagram for establishing the drone inspection strategy in the present invention. DETAILED DESCRIPTION

[0041] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0042] See also Figure 1 As shown, a method for monitoring photovoltaic power theft based on Beidou communication includes the following steps:

[0043] Step 1: Use sensors to monitor the current data of each branch of the PV string. All sensors are integrated with Beidou timing modules, specifically obtaining UTC time through Beidou RDSS (Radio Determination Service). Each data packet is accompanied by a Beidou timing timestamp to facilitate subsequent PV string positioning. By analyzing the current data, determine whether the current in each branch is abnormal. If there is an abnormal current branch, collect the current and voltage data of each branch in real time and convert the data into the algebraic sum of the branch power generation.

[0044] Step 2: Calculate the predicted power generation value of the PV string based on PV power generation environmental data and PV module parameter data; dynamically analyze the predicted power generation value and the algebraic sum of the power generation of each branch to determine the risk of power theft. It should be noted that PV power generation environmental data specifically includes: irradiance data collected by a radiometer and meteorological data of the PV power station obtained by a weather station; PV module parameter data includes: PV module conversion efficiency, actual PV module temperature, standard test temperature of PV modules, and power temperature coefficient of PV modules. Generating power generation predictions through physical models or AI algorithms and comparing them with the algebraic sum of the measured power generation can effectively distinguish between environmental factors and human theft.

[0045] Step 3: When a risk of electricity theft is identified, the Beidou timing function synchronizes all sensor timestamps to locate the PV string with the abnormal current branch. A drone inspection strategy is then established based on this location information and PV power generation environmental data. Specifically, the Beidou short message function synchronizes all sensor timestamps in communication blind spots. Combined with Beidou's high-precision positioning, the longitude and latitude coordinates of the abnormal string are determined. The optimal drone inspection route is then planned based on environmental data (primarily meteorological data that could affect the drone's normal flight).

[0046] Step 4: Implement drone inspection strategies and collect evidence of electricity theft through drone inspections. Specifically, drones can be equipped with infrared thermal imagers and visible light cameras to capture the temperature distribution and wiring status of abnormal branches, automatically identifying abnormal hot spots or illegal wiring, and generating a forensic report.

[0047] Through the above technical solution, this embodiment provides a method for monitoring photovoltaic power theft based on Beidou communication. Through Beidou synchronization, environmental modeling and drone collaboration, it can solve the two problems of high false alarm rate of traditional monitoring systems and low efficiency of manual inspections. First, the dynamic power generation analysis integrating environmental data significantly improves the accuracy of power theft identification and avoids misjudgment caused by meteorological interference. In addition, Beidou's timing and positioning functions break through the limitations of communication infrastructure and realize the rapid positioning of abnormal strings in remote areas. The intelligent inspection of drones replaces manual labor and can perform more accurate detection of abnormal strings, forming a closed-loop anti-power theft system covering monitoring, abnormal point positioning, key detection and evidence collection, which is particularly suitable for the automated supervision of large-scale photovoltaic power stations.

[0048] The process of analyzing current data to determine whether each branch current is abnormal involves collecting branch current and corresponding timestamps, converting the real-time current data into a current-over-time curve, and comparing and analyzing the current curve with a standard current curve for the current environment within a preset interval. The comparison result is indicated as a current anomaly coefficient. By applying a threshold control analysis to the current anomaly coefficient, the branch current anomaly is determined. To determine whether a branch current is abnormal, sensors first collect real-time current data from each branch and Beidou timing timestamps to construct a current-over-time curve. Subsequently, based on the characteristics of the PV modules (such as rated current and temperature coefficient) and current environmental data (such as irradiance, temperature, and humidity), a standard current curve for that environment is generated. This process can be modeled using historical data and is not detailed here. The measured curve is dynamically compared with the standard curve, and the deviation between the two is calculated using a dynamic time warping (DTW) or root mean square error (RMSE) algorithm. The current anomaly coefficient is then output. If this coefficient exceeds a preset threshold, the branch is identified as abnormal, triggering subsequent voltage acquisition and power generation analysis. It should also be noted that, during the specific implementation, an adjustable threshold value can be provided for the current anomaly coefficient, so as to flexibly set the sensitivity for different photovoltaic systems (such as distributed and centralized) and reduce the missed alarm rate.

[0049] Through the above technical solution, this embodiment provides a process for determining whether the current in each branch is abnormal. Traditional methods rely only on the absolute value of the current or a simple fluctuation threshold, and cannot distinguish between environmental noise and electricity theft signals. However, this method significantly reduces the misjudgment rate through curve similarity analysis and dynamic threshold control.

[0050] The process of determining electricity theft risk includes:

[0051] By formula Calculate the algebraic sum of the power generation of each branch ;

[0052] By formula Calculate and obtain the predicted power generation value of the photovoltaic string ;in is the conversion efficiency of the photovoltaic module, is the total area of ​​the string, is the irradiance, is the actual temperature of the PV module, is the standard test temperature for photovoltaic modules. is the power temperature coefficient of the photovoltaic module;

[0053] By algebraically summing multiple groups of power generation and the predicted power generation value of the corresponding PV string The risk coefficient of electricity theft is obtained by difference analysis.

[0054] Through the above technical solution, this embodiment provides a process for judging the risk of electricity theft. Specifically, first, the formula , Calculate the algebraic sum of the power generation of each branch of the photovoltaic string And the predicted power generation value of the photovoltaic string ; The predicted power generation value of the photovoltaic string is an ideal value, which is usually greater than the algebraic sum of power generation . In the formula, is the conversion efficiency of photovoltaic modules, that is, the photoelectric conversion efficiency under standard test conditions (STC). is the total area of ​​the string, is the irradiance, which can be obtained through environmental sensors or satellite data. The actual temperature of the photovoltaic module is affected by the ambient temperature, irradiance and heat dissipation conditions. is the standard test temperature for photovoltaic modules. is the power temperature coefficient of the photovoltaic module, which indicates the attenuation rate of the module output power as the temperature rises (usually -0.3%~-0.5% / ℃). and the predicted power generation value of the corresponding PV string The risk coefficient of electricity theft is obtained by difference analysis.

[0055] The algebraic sum of multiple groups of power generation and the predicted power generation value of the corresponding PV string The difference analysis process includes:

[0056] During the preset monitoring phase, extract Algebraic sum of group power generation Power generation forecast value relative to timestamp ;

[0057] By formula Calculate the risk factor of electricity theft ;in, 、 is the preset weight coefficient;

[0058] The risk factor of electricity theft is compared with the preset threshold For comparison:

[0059] like , then it is judged that there is no risk of electricity theft in the corresponding PV string, and the drone inspection strategy is not implemented;

[0060] like , it is judged that the corresponding PV string has the risk of electricity theft, and the drone inspection strategy is established based on the location information of the PV strings in the abnormal current branch and the PV power generation environment data.

[0061] Through the above technical solution, this embodiment provides a method for algebraically summing multiple groups of power generation. and the predicted power generation value of the corresponding PV string The process of differential analysis, specifically, calculating the risk coefficient of electricity theft , and then compare the electricity theft risk factor with the preset threshold For comparison: When When Power generation forecast value relative to timestamp The difference is small, which can generally be caused by environmental and system factors, such as environmental data collection delay, sensor measurement error, etc. Therefore, it is judged that there is no risk of electricity theft in the corresponding photovoltaic string, and the drone inspection strategy is not implemented. When Power generation forecast value relative to timestamp If the difference is large, it is judged that the corresponding PV string has the risk of electricity theft, and the drone inspection strategy is established based on the location information of the PV string in the current abnormal branch and the PV power generation environment data.

[0062] See also Figure 2 As shown, the process of establishing a drone inspection strategy includes:

[0063] Obtain meteorological data in the photovoltaic power plant area through the weather station, including wind speed, rainfall, humidity and visibility;

[0064] Normalize the acquired meteorological data to obtain the corresponding meteorological normalization index. Specifically, each meteorological data can be normalized to the range of 0~1, such as the wind speed normalization index ,in, is the wind speed measurement value, The wind threshold is level 6. The weighted sum of each meteorological normalized index is calculated according to the preset weights, and the calculation result is output to indicate the navigation feasibility parameter;

[0065] Based on the navigation feasibility parameters, it is determined whether to dispatch a drone to inspect the photovoltaic power station area.

[0066] The process of establishing a drone inspection strategy also includes:

[0067] If the navigation feasibility parameters are within the preset range, the system will conduct a comprehensive analysis of the location of the PV strings with abnormal current branches and the corresponding electricity theft risk factors, and then calculate the unmanned route. If the navigation feasibility parameters are outside the preset range, the inspection will be suspended until the weather improves and rescheduled, and abnormal weather data will be recorded.

[0068] Through the above technical solutions, this embodiment provides a process for establishing a drone inspection strategy. This method achieves safer and more accurate drone inspections through quantitative meteorological data evaluation and dynamic route planning, and is particularly suitable for large-scale, complex photovoltaic power plants.

[0069] The process of comprehensively analyzing the location information of PV strings with abnormal current branches and the power theft risk coefficient of the corresponding PV strings includes:

[0070] Obtain the location information of the drone base station and the 3D model of the PV power plant. Specifically, build a 3D digital twin model of the PV power plant using drone LiDAR scanning or CAD drawings. Establish a spatial coordinate system within the 3D model and convert the location information of PV strings with current anomalies into the spatial coordinates of detection points. Use the drone base station location coordinates and the detection point spatial coordinates as navigation nodes.

[0071] Before the drone is about to fly to the next node, the formula Calculate the priority index of each remaining node , select the node corresponding to the maximum priority index as the next target node; through the above judgment logic, when the drone is in the inspection process, if there are new inspection points, the inspection efficiency will not be reduced due to the premature fixing of the route.

[0072] in, 、 is the preset weight, which can be obtained by fitting empirical data. is the electricity theft risk coefficient of the PV string, is the preset threshold corresponding to the electricity theft risk factor; is the route distance from the remaining nodes to the node where the drone is currently located; The preset detection time of the detection point.

[0073] Through the above technical solution, this embodiment provides a specific process for comprehensively analyzing the location information of photovoltaic strings with abnormal current branches and the corresponding electricity theft risk factors of the photovoltaic strings. By establishing a three-dimensional spatial coordinate system for the photovoltaic power station, the locations of abnormal current branches and drone base stations are mapped as navigation nodes. A dynamic priority index formula is designed, which comprehensively considers the electricity theft risk factor, route distance, and detection time. The priority index of the remaining nodes is calculated in real time during each flight decision, and the highest value is selected as the next target node. This allows for flexible response to newly added inspection points during the inspection process, ensuring priority detection of high-risk targets while optimizing flight path efficiency, solving the response delays and insufficient coverage caused by traditional fixed routes.

[0074] The present invention may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present invention.

[0075] A computer-readable storage medium can be a tangible device that can hold and store instructions used by an instruction execution device. Examples of computer-readable storage media include electrical storage devices, magnetic storage devices, optical storage devices, electromagnetic storage devices, semiconductor storage devices, or any suitable combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or raised structure within a groove on which instructions are stored, and any suitable combination thereof. As used herein, a computer-readable storage medium is not to be construed as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse passing through a fiber optic cable), or an electrical signal transmitted via wires.

[0076] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions to be stored in the computer-readable storage medium in each computing / processing device.

[0077] Although the present invention is disclosed as above, the protection scope of the present invention is not limited thereto. Those skilled in the art may make various changes and modifications without departing from the spirit and scope of the present invention, and these changes and modifications will fall within the protection scope of the present invention.

Claims

1. A method for monitoring photovoltaic power theft based on Beidou communication, characterized in that: The method comprises the following steps: Step 1: Use sensors to monitor the current data of each branch of the photovoltaic string. By analyzing the current data, determine whether the current of each branch is abnormal. If there is an abnormal current branch, collect the current and voltage data of each branch in real time and convert the data into the algebraic sum of the branch power generation; Step 2: Calculate and obtain the power generation forecast value of the photovoltaic string based on the photovoltaic power generation environment data and photovoltaic module parameter data; dynamically analyze the power generation forecast value and the algebraic sum of the power generation of each branch to determine the risk of power theft; Step 3: When it is determined that there is a risk of electricity theft, the Beidou timing function is used to synchronize the timestamps of all sensors to locate the location information of the photovoltaic string with the abnormal current branch; and a drone inspection strategy is established based on the location information and photovoltaic power generation environment data; Step 4: Implement drone inspection strategies and collect evidence of electricity theft through drone inspections. Photovoltaic power generation environmental data includes: irradiance data collected by a radiometer and meteorological data of the photovoltaic power station obtained by a weather station; photovoltaic module parameter data includes: conversion efficiency of the photovoltaic module, actual temperature of the photovoltaic module, standard test temperature of the photovoltaic module, and power temperature coefficient of the photovoltaic module; The process of analyzing current data to determine whether the current in each branch is abnormal includes: Collect branch current and corresponding timestamps, and convert real-time current data into a current-time curve; Compare and analyze the current change curve with the standard change curve of the current in the current environment in the preset range. The comparison and analysis result indicates the current abnormality coefficient. Through the threshold control analysis of the current abnormality coefficient, it is determined whether the branch current is abnormal; The process of determining electricity theft risk includes: By formula Calculate the algebraic sum of the power generation of each branch ; By formula Calculate and obtain the predicted power generation value of the photovoltaic string ;in is the conversion efficiency of the photovoltaic module, is the total area of ​​the string, is the irradiance, is the actual temperature of the PV module, is the standard test temperature for photovoltaic modules. is the power temperature coefficient of the photovoltaic module; By algebraically summing multiple groups of power generation and the predicted power generation value of the corresponding PV string The risk coefficient of electricity theft is obtained by difference analysis; The algebraic sum of multiple groups of power generation and the predicted power generation value of the corresponding PV string The difference analysis process includes: During the preset monitoring phase, extract Algebraic sum of group power generation Power generation forecast value relative to timestamp ; By formula Calculate the risk factor of electricity theft ;in, 、 is the preset weight coefficient; The risk factor of electricity theft is compared with the preset threshold For comparison: like , then it is judged that there is no risk of electricity theft in the corresponding PV string, and the drone inspection strategy is not implemented; like , it is judged that the corresponding PV string has the risk of electricity theft, and the drone inspection strategy is established based on the location information of the PV strings in the abnormal current branch and the PV power generation environment data.

2. The photovoltaic power theft monitoring method based on Beidou communication according to claim 1 is characterized in that: The process of establishing a drone inspection strategy includes: Obtain meteorological data in the photovoltaic power plant area through the weather station, including wind speed, rainfall, humidity and visibility; Normalize the acquired meteorological data to obtain the corresponding meteorological normalization index, perform weighted sum calculation on each meteorological normalization index according to the preset weight, and output the calculation result to indicate the navigation feasibility parameter; Based on the navigation feasibility parameters, it is determined whether to dispatch a drone to inspect the photovoltaic power station area.

3. The photovoltaic power theft monitoring method based on Beidou communication according to claim 2 is characterized in that: The process of establishing a drone inspection strategy also includes: If the navigation feasibility parameters do not exceed the preset range, a comprehensive analysis is performed on the location information of the photovoltaic strings with abnormal current branches and the power theft risk coefficient of the corresponding photovoltaic strings, and the unmanned planned route is obtained based on the comprehensive analysis results.

4. The photovoltaic power theft monitoring method based on Beidou communication according to claim 3 is characterized in that: The process of comprehensively analyzing the location information of PV strings with abnormal current branches and the power theft risk coefficient of the corresponding PV strings includes: Obtain the location information of the drone base station and the three-dimensional model of the photovoltaic power plant, establish a spatial coordinate system in the three-dimensional model, and convert the location information of the photovoltaic strings with current anomalies into the spatial coordinates of the detection points. The location coordinates of the drone base station and the spatial coordinates of the detection points are used as navigation nodes. Before the drone is about to fly to the next node, the formula Calculate the priority index of the remaining nodes , select the node corresponding to the maximum priority index as the next target node; in, 、 is the preset weight, is the electricity theft risk coefficient of the PV string, is the preset threshold corresponding to the electricity theft risk factor; is the route distance from the remaining nodes to the node where the drone is currently located; The preset detection time of the detection point.

Images