Intelligent monitoring and evaluation method for network security situation of power unmanned aerial vehicle

By collecting and formatting data from power plant drone networks, a situational awareness model is constructed for real-time monitoring and evaluation. This addresses the risks of communication link attacks and task scheduling in power plant drone networks, enabling timely identification and protection against potential threats.

CN121690703APending Publication Date: 2026-03-17STATE GRID SHANGHAI MUNICIPAL ELECTRIC POWER CO +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202511819248.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-12-04
Publication Date
2026-03-17

AI Technical Summary

Technical Problem

Power utilities drone networks are vulnerable to attacks on their communication links, and there are risks in task scheduling and node operation. Furthermore, existing security situation assessment methods lack real-time capabilities and comprehensive analysis capabilities, making it difficult to achieve real-time monitoring and intelligent analysis of drone networks.

Method used

By collecting communication data, task data, and network security log information, a unified formatted database is established, a security situation indicator system is constructed, and a situation awareness model is used for real-time monitoring and evaluation to generate security situation data. Based on the evaluation results, security early warning information is generated.

Benefits of technology

It enables real-time, intelligent monitoring and security situation assessment of power plant drone networks, allowing for timely identification of potential threats and improved network protection capabilities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121690703A_ABST
    Figure CN121690703A_ABST
Patent Text Reader

Abstract

The invention discloses an intelligent monitoring and evaluation method for the network security situation of an electric power unmanned aerial vehicle, and relates to the technical field of intelligent monitoring of the network of the electric power unmanned aerial vehicle, and the method comprises the steps: collecting the network operation data of the electric power unmanned aerial vehicle; carrying out formatting and preprocessing on the collected data; extracting characteristic parameters related to network security based on the collected data; constructing a power unmanned aerial vehicle network security situation index system according to the characteristic parameters, and performing quantitative expression on each index; performing real-time monitoring on the operation state of the power unmanned aerial vehicle network by using the situation awareness model, and generating corresponding security situation data; evaluating and analyzing the security situation data to obtain a security situation level of the power unmanned aerial vehicle network; and generating safety early warning information according to an evaluation result. According to the invention, real-time monitoring of the network security state is realized by using the situation awareness model and automatic data processing, and the network protection capability is improved by constructing a security situation index system and a grading evaluation method.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention relates to the field of intelligent monitoring technology for power drone networks, and in particular to an intelligent monitoring and assessment method for the network security status of power drones. Background Technology

[0002] With the intelligent and digital development of power systems, drones are widely used in transmission line inspection, substation monitoring, and power grid operation and maintenance. Power drones, equipped with communication devices, sensors, and mission control modules, can collect real-time power equipment status data, enabling rapid monitoring and inspection of the power grid operating environment. However, power drone networks face the following problems in actual operation: Communication links are vulnerable to attack: Wireless communication links between drones and the control center, and between drones themselves, may be subject to network intrusion, interference, or tampering, affecting the integrity and reliability of data transmission. Task scheduling and node operation are risky: Drone task scheduling and node operation parameters are susceptible to malicious attacks or abnormal influences, causing drones to deviate from expected missions, or even resulting in collisions, loss of control, and other safety accidents. Network security monitoring methods are insufficient: Existing methods mainly rely on single indicators or manual analysis, lacking the ability to comprehensively analyze multi-source data from drone networks, making it difficult to promptly detect potential network security threats. Security situation assessment methods lack real-time capability: Due to the complex operating environment and large data volume of drone networks, existing security situation assessment methods struggle to achieve real-time monitoring and intelligent analysis of drone network status.

[0003] Therefore, how to achieve real-time monitoring, intelligent analysis, and security status assessment of power drone networks based on drone network operation data has become an urgent technical problem to be solved. Summary of the Invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the problem to be solved by this invention is how to achieve comprehensive, real-time, and intelligent monitoring and security situation assessment of power drone networks, so as to identify potential security threats in a timely manner, assist maintenance personnel in taking targeted protective measures, and ensure the safe and stable operation of drone networks.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, embodiments of the present invention provide an intelligent monitoring and evaluation method for the network security status of power unmanned aerial vehicles (UAVs), including: collecting communication data, task data, node operating parameters and network security log information generated during the operation of the power UAV network; The collected communication data, task data, node operating parameters, and network security log information are uniformly formatted and preprocessed to establish a network security monitoring database for power drones; Based on the collected communication data, task data, node operating parameters, and network security log information, feature parameters related to network security are extracted. A cybersecurity situational awareness index system for power drones is constructed based on characteristic parameters, and each index is quantitatively represented. The operational status of the power unmanned aerial vehicle (UAV) network is monitored in real time using a situational awareness model, generating corresponding security situation data. The security situation data is assessed and analyzed to obtain the security situation level of the power unmanned aerial vehicle network; Based on the assessment results, safety warning information is generated to guide safety protection and operational decisions for power-powered unmanned aerial vehicle (UAV) systems.

[0007] As a preferred embodiment of the intelligent monitoring and evaluation method for the cybersecurity status of electric unmanned aerial vehicles (UAVs) described in this invention, the communication data includes communication information between UAVs and between UAVs and the ground control terminal. The mission data includes mission status and instruction information generated during the UAV's inspection, monitoring, and mission scheduling; node operation parameters include the UAV's own flight status parameters, energy consumption, sensor data, and system status; network security log information includes abnormal behavior records, intrusion detection logs, and security event records of the UAV and ground control terminal.

[0008] As a preferred embodiment of the intelligent monitoring and evaluation method for the cybersecurity status of power drones described in this invention, the method includes: uniformly formatting and preprocessing the collected communication data, task data, node operating parameters, and cybersecurity log information to establish a power drone cybersecurity monitoring database, including: The raw data is organized according to a unified data structure to ensure consistency in data types and fields; missing or abnormal data is marked or cleaned; and key timestamps, node identifiers, and task identifiers are uniformly encoded.

[0009] As a preferred embodiment of the intelligent monitoring and evaluation method for the network security status of power drones described in this invention, the characteristic parameters include node access frequency, number of communication link anomalies, number of task instruction execution anomalies, task completion delay, abnormal node operating status indicators, alarm event type and severity.

[0010] As a preferred embodiment of the intelligent monitoring and evaluation method for the cybersecurity status of power unmanned aerial vehicles (UAVs) according to the present invention, the method includes: constructing a cybersecurity status index system for power UAVs based on characteristic parameters, and quantifying each index, including: Normalize each feature parameter and calculate the normalization index value: ; in, Let i be the actual value of the i-th feature parameter. Let i be the minimum value of the i-th feature parameter under historical data or standard settings. The maximum value of the i-th feature parameter under historical data or standard settings. This is the normalized quantized value of the i-th indicator; A comprehensive situational indicator is constructed based on the normalized index values ​​and weights: ; Where n is the total number of indicators, w i Let S be the weight of the i-th indicator, and S be the comprehensive quantitative cybersecurity situation indicator for power drones.

[0011] As a preferred embodiment of the intelligent monitoring and evaluation method for the network security status of power drones described in this invention, the method utilizes a situational awareness model to monitor the network operation status of power drones in real time and generate corresponding security status data, including: inputting collected communication data, task data, node operation parameters and network security log information into the situational awareness model, and the situational awareness model performs correlation analysis and risk inference on various types of data; Calculate the real-time security posture value for each node i, link j, and task k: ; Among them, STV i,j,k R represents the security status values ​​for node i, link j, and task k. i L is the risk indicator for node i. j T is an abnormal indicator for link j. k Let w1, w2, and w3 be the safety indicators for task k, and w1, w2, and w3 be the weighting coefficients.

[0012] As a preferred embodiment of the intelligent monitoring and evaluation method for the network security status of power drones described in this invention, the method involves: evaluating and analyzing security status data to obtain the security status level of the power drone network, including: extracting the risk value of each node, the link anomaly index, and the task execution security coefficient from the security status data generated by the situational awareness model, and constructing a comprehensive security status scoring function. ; Where α, β, γ are weighting coefficients, S is the comprehensive security situation score, N is the total number of nodes, M is the total number of links, and K is the total number of tasks; Based on the comprehensive security situation score, the security situation level of the power unmanned aerial vehicle (UAV) network is classified, resulting in a hierarchical classification:

[0013] Among them, S1, S2, S3, and S4 are the thresholds for security situation scoring, and levels I to V correspond to the network being in a high-risk, medium-high-risk, medium-risk, medium-low-risk, and low-risk state, respectively. The security status level of each drone node, link, and mission is determined, forming a hierarchical result table for the entire network.

[0014] As a preferred embodiment of the intelligent monitoring and assessment method for the cybersecurity status of power unmanned aerial vehicles (UAVs) described in this invention, the method includes: generating security early warning information based on the assessment results, including: When the risk level is I, the network is in a state of severe anomaly or under major attack. Take emergency measures to isolate abnormal nodes, comprehensively adjust task scheduling, and enhance the security strategies of all critical links. When the risk level is II, the network has serious anomalies or local attack threats. The measures include partially isolating the abnormal nodes, adjusting the execution order of critical tasks, and strengthening the security strategy of the affected links. When the risk level is III, the network exhibits general anomalies or potential threats. Monitor abnormal nodes, optimize task scheduling, and enhance security measures for affected links. When the risk level is IV, the network is in a slightly abnormal state. We will continuously monitor the node status, adjust some task scheduling strategies, and enhance the security strategies of key links. When the risk level is V, the network is operating normally, but security rules should be updated and daily network inspections should be maintained.

[0015] In a second aspect, embodiments of the present invention provide a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of the intelligent monitoring and assessment method for the cybersecurity status of power unmanned aerial vehicles as described in the first aspect of the present invention are implemented.

[0016] Thirdly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, they implement the steps of the intelligent monitoring and assessment method for the cybersecurity status of power unmanned aerial vehicles as described in the first aspect of the present invention.

[0017] The beneficial effects of this invention are as follows: It utilizes a situational awareness model and automated data processing to achieve real-time monitoring of network security status, enabling timely detection of potential anomalies and threats. By constructing a security situation indicator system and a hierarchical assessment method, it achieves quantitative analysis of network security risk levels, providing a scientific basis for operation and maintenance. Based on the assessment results, it generates security early warning information, improving network protection capabilities. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A flowchart of an intelligent monitoring and assessment method for the cybersecurity status of power unmanned aerial vehicles (UAVs); Figure 2 A diagram of computer equipment used for intelligent monitoring and assessment of the cybersecurity status of power unmanned aerial vehicles (UAVs). Detailed Implementation

[0020] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0021] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0022] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0023] Example 1 Reference Figures 1-2 This is the first embodiment of the present invention, which provides an intelligent monitoring and assessment method for the cybersecurity status of power unmanned aerial vehicles (UAVs), including: S1: Collect communication data, task data, node operation parameters, and network security log information generated during the operation of the power drone network.

[0024] Furthermore, the communication data includes communication information between drones and between drones and ground control. The mission data includes mission status and instruction information generated during the UAV's inspection, monitoring, and mission scheduling; node operation parameters include the UAV's own flight status parameters, energy consumption, sensor data, and system status; network security log information includes abnormal behavior records, intrusion detection logs, and security event records of the UAV and ground control terminal.

[0025] S2: The collected communication data, task data, node operating parameters and network security log information are uniformly formatted and preprocessed to establish a network security monitoring database for power drones.

[0026] Furthermore, the raw data is organized according to a unified data structure to ensure consistency in data types and fields; missing or abnormal data is marked or cleaned; and key timestamps, node identifiers, and task identifiers are uniformly encoded.

[0027] It should be noted that the raw data is organized according to a unified data structure, defining the data table structure, including field names, data types, and constraints. Missing values ​​are marked; if a key field is missing, the data record will not participate in subsequent analysis. Abnormal data is cleaned; for example, records with CPU usage or battery levels exceeding reasonable ranges are marked as abnormal or corrected using interpolation methods. Duplicate records are deduplicated to ensure that each record in the database is unique. Key fields are uniformly coded, and timestamps are uniformly formatted according to ISO 8601. Node identifiers are generated according to fixed rules, such as "UAV_001, UAV_002". Task identifiers are generated according to task type and task number, such as "PATROL_01, INSPECTION_02".

[0028] The processed data is stored in a cybersecurity monitoring database for power drones, which can be implemented using a relational or time-series database. Consistency verification is performed on the stored data, checking whether field types, missing value markers, and encoding rules meet preset standards. The processed data has a unified data structure, integrity, and consistency, and can be directly used for subsequent feature extraction, situation assessment, and security early warning analysis.

[0029] S3: Based on the collected communication data, task data, node operating parameters, and network security log information, extract feature parameters related to network security.

[0030] Furthermore, the characteristic parameters include node access frequency, number of communication link anomalies, number of task instruction execution anomalies, task completion delay, abnormal node operating status indicators, alarm event type and severity.

[0031] S4: Construct a cybersecurity situational awareness index system for power drones based on feature parameters, and quantify each index.

[0032] Furthermore, each feature parameter is normalized, and the normalized index value is calculated: ; in, Let i be the actual value of the i-th feature parameter. Let i be the minimum value of the i-th feature parameter under historical data or standard settings. The maximum value of the i-th feature parameter under historical data or standard settings. This is the normalized quantized value of the i-th indicator; A comprehensive situational indicator is constructed based on the normalized index values ​​and weights: ; Where n is the total number of indicators, w i Let S be the weight of the i-th indicator, and S be the comprehensive quantitative cybersecurity situation indicator for power drones.

[0033] It should be noted that the following characteristic parameters are collected from the UAV communication and control network: F1: communication link packet loss rate (%), F2: average latency (ms), F3: signal interference intensity (dBm), F4: node authentication failure rate (%), F5: task data transmission success rate (%); the sampling period is 1 minute, and data is collected continuously for 24 hours and stored in the system database. During the data cleaning stage, missing or abnormal data is repaired using linear interpolation, and data exceeding the physically reasonable range (such as packet loss rate > 100%) is removed.

[0034] Based on the historical operational statistics of the power plant drone communication system, the parameter reference range is set as shown in Table 1 below: Table 1 Characteristic parameters and normalization results of the power plant drone communication system

[0035] Based on expert experience and the results of the Analytic Hierarchy Process (AHP), the weights of each characteristic indicator are determined as shown in Table 2 below: Table 2 Weight Allocation Table of Characteristic Parameters for Electric Power Unmanned Aerial Vehicle Communication System

[0036] Based on the normalized index values ​​and weights, a comprehensive situation index S is constructed, and the data in the table above is substituted into it for calculation: S=0.476 Based on the range of values ​​for the comprehensive situation indicator S, the network security status levels of power drones are classified as shown in Table 3 below: Table 3 Classification of Cybersecurity Status of Electric Power Unmanned Aerial Vehicles

[0037] Based on the calculation result S=0.476, the current network is at a low risk level. The system triggers the early warning module and starts the communication quality adaptive scheduling mechanism.

[0038] S5: Utilizes a situational awareness model to monitor the operational status of the power drone network in real time and generate corresponding security situation data.

[0039] Furthermore, the collected communication data, task data, node operating parameters, and network security log information are input into the situational awareness model, which then performs correlation analysis and risk inference on various types of data. Calculate the real-time security posture value for each node i, link j, and task k: ; Among them, STV i,j,k R represents the security status values ​​for node i, link j, and task k. i L is the risk indicator for node i. j T is an abnormal indicator for link j. k Let w1, w2, and w3 be the safety indicators for task k, and w1, w2, and w3 be the weighting coefficients.

[0040] It should be noted that, based on expert experience, w1=0.50, w2=0.30, and w3=0.20; in this embodiment, a real-time monitoring mechanism for the network security status of power drones is constructed. The system first inputs the collected communication data, task data, node operating parameters, and network security log information into the situational awareness model. The situational awareness model, based on multi-source heterogeneous data fusion technology, performs correlation analysis and risk inference on various types of data, thereby reflecting the real-time operating status of the drone network.

[0041] Specifically, the situational awareness model performs feature extraction and structured processing on operational information at different levels: Node-level data includes CPU utilization, remaining battery level, sensor status, and authentication records of the drone equipment, used to characterize the operational stability and potential risks of a single node; link-level data includes packet loss rate, average transmission latency, and signal interference intensity of the communication link, used to reflect communication quality and link security. Task-level data includes task execution success rate, task response latency, and task error count, used to characterize the reliability of task execution and its susceptibility to network influence. Based on the temporal variation characteristics of these different data categories, the model employs risk normalization and correlation mapping methods to map the security status of nodes, links, and tasks into unified quantitative indicators. To reflect the impact of different factors on the overall security situation, the model sets weight coefficients during data fusion. The node layer has a higher weight to highlight the impact of key nodes on system stability; the link layer has a lower weight to reflect the importance of communication channels; and the task layer has a relatively lower weight to supplement the description of business execution status. Through comprehensive analysis of multi-dimensional information, the model can output real-time security status values ​​for each node, link, and task in each monitoring cycle. This status value reflects the overall security status of the power drone network at the current moment. When the model identifies node anomalies, link interruptions, or task delays exceeding thresholds, it generates corresponding risk signals, marking them as potential security events.

[0042] S6: Evaluate and analyze the security situation data to obtain the security situation level of the power drone network.

[0043] Furthermore, from the security situation data generated by the situational awareness model, risk values, link anomaly indices, and task execution security coefficients for each node are extracted to construct a comprehensive security situation scoring function: ; Where α, β, γ are weighting coefficients, S is the comprehensive security situation score, N is the total number of nodes, M is the total number of links, and K is the total number of tasks; Based on the comprehensive security situation score, the security situation level of the power unmanned aerial vehicle (UAV) network is classified, resulting in a hierarchical classification:

[0044] Among them, S1, S2, S3, and S4 are the thresholds for security situation scoring, and levels I to V correspond to the network being in a high-risk, medium-high-risk, medium-risk, medium-low-risk, and low-risk state, respectively. The security status level of each drone node, link, and mission is determined, forming a hierarchical result table for the entire network.

[0045] It should be noted that, based on the network security operation characteristics of UAVs, the node risk weight coefficient α is set to 0.5, the link anomaly weight coefficient β is set to 0.3, and the mission security weight coefficient γ is set to 0.2. Among these, the node's self-protection and anti-attack capabilities are the main influencing factors, and therefore have a higher weight; the link anomaly is secondary; and the security of the mission execution process is relatively controlled by the former two, and therefore has a lower weight.

[0046] Assume there are 10 drone nodes (N=10), 8 communication links (M=8), and 5 tasks (K=5) in the current network. The system analyzes the situation using a situational awareness model, extracts the standardized values ​​(range 0-1) of each indicator, and calculates the comprehensive security situation score S based on the aforementioned weighting coefficients.

[0047] The overall scoring range is divided into the following levels: Level I (High Risk): S≥0.85; Level II (Medium-High Risk): 0.70≤S<0.85; Level III (Medium Risk): 0.55≤S<0.70; Level IV (Medium-Low Risk): 0.40≤S<0.55; Level V (Low Risk): S<0.40. In a single operation, the situational awareness system yielded an average node risk value of 0.62, an average link anomaly index of 0.48, and a mission safety coefficient of 0.72. Substituting these values ​​into the weights, the overall score is S≈0.58, corresponding to Level III (Medium Risk).

[0048] Based on the classification results, the system automatically triggers risk response strategies: disconnection protection is implemented for nodes at high risk (Level I); encryption and data retransmission mechanisms are activated for links at medium to high risk (Level II); For medium-risk (Level III) tasks, alternative paths and temporary task migrations are arranged; for Level IV and V nodes, only periodic monitoring is performed.

[0049] S7: Generate safety warning information based on the assessment results to guide the safety protection and operation decisions of the power unmanned aerial vehicle system.

[0050] Furthermore, when the risk level is I, and the network is in a state of severe anomaly or under major attack, emergency measures should be taken to isolate abnormal nodes, comprehensively adjust task scheduling, and enhance the security strategies of all critical links. When the risk level is II, the network has serious anomalies or local attack threats. The measures include partially isolating the abnormal nodes, adjusting the execution order of critical tasks, and strengthening the security strategy of the affected links. When the risk level is III, the network exhibits general anomalies or potential threats. Monitor abnormal nodes, optimize task scheduling, and enhance security measures for affected links. When the risk level is IV, the network is in a slightly abnormal state. We will continuously monitor the node status, adjust some task scheduling strategies, and enhance the security strategies of key links. When the risk level is V, the network is operating normally, but security rules should be updated and daily network inspections should be maintained.

[0051] In summary, this invention utilizes a situational awareness model and automated data processing to achieve real-time monitoring of network security status, enabling timely detection of potential anomalies and threats. By constructing a security situation indicator system and a tiered assessment method, it achieves quantitative analysis of network security risk levels, providing a scientific basis for operations and maintenance. Based on the assessment results, it generates security early warning information, improving network protection capabilities.

[0052] This embodiment also provides a computer device applicable to the intelligent monitoring and evaluation method for the cybersecurity status of power drones, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the intelligent monitoring and evaluation method for the cybersecurity status of power drones as proposed in the above embodiment.

[0053] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0054] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, it implements the intelligent monitoring and evaluation method for the network security status of power drones as proposed in the above embodiments.

[0055] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. An intelligent monitoring and evaluation method for power unmanned aerial vehicle network security posture, characterized in that, The application relates to a power unmanned aerial vehicle network security monitoring method. The method comprises the following steps: collecting communication data, task data, node operation parameters and network security log information generated in the operation process of the power unmanned aerial vehicle network; unifying the formats and pre-processing the collected communication data, task data, node operation parameters and network security log information to establish a power unmanned aerial vehicle network security monitoring database; extracting feature parameters related to network security based on the collected communication data, task data, node operation parameters and network security log information; constructing a power unmanned aerial vehicle network security situation index system according to the feature parameters and quantitatively representing each index; monitoring the operation state of the power unmanned aerial vehicle network in real time by using a situation awareness model to generate corresponding security situation data; evaluating and analyzing the security situation data to obtain the security situation level of the power unmanned aerial vehicle network; 2.The intelligent monitoring and evaluation method of power UAV network security situation according to claim 1, characterized in that, generating security warning information according to the evaluation result to guide the security protection and operation decision of the power unmanned aerial vehicle system. The communication data comprises communication information between unmanned aerial vehicles and between unmanned aerial vehicles and a ground control terminal. 3.The intelligent monitoring and evaluation method of power UAV network security situation according to claim 1, characterized in that: The task data comprises task state and instruction information generated in the process of executing inspection, monitoring and task scheduling by the unmanned aerial vehicle. The node operation parameters comprise flight state parameters, energy consumption, sensor data and system state of the unmanned aerial vehicle itself. 4.The intelligent monitoring and evaluation method of power UAV network security situation according to claim 1, characterized in that: The network security log information comprises abnormal behavior records, intrusion detection logs and security event records of the unmanned aerial vehicle and the ground control terminal. 5.The intelligent monitoring and evaluation method of power UAV network security situation according to claim 1, characterized in that, The pre-processing of the collected communication data, task data, node operation parameters and network security log information to establish the power unmanned aerial vehicle network security monitoring database comprises the following steps: Each feature parameter is normalized, and a normalized index value is calculated: ; wherein, is the actual value of the i-th characteristic parameter, is the minimum value of the i-th characteristic parameter under historical data or standard setting, is the maximum value of the i-th characteristic parameter under historical data or standard setting, is the normalized quantized value of the i-th index; arranging the original data according to a unified data structure to ensure the consistency of data types and fields; marking or cleaning the missing or abnormal data; and uniformly encoding the key time stamp, node identifier and task identifier. ; wherein n is the total number of indexes, w i is the weight of the i-th index, and S is the comprehensive quantitative power unmanned aerial vehicle network security situation index. 6.The intelligent monitoring and evaluation method of power UAV network security situation according to claim 1, characterized in that: The feature parameters comprise node access frequency, communication link abnormality frequency, task instruction execution abnormality frequency, task completion delay condition, node operation state abnormality index, alarm event type and severity. The construction of the power unmanned aerial vehicle network security situation index system according to the feature parameters and the quantitatively representing each index comprise the following steps: ;; where STV i,j,k is the security situation value of node i, link j, task k, R i is the risk index of node i, L j is the anomaly index of link j, T k is the security index of task k, and w1, w2, and w3 are weight coefficients. 7.The intelligent monitoring and evaluation method of power UAV network security situation according to claim 1, characterized in that: constructing a comprehensive situation index according to the normalized index value and weight: ; The real-time monitoring of the operation state of the power unmanned aerial vehicle network by using the situation awareness model to generate corresponding security situation data comprises the following steps: inputting the collected communication data, task data, node operation parameters and network security log information into the situation awareness model, and the situation awareness model performs correlation analysis and risk inference on each type of data; calculating the real-time security situation value of each node i, link j and task k: The evaluation and analysis of the security situation data to obtain the security situation level of the power unmanned aerial vehicle network comprise the following steps: extracting the node risk value, link abnormality index and task execution security coefficient from the security situation data generated by the situation awareness model to construct a comprehensive security situation scoring function: wherein, alpha, beta and gamma are weight coefficients, S is the comprehensive security situation score, N is the total number of nodes, M is the total number of links, and K is the total number of tasks. According to the comprehensive security situation score, the security situation level of the power unmanned aerial vehicle network is divided, and a hierarchical result is formed: ; Wherein, S1, S2, S3, S4 are the threshold values of the security posture score, and the grades I-V correspond to the high risk, high-middle risk, middle risk, low-middle risk and low risk state of the network respectively; The security posture grades of each unmanned aerial vehicle node, link and task are formed to constitute the hierarchical result table of the whole network. 8.The intelligent monitoring and evaluation method of power UAV network security situation according to claim 1, characterized in that: The security warning information is generated according to the evaluation result, including: When the risk is grade I, the network is in a state of serious abnormality or under a major attack, emergency isolation of abnormal nodes, comprehensive adjustment of task scheduling and enhancement of security strategy of all key links are taken; When the risk is grade II, the network exists a relatively serious abnormality or a local attack threat, partial isolation of abnormal nodes, adjustment of the execution order of key tasks and enhancement of the security strategy of affected links are taken; When the risk is grade III, the network appears a general abnormality or a potential threat, monitoring of abnormal nodes, optimization of task scheduling and improvement of security measures for affected links are taken; When the risk is grade IV, the network is in a state of slight abnormality, continuous monitoring of node state, adjustment of part of the task scheduling strategy and enhancement of the security strategy of key links are taken; When the risk is grade V, the network runs normally, but the security rules are updated and the daily network inspection is kept. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is characterized in that: The processor executes the computer program to realize the steps of the intelligent monitoring and evaluation method of the security posture of the power unmanned aerial vehicle network according to any one of claims 1-8.

10. A computer readable storage medium having stored thereon a computer program, characterized in that: The computer program is executed by the processor to realize the steps of the intelligent monitoring and evaluation method of the security posture of the power unmanned aerial vehicle network according to any one of claims 1-8.