Power distribution gateway operation state monitoring system and method based on secure communication

Abstract

The invention relates to a power distribution gateway operation state monitoring system and method based on safety communication. The system adopts a three-level collaborative architecture of an edge acquisition node, an edge computing node and a cloud server, a first monitoring node establishes an electromagnetic interference quantitative model and an environment temperature and humidity-communication coupling model, and a dynamic self-adaptive threshold value is adopted for communication state judgment; on the premise that the communication state is normal, the second monitoring node is started, and hardware state and data rationality are diagnosed based on comparison of historical data and real-time data; and the third monitoring node performs communication security deep detection, and integrates the multi-source information through a security decision engine to realize comprehensive judgment of the security state of the gateway. And the cloud server optimizes edge side model parameters through a machine learning algorithm based on global data, and realizes group fault prediction and threat intelligence cooperation. According to the invention, omnibearing, intelligent and adaptive monitoring of the operation state of the power distribution gateway is realized, and the reliability and safety of the power distribution network are significantly improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of smart grid, and particularly relates to a power distribution gateway operation state monitoring system and method based on secure communication. BACKGROUND

[0002] With the rapid development of smart grid, the power distribution intelligent gateway, as the core hub connecting the power distribution automation terminal (such as FTU, TTU, DTU) and the upper layer master station system, its operation state stability and safety directly determine the reliability, safety and operation and maintenance efficiency of the power distribution network. There are many deficiencies in the monitoring and testing of the power distribution intelligent gateway in the prior art.

[0003] In the prior art, the patent for invention with publication number CN115622914 A discloses a power distribution intelligent gateway testing system and method, which tests the data acquisition function and internal performance of the gateway through the Internet of Things simulation master station, external data simulation components, etc., but this method mainly focuses on offline or semi-offline state function verification, lacks real-time, non-intrusive monitoring of the communication security of the gateway in the actual running environment, and the testing process may interfere with normal production business. The patent for invention with publication number CN117614802 A proposes a method for confirming the working state of the power gateway based on the detection cycle, which judges whether the gateway is offline by setting the detection cycle, but this method is difficult to accurately locate the fault node in a complex multi-level gateway link, and does not fully consider the dynamic influence of the security risk (such as data theft, tampering) of the communication link and the physical environment (such as electromagnetic interference, temperature and humidity) on the gateway state. The patent for invention with publication number CN118740680 A relates to a power distribution Internet of Things intelligent gateway anomaly identification method, which identifies hardware, software and environmental faults through image recognition and data analysis, but fails to intelligently analyze the root cause of the identified fault types, resulting in unreasonable allocation of operation and maintenance resources, delayed response to key faults, and reduced overall system reliability, and at the same time, its communication security protection and monitoring capability is obviously insufficient.

[0004] In summary, the prior art mainly has the following defects:

[0005] Insufficient communication security monitoring: lack of real-time, in-depth monitoring of the end-to-end encryption strength, integrity check, identity authentication mechanism and anti-network attack (such as DDoS, malicious intrusion) capability of gateway communication data.

[0006] Physical operating environment monitoring is missing: unable to comprehensively monitor the physical environment parameters (such as temperature, humidity, electromagnetic interference strength) in which the gateway is located, and environmental abnormalities are an important factor leading to gateway hardware failure or performance degradation, but are often ignored.

[0007] Weak fault identification and intelligent processing capability: most of the existing methods stay in the level of judging whether there is a fault, and cannot perform correlation analysis, intelligent classification and root cause analysis on multi-source fault information, so it is difficult to support accurate and efficient operation and maintenance decisions.

[0008] Therefore, there is an urgent need in the art for an integrated monitoring system and method capable of comprehensively sensing the communication security, hardware state and physical environment of a power distribution gateway, and intelligently diagnosing and quickly responding to faults. SUMMARY

[0009] The primary purpose of the present application is to overcome the shortcomings of the prior art and provide a power distribution gateway operation state monitoring system based on secure communication, which can realize comprehensive, real-time and accurate monitoring of gateway communication state, hardware state and communication security state.

[0010] To solve the above technical problems, the first aspect provides a power distribution gateway operation state monitoring system based on secure communication, which comprises an edge collection node, an edge computing node and a cloud server:

[0011] The edge collection node is arranged locally at the power distribution gateway and is used to collect the operation state data of the power distribution gateway, wherein the operation state data includes one or more of communication quality parameters, hardware operation parameters, communication security parameters and physical environment parameters;

[0012] The edge computing node is deployed at the regional side of the power distribution gateway, and the edge computing node comprises a first monitoring node, a second monitoring node and a third monitoring node, wherein:

[0013] The first monitoring node comprises an electromagnetic interference quantization model and an environment temperature and humidity-communication coupling model, which quantize the dynamic influence of temperature and humidity on power distribution gateway communication state identification, and adopts a dynamic adaptive threshold to determine the communication state of the power distribution gateway;

[0014] When the monitoring result of the first monitoring node is normal:

[0015] The second monitoring node monitors the hardware state of the power distribution gateway based on the time series of power grid operation history data and real-time collected parameters;

[0016] The third monitoring node performs communication security deep detection, and determines the security state of the power distribution gateway based on a security decision engine and multi-source information;

[0017] The cloud server optimizes the weight coefficients in the above models based on the historical and real-time operation state data of the power distribution gateway through a machine learning algorithm, and sends the optimized model parameters to the edge computing gateway.

[0018] Optionally, the electromagnetic interference quantification model comprises:

[0019] A power grid harmonic influence factor model: ,

[0020] wherein, is the nth harmonic current, is a harmonic current weighting coefficient, is a noise weighting coefficient.

[0021] An electromagnetic interference intensity model: ,

[0022] wherein, represents electromagnetic interference intensity, and respectively represent power grid current effective value and voltage peak value, represents the distance between the interference source and the gateway, represents time, is an attenuation coefficient, and are weight coefficients, which are set according to IEEE Std 519;

[0023] A coupling path analysis model: ,

[0024] wherein, is a gateway receiving end interference voltage, is electromagnetic interference intensity, is the distance of the interference source, is an interference frequency;

[0025] An interference spectrum analysis model: ,

[0026] wherein, is a communication center frequency, is a communication bandwidth, is an electromagnetic interference power spectral density.

[0027] Optionally, the environment-communication coupling model is:

[0028] ,

[0029] wherein, is a temperature and humidity influence coefficient, , is a rated temperature and humidity, , is a current environment temperature and humidity, and α, β, γ are material aging coefficients.

[0030] Optionally, the dynamic adaptive threshold is specifically:

[0031] ,

[0032] wherein, is a dynamic adaptive threshold, is a reference threshold, , , is a weight coefficient.

[0033] Optionally, the second monitoring node performs power grid gateway hardware state monitoring based on the power grid operation history data time series and the real-time collected power grid parameters, including:

[0034] If the real-time collected power grid parameters received by the power grid gateway jump and seriously deviate from the power grid operation history data time series, it is determined that the monitoring loop has a power grid fault;

[0035] If the real-time collected power grid parameters received by the power grid gateway are continuously unchanged, it is determined that the data collection sensor has a fault;

[0036] If the power grid gateway does not receive the real-time collected power grid parameters, and the sensor wireless communication is normal, it is determined that the communication interface of the monitoring loop power grid gateway has a fault.

[0037] Optionally, the third monitoring node includes:

[0038] A communication encryption and identity verification subunit detects the encryption suite strength, certificate validity and identity authentication of the communication link;

[0039] A data integrity check and behavior analysis subunit performs integrity check on the application layer data and performs abnormal analysis based on the behavior baseline;

[0040] An active security defense and threat perception subunit performs intrusion detection and denial of service attack identification;

[0041] A security decision engine cooperates with the outputs of the above three subunits, and interacts with the monitoring results of the first monitoring node and the second monitoring node, and comprehensively determines the gateway state.

[0042] Optionally, the cloud server further performs:

[0043] Based on the global data aggregated by the edge computing node, a group fault trend prediction is performed, and the prediction result is shared with the edge computing node.

[0044] In a second aspect, another object of the present application is to provide a monitoring method based on the above-mentioned system, which can dynamically adapt to the changes of the gateway operating environment, and the monitoring method specifically includes:

[0045] S1: Collecting real-time operation state data of the power distribution gateway through the edge collection node, wherein the operation state data includes communication quality parameters, hardware operation parameters, communication security parameters and physical environment parameters;

[0046] S2: The first monitoring node quantifies the dynamic influence of temperature and humidity and power grid parameters on the communication state recognition of the power distribution gateway by establishing an electromagnetic interference quantification model and an environment temperature and humidity-communication coupling model, and adopts a dynamic adaptive threshold The environment and communication coupling model and the dynamic adaptive threshold are used to determine the communication state of the gateway, and if the determination result is abnormal, abnormal information is output for alarm, and if the determination result is normal, step S3 is entered;

[0047] S3: The second monitoring node performs hardware state and data rationality diagnosis based on historical and real-time data comparison;

[0048] S4: The third monitoring node detects the encryption strength, identity authentication, data integrity and network attack behavior of the communication link, and fuses multi-source information through a security decision engine to perform comprehensive security state determination;

[0049] S5: The edge computing node uploads the monitoring result and the original data to the cloud server; the cloud server optimizes the model parameters of the edge node through a machine learning algorithm and issues them, and based on the global data collected, performs group fault trend prediction, and shares the prediction result with the edge computing node.

[0050] S6: After the edge computing node receives the model parameters issued by the cloud server to update the model, steps S2-S4 are executed.

[0051] In a third aspect, the present application also provides an electronic device, comprising:

[0052] one or more processors;

[0053] a memory; and one or more programs stored in the memory, the one or more programs including instructions for performing the above-mentioned power distribution gateway operation state monitoring method based on secure communication.

[0054] In a fourth aspect, the present application also provides a computer-readable storage medium, comprising one or more programs for execution by one or more processors of an electronic device, the one or more programs including instructions for performing the above-mentioned power distribution gateway operation state monitoring method based on secure communication.

[0055] Compared with the prior art, the technical scheme of the present application has the following beneficial effects:

[0056] 1. Comprehensive monitoring dimension: For the first time, communication performance, hardware state, communication security and physical operating environment are included in a unified monitoring framework, and subsequent monitoring is started after the communication state is normal, avoiding invalid hardware state judgment in the case of unstable communication link, and realizing the stereoscopic and all-around perception of the operation state of the power distribution gateway.

[0057] 2. High-precision diagnosis and low false alarm: By establishing an accurate electromagnetic interference and environment coupling model, using dynamic adaptive threshold, effectively distinguishing external environmental interference from internal real faults, the diagnosis accuracy is significantly improved.

[0058] 3. Active in-depth security defense: Deeply integrated communication security monitoring, and through the security decision engine to realize cross-layer information fusion, with threat perception, attack identification, intelligent research and judgment and collaborative response capability.

[0059] 4. Cloud-edge collaborative evolution: The system has self-learning ability, through cloud global optimization and edge local execution, so that the model parameters continuously evolve, adapt to different gateways and changing environment, and realize predictive maintenance. BRIEF DESCRIPTION OF DRAWINGS

[0060] Figure 1 A power distribution gateway operation state monitoring system based on secure communication provided for the embodiments of the present application;

[0061] Figure 2 A power distribution gateway operation state monitoring method based on secure communication provided for the embodiments of the present application. DETAILED DESCRIPTION

[0062] Obviously, many modifications and changes made by those skilled in the art based on the purpose of the present application belong to the protection scope of the present application.

[0063] Those skilled in the art can understand that, unless specifically stated, the singular form "one", "said" and "the" used herein also includes the plural form. It should be further understood that the wording "comprising" used in the specification of the present application means that the features, integers, steps, operations, elements and / or components exist, but does not exclude the existence or addition of one or more other features, integers, steps, operations, elements, components and / or their groups. It should be understood that when an element, component is "connected" to another element or component, it can be directly connected to the other element or component, or there can be intermediate elements or components. The wording "and / or" used herein includes any unit and all combinations of the associated listed items.

[0064] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0065] With reference to Figure 1 For an embodiment of the present application, the embodiment provides a power distribution gateway operating state monitoring system based on secure communication. With the wide application of the Internet of Things and artificial intelligence in modern power systems, cloud-edge integrated smart grid management systems are gradually popularized in power grid operation monitoring and dispatching systems. The monitoring system proposed in the present application fully utilizes the cloud server and edge computing node that have been constructed:

[0066] The edge collection node is arranged locally at the power distribution gateway and is used to collect operating state data of the power distribution gateway, the operating state data including one or more of communication quality parameters, hardware operating parameters, communication security parameters and physical environment parameters;

[0067] The edge computing node is deployed at the regional side of the power distribution gateway, and the edge computing node includes a first monitoring node, a second monitoring node and a third monitoring node, wherein:

[0068] The first monitoring node includes: establishing an electromagnetic interference quantization model and an environment temperature and humidity-communication coupling model, quantizing the dynamic influence of temperature and humidity and power grid parameters on the communication state recognition of the power distribution gateway, and using a dynamic adaptive threshold to determine the communication state of the power distribution gateway;

[0069] When the monitoring result of the first monitoring node is normal:

[0070] The second monitoring node performs power distribution gateway hardware state monitoring based on power grid operation historical data time series and power grid real-time collection parameters;

[0071] The third monitoring node performs communication security deep detection, and performs power distribution gateway security state determination based on a security decision engine and comprehensive multi-source information.

[0072] The cloud server optimizes the weight coefficients in the above model through a machine learning algorithm based on the historical operating state and real-time operating state data of the power distribution gateway, and sends the optimized model parameters to the edge computing gateway.

[0073] In an optional embodiment, an edge collection node is arranged locally to the power distribution gateway for collecting operation state data of the power distribution gateway, the operation state data including one or more of communication quality parameters, hardware operation parameters, communication security parameters, and physical environment parameters, including:

[0074] The multi-dimensional operation state raw data of the power distribution gateway is collected, specifically including:

[0075] The communication quality parameters include, for example, signal strength, bit error rate, network delay, bandwidth utilization, etc.

[0076] The hardware operation parameters include, for example, CPU utilization, memory occupancy, storage space remaining, power voltage / current, etc.

[0077] The communication security parameters include, for example, communication connection certificate status, encryption suite information, traffic characteristics, etc.

[0078] The physical environment parameters include, for example, temperature, humidity, electromagnetic field strength, and power grid voltage and current parameters in the working environment of the power distribution gateway, which are collected by integrated or external sensors.

[0079] In actual application scenarios, compared with the operating environment of a conventional Internet of Things communication gateway, the power distribution gateway involves high-frequency changes in power grid high and low voltage line supply voltage and current, as well as induced communication electromagnetic interference. These factors form dynamic interference to the communication state monitoring results of the power distribution gateway. In an embodiment of the present application, the first monitoring node quantifies the influence of power grid parameters on the communication state of the power distribution gateway by establishing an electromagnetic interference quantification model.

[0080] ,

[0081] wherein, represents a power grid harmonic influence factor, is the nth harmonic current (from the power grid load), is a harmonic current weighting coefficient, is a noise weighting coefficient, which is set according to the CCITT recommendation.

[0082] ,

[0083] wherein, represents electromagnetic interference intensity, and represent the effective value of the power grid current and the peak value of the voltage, respectively, represents the distance between the interference source and the gateway, represents time, is an attenuation coefficient, and are weight coefficients, which are set in reference to IEEE Std 519.

[0084] Coupling path analysis unit: identify the interference type (such as capacitive coupling, inductive coupling), and calculate the coupling coefficient

[0085] ,

[0086] Where, is the gateway receiving end interference voltage, is the electromagnetic interference intensity, is the distance from the interference source, is the interference frequency.

[0087] It is a dimensionless scaling factor that integrates the propagation distance d, frequency f, and the gateway's own shielding and interface circuit impedance characteristics, which perceives the existence of interference and quantifies its effectiveness in invading the system, The higher the value, the more "sensitive" the gateway is in the current environment, and external interference is easy to "break in" to the internal circuit. It is a real-time, dynamic embodiment of the gateway's electromagnetic compatibility (EMC) performance.

[0088] Interference spectrum analysis unit: perform FFT transform on the collected electromagnetic signals, extract power grid harmonic features (such as 150Hz, 250Hz, etc. Odd harmonics), and compare with the communication frequency band (such as 230MHz carrier), to generate frequency band overlap index :

[0089] ,

[0090] Where, is the communication center frequency, is the communication bandwidth, is the electromagnetic interference power spectral density.

[0091] In an optional embodiment, the power distribution gateway is usually placed in the power distribution room, facing complex temperature and humidity change scenarios. The first monitoring node of the present application also considers the correlation between the communication state of the power distribution gateway and the environmental temperature and humidity to establish an environmental temperature and humidity-communication coupling model, and introduces a temperature and humidity influence coefficient to quantify the influence of environmental temperature and humidity parameters on the operation state of the power distribution gateway:

[0092] ,

[0093] Where, , is the rated temperature and humidity, , is the current environmental temperature and humidity, and α, β, γ are material aging coefficients, which can be fitted by historical data of the gateway.

[0094] In an optional embodiment, considering the influence of electromagnetic interference and environmental temperature and humidity on the communication state of the power distribution gateway, a dynamic adaptive threshold is used when determining the communication state of the power distribution gateway The determination is made as follows:

[0095] ,

[0096] wherein, is a reference threshold value, usually a bit error rate reference threshold value, , , is a weight coefficient, which is dynamically adjusted through machine learning on the basis of empirical values.

[0097] In an optional embodiment, the first monitoring node can also assist in monitoring the cooling fan and ventilation failure of the power distribution gateway according to the temperature and humidity influence coefficient when it changes rapidly.

[0098] In an optional embodiment, the first monitoring node can also dynamically adjust the adaptive threshold in combination with the electromagnetic interference-hardware failure correlation rule to avoid false positives of the communication state of the power distribution gateway:

[0099] Rule 1 - distinguish interference from failure: when there is a communication anomaly, if strong electromagnetic interference ( >1) is detected at the same time, but the gateway's own hardware (such as CPU, memory) self-checks are normal, it is determined that the communication anomaly is caused by external interference, avoiding misjudgment as a hardware failure, guiding anti-interference processing rather than hardware replacement.

[0100] Rule 2 - diagnose power supply problems: by analyzing the synchronicity of power supply voltage fluctuations and electromagnetic field change rate dB / dt, it is determined that the interference affects the power supply quality through the conduction path, guiding the adoption of filtering measures on the power supply side.

[0101] In an optional embodiment, the second monitoring node is started after the first monitoring node determines that the communication state is normal, avoiding invalid hardware state judgment in the case of unstable communication link, and the power distribution gateway hardware state monitoring based on power grid operation historical data time series and real-time collected power grid parameters includes:

[0102] If the real-time collected power grid parameters received by the power distribution gateway jump, seriously deviating from the power grid operation historical data time series, it is determined that the monitoring loop has a power grid failure;

[0103] If the real-time collected power grid parameters received by the power distribution gateway remain unchanged, it is determined that the data acquisition sensor has a failure;

[0104] If the power distribution gateway does not receive real-time power grid parameters, and the sensor wireless communication is normal, it is determined that the communication interface of the monitoring loop power distribution gateway is faulty.

[0105] In an optional embodiment, the third monitoring node comprises:

[0106] The communication encryption and identity authentication subunit is configured to detect the encryption suite strength, certificate validity and identity authentication process of the communication link in depth; the data integrity check and behavior analysis subunit is configured to perform integrity check on the application layer data and perform abnormal analysis based on the behavior baseline; and the active security defense and threat perception subunit is configured to perform intrusion detection and denial of service attack identification.

[0107] The data integrity check and behavior analysis subunit realizes data integrity check through deep packet inspection (DPI) technology and cryptographic message authentication code (MAC), and the active security defense and threat perception subunit integrates an intrusion detection system (IDS) rule library containing power system special protocol attack features.

[0108] In an optional embodiment, the third monitoring node further comprises a security decision engine configured to coordinate the outputs of the three subunits and interact with the first monitoring node and the second monitoring node to comprehensively determine the gateway state, and the security decision engine is configured to attribute the CPU load anomaly to the network attack when the active security defense and threat perception subunit detects a network attack and the second monitoring node detects a CPU load anomaly.

[0109] In an optional embodiment, the cloud server is further configured to optimize the security behavior baseline and threat determination threshold in the third monitoring node using a machine learning algorithm.

[0110] In an optional embodiment, the cloud server deployed at a remote end as an intelligent hub of the system adopts a micro-service architecture and mainly comprises four core modules of data lake and feature engineering, collaborative analysis and model factory, global situation awareness and predictive maintenance, and model management and deployment.

[0111] The cloud server builds a multi-modal data lake and adopts distributed object storage (such as AWS S3 and HDFS) to build the data lake, and stores raw data from edge gateways of different regions and different types, and the data specifically includes:

[0112] Time series data: voltage, current, temperature, humidity, CPU load, bit error rate, etc., with time series labels;

[0113] Event data: alarm events, security events and state switching events reported by the edge gateway;

[0114] Unstructured data: abnormal network traffic packets, system log snapshots captured by the third monitoring node;

[0115] Model parameters: model parameters currently used by the edge gateway (e.g., weight coefficient set {λ1, λ2,...} in dynamic threshold formula)

[0116] Data governance and correlation: Establish a unified data model and asset directory, use data lineage technology to track data sources and processing processes; through key fields such as gateway ID and timestamp, correlate environmental data, operational data, and security event data to form a complete "panoramic view" of gateway operation.

[0117] Automatic feature engineering: Based on domain knowledge (power system, network security) and automatic feature generation tools (such as TSFresh for time series features), extract features with predictive value from raw data. For example: extract "temperature rise rate" and "periodic fluctuation amplitude" from temperature time series data; extract "number of connection attempts per hour" and "access frequency of rarely used ports" from network traffic; and joint statistical features such as "electromagnetic interference-communication error rate".

[0118] Collaborative analysis and model factory module includes a set of model library covering different scenarios, such as general models, regional specific models adapted to specific power grid environment, and specific models for different gateway hardware models. Based on this, use collaborative machine learning algorithms such as XGBoost, federated learning algorithms, and knowledge graph technology to deeply optimize model parameters required by edge-side monitoring units, including dynamic adaptive threshold weight coefficients, security behavior baselines, and threat determination thresholds.

[0119] Global situational awareness and predictive maintenance module includes: group failure prediction: use time series prediction models (such as LSTM, Transformer) to analyze the trend of network gateway performance indicators. If a large number of gateway temperature readings in a certain region show a synchronous slow upward trend, it can be predicted that there may be potential risks in the cooling system of the machine room in that region, thus issuing an early warning before the device goes down.

[0120] Security threat intelligence center: cloud server as a global security intelligence hub. When a third monitoring node of an edge gateway discovers a new attack pattern, the attack features will be immediately uploaded to the cloud. After rapid analysis by the cloud server, the threat features (such as malicious IP, attack signature) can be distributed to the intrusion detection system (IDS) rule library of all other edge gateways within a few minutes, achieving "one discovery, whole network immunity" collaborative defense.

[0121] The cloud server has global situation awareness capability, can perform group fault prediction and rapid distribution of global security threat information. Finally, through the efficient model management and deployment module, the optimized model is accurately deployed to the target edge computing gateway in a differential incremental manner, forming a complete closed loop from analysis, decision to execution, and driving the system to continuously evolve.

[0122] Referring to Figure 2 For an embodiment of the present application, the embodiment provides a power distribution gateway operating state monitoring method based on secure communication, comprising the following steps:

[0123] S1: Collecting real-time operating state data of the power distribution gateway through the edge collection node, wherein the operating state data includes communication quality parameters, hardware operating parameters, communication security parameters and physical environment parameters;

[0124] S2: The first monitoring node quantifies the dynamic influence of temperature and humidity and power grid parameters on the communication state recognition of the power distribution gateway by establishing an electromagnetic interference quantification model and an environment temperature and humidity-communication coupling model, and adopts a dynamic adaptive threshold The environment and communication coupling model and the dynamic adaptive threshold are used to determine the communication state of the gateway, and if the determination result is abnormal, abnormal information is output for alarm, and if the determination result is normal, step S3 is entered;

[0125] S3: The second monitoring node performs hardware state and data rationality diagnosis based on historical and real-time data comparison;

[0126] S4: The third monitoring node detects the encryption strength, identity authentication, data integrity and network attack behavior of the communication link, and fuses multi-source information through a security decision engine to perform comprehensive security state determination;

[0127] S5: The edge computing node uploads the monitoring results and raw data to the cloud server; the cloud server optimizes the edge node model parameters through a machine learning algorithm and issues them, and based on the gathered global data, performs group fault trend prediction, and shares the prediction results with the edge computing node.

[0128] S6: After the edge computing node receives the model parameters issued by the cloud server to update the model, steps S2-S4 are performed.

[0129] In an embodiment of the present application, an electronic device is also provided, comprising: one or more processors; a memory; and one or more programs stored in the memory, the one or more programs including instructions for performing the method described in the second aspect.

[0130] In one embodiment of the invention, a computer-readable storage medium is also provided, including one or more programs executable by one or more processors of an electronic device, the one or more programs including instructions for performing the method described in the second aspect above.

[0131] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0132] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0133] Finally, it should be noted that in this document, relationships such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

Claims

1. A power distribution gateway operating state monitoring system based on secure communication, the system comprising an edge collection node, an edge computing node and a cloud server, characterized in that, the edge collection node is arranged at the local power distribution gateway, and is used to collect the operating state data of the power distribution gateway, wherein the operating state data comprises one or more of communication quality parameters, hardware operating parameters, communication security parameters and physical environment parameters; the edge computing node is deployed at the regional side of the power distribution gateway, and comprises a first monitoring node, a second monitoring node and a third monitoring node, wherein: The first monitoring node comprises: establishing an electromagnetic interference quantification model and an environment temperature and humidity-communication coupling model, quantifying the dynamic influence of temperature and humidity and power grid parameters on power distribution gateway communication state identification, and adopting a dynamic adaptive threshold Power distribution gateway communication state determination is performed. when the monitoring result of the first monitoring node is normal: the second monitoring node performs power distribution gateway hardware state monitoring based on power grid operation historical data time series and real-time collected power grid parameters; the third monitoring node performs communication security deep detection, and performs power distribution gateway security state judgment based on a security decision engine integrating multi-source information; the cloud server optimizes the weight coefficients in the above model based on power distribution gateway historical operating state and real-time operating state data through a machine learning algorithm, and sends the optimized model parameters to the edge computing gateway.

2. The system of claim 1, wherein, the electromagnetic interference quantification model comprises: Power grid harmonic influence factor model: , wherein, is the nth harmonic current, is a harmonic current weighting factor, is a noise weighting factor; Electromagnetic interference strength model: , wherein, denotes the electromagnetic interference strength, and denote the grid current effective value and the voltage peak value, respectively, denotes the distance of the interference source from the gateway, denotes the time, is an attenuation coefficient, and are weight coefficients, set with reference to IEEE Std 519; Coupling path analysis model: , wherein, Vgi is the interference voltage at the receiving end of the gateway, Ei is the electromagnetic interference strength, Di is the distance of the interference source, fi is the interference frequency; Interference spectrum analysis model: , wherein, is the center frequency of the communication, is the bandwidth of the communication, is the electromagnetic interference power spectral density.

3. The system of claim 1, wherein, the environment-communication coupling model is: ， wherein, is the temperature and humidity influence coefficient, , is the rated temperature and humidity, , is the current ambient temperature and humidity, and α, β, γ are material aging coefficients.

4. The system of claim 1, wherein, The dynamic adaptive threshold Specifically: ， wherein is a dynamic adaptive threshold, is a reference threshold, , , is a weight coefficient.

5. The system of claim 1, wherein, the second monitoring node performs power distribution gateway hardware state monitoring based on power grid operation historical data time series and real-time collected power grid parameters, comprising: if the real-time collected power grid parameters received by the power distribution gateway jump, and seriously deviate from the power grid operation historical data time series, it is determined that the power grid of the monitoring loop is faulty; if the real-time collected power grid parameters received by the power distribution gateway do not change continuously, it is determined that the data collection sensor is faulty; if the power distribution gateway does not receive real-time collected power grid parameters, and the sensor wireless communication is normal, it is determined that the communication interface of the power distribution gateway of the monitoring loop is faulty.

6. The system of claim 1, wherein, the third monitoring node comprises: a communication encryption and identity verification subunit that detects the encryption suite strength, certificate validity and identity authentication of the communication link; a data integrity check and behavior analysis subunit that checks the integrity of the application layer data and performs abnormal analysis based on the behavior baseline; an active security defense and threat perception subunit that performs intrusion detection and denial of service attack identification; a security decision engine that cooperates with the outputs of the above three subunits, and interacts with the monitoring results of the first monitoring node and the second monitoring node to comprehensively determine the gateway state.

7. The system of claim 1, wherein, the cloud server further performs: based on the global data aggregated by the edge computing node, group fault trend prediction is performed, and the prediction result is shared with the edge computing node.

8. A method for monitoring the operating state of a power distribution gateway based on secure communication based on the system of any one of claims 1-7, characterized in that, comprising the following steps: S1: collecting real-time operating state data of the power distribution gateway through the edge collection node, wherein the operating state data comprises communication quality parameters, hardware operating parameters, communication security parameters and physical environment parameters; S2: The first monitoring node quantifies the dynamic influence of temperature and humidity and power grid parameters on power distribution gateway communication state recognition by establishing electromagnetic interference quantification model and environment temperature and humidity-communication coupling model, and adopts dynamic adaptive threshold The environment and communication coupling model and dynamic adaptive threshold are used to determine the gateway communication state, and if the determination result is abnormal, abnormal information is output for alarm, and if the determination result is normal, step S3 is entered; S3: the second monitoring node performs hardware state and data rationality diagnosis based on historical and real-time data comparison; S4: the third monitoring node detects the encryption strength, identity authentication, data integrity and network attack behavior of the communication link, and integrates multi-source information through a security decision engine to comprehensively determine the security state; S5: The edge computing node uploads the monitoring results and the original data to the cloud server; the cloud server optimizes the edge node model parameters through a machine learning algorithm and issues them, and based on the converged global data, predicts the group failure trend, and shares the prediction results with the edge computing node; S6: After the edge computing node receives the model parameters issued by the cloud server and updates the model, it executes steps S2-S4.

9. An electronic device, comprising: Comprising: one or more processors; a memory; and one or more programs stored in the memory, the one or more programs including instructions for performing the power distribution gateway running state monitoring method based on secure communication as claimed in claim 8.

10. A computer-readable storage medium, characterized in that, Comprising one or more programs for one or more processors of an electronic device to execute, the one or more programs including instructions for performing the power distribution gateway running state monitoring method based on secure communication as claimed in claim 8.

Images