Method for accessing power terminal equipment to power trusted wireless local area network

Abstract

The invention discloses a method for accessing electric power terminal equipment to an electric power trusted wireless local area network, which relates to the technical field of electric power communication and comprises the following steps: acquiring known connected electric power terminal equipment of an electric power business platform, and constructing a metadata portrait according to historical operation preference parameters; through a fingerprint extraction algorithm, collecting equipment operation metadata in real time, and constructing a power terminal request instruction sequence; obtaining a cloud object model and the request instruction sequence to perform association matching screening, and packaging into an adaptation protocol standard data frame of the power terminal request instruction; establishing a multi-protocol monitoring interface power access model, and verifying whether the real-time power terminal request instruction has request abnormity or not; if it is judged that connection establishment is allowed, a dynamic communication behavior monitoring model is established according to the metadata portrait of the known power terminal equipment and the adaptation protocol standard data frame of the power terminal request instruction, and whether the power terminal request instruction is legal or not is analyzed. The method has the beneficial effect that the stability of the power system is enhanced.

Description

Technical Field

[0001] This invention relates to the field of power communication technology, specifically to a method for power terminal equipment to access a trusted power wireless local area network. Background Technology

[0002] Existing technologies mostly rely on rule-based protocol matching and simple anomaly detection methods, which typically focus on a single dimension of detecting the frequency of requests from power terminal devices or the content of data frames. However, these methods exhibit significant limitations in highly dynamic environments. Specifically, existing technologies cannot handle the complex relationships between device request behaviors, nor can they effectively identify various potential security threats. In particular, when power terminal devices are connected to power service platforms, simple rule matching and anomaly detection are insufficient to address multi-dimensional security risks such as malicious attacks, device malfunctions, or abnormal operations, thereby reducing the security and stability of the system. Summary of the Invention

[0003] To address the aforementioned technical issues, this paper provides a method for power terminal equipment to access a trusted power wireless local area network. This technical solution resolves the multi-dimensional security risks associated with malicious attacks, equipment malfunctions, or abnormal operations.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is as follows: A method for power terminal equipment to access a trusted power wireless local area network includes: Based on the historical database, the known connected power terminal devices of the power business platform are obtained, and the metadata profile of the known power terminal devices is constructed according to the operation preference parameters of the historically known connected power terminal devices. By using a power terminal fingerprint extraction algorithm, the target power terminal equipment model can be identified, equipment operation metadata can be collected in real time, and a power terminal request command sequence can be constructed. The cloud-based object model of the power business platform is obtained and matched with the power terminal request instruction sequence for screening. The sequence of power terminal request instructions is semantically parsed and structurally reorganized according to the adaptation model protocol, and encapsulated into a standard data frame of the power terminal request instruction adaptation protocol. Based on the cloud-based object model of the power business platform, a multi-protocol monitoring interface power access model is established. The standard data frame of the power terminal request instruction is used as input to verify whether there is a request anomaly in the real-time power terminal request instruction. If so, the connection is refused; otherwise, the connection is allowed. If the connection is deemed permissible, a dynamic communication behavior monitoring model is established based on the known metadata profile of the power terminal equipment and the standard data frame of the power terminal request command's adaptation protocol. The model analyzes whether the power terminal request command is valid. If it is, the connection is deemed to be normal; otherwise, the connection is deemed to be disconnected.

[0005] Preferably, based on a historical database, historical operating data of known connected power terminal equipment of the power business platform is extracted by querying using SQL structured query language, and missing values ​​are processed by mean interpolation to perform data preprocessing; the historical operating data includes: communication characteristics, data characteristics and power consumption characteristics; Based on the known connected power terminal equipment on the power business platform, obtain the unique device ID of the power terminal equipment and determine the model of the power terminal equipment. Based on historical operational data, extract the timestamps of all heartbeat packets, calculate the time difference between adjacent heartbeat packets, and form a heartbeat interval sequence. Based on historical operating data, the mean and standard deviation of data packet size for each power terminal device are statistically analyzed, and a reasonable range for data packet size is determined by combining the Gaussian distribution model. Based on the power terminal equipment model, the corresponding communication protocol type is matched to obtain the power terminal equipment communication protocol type; Based on the Modbus register address, known power terminal devices of the same model are grouped and aggregated. Each address corresponds to a massive set of data values ​​of a power terminal device, and the data point address is obtained. Based on the known connected power terminal equipment of the power business platform, obtain the semantic address information of the power terminal equipment; Based on the obtained data point address, check the massive data value set corresponding to each address for a power terminal device. If all values ​​are in {0,1}, the data type is Boolean; if all values ​​are integers, the data type is integer; otherwise, it is floating-point. For Boolean data, directly calculate the values ​​and frequencies; For integer or floating-point data, the range of values ​​is obtained using the mean ± 3σ principle; Integrate data point addresses, semantic addresses, and numerical ranges, store them in a structured manner in the profile, and construct a data point mapping table; By coupling the communication protocol type, data point mapping table, and power consumption characteristics of power terminal equipment, a metadata profile of known power terminal equipment is constructed.

[0006] Preferably, the power consumption characteristics of power terminal equipment under different operating modes are defined by the following formulas: in, This represents the power consumption characteristics of the power terminal equipment at time t, where t is a timestamp. In the first operating mode, the data packet Weighting factor for power consumption, For a moment Data packet size In the first operating mode, the device activity level Weighting factor for power consumption, For time The time interval of heartbeats is used as the baseline. K represents the base power consumption in the first operating mode, and K is the total number of operating modes. In the Kth operating mode, the data packet Weighting factor for power consumption, For the Kth operating mode, device activity Weighting factor for power consumption, For time The time interval of heartbeats is used as the baseline. This represents the base power consumption for the Kth operating mode.

[0007] Preferably, the DPDK data plane development kit technology is used to capture network data packets sent and received by the target power terminal equipment in real time and extract key information from the data packets; the key information includes: source IP address, destination IP address, source port number, destination port and protocol type; It integrates source IP address, destination IP address, source port number, destination port and protocol type, and aggregates them into multiple independent session streams; Based on multiple independent session streams, multi-dimensional feature information is extracted; the multi-dimensional feature information includes: link layer features, network / transport layer features and application layer features.

[0008] Preferably, multiple feature information is paired with the metadata profile of known power terminal equipment to construct a feature vector, which is then normalized. Using cosine similarity, the similarity between the feature vector and the target power terminal equipment model is calculated. If the similarity is higher than a preset threshold, it is determined that the target power terminal equipment model is successfully matched with the known power terminal equipment. The preset threshold is 0.7; Based on the feature vectors, a random forest model is trained. Based on Bootstrap random sampling, multiple decision trees are generated from the training dataset. Each tree is split based on a different feature subset. The model of the target power terminal equipment is determined through a voting mechanism. Based on the determined model of the target power terminal equipment, the operating metadata of the target power terminal equipment is collected in real time; the operating metadata includes: data packet size, heartbeat packet timestamp and power consumption value; Based on real-time acquisition of operational metadata of the target power terminal equipment, a power terminal request instruction sequence is constructed; the instruction sequence includes: device access request, data upload request, and remote control instruction.

[0009] Preferably, a protocol parser matching the power terminal equipment model is identified based on a predefined cloud-based object model parsing rule base; the parsing rule base includes: instruction type, parameter format, and data type; Based on the protocol parser that matches the power terminal equipment model, the power terminal request instruction sequence is disassembled to extract the data point address and data value; Based on the data point address, the corresponding semantic address information is searched in the data point mapping table to realize the semantic parsing of the power terminal request command sequence; Based on the semantic parsing of the power terminal request instruction sequence, the power terminal request instruction sequence is structurally reassembled and encapsulated according to the data frame format of the model protocol; the data frame format encapsulation includes: frame header, instruction type, parameter list and check code; The frame header is used to identify the start and end of a data frame; The instruction type indicates the specific operation requested by the power terminal; The parameter list details the data points and values ​​involved in the request; Checksums are used to ensure the integrity of data frames during transmission.

[0010] Preferably, the adapted protocol standard data frame, which is encapsulated according to the data frame format of the cloud-based object model, is sent to the model protocol interface of the power business platform to achieve reliable communication between the power terminal equipment and the power business platform; For different models of power terminal equipment, the format and content of data frames are dynamically adjusted according to the communication protocol type and data point mapping table in the metadata profile of the power terminal equipment. The integrity of the adaptation protocol standard data frame is verified using a hash algorithm. If the verification passes, the adaptation protocol standard data frame is sent to the power business platform for processing. If the verification fails, the structure is reorganized again until a compliant standard data frame is generated.

[0011] Preferably, based on the cloud-based object model of the power business platform, a multi-protocol monitoring interface power access model is established, using the standard data frame of the power terminal request command as the input to verify whether there is any request anomaly in the real-time power terminal request command; Based on the historical database, the historical request frequency and profile information of power terminal equipment are obtained. The request frequency is standardized using the Z-score standardization method. If the absolute value of the request frequency exceeds 3, it is judged as an abnormal frequency. Check whether the frame header, instruction type, parameter list and checksum of the data frame conform to the object model protocol specification. If the data frame content is missing or incorrect, it is judged as data abnormal and the connection is refused to be established. If the data frame content is complete and passes the verification, a deep learning model is trained to perform semantic understanding of the instruction types and data values ​​in the data frame and determine whether it conforms to the power business platform specifications. If the frequency, data frame content, command type, or data value violates the specification, it is determined to be a command error and the connection is refused. If the frequency, data frame content, instruction type, and data value conform to the specifications, then it is determined that the connection can be established.

[0012] Preferably, if it is determined that the connection can be established, a dynamic communication behavior monitoring model is established according to the known metadata profile of the power terminal equipment and the standard data frame of the power terminal request instruction. The system performs real-time parsing of the standard data frames of the power terminal request command adaptation protocol to identify the operation type, data point address, and data value in the command sequence. Based on a dynamic communication behavior monitoring model, a legal instruction library is preset; the legal instruction library includes: legal operation types, corresponding data point address ranges, and expected data value ranges; According to the preset legal instruction library, the operation type of the parsed power terminal request instruction sequence is compared with the legal instruction library. If the operation type is not in the legal instruction library, it is determined to be an illegal instruction. Check whether the data point address is in the corresponding data point mapping table in the metadata profile and whether the data value is within the expected range. If the address does not match or the data value is out of range, it is determined to be an illegal instruction. If an illegal command is detected, a security alert will be triggered immediately, the abnormal behavior will be recorded, and the connection will be disconnected. If the command is determined to be legitimate, the sending frequency and time interval of the command are analyzed and compared with historical behavior patterns to detect any abnormal behavior patterns. If the frequency and time interval analysis shows normality, the connection is deemed normal, allowing data interaction between the power terminal equipment and the power service platform. Compared with the prior art, the beneficial effects of this invention are: This invention proposes a method for power terminal devices to access a trusted power wireless local area network. By constructing a metadata profile of the power terminal devices, introducing a multi-protocol monitoring interface, adapting power terminal request commands to standard data frames, and implementing a dynamic communication behavior monitoring model, the security of power terminal device access is comprehensively enhanced. This scheme, combining historical data, device fingerprinting, and protocol parsing, can accurately identify the legitimacy of request commands and further improves anomaly detection capabilities based on behavioral pattern analysis. This not only significantly improves the security of the power service platform but also effectively reduces the risks caused by malicious attacks and equipment failures, thereby enhancing the stability of the power system. Attached Figure Description

[0013] Figure 1A flowchart illustrating a method for power terminal equipment to access a trusted wireless local area network. Detailed Implementation

[0014] The following description is intended to disclose the invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art.

[0015] Reference Figure 1 As shown, a method for power terminal equipment to access a trusted power wireless local area network includes: S1. Based on the historical database, obtain the known connected power terminal devices of the power business platform, and construct the metadata profile of the known power terminal devices according to the operating preference parameters of the historically known connected power terminal devices; the metadata profile includes: terminal communication protocol type, data point mapping table and power consumption characteristics; Step S1 includes the following: Based on the historical database, historical operating data of known connected power terminal equipment of the power business platform is extracted by querying with SQL structured query language, and missing values ​​are processed by mean imputation to perform data preprocessing; the historical operating data includes communication characteristics, data characteristics and power consumption characteristics; Based on the known connected power terminal equipment on the power business platform, obtain the unique device ID of the power terminal equipment and determine the model of the power terminal equipment. Based on historical operational data, extract the timestamps of all heartbeat packets, calculate the time difference between adjacent heartbeat packets, and form a heartbeat interval sequence. Based on historical operating data, the mean and standard deviation of data packet size for each power terminal device are statistically analyzed, and a reasonable range for data packet size is determined by combining the Gaussian distribution model. Based on the power terminal equipment model, the corresponding communication protocol type is matched to obtain the power terminal equipment communication protocol type; Based on the Modbus register address, known power terminal devices of the same model are grouped and aggregated. Each address corresponds to a massive set of data values ​​of a power terminal device, and the data point address is obtained. Based on the known connected power terminal equipment of the power business platform, obtain the semantic address information of the power terminal equipment; Based on the obtained data point address, check the massive data value set corresponding to each address for a power terminal device. If all values ​​are in {0,1}, the data type is Boolean; if all values ​​are integers, the data type is integer; otherwise, it is floating-point. For Boolean data, directly calculate the values ​​and frequencies; For integer or floating-point data, the range of values ​​is obtained using the mean ± 3σ principle; Integrate data point addresses, semantic addresses, and numerical ranges, store them in a structured manner in the profile, and construct a data point mapping table; The power consumption characteristics of power terminal equipment under different operating modes are analyzed using the piecewise function method, as shown in the following formula: in, This represents the power consumption characteristics of the power terminal equipment at time t, where t is a timestamp. In the first operating mode, the data packet Weighting factor for power consumption, For a moment Data packet size In the first operating mode, the device activity level Weighting factor for power consumption, For time The time interval of heartbeats is used as the baseline. K represents the base power consumption in the first operating mode, and K is the total number of operating modes. In the Kth operating mode, the data packet Weighting factor for power consumption, For the Kth operating mode, device activity Weighting factor for power consumption, For time The time interval of heartbeats is used as the baseline. This represents the base power consumption for the Kth operating mode. By coupling the communication protocol type, data point mapping table, and power consumption characteristics of power terminal equipment, a metadata profile of known power terminal equipment is constructed.

[0016] When using it, refer to the content of step S1 above: In existing domestic and international technologies, the construction of metadata profiles for power terminal equipment faces several technical shortcomings. First, in large-scale networked environments, some equipment characteristics may be overlooked, failing to fully consider the differences in actual operation between different protocols and equipment models, resulting in insufficient equipment performance and data accuracy. Finally, existing power consumption analysis methods often fail to comprehensively cover changes under different operating modes, affecting the prediction of equipment optimization and energy saving. This step effectively overcomes these shortcomings through multi-dimensional extraction and refined analysis, including communication protocols, data points, power consumption characteristics, and equipment operating modes. By using the mean ± 3σ principle and piecewise function method to conduct refined analysis of equipment power consumption, it can more accurately describe the performance of equipment under different conditions, thereby providing a more accurate metadata profile for the power business platform, improving equipment monitoring and optimization efficiency, realizing intelligent energy management, and promoting the digital transformation of the power industry.

[0017] S2. Using a power terminal fingerprint extraction algorithm, identify the target power terminal equipment model, collect equipment operation metadata in real time, and construct a power terminal request command sequence; Step S2 includes the following: Using the DPDK data plane development kit, network data packets sent and received by the target power terminal equipment are captured in real time, and key information in the data packets is extracted. The key information includes: source IP address, destination IP address, source port number, destination port and protocol type. It integrates source IP address, destination IP address, source port number, destination port and protocol type, and aggregates them into multiple independent session streams; Based on multiple independent session streams, multi-dimensional feature information is extracted; the multi-dimensional feature information includes: link layer features, network / transport layer features and application layer features.

[0018] Step S2 also includes the following: Pair multiple feature information with the metadata profile of known power terminal equipment, construct feature vectors, and perform normalization processing; Using cosine similarity, the similarity between the feature vector and the target power terminal equipment model is calculated. If the similarity is higher than a preset threshold, it is determined that the target power terminal equipment model is successfully matched with the known power terminal equipment. The preset threshold is 0.7; Based on the feature vectors, a random forest model is trained. Based on Bootstrap random sampling, multiple decision trees are generated from the training dataset. Each tree is split based on a different feature subset. The model of the target power terminal equipment is determined through a voting mechanism. Based on the determined model of the target power terminal equipment, the operating metadata of the target power terminal equipment is collected in real time; the operating metadata includes: data packet size, heartbeat packet timestamp and power consumption value; Based on real-time acquisition of operational metadata of the target power terminal equipment, a power terminal request instruction sequence is constructed; the instruction sequence includes: device access request, data upload request, and remote control instruction.

[0019] When using it, refer to the content of step S2 above: In existing domestic and international technologies, power terminal equipment model identification typically relies on traditional protocol analysis or hardware feature-based methods. However, these methods have limitations in accuracy and real-time performance under complex environments. Traditional methods often fail to efficiently extract fine-grained operational data between devices, resulting in low identification accuracy. Furthermore, they are prone to misjudgment and response delays when dealing with a large number of devices. In contrast, this method combines DPDK data plane technology, feature extraction, and a random forest model to achieve efficient real-time identification of power terminal equipment and accurately match device models using cosine similarity. By collecting device operational metadata in real time and constructing a power terminal request command sequence, this method significantly improves identification accuracy and response speed, making it particularly suitable for power terminal management and scheduling in multi-device, complex environments.

[0020] S3. Obtain the cloud-based object model of the power business platform and the power terminal request instruction sequence for association matching and filtering. Perform semantic parsing and structured reorganization on the power terminal request instruction sequence according to the adaptation model protocol, and encapsulate it into a standard data frame of the power terminal request instruction adaptation protocol. Step S3 includes the following: Based on a cloud-based object model parsing rule base, a protocol parser matching the model of the power terminal equipment is identified; the parsing rule base includes: instruction type, parameter format, and data type; Based on the protocol parser that matches the power terminal equipment model, the power terminal request instruction sequence is disassembled to extract the data point address and data value; Based on the data point address, the corresponding semantic address information is searched in the data point mapping table to realize the semantic parsing of the power terminal request command sequence; Based on the semantic parsing of the power terminal request instruction sequence, the power terminal request instruction sequence is structurally reassembled and encapsulated according to the data frame format of the model protocol; the data frame format encapsulation includes: frame header, instruction type, parameter list and check code; The frame header is used to identify the start and end of a data frame; The instruction type indicates the specific operation requested by the power terminal; The parameter list details the data points and values ​​involved in the request; Checksums are used to ensure the integrity of data frames during transmission.

[0021] Step S3 also includes the following: The adapted protocol standard data frame, which is encapsulated according to the data frame format of the cloud-based object model, is sent to the model protocol interface of the power business platform to realize reliable communication between the power terminal equipment and the power business platform. For different models of power terminal equipment, the format and content of data frames are dynamically adjusted according to the communication protocol type and data point mapping table in the metadata profile of the power terminal equipment. The integrity of the adaptation protocol standard data frame is verified using a hash algorithm. If the verification passes, the adaptation protocol standard data frame is sent to the power business platform for processing. If the verification fails, the structure is reorganized again until a compliant standard data frame is generated.

[0022] When using it, refer to the content of step S3 above: Existing domestic and international power terminal equipment model identification technologies mainly rely on protocol-based parsing and hardware feature identification. However, these methods often face challenges in terms of accuracy and real-time performance in complex environments. Traditional protocol parsing cannot extract detailed equipment operating data, resulting in low identification accuracy. Furthermore, with an increased number of devices or complex environments, it is prone to misjudgments and response delays, affecting system stability and efficiency. This step, however, can effectively improve the accuracy and response speed of equipment identification in multi-device and complex environments. This not only overcomes the limitations of traditional methods but also achieves efficient data conversion and unified processing between devices through protocol adaptation and data standardization, improving system interoperability, flexibility, and scalability.

[0023] S4. Based on the cloud-based object model of the power business platform, establish a multi-protocol monitoring interface power access model. Using the standard data frame of the power terminal request instruction as the input, verify whether there is a request anomaly in the real-time power terminal request instruction. If so, determine to refuse to establish a connection; otherwise, determine to allow the establishment of a connection. Step S4 includes the following: Based on the cloud-based object model of the power business platform, a multi-protocol monitoring interface power access model is established. The standard data frame of the power terminal request command is used as input to verify whether there is any request anomaly in the real-time power terminal request command. Based on the historical database, the historical request frequency and profile information of power terminal equipment are obtained. The request frequency is standardized using the Z-score standardization method. If the absolute value of the request frequency exceeds 3, it is judged as an abnormal frequency. Check whether the frame header, instruction type, parameter list and checksum of the data frame conform to the cloud object model specification. If the data frame content is missing or incorrect, it is judged as data abnormal and the connection is refused. If the data frame content is complete and passes the verification, a deep learning model is trained to perform semantic understanding of the instruction types and data values ​​in the data frame and determine whether it conforms to the power business platform specifications. If the frequency, data frame content, command type, or data value violates the specification, it is determined to be a command error and the connection is refused. If the frequency, data frame content, instruction type, and data value conform to the specifications, then it is determined that the connection can be established.

[0024] When using it, refer to the content of step S4 above: Existing domestic and international technologies for power terminal equipment access and protocol verification typically employ simple protocol matching and rule detection, lacking in-depth analysis and multi-dimensional detection of complex abnormal behaviors. Current technologies often focus on single-dimensional detection, neglecting the overall correlation and dynamic changes in device request behavior, resulting in an inability to effectively address complex security threats in smart grid environments in practical applications. This new step, through multi-protocol monitoring interfaces, historical data-based request frequency analysis, protocol state machine verification, and semantic understanding using deep learning models, can comprehensively assess the security of device requests. This significantly improves the system's ability to identify abnormal requests, reduces system security risks caused by malicious attacks or equipment failures, and effectively enhances the security and stability of the power business platform.

[0025] S5. If it is determined that the connection can be established, a dynamic communication behavior monitoring model is established according to the known metadata profile of the power terminal equipment and the standard data frame of the power terminal request instruction. The model is used to analyze whether the power terminal request instruction is legal. If it is, the connection is determined to be normal; otherwise, the connection is determined to be disconnected. Step S5 includes the following: If it is determined that the connection can be established, a dynamic communication behavior monitoring model is established according to the known metadata profile of the power terminal equipment and the standard data frame of the power terminal request instruction. The system performs real-time parsing of the standard data frames of the power terminal request command adaptation protocol to identify the operation type, data point address, and data value in the command sequence. Based on a dynamic communication behavior monitoring model, a legal instruction library is preset; the legal instruction library includes: legal operation types, corresponding data point address ranges, and expected data value ranges; According to the preset legal instruction library, the operation type of the parsed power terminal request instruction sequence is compared with the legal instruction library. If the operation type is not in the legal instruction library, it is determined to be an illegal instruction. Check whether the data point address is in the corresponding data point mapping table in the metadata profile and whether the data value is within the expected range. If the address does not match or the data value is out of range, it is determined to be an illegal instruction. If an illegal command is detected, a security alert will be triggered immediately, the abnormal behavior will be recorded, and the connection will be disconnected. If the instruction is determined to be legitimate, the sending frequency and time interval of the instruction are analyzed and compared with historical behavior patterns to detect any abnormal behavior patterns. If the frequency and time interval analysis shows that they are normal, the connection is determined to be normal, and data interaction between the power terminal equipment and the power business platform is allowed.

[0026] When using it, refer to the content of step S5 above: Existing domestic and international technologies typically employ rule-based protocol matching and simple anomaly detection methods. These methods mostly focus on detecting a single dimension, such as data frame content or request frequency. However, these methods cannot effectively address complex anomaly behaviors, especially in highly dynamic environments like smart grids, where they lack analysis of the overall correlation of device request behaviors. Therefore, they often fail to effectively identify multiple potential security threats. In contrast, the proposed steps, by introducing a dynamic communication behavior monitoring model and a pre-set legitimate command library, combined with in-depth analysis of device metadata profiles, can comprehensively and accurately identify illegal request commands. Furthermore, the comparison of behavioral patterns based on command frequency and time intervals further enhances the ability to detect anomalies, significantly improving system security and stability, and effectively reducing security risks caused by malicious attacks or device malfunctions.

[0027] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the claimed invention. The scope of protection claimed by the appended claims and their equivalents is defined.

Claims

1. A method for power terminal equipment to access a trusted power wireless local area network, characterized in that, include: S1. Based on the historical database, obtain the known connected power terminal devices of the power business platform, and construct the metadata profile of the known power terminal devices according to the operation preference parameters of the historically known connected power terminal devices. S2. Using a power terminal fingerprint extraction algorithm, identify the target power terminal equipment model, collect equipment operation metadata in real time, and construct a power terminal request command sequence; S3. Obtain the physical model of the power business platform and the power terminal request instruction sequence, perform association matching and filtering, and perform semantic parsing and structured reorganization on the power terminal request instruction sequence according to the adaptation model protocol, and encapsulate it into a standard data frame of the power terminal request instruction adaptation protocol. S4. Based on the model protocol of the power business platform, establish a multi-protocol monitoring interface power access model. Use the standard data frame of the power terminal request instruction as the input to verify whether there is a request anomaly in the real-time power terminal request instruction. If so, determine to refuse to establish a connection; otherwise, determine to allow the establishment of a connection. S5. If it is determined that the connection can be established, a dynamic communication behavior monitoring model is established according to the known metadata profile of the power terminal equipment and the standard data frame of the power terminal request instruction. The model is used to analyze whether the power terminal request instruction is legal. If it is, the connection is determined to be normal; otherwise, the connection is determined to be disconnected.

2. The method for power terminal equipment to access a trusted power wireless local area network according to claim 1, characterized in that, S1 includes: Based on the historical database, historical operating data of known connected power terminal equipment of the power business platform is extracted by querying with SQL structured query language, and missing values ​​are processed by mean imputation to perform data preprocessing; the historical operating data includes communication characteristics, data characteristics and power consumption characteristics; Based on the known connected power terminal equipment on the power business platform, obtain the unique device ID of the power terminal equipment and determine the model of the power terminal equipment. Based on historical operational data, extract the timestamps of all heartbeat packets, calculate the time difference between adjacent heartbeat packets, and form a heartbeat interval sequence. Based on historical operating data, the mean and standard deviation of data packet size for each power terminal device are statistically analyzed, and a reasonable range for data packet size is determined by combining the Gaussian distribution model. Based on the power terminal equipment model, the corresponding communication protocol type is matched to obtain the power terminal equipment communication protocol type; Based on the Modbus register address, known power terminal devices of the same model are grouped and aggregated. Each address corresponds to a massive set of data values ​​of a power terminal device, and the data point address is obtained. Based on the known connected power terminal equipment of the power business platform, obtain the semantic address information of the power terminal equipment; Based on the obtained data point address, check the massive data value set corresponding to each address for a power terminal device. If all values ​​are in {0,1}, the data type is Boolean; if all values ​​are integers, the data type is integer; otherwise, it is floating-point. For Boolean data, directly calculate the values ​​and frequencies; For integer or floating-point data, the range of values ​​is obtained using the mean ± 3σ principle; Integrate data point addresses, semantic addresses, and numerical ranges, store them in a structured manner in the profile, and construct a data point mapping table; By coupling the communication protocol type, data point mapping table, and power consumption characteristics of power terminal equipment, a metadata profile of known power terminal equipment is constructed.

3. The power consumption characteristics of the power terminal equipment under different operating modes according to claim 2, the formula includes: in, This represents the power consumption characteristics of the power terminal equipment at time t, where t is a timestamp. In the first operating mode, the data packet Weighting factor for power consumption, For a moment Data packet size In the first operating mode, the device activity level Weighting factor for power consumption, For time The time interval of heartbeats is used as the baseline. K represents the base power consumption in the first operating mode, and K is the total number of operating modes. In the Kth operating mode, the data packet Weighting factor for power consumption, For the Kth operating mode, device activity Weighting factor for power consumption, For time The time interval of heartbeats is used as the baseline. This represents the base power consumption for the Kth operating mode.

4. A method for power terminal equipment to access a trusted power wireless local area network according to claim 1, characterized in that, S2 includes: Using the DPDK data plane development kit, network data packets sent and received by the target power terminal equipment are captured in real time, and key information in the data packets is extracted. The key information includes: source IP address, destination IP address, source port number, destination port and protocol type. It integrates source IP address, destination IP address, source port number, destination port and protocol type, and aggregates them into multiple independent session streams; Based on multiple independent session streams, multi-dimensional feature information is extracted; the multi-dimensional feature information includes: link layer features, network / transport layer features and application layer features.

5. A method for power terminal equipment to access a trusted power wireless local area network according to claim 4, characterized in that, S2 further includes: Pair multiple feature information with the metadata profile of known power terminal equipment, construct feature vectors, and perform normalization processing; Using cosine similarity, the similarity between the feature vector and the target power terminal equipment model is calculated. If the similarity is higher than a preset threshold, it is determined that the target power terminal equipment model is successfully matched with the known power terminal equipment. The preset threshold is 0.7; Based on the feature vectors, a random forest model is trained. Based on Bootstrap random sampling, multiple decision trees are generated from the training dataset. Each tree is split based on a different feature subset. The model of the target power terminal equipment is determined through a voting mechanism. Based on the determined model of the target power terminal equipment, the operating metadata of the target power terminal equipment is collected in real time; the operating metadata includes: data packet size, heartbeat packet timestamp and power consumption value; Based on real-time acquisition of operational metadata of the target power terminal equipment, a power terminal request instruction sequence is constructed; the instruction sequence includes: device access request, data upload request, and remote control instruction.

6. A method for power terminal equipment to access a trusted power wireless local area network according to claim 5, characterized in that, S3 includes: Based on a predefined cloud-based object model parsing rule base, a protocol parser matching the power terminal equipment model is identified; the parsing rule base includes: instruction type, parameter format, and data type; Based on the protocol parser that matches the power terminal equipment model, the power terminal request instruction sequence is disassembled to extract the data point address and data value; Based on the data point address, the corresponding semantic address information is searched in the data point mapping table to realize the semantic parsing of the power terminal request command sequence; Based on the semantic parsing of the power terminal request instruction sequence, the power terminal request instruction sequence is structurally recombined and encapsulated according to the data frame format of the cloud-based object model; the data frame format encapsulation includes: frame header, instruction type, parameter list and check code; The frame header is used to identify the start and end of a data frame; The instruction type indicates the specific operation requested by the power terminal; The parameter list details the data points and values ​​involved in the request; Checksums are used to ensure the integrity of data frames during transmission.

7. A method for power terminal equipment to access a trusted power wireless local area network according to claim 6, characterized in that, S3 further includes: The adapted protocol standard data frame, which is encapsulated according to the data frame format of the cloud-based object model, is sent to the model protocol interface of the power business platform to realize reliable communication between the power terminal equipment and the power business platform. For different models of power terminal equipment, the format and content of data frames are dynamically adjusted according to the communication protocol type and data point mapping table in the metadata profile of the power terminal equipment. The integrity of the adaptation protocol standard data frame is verified using a hash algorithm. If the verification passes, the adaptation protocol standard data frame is sent to the power business platform for processing. If the verification fails, the structure is reorganized again until a compliant standard data frame is generated.

8. A method for power terminal equipment to access a trusted power wireless local area network according to claim 7, characterized in that, S4 includes: Based on the cloud-based object model of the power business platform, a multi-protocol monitoring interface power access model is established. The standard data frame of the power terminal request command is used as input to verify whether there is any request anomaly in the real-time power terminal request command. Based on the historical database, the historical request frequency and profile information of power terminal equipment are obtained. The request frequency is standardized using the Z-score standardization method. If the absolute value of the request frequency exceeds 3, it is judged as an abnormal frequency. Check whether the frame header, instruction type, parameter list and checksum of the data frame conform to the model protocol specification. If the data frame content is missing or incorrect, it is judged as data abnormal and the connection is refused to be established. If the data frame content is complete and passes the verification, a deep learning model is trained to perform semantic understanding of the instruction types and data values ​​in the data frame and determine whether it conforms to the power business platform specifications. If the frequency, data frame content, command type, or data value violates the specification, it is determined to be a command error and the connection is refused. If the frequency, data frame content, instruction type, and data value conform to the specifications, then it is determined that the connection can be established.

9. A method for power terminal equipment to access a trusted power wireless local area network according to claim 8, characterized in that, S5 includes: If it is determined that the connection can be established, a dynamic communication behavior monitoring model is established according to the known metadata profile of the power terminal equipment and the standard data frame of the power terminal request instruction. The system performs real-time parsing of the standard data frames of the power terminal request command adaptation protocol to identify the operation type, data point address, and data value in the command sequence. Based on a dynamic communication behavior monitoring model, a legal instruction library is preset; the legal instruction library includes: legal operation types, corresponding data point address ranges, and expected data value ranges; According to the preset legal instruction library, the operation type of the parsed power terminal request instruction sequence is compared with the legal instruction library. If the operation type is not in the legal instruction library, it is determined to be an illegal instruction. Check whether the data point address is in the corresponding data point mapping table in the metadata profile and whether the data value is within the expected range. If the address does not match or the data value is out of range, it is determined to be an illegal instruction. If an illegal command is detected, a security alert will be triggered immediately, the abnormal behavior will be recorded, and the connection will be disconnected. If the instruction is determined to be legitimate, the sending frequency and time interval of the instruction are analyzed and compared with historical behavior patterns to detect any abnormal behavior patterns. If the frequency and time interval analysis shows that they are normal, the connection is determined to be normal, and data interaction between the power terminal equipment and the power business platform is allowed.

Images