Modularized intelligent identification and configuration system for portable Internet of Things electric energy metering box

Abstract

The invention discloses a modularized intelligent identification and configuration system for a portable Internet of Things electric energy metering box, and relates to the technical field of Internet of Things. Electric energy data are collected in real time through an integrated sensor network, and are cleaned, compressed and preliminarily filtered by a data processing module; a deep learning algorithm is adopted to perform feature extraction and abnormal power consumption behavior detection on the data, and rapid response is ensured; a graphical operation interface is provided through the user interface module, and a user is allowed to update configuration immediately according to requirements; the link state is monitored through the LACP, the optimal link is automatically selected, and stable data transmission is ensured; temporarily storing data through a local cache and backup module when the network fluctuates, and automatically synchronizing the data to the cloud after the network is recovered; the system load is monitored through the self-adaptive optimization module, resource allocation is dynamically adjusted, and efficient and stable operation of the system is guaranteed; the data processing speed of the metering box equipment of the electric power internet of things is greatly improved, and the flexibility and the stability are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and more specifically to a modular intelligent identification and configuration system for a portable Internet of Things electric energy meter box. Background Art

[0002] As an important part of the smart grid, the demand for modular intelligent identification and configuration systems for portable IoT power meter boxes is becoming increasingly prominent. Traditional power meter boxes have problems such as decentralized management and data islands, which make it difficult to meet the needs of modern power grids for efficient, intelligent and flexible management. In this context, the modular intelligent identification and configuration system for portable IoT power meter boxes came into being, aiming to achieve intelligent management and configuration of power meter boxes through integrated technical means, and improve the operation efficiency and management level of the power grid.

[0003] The existing portable IoT electric energy meter box modular intelligent identification and configuration system integrates high-precision measurement, communication and control functions through software and hardware integration and modular design. These systems can realize online monitoring of all parameters, ensure the accuracy and real-time of data, and support line loss analysis and meter inaccuracy analysis of the master station. The system adopts an intelligent measurement switch to communicate with the concentrator through a carrier, upload high-precision electrical parameters to the acquisition master station, and realize efficient data processing and convenient and flexible business applications. For example, Chinese patent CN202010484461.6 discloses an electric IoT meter box device based on IoT sensing technology, including a box shell, a door lock device, a control device, at least one electric energy meter, an IoT sensing device and a monitoring device. The device enhances the IoT capability and sensing capability of the electric IoT meter box device through the IoT sensing device, and realizes holographic full-time protection monitoring and early warning, accurate identification of topological relationships of low-voltage stations, line loss analysis and judgment, active anti-theft of electricity, automatic identification of meter row and column relationships, remote calibration of meters, and meter box environment monitoring. However, the IoT sensing device mentioned in the patent is used to obtain relevant data from the power IoT metering box equipment, but when processing complex or large amounts of data, the recognition speed may slow down. This delay may lead to a decrease in processing efficiency and affect the user experience in situations where a quick response is required, such as emergency troubleshooting or user complaint processing. In addition, in actual applications, the system may be subject to hardware or software limitations and cannot be flexibly adjusted according to actual needs. This may cause the system to be unable to meet the customized needs of different users or different scenarios, limiting the scope of application of the system. At the same time, IoT communication technology may be affected by various factors such as the environment, equipment or network operators, resulting in insufficient network stability. Network instability may cause data transmission delays or loss, affecting the system's real-time monitoring and data analysis functions. At the same time, network failures may also cause serious consequences such as system paralysis or data loss. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention discloses a modular intelligent identification and configuration system for a portable Internet of Things electric energy meter box to solve the problems in the background technology.

[0005] The present invention adopts the following technical solutions:

[0006] A modular intelligent identification and configuration system for a portable Internet of Things electric energy metering box includes: a data processing module for regularly reading electric energy metering data through a sensor network, and performing cleaning, compression encoding and preliminary filtering on the collected raw data, transmitting the processed data to an identification and analysis module through an internal message bus AMQP, and recording a log file;

[0007] The identification and analysis module is used to monitor the data flow of the data processing module in real time through the zero-copy message queue, use the deep anomaly recognition algorithm to extract features from the received processed data, classify and identify power consumption patterns, and detect abnormal power consumption behaviors, and transmit the identification results and anomaly detection results to the user interface module.

[0008] The user interface module is used to load the configuration file template and initialize the user interface, and provide a graphical interface through the document object model, allowing users to update the configuration database in real time during configuration operations;

[0009] The multi-link communication module is used to regularly check the status of each communication link through the link aggregation control protocol LACP. According to the detection results, it automatically selects the optimal communication link through the multi-mode communication method and redundancy mechanism and switches to the backup link when the quality of the current link decreases. It uses the selected link to send data to the cloud server, and records the failure reason and tries to resend when the transmission fails.

[0010] A local cache and backup module, which is used to temporarily store data in a local cache area through an SQLite database based on the communication link status detection result of the multi-link communication module when a network fluctuation is detected, and mark it as a pending synchronization state, and automatically upload the cached data to the cloud server through a retransmission request after the network returns to normal, and clear the cached data record after the upload is successful;

[0011] An adaptive optimization module is used to monitor the system load in real time and automatically adjust the resource allocation strategy; the adaptive optimization module includes a system status monitoring submodule, a load evaluation submodule, a resource scheduling submodule and an online learning submodule; the output end of the system status monitoring submodule is connected to the input end of the load evaluation submodule; the output end of the load evaluation submodule is connected to the input end of the resource scheduling submodule; the output end of the resource scheduling submodule is connected to the input end of the online learning submodule.

[0012] As a further technical solution of the present invention, the processing method of the data processing module is: regularly triggering the data acquisition process through a timer mechanism, using the serial communication protocol SPI to read the electric energy metering data from the sensor network, and storing the read raw data in binary format in the memory mapping area; based on the collected data, the data processing module verifies the validity of the collected raw data through a data verification algorithm, compresses and encodes the data through a compression algorithm, and performs initial data filtering processing through a sliding window filtering algorithm; the processed data is transmitted to the identification and analysis module through the internal message bus AMQP; during the data processing process, the data processing module also records log files through the syslog service, including data acquisition timestamps, data cleaning results, compression encoding details, and data transmission status.

[0013] As a further technical solution of the present invention, the zero-copy message queue transfers the data processed by the data processing module from the kernel space to the shared memory area managed by the message queue through a direct memory access mechanism. In the shared memory area, the zero-copy message queue stores and manages the data flow through a ring buffer; the identification and analysis module immediately triggers the corresponding processing function and reads the data from the shared memory area when new data arrives through event notification or polling method.

[0014] As a further technical solution of the present invention, the zero-copy message queue also ensures the correctness and reliability of data reading in a multi-threaded or multi-process environment through a locking mechanism, version control or transaction processing method during data reading.

[0015] As a further technical solution of the present invention, after receiving the data stream, the deep anomaly recognition algorithm automatically learns and extracts high-dimensional features in the data through a convolutional neural network, including the timing, periodicity and potential abnormal pattern information of the electricity consumption data; the convolutional neural network performs a multi-level abstract representation of the input features through a forward propagation mechanism, and optimizes the model parameters through a back propagation algorithm; then, the deep anomaly recognition algorithm classifies the electricity consumption pattern of the extracted features through a support vector machine; based on the classified data, the normal electricity consumption pattern is modeled through an autoencoder, and the reconstruction error is used to determine whether the input data deviates from the normal pattern. When the reconstruction error exceeds the preset threshold, the algorithm determines that there is abnormal electricity consumption behavior, and triggers the alarm mechanism through an event-driven programming model.

[0016] As a further technical solution of the present invention, during the anomaly detection process, the deep anomaly recognition algorithm records the analysis results through the system log system syslog, including the anomaly type, occurrence time, and duration information, and measures the difference between abnormal data and normal data through a density-based clustering method to calculate the degree of anomaly.

[0017] As a further technical solution of the present invention, the operation method of the user interface module includes: the user selects the required functional modules, the user adds or deletes the functional modules by dragging and dropping, dynamically generates a configuration file according to the user's selection and applies the configuration file to the system to make the new configuration effective, and saves the configuration file for subsequent modification or rollback.

[0018] As a further technical solution of the present invention, the multi-link communication module first establishes a link aggregation group by initializing the LACP protocol, aggregates multiple physical links into a logical link, and periodically sends jump messages through the link detection mechanism of the LACP protocol to detect the communication status of each communication link, including signal strength and packet loss rate indicators; if it is detected that the signal strength of a link decreases or the packet loss rate increases, the state change of the link is recorded, and the link selection logic is triggered; during the data transmission process, the multi-link communication module switches multiple communication modes through a multi-mode communication protocol switching mechanism, and the communication modes include Wi-Fi, Bluetooth, and cellular networks; during the data transmission process, when the multi-link communication module detects that the current link quality decreases or the transmission fails, the redundant link switching mechanism is used to ensure the continuity and stability of data transmission; when data transmission fails, the multi-link communication module records the failure information through the system log management system, including the time, reason, and link status information of each transmission failure, and stores the failure information in a local log file; after the storage is completed, the retry mechanism and error recovery algorithm are used to try to resend the data according to the recorded information until the data is successfully transmitted.

[0019] As a further technical solution of the present invention, the system status monitoring submodule includes a system status acquisition unit, a performance monitoring unit and a log recording unit; the system status acquisition unit is used to monitor the real-time system call situation; the performance monitoring unit is used to monitor the system resources in real time, including CPU, memory, and disk IO indicators; the log recording unit is used to record and store monitoring data; the load evaluation submodule includes a load calculation unit and a PID controller unit; the load calculation unit calculates the current system load through a statistical method, and the evaluation includes CPU utilization and memory usage indicators; the PID controller unit adjusts the resource allocation strategy according to the deviation between the current load and the target load through a PID controller algorithm; the resource scheduling submodule includes a process priority adjustment unit, CPU time slice allocation unit and memory management unit; the process priority adjustment unit realizes dynamic adjustment of process priority by adjusting method based on nice value; the CPU time slice allocation unit realizes dynamic allocation of CPU time slice by dynamic scheduling algorithm; the memory management unit realizes efficient management of memory by least recently used LRU algorithm; the online learning submodule includes data collection unit, model training unit and strategy generation unit; the data collection unit is used to collect historical load data; based on historical data, the model training unit trains future load prediction model by reinforcement learning algorithm, and outputs load prediction to the strategy generation unit; the strategy generation unit generates future resource allocation strategy by decision tree to ensure efficient operation of the system under different load conditions.

[0020] The positive beneficial effects of the present invention are:

[0021] 1. The present invention adopts an efficient data processing module to quickly clean, compress, encode and preliminarily filter the collected raw data, significantly improving the data processing speed. The recognition and analysis module adopts a deep anomaly recognition algorithm to achieve rapid feature extraction and power consumption pattern recognition of processed data, reducing the situation where the recognition speed slows down, especially in emergency troubleshooting or user complaint processing, improving processing efficiency and user experience.

[0022] 2. The user interface module provides a graphical interface, allowing users to update the configuration database in real time, so that the system can be flexibly adjusted according to actual needs. This modularization and user-defined configuration capability solves the problem that the system may be limited by hardware or software in the existing technology, allowing the system to meet the customized needs of different users or different scenarios, and expanding the application scope of the system.

[0023] 3. The multi-link communication module regularly checks the status of each communication link through the link aggregation control protocol LACP, and automatically selects the optimal communication link, switching to the backup link when the quality of the current link decreases, thereby enhancing network stability. The local cache and backup module temporarily stores data in the local cache area when the network fluctuates, and automatically synchronizes it to the cloud server after the network returns to normal, reducing the risk of data transmission delay or loss and improving the system's real-time monitoring and data analysis capabilities.

[0024] 4. The adaptive optimization module monitors the system load in real time and automatically adjusts the resource allocation strategy, improving the system's adaptability and resource optimization capabilities under different workloads. This adaptive optimization mechanism helps the system maintain efficient and stable operation when facing different workloads and environmental changes, avoiding system paralysis or performance degradation caused by excessive load. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 This is a schematic diagram of the overall architecture of a modular intelligent identification and configuration system for a portable Internet of Things electric energy meter box of the present invention;

[0026] Figure 2 This is a working principle framework diagram of the multi-link communication module of the present invention. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] In the present invention, if Figure 1 As shown: A modular intelligent identification and configuration system for a portable Internet of Things electric energy metering box includes: a data processing module for regularly reading electric energy metering data through a sensor network, and cleaning, compressing and encoding the collected raw data, and performing preliminary filtering processing. The processed data is transmitted to the identification and analysis module through the internal message bus AMQP, and a log file is recorded;

[0029] The identification and analysis module is used to monitor the data flow of the data processing module in real time through the zero-copy message queue, use the deep anomaly recognition algorithm to extract features from the received processed data, classify and identify power consumption patterns, and detect abnormal power consumption behaviors, and transmit the identification results and anomaly detection results to the user interface module.

[0030] The user interface module is used to load the configuration file template and initialize the user interface. It provides a graphical interface through the document object model, allowing users to instantly update the configuration database during configuration operations. The operation method of the user interface module includes: the user selects the required functional module, the user adds or deletes the functional module by dragging and dropping, dynamically generates a configuration file based on the user's selection and applies the configuration file to the system to make the new configuration effective, and saves the configuration file for subsequent modification or rollback. In the specific implementation,

[0031] The multi-link communication module is used to regularly check the status of each communication link through the link aggregation control protocol LACP. According to the detection results, it automatically selects the optimal communication link through the multi-mode communication method and redundancy mechanism and switches to the backup link when the quality of the current link decreases. It uses the selected link to send data to the cloud server, and records the failure reason and tries to resend when the transmission fails.

[0032] A local cache and backup module, which is used to temporarily store data in a local cache area through an SQLite database based on the communication link status detection result of the multi-link communication module when a network fluctuation is detected, and mark it as a pending synchronization state, and automatically upload the cached data to the cloud server through a retransmission request after the network returns to normal, and clear the cached data record after the upload is successful;

[0033] An adaptive optimization module is used to monitor the system load in real time and automatically adjust the resource allocation strategy; the adaptive optimization module includes a system status monitoring submodule, a load evaluation submodule, a resource scheduling submodule and an online learning submodule; the output end of the system status monitoring submodule is connected to the input end of the load evaluation submodule; the output end of the load evaluation submodule is connected to the input end of the resource scheduling submodule; the output end of the resource scheduling submodule is connected to the input end of the online learning submodule.

[0034] Among them, the data processed by the data processing module is transmitted to the identification and analysis module through the internal message bus AMQP, and the log file is recorded. The identification and analysis module transmits the identification results and anomaly detection results to the user interface module. The input end of the identification and analysis module monitors the data flow of the data processing module in real time through the zero-copy message queue. The user interface module allows the user to update the configuration database in real time during the configuration operation. The user interface module allows the input end to load the configuration file template and initialize the user interface, and receive the identification results and anomaly detection results of the identification and analysis module. The multi-link communication module uses the selected link to send data to the cloud server, and records the failure reason and tries to resend when the transmission fails. The input end of the multi-link communication module is based on the state data to be synchronized of the local cache and backup module, and the result data of the identification and analysis module. After the network returns to normal, the local cache and backup module automatically uploads the cached data to the cloud server through a retransmission request. Based on the communication link status detection results of the multi-link communication module, the local cache and backup module temporarily stores the data in the local cache area through the SQLite database when network fluctuations are detected. The adaptive optimization module monitors the system load in real time, and its input includes the output results of the system status monitoring submodule, load evaluation submodule, resource scheduling submodule and online learning submodule.

[0035] Furthermore, the processing method of the data processing module is: regularly triggering the data collection process through a timer mechanism, reading the electric energy metering data from the sensor network using the serial communication protocol SPI, and storing the read raw data in a memory mapping area in a binary format; based on the collected data, the data processing module verifies the validity of the collected raw data through a data verification algorithm, compresses and encodes the data through a compression algorithm, and performs initial data filtering processing through a sliding window filtering algorithm; the processed data is transmitted to the identification and analysis module through an internal message bus AMQP; during the data processing process, the data processing module also records a log file through the syslog service, including a data collection timestamp, data cleaning results, compression encoding details, and data transmission status. In a specific implementation, the data processing module regularly triggers the data collection process through a timer mechanism, reads the electric energy metering data from the sensor network using the serial communication protocol SPI (Serial Peripheral Interface), and stores the read raw data in a binary format in a memory mapping area. Based on the collected data, the data processing module verifies the validity of the collected raw data through a data verification algorithm, compresses and encodes the data through a compression algorithm (such as the LZW compression algorithm), and performs preliminary data filtering through a sliding window filtering algorithm. The processed data is transmitted to the identification and analysis module through the internal message bus AMQP (Advanced Message Queuing Protocol). During the data processing process, the data processing module also records log files through the syslog service, including data collection timestamps, data cleaning results, compression encoding details, and data transmission status.

[0036] In actual work, the data processing module first triggers the data collection process regularly through the timer mechanism to ensure the regular update of data and improve the timeliness and accuracy of data. The SPI protocol is used to read the power metering data from the sensor network to ensure the efficiency and reliability of data transmission. Secondly, the raw data is stored in the memory mapping area, which reduces the overhead of data copying and improves the speed of data processing. The data verification algorithm verifies the validity of the collected raw data to ensure that only valid data enters the next step of processing, reducing the invalid workload of subsequent processing. The data is compressed and encoded by the LZW compression algorithm, which reduces the bandwidth resources required for data transmission and improves the transmission efficiency. The sliding window filtering algorithm performs preliminary filtering on the data, removes noise and outliers, and improves the data quality. Finally, the processed data is transmitted to the identification and analysis module through the AMQP protocol to ensure the security and reliability of data transmission. Throughout the process, detailed log files are recorded through the syslog service to facilitate subsequent troubleshooting and performance analysis.

[0037] Compared with the existing technology, the advantages and characteristics of the data processing module in the modular intelligent identification and configuration system of the portable Internet of Things electric energy meter box mainly include: first, the data collection process is triggered regularly through the timer mechanism, which ensures the regular update and timeliness of the data and improves the response speed of the system. Secondly, the SPI protocol is used for data transmission, which improves the efficiency and reliability of data transmission. Thirdly, the memory mapping technology is used to reduce the overhead of data copying and improve the speed of data processing. Through the data verification algorithm, compression algorithm and sliding window filtering algorithm, the validity of the data is ensured, the amount of data is reduced and the data quality is improved, thereby improving the overall performance of the system. Finally, the data transmission is carried out through the AMQP protocol, which ensures the security and reliability of data transmission, and the detailed log files are recorded through the syslog service to facilitate subsequent troubleshooting and performance optimization. These advantages and characteristics make the data processing module perform well in the modular intelligent identification and configuration system of the portable Internet of Things electric energy meter box, can effectively process large amounts of data, and ensure the efficient and stable operation of the system.

[0038] Furthermore, the zero-copy message queue transmits the data processed by the data processing module from the kernel space to the shared memory area managed by the message queue through a direct memory access mechanism. In the shared memory area, the zero-copy message queue stores and manages the data flow through a ring buffer; the identification and analysis module immediately triggers the corresponding processing function when new data arrives through an event notification or polling method to read data from the shared memory area. Furthermore, during the data reading process, the zero-copy message queue also ensures the correctness and reliability of data reading in a multi-threaded or multi-process environment through a lock mechanism, version control or transaction processing method. In a specific implementation, the zero-copy message queue transmits the data processed by the data processing module from the kernel space to the shared memory area managed by the message queue through a direct memory access mechanism (DMA). The DMA mechanism allows data to be directly transmitted between the kernel space and the user space, avoiding the performance loss caused by multiple memory copies in the traditional data replication process. In the shared memory area, the zero-copy message queue stores and manages the data flow through a ring buffer. The ring buffer is an efficient memory management structure that can recycle fixed memory space, thereby reducing memory fragmentation and frequent memory allocation operations. In addition, during the data reading process, the zero-copy message queue ensures the correctness and reliability of data reading in a multi-threaded or multi-process environment through locking mechanisms (such as mutex locks or read-write locks), version control (such as atomic operations) or transaction processing methods (such as two-phase commit).

[0039] The application of zero-copy message queues in actual work can produce significant beneficial effects. First, the data is transferred from kernel space to user space through the DMA mechanism, which reduces the number of data copies between different memory areas and greatly improves the data transmission efficiency. The design of the ring buffer makes data storage and management more efficient, reduces the generation of memory fragmentation, and thus improves memory utilization. In addition, the correctness and reliability of data reading are ensured through lock mechanisms, version control or transaction processing methods, and the consistency and integrity of data can be guaranteed even in multi-threaded or multi-process environments. This design not only improves the concurrent processing capability of the system, but also enhances the stability and reliability of the system. Therefore, the application of zero-copy message queues in the modular intelligent identification and configuration system of portable IoT power meter boxes can significantly improve the speed of data processing and the overall performance of the system.

[0040] In the specific implementation, the logical operation process of the zero-copy message queue in the modular intelligent identification and configuration system of the portable Internet of Things electricity meter box is as follows: First, the data processing module transfers the processed data from the kernel space to the shared memory area managed by the message queue through the DMA mechanism. The data is stored in a ring buffer that cyclically uses a fixed memory space to avoid frequent memory allocation and release operations. When new data arrives, the identification and analysis module immediately triggers the corresponding processing function through event notification or polling method to read the data from the shared memory area. During the data reading process, the zero-copy message queue ensures the correctness and reliability of data reading in a multi-threaded or multi-process environment through a lock mechanism, version control or transaction processing method. Throughout the process, data transmission and storage are efficient, reducing unnecessary memory copying and management overhead, and ensuring the real-time and reliability of data processing.

[0041] Compared with the existing technology, the advantages and characteristics of the zero-copy message queue in the modular intelligent identification and configuration system of the portable Internet of Things power meter box mainly include: First, the zero-copy transmission of data is realized through the DMA mechanism, which greatly reduces the number of data copies between the kernel space and the user space and improves the efficiency of data transmission. Secondly, the design of the ring buffer makes data storage and management more efficient, reduces the generation of memory fragmentation, and improves memory utilization. In addition, the correctness and reliability of data reading are ensured through the lock mechanism, version control or transaction processing method, and the stability and reliability of the system are enhanced. These advantages and characteristics make the zero-copy message queue perform well in the modular intelligent identification and configuration system of the portable Internet of Things power meter box, can effectively process large amounts of data, and ensure the efficient and stable operation of the system.

[0042] Furthermore, after receiving the data stream, the deep anomaly recognition algorithm automatically learns and extracts high-dimensional features in the data through a convolutional neural network, including the time series, periodicity and potential abnormal pattern information of the power consumption data; the convolutional neural network performs multi-level abstract representation of the input features through a forward propagation mechanism, and optimizes the model parameters through a back-propagation algorithm; then, the deep anomaly recognition algorithm classifies the power consumption pattern of the extracted features through a support vector machine; based on the classified data, the normal power consumption pattern is modeled through an autoencoder, and the reconstruction error is used to determine whether the input data deviates from the normal pattern. When the reconstruction error exceeds a preset threshold, the algorithm determines that there is abnormal power consumption behavior and triggers an alarm mechanism through an event-driven programming model. Furthermore, during the anomaly detection process, the deep anomaly recognition algorithm records the analysis results through the system log system syslog, including the anomaly type, occurrence time, and duration information, and measures the difference between abnormal data and normal data through a density-based clustering method to calculate the degree of anomaly. In the specific implementation, the deep anomaly recognition algorithm automatically learns and extracts high-dimensional features in the data through the Convolutional Neural Network (CNN), including the time series, periodicity and potential abnormal pattern information of the power consumption data. CNN uses the forward propagation mechanism to perform multi-level abstract representation of the input features, and optimizes the model parameters through the backpropagation algorithm to improve the accuracy of feature extraction. Then, the algorithm classifies the power consumption pattern of the extracted features through the Support Vector Machine (SVM). Based on the classified data, the algorithm models the normal power consumption pattern through the autoencoder, and determines whether the input data deviates from the normal pattern through the reconstruction error. When the reconstruction error exceeds the preset threshold, the algorithm determines that there is abnormal power consumption behavior. Finally, the algorithm records the analysis results through the system log system (Syslog), and measures the difference between abnormal data and normal data through the density-based clustering method (Density-BasedClustering) to calculate the degree of abnormality.

[0043] In actual work, the deep anomaly recognition algorithm firstly automatically learns and extracts high-dimensional features in the data through convolutional neural networks, so that the algorithm can capture complex and imperceptible abnormal patterns, improving the accuracy and robustness of anomaly detection. Secondly, the power consumption pattern is classified by support vector machine, which can effectively divide the power consumption data into different pattern categories, providing a basis for subsequent anomaly detection. Furthermore, the normal power consumption pattern is modeled by autoencoder, and the input data is judged whether it deviates from the normal pattern by reconstruction error. This method can identify those data points that are significantly different from the normal pattern and detect abnormal behavior in time. Finally, the analysis results are recorded by the system log system, and the difference between abnormal data and normal data is measured by density-based clustering method, so that the results of anomaly detection have high interpretability, which is convenient for operation and maintenance personnel to understand and take corresponding measures. This design not only improves the detection accuracy of the system, but also enhances the maintainability and ease of use of the system.

[0044] In the specific implementation, the deep anomaly recognition algorithm first receives the data stream and automatically learns and extracts high-dimensional features in the data through convolutional neural networks, including the time series, periodicity and potential abnormal pattern information of the power consumption data. Then, CNN uses the forward propagation mechanism to perform multi-level abstract representation of the input features, and optimizes the model parameters through the back-propagation algorithm to improve the accuracy of feature extraction. Then, the algorithm classifies the power consumption pattern of the extracted features through the support vector machine. Based on the classified data, the algorithm models the normal power consumption pattern through the autoencoder, and determines whether the input data deviates from the normal pattern through the reconstruction error. When the reconstruction error exceeds the preset threshold, the algorithm determines that there is abnormal power consumption behavior and triggers the alarm mechanism through the event-driven programming model. During the anomaly detection process, the algorithm records the analysis results through the system log system, including the type of anomaly, the time of occurrence, and the duration of the anomaly, and measures the difference between the abnormal data and the normal data through the density-based clustering method to calculate the degree of anomaly.

[0045] Compared with the existing technology, the deep anomaly recognition algorithm automatically learns and extracts high-dimensional features in the data through convolutional neural networks, so that the algorithm can capture complex and imperceptible abnormal patterns, improving the accuracy and robustness of anomaly detection. Secondly, the power consumption pattern is classified by support vector machine, which improves the accuracy and generalization ability of classification. Furthermore, the normal power consumption pattern is modeled by autoencoder, and the input data is judged whether it deviates from the normal pattern by reconstruction error. This method can effectively identify those data points that are significantly different from the normal pattern and detect abnormal behavior in time. Finally, the analysis results are recorded by the system log system, and the difference between abnormal data and normal data is measured by density-based clustering method, so that the results of anomaly detection have high interpretability, which is convenient for operation and maintenance personnel to understand and take corresponding measures. These advantages and characteristics make the deep anomaly recognition algorithm perform well in the modular intelligent identification and configuration system of portable IoT power meter box, which can effectively process large amounts of data and ensure the efficient and stable operation of the system.

[0046] Furthermore, the multi-link communication module first establishes a link aggregation group by initializing the LACP protocol, aggregates multiple physical links into one logical link, and periodically sends jump messages through the link detection mechanism of the LACP protocol to detect the communication status of each communication link, including signal strength and packet loss rate indicators; if it is detected that the signal strength of a link decreases or the packet loss rate increases, the state change of the link is recorded, and the link selection logic is triggered; during the data transmission process, the multi-link communication module switches multiple communication modes through a multi-mode communication protocol switching mechanism, and the communication modes include Wi-Fi, Bluetooth, and cellular networks; during the data transmission process, when the multi-link communication module detects that the current link quality decreases or the transmission fails, the redundant link switching mechanism is used to ensure the continuity and stability of data transmission; when data transmission fails, the multi-link communication module records the failure information through the system log management system, including the time, reason, and link status information of each transmission failure, and stores the failure information in the local log file; after the storage is completed, the retry mechanism and error recovery algorithm are used to try to resend the data according to the recorded information until the data is successfully transmitted. In a specific implementation, Figure 2As shown in the figure: The multi-link communication module establishes a link aggregation group (LAG) through the link aggregation control protocol (LACP) to aggregate multiple physical links into one logical link. The LACP protocol periodically detects the status of each communication link by sending heartbeat messages, including indicators such as signal strength and packet loss rate. When it is detected that the signal strength of a link decreases or the packet loss rate increases, the module records the state change of the link and triggers the link selection logic. The multi-link communication module also switches multiple communication modes (such as Wi-Fi, Bluetooth, and cellular networks) through a multi-mode communication protocol switching mechanism to ensure the continuity and stability of data transmission. During the data transmission process, the module ensures the reliability of data transmission through a redundant link switching mechanism. When data transmission fails, the module records the failure information through the system log management system, and tries to resend the data through a retry mechanism and an error recovery algorithm until it is successfully transmitted.

[0047] In the specific implementation, first, the multi-link communication module establishes a link aggregation group through the LACP protocol, which improves the reliability of the communication link. The LACP protocol detects the link status by sending heartbeat messages regularly, ensuring real-time monitoring of the link. Secondly, through the multi-mode communication protocol switching mechanism, the module can flexibly switch between different communication modes, select the optimal communication mode according to the current environmental conditions, and improve the flexibility and adaptability of communication. Furthermore, through the redundant link switching mechanism, when the current link quality is detected to be degraded or the transmission fails, the module can immediately switch to the backup link to ensure the continuity and stability of data transmission. Finally, the failure information is recorded through the system log management system, and the data is tried to be resent through the retry mechanism and error recovery algorithm to ensure that the data can be successfully transmitted in the end. This design not only improves the communication reliability of the system, but also enhances the fault tolerance of the system and the stability of data transmission.

[0048] Compared with the existing technology, the multi-link communication module establishes a link aggregation group through the LACP protocol, which improves the reliability of the communication link and ensures real-time monitoring of the link. Secondly, through the multi-mode communication protocol switching mechanism, the module can flexibly switch between different communication modes, which improves the flexibility and adaptability of communication. Furthermore, through the redundant link switching mechanism, the continuity and stability of data transmission are ensured, and the fault tolerance of the system is enhanced. Finally, the failure information is recorded through the system log management system, and the retry mechanism and error recovery algorithm are used to ensure that the data can be successfully transmitted in the end, which improves the overall performance and reliability of the system. These advantages and characteristics make the multi-link communication module perform well in the modular intelligent identification and configuration system of the portable Internet of Things electricity meter box, which can effectively handle the data transmission requirements in complex environments and ensure the efficient and stable operation of the system.

[0049] Furthermore, the system status monitoring submodule includes a system status acquisition unit, a performance monitoring unit and a log recording unit; the system status acquisition unit is used to monitor the system call status in real time; the performance monitoring unit is used to monitor the system resources in real time, including CPU, memory, and disk IO indicators; the log recording unit is used to record and store monitoring data; the load evaluation submodule includes a load calculation unit and a PID controller unit; the load calculation unit calculates the current system load through a statistical method, and the evaluation includes CPU utilization and memory usage indicators; the PID controller unit adjusts the resource allocation strategy according to the deviation between the current load and the target load through a PID controller algorithm; the resource scheduling submodule includes a process priority adjustment unit, a C PU time slice allocation unit and memory management unit; the process priority adjustment unit realizes dynamic adjustment of process priority through a nice value adjustment method; the CPU time slice allocation unit realizes dynamic allocation of CPU time slices through a dynamic scheduling algorithm; the memory management unit realizes efficient management of memory through the least recently used LRU algorithm; the online learning submodule includes a data collection unit, a model training unit and a strategy generation unit; the data collection unit is used to collect historical load data; based on historical data, the model training unit trains the future load prediction model through a reinforcement learning algorithm, and outputs the load prediction to the strategy generation unit; the strategy generation unit generates future resource allocation strategies through a decision tree to ensure efficient operation of the system under different load conditions. In the specific implementation, the system status monitoring submodule monitors the system call status in real time through the system status acquisition unit, monitors the system resources in real time through the performance monitoring unit, including CPU, memory, disk I / O and other indicators, and records and stores monitoring data through the log recording unit. The load evaluation submodule calculates the current system load using a statistical method through the load calculation unit, evaluates indicators including CPU utilization and memory usage, and uses the PID controller algorithm through the PID controller unit to adjust the resource allocation strategy according to the deviation between the current load and the target load. The resource scheduling submodule dynamically adjusts the process priority using a nice value-based adjustment method through the process priority adjustment unit, dynamically allocates CPU time slices through the CPU time slice allocation unit using a dynamic scheduling algorithm, and efficiently manages memory using the least recently used (LRU) algorithm through the memory management unit. The online learning submodule collects historical load data through the data collection unit, trains the future load prediction model through the model training unit using a reinforcement learning algorithm, and outputs the load prediction to the strategy generation unit. The decision tree algorithm generates the future resource allocation strategy to ensure the efficient operation of the system under different load conditions. The application of the adaptive optimization module in actual work can produce significant beneficial effects. First, through real-time monitoring of the system status and performance, the transparency and traceability of the system operation status are ensured.Secondly, the resource allocation strategy is dynamically adjusted through the load evaluation submodule, so that the system can automatically adjust resource allocation according to the current load situation, improving the response speed and efficiency of the system. Furthermore, the resource scheduling submodule optimizes process priority, CPU time slice allocation and memory management, improves the utilization of system resources, and ensures that key tasks can be processed first. Finally, the online learning submodule predicts future load conditions and generates resource allocation strategies based on them, enhancing the system's forward-looking and adaptive capabilities. This design not only improves the overall performance of the system, but also enhances the stability and reliability of the system.

[0050] In the specific implementation, the logical operation process of the adaptive optimization module in the modular intelligent identification and configuration system of the portable Internet of Things electricity meter box is as follows: First, the system status monitoring submodule monitors the system call situation in real time through the system status acquisition unit, and monitors the system resources through the performance monitoring unit, including CPU utilization, memory usage, disk I / O and other indicators. The monitoring data is recorded and stored by the log recording unit. Then, the load evaluation submodule calculates the current system load through the load calculation unit, and adjusts the resource allocation strategy according to the deviation between the current load and the target load through the PID controller unit. Next, the resource scheduling submodule dynamically adjusts the process priority through the process priority adjustment unit, dynamically allocates the CPU time slice through the CPU time slice allocation unit, and efficiently manages the memory through the memory management unit. Finally, the online learning submodule collects historical load data through the data collection unit, and trains the future load prediction model through the model training unit, outputs the load prediction to the strategy generation unit, and generates the future resource allocation strategy through the decision tree algorithm to ensure the efficient operation of the system under different load conditions.

[0051] Compared with the existing technology, the adaptive optimization module improves the transparency and traceability of the system by monitoring the system status and performance in real time. Secondly, by dynamically adjusting the resource allocation strategy, the system can automatically adjust the resource allocation according to the current load situation, which improves the response speed and efficiency of the system. Furthermore, by optimizing resource scheduling, the utilization rate of system resources is improved, ensuring that key tasks can be given priority. Finally, by predicting future load conditions through online learning and generating resource allocation strategies based on this, the system's foresight and adaptability are enhanced. These advantages and characteristics make the adaptive optimization module perform well in the modular intelligent identification and configuration system of portable IoT power meter boxes, which can effectively handle resource management requirements in complex environments and ensure efficient and stable operation of the system.

[0052] Although the specific embodiments of the present invention are described above, it should be understood by those skilled in the art that these specific embodiments are only illustrative, and those skilled in the art may omit, replace, and change the details of the above methods and systems in various ways without departing from the principles and essence of the present invention. For example, merging the above method steps so as to perform substantially the same functions in substantially the same manner to achieve substantially the same results is within the scope of the present invention. Therefore, the scope of the present invention is limited only by the appended claims.

Claims

1. A modular intelligent identification and configuration system for portable Internet of Things electric energy metering boxes, characterized in that: include: The data processing module is used to regularly read the electric energy metering data through the sensor network, and clean, compress and encode the collected raw data, and perform preliminary filtering. The processed data is transmitted to the identification and analysis module through the internal message bus AMQP, and the log file is recorded; The identification and analysis module is used to monitor the data flow of the data processing module in real time through the zero-copy message queue, use the deep anomaly recognition algorithm to extract features from the received processed data, classify and identify power consumption patterns, and detect abnormal power consumption behaviors, and transmit the identification results and anomaly detection results to the user interface module. The user interface module is used to load the configuration file template and initialize the user interface, and provide a graphical interface through the document object model, allowing users to update the configuration database in real time during configuration operations; The multi-link communication module is used to regularly check the status of each communication link through the link aggregation control protocol LACP. According to the detection results, it automatically selects the optimal communication link through the multi-mode communication method and redundancy mechanism and switches to the backup link when the quality of the current link decreases. It uses the selected link to send data to the cloud server, and records the failure reason and tries to resend when the transmission fails. A local cache and backup module, which is used to temporarily store data in a local cache area through an SQLite database based on the communication link status detection result of the multi-link communication module when a network fluctuation is detected, and mark it as a pending synchronization state, and automatically upload the cached data to the cloud server through a retransmission request after the network returns to normal, and clear the cached data record after the upload is successful; An adaptive optimization module is used to monitor the system load in real time and automatically adjust the resource allocation strategy; the adaptive optimization module includes a system status monitoring submodule, a load evaluation submodule, a resource scheduling submodule and an online learning submodule; the output end of the system status monitoring submodule is connected to the input end of the load evaluation submodule; the output end of the load evaluation submodule is connected to the input end of the resource scheduling submodule; the output end of the resource scheduling submodule is connected to the input end of the online learning submodule.

2. According to claim 1, a portable Internet of Things electric energy meter box modular intelligent identification and configuration system is characterized by: The processing method of the data processing module is as follows: the data collection process is triggered regularly through a timer mechanism, the electric energy metering data is read from the sensor network using the serial communication protocol SPI, and the read raw data is stored in a memory mapping area in binary format; based on the collected data, the data processing module verifies the validity of the collected raw data through a data verification algorithm, compresses and encodes the data through a compression algorithm, and performs initial data filtering processing through a sliding window filtering algorithm; the processed data is transmitted to the identification and analysis module through an internal message bus AMQP; during the data processing process, the data processing module also records a log file through a syslog service, which includes a data collection timestamp, data cleaning results, compression encoding details, and data transmission status.

3. According to claim 1, a portable Internet of Things electric energy meter box modular intelligent identification and configuration system is characterized by: The zero-copy message queue transmits the data processed by the data processing module from the kernel space to the shared memory area managed by the message queue through the direct memory access mechanism. In the shared memory area, the zero-copy message queue stores and manages the data flow through the ring buffer; The identification and analysis module immediately triggers a corresponding processing function when new data arrives through event notification or polling method to read data from the shared memory area.

4. According to claim 1, a portable Internet of Things electric energy meter box modular intelligent identification and configuration system is characterized by: During the data reading process, the zero-copy message queue also ensures the correctness and reliability of data reading in a multi-threaded or multi-process environment through a lock mechanism, version control or transaction processing method.

5. According to claim 1, a portable Internet of Things electric energy meter box modular intelligent identification and configuration system is characterized by: After receiving the data stream, the deep anomaly recognition algorithm automatically learns and extracts high-dimensional features in the data through a convolutional neural network, including the time series, periodicity and potential abnormal pattern information of the power consumption data; the convolutional neural network performs a multi-level abstract representation of the input features through a forward propagation mechanism, and optimizes the model parameters through a back-propagation algorithm; then, the deep anomaly recognition algorithm classifies the power consumption pattern of the extracted features through a support vector machine; Based on the classified data, the normal power consumption pattern is modeled through the autoencoder, and the reconstruction error is used to determine whether the input data deviates from the normal pattern. When the reconstruction error exceeds the preset threshold, the algorithm determines that there is abnormal power consumption behavior and triggers the alarm mechanism through the event-driven programming model.

6. A modular intelligent identification and configuration system for a portable Internet of Things electric energy meter box according to claim 5, characterized in that: During the anomaly detection process, the deep anomaly recognition algorithm records the analysis results through the system log system syslog, including the anomaly type, occurrence time, and duration information, and measures the difference between abnormal data and normal data through a density-based clustering method to calculate the degree of anomaly.

7. According to claim 1, a portable Internet of Things electric energy meter box modular intelligent identification and configuration system is characterized by: The operation method of the user interface module includes: the user selects the required functional module, the user adds or deletes the functional module by dragging and dropping, dynamically generates a configuration file according to the user's selection and applies the configuration file to the system to make the new configuration effective, and saves the configuration file for subsequent modification or rollback.

8. According to claim 1, a portable Internet of Things electric energy meter box modular intelligent identification and configuration system is characterized by: The multi-link communication module first establishes a link aggregation group by initializing the LACP protocol, aggregates multiple physical links into one logical link, and regularly sends jump messages to detect the communication status of each communication link through the link detection mechanism of the LACP protocol, including signal strength and packet loss rate indicators; If it is detected that the signal strength of a link decreases or the packet loss rate increases, the state change of the link is recorded and the link selection logic is triggered; during the data transmission process, the multi-link communication module switches multiple communication modes through a multi-mode communication protocol switching mechanism, and the communication modes include Wi-Fi, Bluetooth, and cellular networks; During data transmission, when the multi-link communication module detects that the quality of the current link has decreased or the transmission has failed, it ensures the continuity and stability of data transmission through a redundant link switching mechanism; When data transmission fails, the multi-link communication module records the failure information through the system log management system, including the time, reason, and link status information of each transmission failure, and stores the failure information in a local log file; After the storage is completed, the retry mechanism and error recovery algorithm try to resend the data according to the recorded information until the data is successfully transmitted.

9. A modular intelligent identification and configuration system for a portable Internet of Things electric energy meter box according to claim 1, characterized in that: The system status monitoring submodule includes a system status acquisition unit, a performance monitoring unit and a log recording unit; the system status acquisition unit is used to monitor the real-time system call situation; the performance monitoring unit is used to monitor the system resources in real time, including CPU, memory, and disk IO indicators; the log recording unit is used to record and store monitoring data; the load evaluation submodule includes a load calculation unit and a PID controller unit; the load calculation unit calculates the current system load by a statistical method, and the evaluation includes CPU utilization and memory usage indicators; the PID controller unit adjusts the resource allocation strategy according to the deviation between the current load and the target load through the PID controller algorithm; the resource scheduling submodule includes a process priority adjustment unit, a CPU time slice allocation unit and a memory management unit; the process priority adjustment unit realizes dynamic adjustment of the process priority through a nice value adjustment method; the CPU time slice allocation unit realizes dynamic allocation of CPU time slices through a dynamic scheduling algorithm; the memory management unit realizes efficient management of memory through the least recently used LRU algorithm; the online learning submodule includes a data collection unit, a model training unit and a strategy generation unit; the data collection unit is used to collect historical load data; Based on historical data, the model training unit trains a future load prediction model through a reinforcement learning algorithm, and outputs the load prediction to the strategy generation unit; The strategy generation unit generates future resource allocation strategies through a decision tree to ensure efficient operation of the system under different load conditions.

Images