Power Internet of Things data transmission method and device and medium

Abstract

The invention discloses a power Internet of Things data transmission method and device and a medium, and belongs to the field of power network networking, and the transmission method comprises the steps: collecting power data such as current, voltage and power in real time based on a sensor, and carrying out the de-noising of the data through Kalman filtering; layering packaging is carried out according to the data type, a data compression algorithm is applied to compress the data, the transmission bandwidth is reduced, the compressed data is encrypted, and integrity verification information is added; dynamically selecting a transmission channel by using a reinforcement learning algorithm according to a real-time network state; the data are packaged and sent to the cloud through the selected transmission channel, the data are received at the cloud, and the power data are stored and managed by using a time sequence database; and analyzing the received data, generating a real-time report, carrying out anomaly detection and load prediction through a random forest algorithm, and carrying out adaptive adjustment according to the real-time monitoring data. By dynamically selecting a transmission channel and a self-adaptive transmission strategy, network instability is dealt with, and timely transmission of data is ensured.

Description

Technical Field

[0001] The present invention belongs to the technical field of electric power Internet of Things, and more specifically, particularly relates to an electric power Internet of Things data transmission method, device and medium. Background Art

[0002] The advanced metering infrastructure system collects power consumption data from users' smart meters through smart metering terminals, and performs relevant diagnosis and data analysis to monitor users' power consumption behavior and meter status. However, the collection and storage of data in AMI will bring privacy issues to users, such as using man-in-the-middle attacks, DoS attacks, data eavesdropping, etc. to steal users' relevant privacy data, launch attacks on users' switch-on and switch-off, and even tamper with users' power consumption data to steal electricity. With the implementation of the construction of the power Internet of Things and the large-scale installation and use of smart sensor devices, and the need for smart meters to share data with users and power grid companies, the AMI system is required to have good computing power and lightweight security protocols. At present, some studies on data security protection use homomorphic encryption and secure data obfuscation schemes to prevent eavesdroppers from monitoring users' power consumption behavior, but the packet loss rate is high during data transmission and it is vulnerable to network attacks.

[0003] In addition, the power networks in different countries are diverse, and the types of network attacks they face are also complex and varied, which puts higher demands on privacy protection methods. With the improvement of the safety factor of smart meter management and the increase in the types of communication network attacks, it is very necessary to achieve efficient power Internet of Things data security.

[0004] Power IoT devices are usually distributed over a wide geographical area, and network connections may be affected by environmental factors (such as weather, terrain) or network congestion, resulting in data loss or delay. The amount of data generated by the power IoT is huge, requiring efficient data processing and analysis capabilities, and traditional data processing methods may not meet the needs of real-time analysis. The data formats and types generated by different devices may be inconsistent, making data integration and analysis difficult. In load forecasting and management, the lack or delay of real-time data may lead to inaccurate forecasts, thereby affecting energy scheduling and utilization efficiency. Summary of the invention

[0005] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0006] In view of the problems of the above or existing power Internet of Things data transmission methods, the present invention is proposed.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] The embodiment of the present invention provides a method for transmitting data of an electric power Internet of Things, including: collecting electric power data such as current, voltage and power in real time based on sensors, and denoising the data using Kalman filtering; performing layered packaging according to data types, applying a data compression algorithm to compress the data, reducing the transmission bandwidth, encrypting the compressed data, and adding integrity verification information; dynamically selecting a transmission channel using a reinforcement learning algorithm according to the real-time network status; packaging the data and sending it to the cloud through the selected transmission channel, receiving the data in the cloud, and using a time series database to store and manage the electric power data; analyzing the received data, generating a real-time report, performing anomaly detection and load forecasting using a random forest algorithm, and performing adaptive adjustments based on real-time monitoring data.

[0009] As a preferred solution of the power Internet of Things data transmission method of the present invention, wherein: the real-time collection of power data such as current, voltage and power based on sensors and the use of Kalman filtering to denoise the data include:

[0010] If the goal is to estimate the true values ​​of current, voltage, and power, the system is described by the following state-space model:

[0011] Equation of state:

[0012] x k =Ax k-1 +Bu k +ω k

[0013] Among them, X k are the current, voltage and power state vectors, A is the state transfer matrix, B is the control input matrix, u k is the control input, w k is the process noise;

[0014] Observation equation:

[0015] z k =Hx k +v k

[0016] Among them, z k is the observation value, H is the observation matrix, v k is the measurement noise;

[0017] The specific steps for data denoising using Kalman filtering are as follows:

[0018] Initialize the state vector x0, initialize the covariance matrix P0, set the process noise covariance Q and the measurement noise covariance R; then predict the step and update the step.

[0019] As a preferred solution of the power Internet of Things data transmission method of the present invention, wherein: the layered packaging according to the data type, applying the data compression algorithm to compress the data, and reducing the transmission bandwidth, includes:

[0020] The data is divided into an important data layer, a status information layer and a historical data layer. The important data layer includes real-time monitoring data such as current, voltage and power, the status information layer includes equipment status, operating time and fault status, etc., and the historical data layer includes historical data records over a period of time. Each layer of data is packaged according to the agreed format.

[0021] As a preferred solution of the power Internet of Things data transmission method described in the present invention, the method comprises: encrypting the compressed data and adding integrity verification information, including: the sender generates a secure random key and ensures that only the receiver can access it, and the sender encrypts the compressed data using the selected encryption algorithm and key; before data encryption, the sender performs hash processing on the compressed data to generate a unique hash value, and sends the calculated hash value together with the encrypted data to the receiver, and the sender sends the encrypted data and the hash value together to the receiver; the receiver recalculates the hash value of the decrypted data, and compares the calculated hash value with the received hash value. If they are consistent, it indicates that the data is complete; if they are inconsistent, it means that the data has been tampered with, and the receiver can request to retransmit the data.

[0022] As a preferred solution of the power Internet of Things data transmission method of the present invention, wherein: the dynamic selection of the transmission channel using the reinforcement learning algorithm according to the real-time network status includes:

[0023] Initialize the state space, action space and reward function, set the initial strategy, monitor the network status in real time, and update the current state variables;

[0024] Select the transmission channel based on the current state and the learned strategy, using the ε-greedy strategy, that is, select the optimal channel most of the time, occasionally randomly select to explore new channels, and transmit data on the selected channel;

[0025] After the transmission is completed, feedback information such as transmission rate, delay and packet loss is collected, rewards are calculated, and the Q value or strategy is updated according to the collected reward information. The reinforcement learning algorithm Q-learning is used to update the model and select a better channel in the future. The expression is as follows:

[0026]

[0027] Where Q(s,a) is the Q value of taking action a in state s, α is the learning rate, r is the starting state, s is the action to be taken, a is the reward obtained after that, γ is the discount factor, s′ is the new state transferred to after the action is taken, and a′ is the possible action to be taken in the new state s′.

[0028] As a preferred solution of the power Internet of Things data transmission method of the present invention, wherein: the data is packaged and sent to the cloud through the selected transmission channel, the data is received in the cloud, and the power data is stored and managed using a time series database, including:

[0029] Configure a server to receive data packets from different devices. When a data packet arrives, first perform an integrity check to ensure that the data has not been modified during transmission. If the data passes the verification, proceed to the next step.

[0030] Establish a model suitable for storing power data, including fields such as timestamp, voltage, current, and power. Insert the decompressed data into the time series database one by one to ensure that the data is stored in chronological order, set the data retention policy, and use the query function of the time series database to extract data within a specific time period for analysis as needed.

[0031] As a preferred solution of the power Internet of Things data transmission method of the present invention, the received data is analyzed to generate a real-time report, anomaly detection and load forecasting are performed by a random forest algorithm, and adaptive adjustment is performed according to real-time monitoring data, including:

[0032] Extract features from the received data, generate real-time reports by analyzing the received data, and the reports include real-time power indicators, anomaly detection results, and load forecast results; use historical data to train the random forest model to identify normal and abnormal power usage patterns, make predictions on real-time data, check whether the current data point deviates from the normal pattern, and mark it as an abnormal event if the predicted result differs greatly from the actual result. Train a random forest regression model based on historical power consumption data to predict future power loads, input real-time monitoring data into the trained model, and generate predicted values ​​for future loads; if the predicted load exceeds the system's safety threshold, take measures to trigger an early warning when an anomaly is detected.

[0033] A power Internet of Things data transmission device, comprising: a data acquisition and processing module, for collecting power data such as current, voltage and power in real time based on sensors, and using Kalman filtering to denoise the data;

[0034] The data compression and encryption module is used to perform layered packaging according to data type, apply data compression algorithm to compress data, reduce transmission bandwidth, encrypt compressed data, and add integrity verification information; the transmission channel selection module is used to dynamically select the transmission channel according to the real-time network status using the reinforcement learning algorithm; the data transmission module is used to package the data and send it to the cloud through the selected transmission channel, receive the data in the cloud, and use the time series database to store and manage power data; the detection and prediction module is used to analyze the received data, generate real-time reports, perform anomaly detection and load forecasting through the random forest algorithm, and make adaptive adjustments based on real-time monitoring data.

[0035] A computing device, comprising:

[0036] at least one processor, memory, and input-output unit;

[0037] Among them, the memory is used to store computer programs, and the processor is used to call the computer programs stored in the memory to execute the steps of the power Internet of Things data transmission method.

[0038] A computer-readable storage medium includes instructions, which, when executed on a computer, enable the computer to execute the steps of a power Internet of Things data transmission method.

[0039] The beneficial effects of the present invention are as follows: the present invention can effectively cope with network instability and ensure timely data transmission by dynamically selecting transmission channels and applying adaptive transmission strategies. Real-time monitoring and fault detection can be achieved, and the system can quickly switch to backup channels when equipment fails to reduce data loss. Encryption algorithms and integrity checks are used to protect the security of data during transmission, prevent information leakage and data tampering. Advanced security mechanisms are used to enhance the system's ability to resist network attacks and ensure the safe operation of the power Internet of Things. The integrated time series database and intelligent analysis algorithm can quickly process and analyze large amounts of data, generate real-time reports, and support timely decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0041] Figure 1 A flowchart of a power Internet of Things data transmission method provided by an embodiment of the present invention.

[0042] Figure 2A schematic diagram of the structure of a power Internet of Things data transmission device provided in an embodiment of the present invention.

[0043] Figure 3 A schematic structural diagram of a medium according to an embodiment of the present invention is schematically shown.

[0044] Figure 4 A schematic diagram of the structure of a computing device according to an embodiment of the present invention is schematically shown.

[0045] In the drawings, the same or corresponding reference numerals represent the same or corresponding parts. DETAILED DESCRIPTION

[0046] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0047] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0048] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0049] Example 1

[0050] Reference below Figure 1 , Figure 1 This is a flow chart of a power Internet of Things data transmission method provided by an embodiment of the present invention. It should be noted that the embodiments of the present invention can be applied to any applicable scenario.

[0051] Figure 1 The process of the power Internet of Things data transmission method provided by an embodiment of the present invention includes:

[0052] S1: Collect power data such as current, voltage and power in real time based on sensors, and use Kalman filtering to denoise the data.

[0053] Preferably, if the goal is to estimate the true values ​​of current, voltage and power, the system is described by the following state-space model:

[0054] Equation of state:

[0055] x k =Axk-1 +Bu k +ω k

[0056] Among them, X k are the current, voltage and power state vectors, A is the state transfer matrix, B is the control input matrix, u k is the control input, w k is the process noise;

[0057] Observation equation:

[0058] z k =Hx k +v k

[0059] Among them, z k is the observation value, H is the observation matrix, v k is the measurement noise;

[0060] The specific steps for data denoising using Kalman filtering are as follows:

[0061] Initialize the state vector x0, initialize the covariance matrix P0, set the process noise covariance Q and the measurement noise covariance R; then predict the step and update the step.

[0062] Furthermore, initialize the state vector x0:

[0063] Choose an initial state vector, for example:

[0064]

[0065] Among them, I0, V0 and P0 are the initial current, voltage and power values;

[0066] Initialize the covariance matrix P0:

[0067] Set the initial covariance matrix to represent an estimate of the uncertainty of the initial state:

[0068]

[0069] in, is the initial uncertainty;

[0070] Set the process noise covariance Q and measurement noise covariance R:

[0071] Usually use empirical values ​​or determine by experiment:

[0072]

[0073] At each time step k, the following predictions are made:

[0074] Prediction status:

[0075]

[0076] Prediction covariance:

[0077] P k|k-1 =AP k-1|k-1 A T +Q

[0078] Upon receiving the observation z k Then, make the following updates:

[0079] Calculate the Kalman gain:

[0080] K k =P k|k-1 H T (HP k|k-1 H T +R) -1

[0081] Update the state estimate:

[0082]

[0083] Update the covariance:

[0084] P k|k =(IK k H)P k|k-1

[0085] Assume that the initial values ​​of current, voltage and power are I0=10A, V0=220V and P0=200W respectively, and set the following parameters:

[0086] The state transfer matrix A is the identity matrix, the control input matrix B is zero,

[0087] Process noise covariance Q = diag(0.1^2,0.1^2,0.1^2);

[0088] Measurement noise covariance R = diag(0.5^2, 1^2, 5^2);

[0089] At each time step k, the prediction and update steps are repeated, with the input measurement value z k , such as z k =[10.2,221,2180], perform the Kalman filtering process, and obtain the denoised current, voltage, and power estimates.

[0090] S2: Pack the data in layers according to the data type, apply the data compression algorithm to compress the data, reduce the transmission bandwidth, encrypt the compressed data, and add integrity check information.

[0091] Preferably, the data is divided into an important data layer, a status information layer and a historical data layer, wherein the important data layer includes real-time monitoring data such as current, voltage and power, the status information layer includes equipment status, operating time and fault status, etc., and the historical data layer includes historical data records within a period of time in the past, and each layer of data is packaged according to an agreed format;

[0092] The sender generates a secure random key and ensures that only the receiver can access it. The sender encrypts the compressed data using the selected encryption algorithm and key. Before encrypting the data, the sender hashes the compressed data to generate a unique hash value, and sends the calculated hash value together with the encrypted data to the receiver. The sender sends the encrypted data and the hash value together to the receiver.

[0093] The receiver recalculates the hash value of the decrypted data and compares the calculated hash value with the received hash value. If they are consistent, the data is complete; if they are inconsistent, it means that the data has been tampered with and the receiver can request retransmission of the data.

[0094] S3: Dynamically select the transmission channel using reinforcement learning algorithm based on the real-time network status.

[0095] Preferably, the state space, action space and reward function are initialized, the initial strategy is set, the network status is monitored in real time, and the current state variables are updated;

[0096] Select the transmission channel based on the current state and the learned strategy, using the ε-greedy strategy, that is, select the optimal channel most of the time, occasionally randomly select to explore new channels, and transmit data on the selected channel;

[0097] After the transmission is completed, feedback information such as transmission rate, delay and packet loss is collected, rewards are calculated, and the Q value or strategy is updated according to the collected reward information. The reinforcement learning algorithm Q-learning is used to update the model and select a better channel in the future. The expression is as follows:

[0098]

[0099] Where Q(s,a) is the Q value of taking action a in state s, α is the learning rate, r is the starting state, s is the action to be taken, a is the reward obtained after that, γ is the discount factor, s′ is the new state transferred to after the action is taken, and a′ is the possible action to be taken in the new state s′.

[0100] Furthermore, the action space AAA defines the available transmission channels, for example:

[0101] Channel 1, Channel 2 and Channel 3;

[0102] Reward function R(s,a): defines the reward based on the quality and efficiency of the transmission, for example:

[0103] The higher the transmission rate, the greater the reward; the lower the latency, the greater the reward; the lower the packet loss rate, the greater the reward;

[0104] The reward is expressed as a composite score:

[0105] R(s,a)=transmission rate score-delay score-packet loss score

[0106] The current network state variables are monitored in real time through sensors or monitoring systems, and the current state s is updated. The ε-greedy strategy is used to select the transmission channel:

[0107] Setting the ε value (e.g., 0.1) means that the current optimal channel is selected 90% of the time and a random selection is made 10% of the time; action a is selected based on the current state s and the learned strategy, and data is transmitted on the selected channel. Feedback information during the transmission process is recorded; after the transmission is completed, the reward r is collected and calculated.

[0108] Furthermore, the current state bandwidth is initialized to 500Mbps, the delay is 20ms, the channel 1 load is 70%, the channel 2 load is 50%, and the channel 3 load is 30%; the action space selects channel 1, channel 2, and channel 3, and the initial Q value is set to 0;

[0109] Assume that channel 3 is selected and data transmission starts. The transmission rate is 450Mbps, the delay is 15ms, and the packet loss is 0%. The reward r=10 is calculated. The Q value is updated using the collected feedback information to obtain the Q value of the new state. The channel is selected according to the new state for the next data transmission. The above steps are repeated.

[0110] S4: Pack the data and send it to the cloud through the selected transmission channel, receive the data in the cloud, and use the time series database to store and manage the power data.

[0111] Preferably, a server is configured to receive data packets from different devices. When a data packet arrives, an integrity check is first performed to ensure that the data has not been modified during transmission. If the data passes the verification, the next step is performed;

[0112] Establish a model suitable for storing power data, including fields such as timestamp, voltage, current, and power. Insert the decompressed data into the time series database one by one to ensure that the data is stored in chronological order, set the data retention policy, and use the query function of the time series database to extract data within a specific time period for analysis as needed.

[0113] S5: Analyze the received data, generate real-time reports, perform anomaly detection and load forecasting through random forest algorithm, and make adaptive adjustments based on real-time monitoring data.

[0114] Preferably, features are extracted from the received data, and a real-time report is generated by analyzing the received data, the report including real-time power indicators, anomaly detection results, and load forecast results;

[0115] Use historical data to train a random forest model to identify normal and abnormal power usage patterns, make predictions on real-time data, check whether the current data point deviates from the normal pattern, and mark it as an abnormal event if the predicted result is significantly different from the actual result. Train a random forest regression model based on historical power consumption data to predict future power loads, and input real-time monitoring data into the trained model to generate predicted values ​​for future loads;

[0116] If the predicted load exceeds the safety threshold of the system, measures are taken to trigger an early warning when anomalies are detected.

[0117] Furthermore, historical electricity usage data was collected, including samples marked as normal and abnormal, and the historical data was preprocessed, cleaned, and features were extracted; 80% of the historical data was used as a training set and 20% as a test set;

[0118] Build a random forest model, set the number of trees and other hyperparameters, train the model to identify normal and abnormal electricity usage patterns, input the latest real-time feature data into the trained random forest model, and the model outputs the results to determine whether the current data is abnormal. If the results show abnormality, record the event and mark it as an abnormal event;

[0119] Use historical electricity consumption data to train a random forest regression model with the goal of predicting future electricity load. Select feature variables (such as past power usage and time characteristics) for model training. Input the current real-time monitoring data into the trained regression model. The model generates predicted values ​​for future loads and records the prediction results. Define system safety thresholds, such as a safe upper limit for power load of 5000W. Regularly check the generated load prediction values. If the predicted value exceeds the set safety threshold, record the event and prepare to trigger an early warning.

[0120] After introducing the method of the exemplary embodiment of the present invention, next, refer to Figure 2 A novel anti-counterfeiting drip irrigation tape color strip line recycling device according to an exemplary embodiment of the present invention is described, and the device comprises:

[0121] Data acquisition and processing module, used to collect power data such as current, voltage and power in real time based on sensors, and use Kalman filtering to denoise the data;

[0122] The data compression and encryption module is used to package data in layers according to data types, compress data using data compression algorithms to reduce transmission bandwidth, encrypt compressed data, and add integrity check information;

[0123] The transmission channel selection module is used to dynamically select the transmission channel based on the real-time network status using the reinforcement learning algorithm;

[0124] Data transmission module, used to package and send data to the cloud through the selected transmission channel, receive data in the cloud, and use the time series database to store and manage power data;

[0125] The detection and prediction module is used to analyze the received data, generate real-time reports, perform anomaly detection and load forecasting through the random forest algorithm, and make adaptive adjustments based on real-time monitoring data.

[0126] After introducing the method and apparatus of the exemplary embodiment of the present invention, next, reference is made to Figure 3 For a description of a computer-readable storage medium according to an exemplary embodiment of the present invention, please refer to Figure 3 , the computer-readable storage medium shown is a CD 30, on which a computer program (i.e., a program product) is stored. When the computer program is executed by the processor, the steps recorded in the above method implementation method are implemented, for example, based on the real-time collection of power data such as current, voltage, and power by sensors, the data is denoised using Kalman filtering; hierarchical packaging is performed according to the data type, the data is compressed using a data compression algorithm to reduce the transmission bandwidth, the compressed data is encrypted, and integrity verification information is added; according to the real-time network status, a reinforcement learning algorithm is used to dynamically select a transmission channel; the data is packaged and sent to the cloud through the selected transmission channel, the data is received in the cloud, and the power data is stored and managed using a time series database; the received data is analyzed to generate a real-time report, anomaly detection and load forecasting are performed using a random forest algorithm, and adaptive adjustments are performed based on real-time monitoring data; the specific implementation method of each step is not repeated here.

[0127] It should be noted that examples of the computer-readable storage medium may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0128] After introducing the method, apparatus and medium of the exemplary embodiments of the present invention, next, reference is made to Figure 4A computing device for sub-pixel search of the surface of the core synchronization mechanism of the exemplary embodiment of the present invention.

[0129] Figure 4 A block diagram of an exemplary computing device 40 suitable for implementing embodiments of the present invention is shown, and the computing device 40 may be a computer system or a server. Figure 4 The computing device 40 shown is only an example and should not bring any limitation to the functionality and scope of use of the embodiments of the present invention.

[0130] like Figure 4 As shown, the components of the computing device 40 may include, but are not limited to: one or more processors or processing units 401, a system memory 402, and a bus 403 connecting different system components (including the system memory 402 and the processing unit 401).

[0131] The computing device 40 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the computing device 40, including volatile and non-volatile media, removable and non-removable media.

[0132] System memory 402 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 4021 and / or cache memory 4022. Computing device 40 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, ROM 4023 may be used to read and write non-removable, non-volatile magnetic media ( Figure 4 is not shown in the Figure 4 As shown in FIG. 4 , a disk drive for reading and writing a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 403 via one or more data medium interfaces. System memory 402 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of various embodiments of the present invention.

[0133] A program / utility 4025 having a set (at least one) of program modules 4024 may be stored, for example, in system memory 402, and such program modules 4024 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 4024 generally perform the functions and / or methods of the embodiments described herein.

[0134] The computing device 40 may also communicate with one or more external devices 404 (e.g., a keyboard, a pointing device, a display, etc.). Such communication may be performed via an input / output (I / O) interface 405. Furthermore, the computing device 40 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 406. Figure 4 As shown, the network adapter 406 communicates with other modules (such as the processing unit 401, etc.) of the computing device 40 via the bus 403. It should be understood that although Figure 4 Not shown, other hardware and / or software modules may be used in conjunction with computing device 40 .

[0135] The processing unit 401 executes various functional applications and data processing by running the program stored in the system memory 402, for example, based on the real-time collection of power data such as current, voltage and power by sensors, and uses Kalman filtering to denoise the data; hierarchical packaging according to the data type, compressing the data by applying the data compression algorithm, reducing the transmission bandwidth, encrypting the compressed data, and adding integrity verification information; dynamically selecting the transmission channel using the reinforcement learning algorithm according to the real-time network status; packaging the data to the cloud through the selected transmission channel, receiving the data in the cloud, and using the time series database to store and manage the power data; analyzing the received data, generating a real-time report, performing anomaly detection and load forecasting through the random forest algorithm, and making adaptive adjustments based on the real-time monitoring data. The specific implementation methods of each step will not be repeated here. It should be noted that although several units / modules or sub-units / sub-modules of the synchronous escape wiring device based on multi-commodity flow are mentioned in the above detailed description, this division is only exemplary and not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more units / modules described above can be concretized in one unit / module. On the contrary, the features and functions of one unit / module described above may be further divided into multiple units / modules to be embodied.

[0136] In the description of the present invention, it should be noted that the terms “first”, “second” and “third” are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0137] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0138] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0139] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0140] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0141] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0142] Finally, it should be noted that the above-described embodiments are only specific implementations of the present invention, which are used to illustrate the technical solutions of the present invention, rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

[0143] In addition, although the operations of the method of the present invention are described in a specific order in the drawings, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps.

Claims

1. A method for transmitting data in the power Internet of Things, characterized in that: include: Based on real-time sensor data collection such as current, voltage and power, Kalman filtering is used to denoise the data; Pack data in layers according to data type, apply data compression algorithm to compress data, reduce transmission bandwidth, encrypt compressed data, and add integrity check information; According to the real-time network status, the transmission channel is dynamically selected using the reinforcement learning algorithm; Packaging and sending data to the cloud through the selected transmission channel, receiving data in the cloud, and using a time series database to store and manage power data; The received data is analyzed to generate real-time reports, anomaly detection and load forecasting are performed through random forest algorithm, and adaptive adjustments are made based on real-time monitoring data.

2. The power Internet of Things data transmission method according to claim 1, characterized in that: The method of collecting power data such as current, voltage and power in real time based on sensors and using Kalman filtering to denoise the data includes: If the goal is to estimate the true values ​​of current, voltage, and power, the system is described by the following state-space model: Equation of state: x k =Ax k-1 +Bu k +ω k Among them, X k are the current, voltage and power state vectors, A is the state transfer matrix, B is the control input matrix, u k is the control input, w k is the process noise; Observation equation: z k =Hx k +v k Among them, z k is the observation value, H is the observation matrix, v k is the measurement noise; The specific steps for data denoising using Kalman filtering are as follows: Initialize the state vector x0, initialize the covariance matrix P0, set the process noise covariance Q and the measurement noise covariance R; then predict the step and update the step.

3. The power Internet of Things data transmission method according to claim 1, characterized in that: The layered packaging according to the data type and the application of data compression algorithm to compress the data to reduce the transmission bandwidth include: The data is divided into an important data layer, a status information layer and a historical data layer. The important data layer includes real-time monitoring data such as current, voltage and power, the status information layer includes equipment status, operating time and fault status, etc., and the historical data layer includes historical data records over a period of time. Each layer of data is packaged according to the agreed format.

4. The power Internet of Things data transmission method according to claim 1, characterized in that: The method of encrypting the compressed data and adding integrity check information includes: The sender generates a secure random key and ensures that only the receiver can access it. The sender encrypts the compressed data using the selected encryption algorithm and key. Before encrypting the data, the sender hashes the compressed data to generate a unique hash value, and sends the calculated hash value together with the encrypted data to the receiver. The sender sends the encrypted data and the hash value together to the receiver. The receiver recalculates the hash value of the decrypted data and compares the calculated hash value with the received hash value. If they are consistent, the data is complete; if they are inconsistent, it means that the data has been tampered with and the receiver can request retransmission of the data.

5. The power Internet of Things data transmission method according to claim 1, characterized in that: The method of dynamically selecting a transmission channel using a reinforcement learning algorithm according to the real-time network status includes: Initialize the state space, action space and reward function, set the initial strategy, monitor the network status in real time, and update the current state variables; Select the transmission channel based on the current state and the learned strategy, using the ε-greedy strategy, that is, select the optimal channel most of the time, occasionally randomly select to explore new channels, and transmit data on the selected channel; After the transmission is completed, feedback information such as transmission rate, delay and packet loss is collected, rewards are calculated, and the Q value or strategy is updated according to the collected reward information. The reinforcement learning algorithm Q-learning is used to update the model and select a better channel in the future. The expression is as follows: Where Q(s,a) is the Q value of taking action a in state s, α is the learning rate, r is the starting state, s is the action to be taken, a is the reward obtained after that, γ is the discount factor, s′ is the new state transferred to after the action is taken, and a′ is the possible action to be taken in the new state s′.

6. The power Internet of Things data transmission method according to claim 1, characterized in that: The method includes packaging and sending the data to the cloud through the selected transmission channel, receiving the data in the cloud, and using a time series database to store and manage the power data, including: Configure a server to receive data packets from different devices. When a data packet arrives, first perform an integrity check to ensure that the data has not been modified during transmission. If the data passes the verification, proceed to the next step. Establish a model suitable for storing power data, including fields such as timestamp, voltage, current, and power. Insert the decompressed data into the time series database one by one to ensure that the data is stored in chronological order, set the data retention policy, and use the query function of the time series database to extract data within a specific time period for analysis as needed.

7. The power Internet of Things data transmission method according to claim 1, characterized in that: The received data is analyzed to generate real-time reports, anomaly detection and load forecasting are performed through the random forest algorithm, and adaptive adjustments are made based on real-time monitoring data, including: Extract features from received data and generate real-time reports by analyzing the received data. The reports include real-time power indicators, anomaly detection results, and load forecast results. Use historical data to train a random forest model to identify normal and abnormal power usage patterns, make predictions on real-time data, check whether the current data point deviates from the normal pattern, and mark it as an abnormal event if the predicted result is significantly different from the actual result. Train a random forest regression model based on historical power consumption data to predict future power loads, and input real-time monitoring data into the trained model to generate predicted values ​​for future loads; If the predicted load exceeds the safety threshold of the system, measures are taken to trigger an early warning when anomalies are detected.

8. A power Internet of Things data transmission device, characterized in that: include: Data acquisition and processing module, used to collect power data such as current, voltage and power in real time based on sensors, and use Kalman filtering to denoise the data; The data compression and encryption module is used to package data in layers according to data types, compress data using data compression algorithms to reduce transmission bandwidth, encrypt compressed data, and add integrity check information; The transmission channel selection module is used to dynamically select the transmission channel based on the real-time network status using the reinforcement learning algorithm; Data transmission module, used to package and send data to the cloud through the selected transmission channel, receive data in the cloud, and use the time series database to store and manage power data; The detection and prediction module is used to analyze the received data, generate real-time reports, perform anomaly detection and load forecasting through the random forest algorithm, and make adaptive adjustments based on real-time monitoring data.

9. A computing device, comprising: at least one processor, memory, and input-output unit; The memory is used to store a computer program, and the processor is used to call the computer program stored in the memory to execute the steps of the power Internet of Things data transmission method according to any one of claims 1 to 7.

10. A computer-readable storage medium comprising instructions, which, when executed on a computer, enables the computer to execute the steps of the power Internet of Things data transmission method as described in any one of claims 1 to 7.

Images