A low voltage data acquisition device and method based on the Internet of Things

Abstract

The present application provides a low-voltage data acquisition device and method based on the Internet of Things. By synchronously measuring the current data of each sensor node, the missing state of all current data is estimated to obtain the state residual of the current data corresponding to each sensor node, and then the time-space correlation of all sensor nodes in the power grid in the power measurement is determined by the correlation coefficient of all state residuals and the topological structure between each adjacent node in the power grid node network; according to the transient energy and time-space correlation of each sensor node, all current data of low-voltage wireless synchronous measurement are confidence-associated to obtain the measurement confidence of each sensor node; when the measurement confidence of the sensor node is less than the preset measurement confidence threshold, the current value measured by the sensor node is reconstructed according to the measurement confidence. The scheme of the present application can realize the confidence evaluation of synchronous acquisition of power data, thereby improving the reliability of low-voltage data acquisition.

Description

Technical Field

[0001] The present application relates to the field of electric power measurement technology, and more specifically, to a low-voltage data acquisition device and method based on the Internet of Things. Background Art

[0002] Power measurement is the process of accurately quantifying and recording electrical parameters in the power system. It is an important basis for the operation of the power system. By monitoring key parameters such as current, voltage, and power, power measurement can grasp the operating status of the power grid in real time, detect anomalies or faults in a timely manner, and ensure the stability and safety of power supply. At the same time, power measurement data provides support for power grid dispatch and optimization, helps to reasonably distribute loads, and improve the overall operating efficiency of the power grid. With the rapid development of new energy and distributed energy, power measurement plays a further role, which can effectively evaluate the operating status of distributed energy and promote its reasonable access and utilization.

[0003] In the current low-voltage power measurement system, in the process of power data collection in multi-node power grids, traditional measurement methods are affected by environmental factors, equipment failures or data transmission delays, resulting in missing or errors in the measurement data, which in turn affects the accuracy of power monitoring and scheduling decisions. Although some systems use synchronous sampling technology to ensure the timeliness of data, in complex power grid environments, the spatiotemporal relationship between nodes and the influence of topological structure are often not fully considered, resulting in the difficulty in ensuring the validity and reliability of the measurement data. Based on the confidence assessment mechanism, a credible assessment of the measurement data can timely discover the missing or errors in the measurement data and make timely corrections, thereby improving the reliability of the measurement data. Therefore, how to achieve confidence assessment of synchronous power data collection, thereby improving the reliability of low-voltage data collection, has become a difficult problem faced by the industry. Summary of the invention

[0004] The present application provides a low-voltage data acquisition device and method based on the Internet of Things, which can realize confidence assessment of synchronous power data acquisition, thereby improving the reliability of low-voltage data acquisition.

[0005] In a first aspect, the present application provides a low-voltage data collection method based on the Internet of Things, comprising:

[0006] Receive a synchronous sampling instruction sent by the power Internet of Things terminal, and synchronously collect current data of each sensor node according to the synchronous sampling instruction;

[0007] Constructing a power grid node network according to the spatial distance relationship between each sensor node, and then determining the correlation coefficient of the topological structure between each adjacent node in the power grid node network;

[0008] The missing state of the current data of each sensor node is estimated to obtain the state residual of the current data corresponding to each sensor node, and then the spatiotemporal correlation of all sensor nodes in the power grid in power measurement is determined through the correlation coefficient of all state residuals and the topological structure between each adjacent node;

[0009] Extracting the transient energy of each sensor node in the power measurement from the current data of each sensor node, and then performing confidence association on all the current data of the low-voltage wireless synchronous measurement according to all the transient energies and the spatiotemporal correlation to obtain the measurement confidence of each sensor node;

[0010] For each sensor node, when the measurement confidence of the sensor node is less than a preset measurement confidence threshold, the current value measured by the sensor node is reconstructed according to the measurement confidence.

[0011] Preferably, constructing a power grid node network based on the spatial distance relationship between the sensor nodes specifically includes:

[0012] Get the geographic location information of all sensor nodes;

[0013] Determine the spatial distance between each adjacent sensor node by using the geographical location information;

[0014] The grid node network is determined by the geographical location information and the spatial distances between each adjacent sensor node.

[0015] Preferably, determining the correlation coefficient of the topological structure between adjacent nodes in the power grid node network specifically includes:

[0016] Selecting a node from the grid node network as a selected node;

[0017] Determine the adjacency coefficient between the selected node and other adjacent nodes according to the average topological distance between the selected node and other adjacent nodes and the average communication delay between the selected node and other adjacent nodes;

[0018] Continue to determine the adjacency coefficients between the remaining nodes and other adjacent nodes;

[0019] The correlation coefficient of the topological structure between each adjacent node in the power grid node network is determined by all the adjacency coefficients.

[0020] Preferably, performing missing state estimation on the current data of each sensor node to obtain the state residual of the current data corresponding to each sensor node specifically includes:

[0021] For the current data of each sensor node, based on the Gaussian distribution assumption, the least square method is used to estimate the state of the current data to obtain the optimal state estimation value of the current data;

[0022] The estimation error of the missing measurement of the sensor node is determined by the current data and the optimal state estimation value, and the estimation error is used as the state residual of the current data corresponding to the sensor node.

[0023] Preferably, determining the spatiotemporal correlation of all sensor nodes in the power grid in power measurement through all state residuals and correlation coefficients of topological structures between adjacent nodes specifically includes:

[0024] Selecting a sensor node as a selected sensor node;

[0025] Determine the estimated deviation between the selected sensor node and other adjacent sensor nodes through the state residual of the selected sensor node and the state residual of other adjacent sensor nodes;

[0026] Determine the temporal relationship of current data between the selected sensor node and other adjacent sensor nodes based on the covariance matrix;

[0027] Determine the spatiotemporal correlation between the selected sensor node and other adjacent sensor nodes in the power grid by using the temporal relationship, the estimated deviation and the correlation coefficient of the topological structure between the selected sensor node and other adjacent sensor nodes;

[0028] Continue to determine the spatiotemporal correlation between the remaining sensor nodes and other adjacent sensor nodes;

[0029] The spatiotemporal correlations of all sensor nodes in the power grid in power measurement are determined through all spatiotemporal correlations.

[0030] Preferably, extracting the transient energy of each sensor node in power measurement from the current data of each sensor node specifically includes:

[0031] Preset current thresholds based on historical current data;

[0032] For the current data of each sensor node, the current average value greater than the current threshold in the current data is used as the transient energy of the sensor node in power measurement.

[0033] Preferably, reconstructing the current value measured by the sensor node according to the measurement confidence specifically includes:

[0034] Determining a reconstruction weight of a pre-trained data reconstruction model through the measurement confidence;

[0035] The current data of the sensor node is reconstructed according to the data reconstruction model to obtain the current value after the missing measurement data is restored.

[0036] In a second aspect, the present application provides a low-voltage data acquisition device based on the Internet of Things, comprising:

[0037] The acquisition module is used to receive the synchronous sampling instruction sent by the power Internet of Things terminal, and synchronously acquire the current data of each sensor node according to the synchronous sampling instruction;

[0038] A processing module, used to construct a power grid node network according to the spatial distance relationship between each sensor node, and then determine the correlation coefficient of the topological structure between each adjacent node in the power grid node network;

[0039] The processing module is further used to estimate the missing state of the current data of each sensor node, obtain the state residual of the current data corresponding to each sensor node, and then determine the spatiotemporal correlation of all sensor nodes in the power grid in power measurement through all the state residuals and the correlation coefficient of the topological structure between each adjacent node;

[0040] The processing module is further used to extract the transient energy of each sensor node in the power measurement from the current data of each sensor node, and then perform confidence association on all current data of low-voltage wireless synchronous measurement according to all transient energies and the spatiotemporal correlation to obtain the measurement confidence of each sensor node;

[0041] The execution module is used for reconstructing the current value measured by each sensor node according to the measurement confidence when the measurement confidence of the sensor node is less than a preset measurement confidence threshold.

[0042] In a third aspect, the present application provides a computer device, comprising a memory and a processor, wherein the memory stores codes, and the processor is configured to obtain the codes and execute the above-mentioned low-voltage data collection method based on the Internet of Things.

[0043] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned low-voltage data acquisition method based on the Internet of Things is implemented.

[0044] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects:

[0045] In an embodiment of the present application, a synchronous sampling instruction sent by a power Internet of Things terminal is received, and current data of each sensor node is synchronously collected according to the synchronous sampling instruction; a power grid node network is constructed according to the spatial distance relationship between each sensor node, and then the correlation coefficient of the topological structure between each adjacent node in the power grid node network is determined; the missing state of the current data of each sensor node is estimated to obtain the state residual of the current data corresponding to each sensor node, and then the spatiotemporal correlation of all sensor nodes in the power grid in power measurement is determined through all the state residuals and the correlation coefficient of the topological structure between each adjacent node; the transient energy of each sensor node in power measurement is extracted from the current data of each sensor node, and then confidence association is performed on all current data of low-voltage wireless synchronous measurement according to all transient energies and the spatiotemporal correlation to obtain the measurement confidence of each sensor node; for each sensor node, when the measurement confidence of the sensor node is less than a preset measurement confidence threshold, the current value measured by the sensor node is reconstructed according to the measurement confidence.

[0046] It can be seen that the present application uses all transient energy and spatiotemporal correlations to perform confidence association on all current data measured by low-voltage wireless synchronous measurement to obtain the measurement confidence of each sensor node. When the measurement confidence is less than the preset measurement confidence threshold, the measured current data is reconstructed; first, by constructing a power grid node network and determining the topological structure correlation coefficient between each node, considering the spatiotemporal relationship between nodes in a multi-node power grid, it can help identify the potential correlation between nodes, and can effectively evaluate the mutual influence of power data between different nodes, which is convenient for further analysis of the overall consistency and effectiveness of power measurement data; then, through missing state estimation and state residual analysis, the missing state of sensor node current data can be evaluated, and the correlation coefficient of the topological structure between adjacent nodes can be combined to determine the location of each sensor node. The spatiotemporal correlation in power measurement can timely detect and handle data missing or anomalies caused by factors such as equipment failure or transmission delay; finally, by extracting the transient energy of each sensor node and combining the spatiotemporal correlation, the confidence association of all current data is achieved, and the measurement confidence of each sensor node is generated. By quantifying the measurement reliability of each sensor node, it can help the system automatically evaluate the credibility of the data, thereby improving the accuracy of the overall power measurement. Furthermore, when the measurement confidence of the sensor node is lower than the preset threshold, the possible measurement errors are automatically corrected and restored, thereby ensuring the reliability and accuracy of low-voltage data acquisition; in summary, the present application scheme can realize the confidence evaluation of synchronous power data acquisition, thereby improving the reliability of low-voltage data acquisition. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is an exemplary flow chart of a low-voltage data collection method based on the Internet of Things according to some embodiments of the present application;

[0048] Figure 2 is a schematic structural diagram of a phasor measurement module according to some embodiments of the present application;

[0049] Figure 3 is a schematic diagram of a process for determining a state residual according to some embodiments of the present application;

[0050] Figure 4 It is a structural schematic diagram of a low-voltage data acquisition device based on the Internet of Things according to some embodiments of the present application;

[0051] Figure 5 It is a structural schematic diagram of a computer device for implementing a low-voltage data collection method based on the Internet of Things as shown in some embodiments of the present application. DETAILED DESCRIPTION

[0052] In order to better understand the technical solution of the present application, the technical solution of the present application will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0053] refer to Figure 1 , which is an exemplary flow chart of a low-voltage data collection method based on the Internet of Things according to some embodiments of the present application. The low-voltage data collection method 100 based on the Internet of Things mainly includes the following steps:

[0054] In step 101, a synchronous sampling instruction sent by a power Internet of Things terminal is received, and current data of each sensor node is synchronously collected according to the synchronous sampling instruction.

[0055] When implementing it, first refer to Figure 2, which is a schematic diagram of the structure of a phasor measurement module according to some embodiments of the present application, wherein the phasor measurement module includes a global positioning system (GPS, Global Positioning System), a communication interface, a communication network, a phasor data concentrator and a phasor measurement unit (PMU, Phasor Measurement Unit), where GPS is used to provide high-precision time synchronization signals to ensure that the measurement data of each PMU has a unified timestamp; the communication interface is used to connect the PMU with the communication network, which can transmit measurement data and receive control instructions; the communication network is used to carry the transmission channel of PMU data, and transmit the collected phasor data from each node to the concentrator or control center; the phasor data concentrator is used to aggregate the data of multiple PMUs, perform time alignment and quality inspection on the data, and provide unified measurement results to the superior system; the PMU is used to measure the voltage, current phasor and frequency in the power grid in real time, and provide synchronized dynamic power grid status data; the load status of the power grid can be monitored in real time through the phasor measurement module. When the power grid load is unbalanced, the power Internet of Things terminal automatically broadcasts the synchronous sampling instruction to all connected sensor nodes through the wireless communication protocol (such as Zigbee). After receiving the synchronous sampling instruction, the wireless terminal acquisition device of the sensor node performs low-voltage wireless synchronous acquisition of the line current according to the preset sampling frequency, and then uses the collected data as the current data of the sensor node, and remotely transmits the current data of each sensor node to the wireless data collection terminal through wireless encryption transparent transmission technology.

[0056] It should be noted that the wireless encryption transparent transmission technology in this application adopts an adaptive transmission strategy, which does not require the configuration of the address communication mechanism. Through intelligent identification and automatic matching, it removes the restrictions on data transmission length and baud rate, realizes fast connection and data transmission between devices, thereby ensuring the integrity and timely transmission of data.

[0057] It should also be noted that the synchronous sampling in this application reduces the time difference of power data transmission, which can improve the timing consistency of current data collected by different sensor nodes, thereby laying an accurate time benchmark for subsequent spatiotemporal correlation analysis.

[0058] In step 102, a power grid node network is constructed according to the spatial distance relationship between each sensor node, and then the correlation coefficient of the topological structure between each adjacent node in the power grid node network is determined.

[0059] In some embodiments, constructing a power grid node network based on the spatial distance relationship between each sensor node can be achieved by using the following steps:

[0060] Get the geographic location information of all sensor nodes;

[0061] Determine the spatial distance between each adjacent sensor node by using the geographical location information;

[0062] The grid node network is determined by the geographical location information and the spatial distances between each adjacent sensor node.

[0063] In the specific implementation, first, the geographic location information of each sensor node can be collected through the Global Positioning System (GPS); then, all the collected geographic location information is mapped to a unified three-dimensional space, and the geographic location information of each sensor node has a unique three-dimensional coordinate, and the spatial distance between every two adjacent sensor nodes is further calculated through the Euclidean distance; finally, each sensor node is regarded as a node in the graph, and the spatial distance between each pair of adjacent nodes is used as the edge weight of the graph, and the constructed graph is then used as a power grid node network.

[0064] In some embodiments, determining the correlation coefficient of the topological structure between adjacent nodes in the grid node network may be achieved by using the following steps:

[0065] Selecting a node from the grid node network as a selected node;

[0066] Determine the adjacency coefficient between the selected node and other adjacent nodes according to the average topological distance between the selected node and other adjacent nodes and the average communication delay between the selected node and other adjacent nodes;

[0067] Continue to determine the adjacency coefficients between the remaining nodes and other adjacent nodes;

[0068] The correlation coefficient of the topological structure between each adjacent node in the power grid node network is determined by all the adjacency coefficients.

[0069] In the specific implementation, first, a node is arbitrarily selected from the power grid node network as the selected node; then, the reciprocal of the sum of the average topological distance and the constant 1 can be used as the influencing factor of the topological distance, and the reciprocal of the sum of the average communication delay and the constant 1 can be used as the influencing factor of the communication delay, and further the sum of the influencing factor of the topological distance and the influencing factor of the communication delay is used as the adjacency coefficient between the selected node and other adjacent nodes, and the above steps are repeated, and other nodes are taken as selected nodes in turn, and the adjacency coefficients between them and their adjacent nodes are calculated; finally, the sum of all the adjacency coefficients is taken as the total adjacency coefficient, and the ratio between the adjacency coefficient between adjacent nodes and the total adjacency coefficient is taken as the correlation coefficient of the topological structure between the adjacent nodes.

[0070] It should be noted that in the present application, a network detection tool (such as Ping) can be used to actually measure the number of path hops and link bandwidth between nodes, and the topological distance between nodes is obtained by weighting the number of path hops and link bandwidth. In other embodiments, other existing technologies can also be used to implement it, which will not be elaborated here.

[0071] It should also be noted that the adjacency coefficient in this application is a metric for measuring the strength of the direct association between adjacent nodes in the power grid topology structure; the association coefficient in this application is an indicator for measuring the strength of the association between adjacent nodes in the power grid node network.

[0072] In step 103, the missing state of the current data of each sensor node is estimated to obtain the state residual of the current data corresponding to each sensor node, and then the spatiotemporal correlation of all sensor nodes in the power measurement in the power grid is determined through all the state residuals and the correlation coefficient of the topological structure between each adjacent node.

[0073] In some embodiments, reference Figure 3 As shown, this figure is a schematic diagram of a process for determining a state residual in some embodiments of the present application. In this embodiment, the missing state of the current data of each sensor node is estimated, and the state residual of the current data corresponding to each sensor node is obtained, which can be implemented by the following steps:

[0074] In step 1031, for the current data of each sensor node, based on the Gaussian distribution assumption, the state of the current data is estimated using the least square method to obtain the optimal state estimation value of the current data;

[0075] In step 1032, an estimation error of the missing measurement of the sensor node is determined by using the current data and the optimal state estimation value, and the estimation error is used as the state residual of the current data corresponding to the sensor node.

[0076] In the specific implementation, first, for the current data of each sensor node, a prediction model of the current data (such as a prediction model based on time series) is set. According to the Gaussian distribution assumption, the prediction error of the current data can be regarded as normally distributed, and the least squares method is used to solve the optimal estimate of the current data; then, the absolute difference between the current data and the corresponding optimal estimate can be used as the estimated error of the missing measurement of the sensor node, and finally the estimated error is used as the state residual of the current data corresponding to the sensor node; it should be noted that the present application obtains the state estimate of the current data through the least squares method, which can effectively fill the data missing in the measurement and reduce the error caused by incomplete data.

[0077] It should be noted that the state residual in this application refers to the deviation between the measured value and its optimal state estimate, which is used to measure the degree to which the measured data deviates from the expected state of the model.

[0078] In some embodiments, determining the spatiotemporal correlation of all sensor nodes in the power grid in power measurement by using all state residuals and correlation coefficients of topological structures between adjacent nodes can be implemented by the following steps:

[0079] Selecting a sensor node as a selected sensor node;

[0080] Determine the estimated deviation between the selected sensor node and other adjacent sensor nodes through the state residual of the selected sensor node and the state residual of other adjacent sensor nodes;

[0081] Determine the temporal relationship of current data between the selected sensor node and other adjacent sensor nodes based on the covariance matrix;

[0082] Determine the spatiotemporal correlation between the selected sensor node and other adjacent sensor nodes in the power grid by using the temporal relationship, the estimated deviation and the correlation coefficient of the topological structure between the selected sensor node and other adjacent sensor nodes;

[0083] Continue to determine the spatiotemporal correlation between the remaining sensor nodes and other adjacent sensor nodes;

[0084] The spatiotemporal correlations of all sensor nodes in the power grid in power measurement are determined through all spatiotemporal correlations.

[0085] In the specific implementation, firstly, a sensor node is arbitrarily selected as the selected sensor node, and the average absolute difference of the state residual between the selected sensor node and other adjacent sensor nodes is used as the estimated deviation between the selected sensor node and other adjacent sensor nodes; secondly, the covariance of the current data between the selected sensor node and each other adjacent sensor node in the time series is calculated respectively, and then the mean value between all the calculated covariances is used as the description index of the time series relationship of the current data between the selected sensor node and other adjacent sensor nodes; then, the exponential function value of the reciprocal of the estimated deviation with the natural exponential as the base can be used as the adjustment factor, and then the product of the adjustment factor, the time series relationship and the correlation coefficient is used as the spatiotemporal correlation between the selected sensor node and other adjacent sensor nodes in the power grid, and the above steps are repeated to continue to determine the spatiotemporal correlation between the remaining sensor nodes and other adjacent sensor nodes; finally, all the spatiotemporal correlations can be constructed into a spatiotemporal correlation matrix according to the corresponding sensor node position information, and the spatiotemporal correlation matrix can be used to describe the spatiotemporal correlation of all sensor nodes in the power grid in power measurement.

[0086] It should be noted that the spatiotemporal correlation in this application is an indicator for measuring the degree of correlation between adjacent sensor node state changes in time and space; the spatiotemporal correlation in this application describes the correlation in time and space between the power measurement values ​​of all sensor nodes in the power grid.

[0087] In step 104, the transient energy of each sensor node in power measurement is extracted from the current data of each sensor node, and then confidence association is performed on all current data of low-voltage wireless synchronous measurement based on all transient energies and the spatiotemporal correlation to obtain the measurement confidence of each sensor node.

[0088] In some embodiments, extracting the transient energy of each sensor node in power measurement from the current data of each sensor node may be implemented by the following steps:

[0089] Preset current thresholds based on historical current data;

[0090] For the current data of each sensor node, the current average value greater than the current threshold in the current data is used as the transient energy of the sensor node in power measurement.

[0091] In specific implementation, first, historical current data can be collected to obtain long-term current measurement data of sensor nodes under normal operating conditions, and then a current threshold can be set based on the historical current data to distinguish normal working conditions from transient working conditions. For example, the 95% quantile higher than the normal current mean can be selected as the threshold. Then, the current data collected in real time by each sensor node is analyzed point by point, and the current value of each sampling point is compared with the current threshold. When the current value is greater than the current threshold, the current value is regarded as a transient current. When the current value is less than or equal to the current threshold, the current value is regarded as a normal current. Through the above method, all transient currents of the sensor node can be obtained, and then the mean of all transient currents is used as the transient energy of the sensor node in power measurement. The above method can be repeated to obtain the transient energy of all sensor nodes in power measurement.

[0092] In some embodiments, confidence association is performed on all current data of low-voltage wireless synchronous measurement based on all transient energies and the spatiotemporal correlation to obtain the measurement confidence of each sensor node, which can be achieved by using the following steps:

[0093] Selecting a sensor node as a selected sensor node;

[0094] Determine the correlation coefficient of transient energy between the selected sensor node and other adjacent sensor nodes by using the transient energy corresponding to the selected sensor node and the transient energy corresponding to other adjacent sensor nodes;

[0095] Performing correlation analysis on the current data between the selected sensor node and other adjacent sensor nodes through the temporal-spatial correlation and the correlation coefficient of transient energy to obtain the measurement confidence of the selected sensor node;

[0096] Continue to determine the measurement confidence of the remaining sensor nodes.

[0097] In the specific implementation, first, a sensor node is arbitrarily selected as the selected sensor node, and the transient energy of the sensor nodes adjacent to the selected sensor node is obtained. The average Euclidean distance between the transient energy corresponding to the selected sensor node and other adjacent sensor nodes can be used as the correlation coefficient of the transient energy between the selected sensor node and other adjacent sensor nodes; then, the spatiotemporal correlation between the selected sensor node and all other adjacent sensor nodes can be obtained from the spatiotemporal correlation matrix used to describe the spatiotemporal correlation of all sensor nodes in the power grid, and the average value of all spatiotemporal correlations and the product of the correlation coefficient are used as the measurement confidence of the selected sensor node. Repeat the selection of other remaining sensor nodes to obtain the measurement confidence of the remaining sensor nodes.

[0098] It should be noted that the measurement confidence in this application refers to a quantitative evaluation index of the reliability of the measurement data of the sensor node; the larger the measurement confidence, the higher the reliability of the measurement data, and the smaller the measurement confidence, the lower the reliability of the measurement data.

[0099] In step 105, for each sensor node, when the measurement confidence of the sensor node is less than a preset measurement confidence threshold, the current value measured by the sensor node is reconstructed according to the measurement confidence.

[0100] It should be noted that in the present application, the measurement confidence of each sensor node is judged. When the measurement confidence of the sensor node is less than the preset measurement confidence threshold, it means that the reliability of the current data measured by the sensor node is relatively low. Therefore, it is necessary to calibrate the current data measured by the sensor node to improve the reliability of the measured current data. When the measurement confidence of the sensor node is greater than or equal to the preset measurement confidence threshold, it means that the reliability of the current data measured by the sensor node is high. Therefore, there is no need to process the current data measured by the sensor node.

[0101] In some embodiments, reconstructing the current value measured by the sensor node according to the measurement confidence can be achieved by using the following steps:

[0102] Determining a reconstruction weight of a pre-trained data reconstruction model through the measurement confidence;

[0103] The current data of the sensor node is reconstructed according to the data reconstruction model to obtain the current value after the missing measurement data is restored.

[0104] In the specific implementation, first, the reliability of the current data of the sensor node is evaluated according to the measurement confidence, and the confidence is mapped to the weight of the data reconstruction model, which is used to adjust the model's contribution to the reconstruction of different node data. For example, a higher correction weight is given to low-confidence current data to enhance the model correction capability. Then, a pre-trained data reconstruction model (such as a model based on a neural network or a matrix completion algorithm) is used to input the measured current data and related features, and the missing or abnormal data is completed or corrected in combination with the reconstruction weight of the model. Finally, the model outputs the corrected complete current data, and uses the complete current data as the restored measurement value.

[0105] On the other hand, in some embodiments, the present application provides a low-voltage data acquisition device based on the Internet of Things, referring to Figure 4 , which is a schematic diagram of the structure of a low-voltage data acquisition device based on the Internet of Things according to some embodiments of the present application, the low-voltage data acquisition device 400 includes: a collection module 401, a processing module 402 and an execution module 403, which are described as follows:

[0106] The acquisition module 401 in the present application is mainly used to receive the synchronous sampling instruction sent by the power Internet of Things terminal, and synchronously collect the current data of each sensor node according to the synchronous sampling instruction;

[0107] Processing module 402, in the present application, the processing module 402 is used to construct a power grid node network according to the spatial distance relationship between each sensor node, and then determine the correlation coefficient of the topological structure between each adjacent node in the power grid node network;

[0108] The processing module 402 in the present application is also used to estimate the missing state of the current data of each sensor node, obtain the state residual of the current data corresponding to each sensor node, and then determine the spatiotemporal correlation of all sensor nodes in the power grid in power measurement through all state residuals and the correlation coefficient of the topological structure between each adjacent node;

[0109] The processing module 402 in the present application is also used to extract the transient energy of each sensor node in the power measurement from the current data of each sensor node, and then perform confidence association on all current data of low-voltage wireless synchronous measurement according to all transient energies and the spatiotemporal correlation to obtain the measurement confidence of each sensor node;

[0110] The execution module 403 in the present application is mainly used for reconstructing the current value measured by each sensor node according to the measurement confidence when the measurement confidence of the sensor node is less than a preset measurement confidence threshold.

[0111] In addition, the present application also provides a computer device, which includes a memory and a processor, the memory stores a code, and the processor is configured to obtain the code and execute the above-mentioned low-voltage data collection method based on the Internet of Things.

[0112] In some embodiments, reference Figure 5 , which is a schematic diagram of the structure of a computer device for implementing a low-voltage data collection method based on the Internet of Things according to some embodiments of the present application. The low-voltage data collection method based on the Internet of Things in the above embodiment can be Figure 5 The computer device 500 shown in the figure is implemented, and the computer device 500 includes at least one processor 501, a communication bus 502, a memory 503 and at least one communication interface 504.

[0113] The processor 501 may be a general-purpose central processing unit (CPU) or an application-specific integrated circuit (ASIC).

[0114] The communication bus 502 may be used to transmit information between the above-mentioned components.

[0115] The memory 503 may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, an optical disc storage (including a compressed optical disc, a laser disc, an optical disc, a digital versatile disc, a Blu-ray disc, etc.), a magnetic disk or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer, but is not limited thereto. The memory 503 may exist independently and be connected to the processor 501 via the communication bus 502. The memory 503 may also be integrated with the processor 501.

[0116] The memory 503 is used to store the program code for executing the solution of the present application, and the execution is controlled by the processor 501. The processor 501 is used to execute the program code stored in the memory 503. The program code may include one or more software modules. The low-voltage data acquisition method based on the Internet of Things in the above embodiment can be implemented by the processor 501 and one or more software modules in the program code in the memory 503.

[0117] The communication interface 504 uses any transceiver or other device for communicating with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0118] In a specific implementation, as an embodiment, a computer device may include multiple processors, each of which may be a single-CPU processor or a multi-CPU processor. The processor here may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0119] The above-mentioned computer device may be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device may be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device or an embedded device. The embodiment of the present application does not limit the type of computer device.

[0120] In addition, the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned low-voltage data collection method based on the Internet of Things is implemented.

[0121] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0122] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A low voltage data acquisition method based on the Internet of Things, characterized in that: The method includes: Receive a synchronous sampling instruction sent by the power Internet of Things terminal, and synchronously collect current data of each sensor node according to the synchronous sampling instruction; Constructing a power grid node network according to the spatial distance relationship between each sensor node, and then determining the correlation coefficient of the topological structure between each adjacent node in the power grid node network; The missing state of the current data of each sensor node is estimated to obtain the state residual of the current data corresponding to each sensor node, and then the spatiotemporal correlation of all sensor nodes in the power grid in power measurement is determined through the correlation coefficient of all state residuals and the topological structure between each adjacent node; Extracting the transient energy of each sensor node in the power measurement from the current data of each sensor node, and then performing confidence association on all the current data of the low-voltage wireless synchronous measurement according to all the transient energies and the spatiotemporal correlation to obtain the measurement confidence of each sensor node; For each sensor node, when the measurement confidence of the sensor node is less than a preset measurement confidence threshold, reconstructing the current value measured by the sensor node according to the measurement confidence; Among them, the temporal and spatial correlation of all sensor nodes in the power grid in power measurement is determined by all state residuals and the correlation coefficient of the topological structure between each adjacent node, specifically including: Selecting a sensor node as a selected sensor node; Determine the estimated deviation between the selected sensor node and other adjacent sensor nodes through the state residual of the selected sensor node and the state residual of other adjacent sensor nodes; Determine the temporal relationship of current data between the selected sensor node and other adjacent sensor nodes based on the covariance matrix; Determine the spatiotemporal correlation between the selected sensor node and other adjacent sensor nodes in the power grid by using the temporal relationship, the estimated deviation and the correlation coefficient of the topological structure between the selected sensor node and other adjacent sensor nodes; Continue to determine the spatiotemporal correlation between the remaining sensor nodes and other adjacent sensor nodes; The spatiotemporal correlations in the power measurements of all sensor nodes in the power grid are determined by all the spatiotemporal correlations, and the spatiotemporal correlations describe the correlations in time and space between the power measurements of all sensor nodes in the power grid.

2. The method according to claim 1, characterized in that The construction of a power grid node network based on the spatial distance relationship between each sensor node specifically includes: Get the geographic location information of all sensor nodes; Determine the spatial distance between each adjacent sensor node by using the geographical location information; The grid node network is determined by the geographical location information and the spatial distances between each adjacent sensor node.

3. The method according to claim 1, characterized in that Determining the correlation coefficient of the topological structure between each adjacent node in the power grid node network specifically includes: Selecting a node from the grid node network as a selected node; Determine the adjacency coefficient between the selected node and other adjacent nodes according to the average topological distance between the selected node and other adjacent nodes and the average communication delay between the selected node and other adjacent nodes; Continue to determine the adjacency coefficients between the remaining nodes and other adjacent nodes; The correlation coefficient of the topological structure between each adjacent node in the power grid node network is determined by all the adjacency coefficients.

4. The method according to claim 1, characterized in that The missing state of the current data of each sensor node is estimated to obtain the state residual of the current data corresponding to each sensor node, which specifically includes: For the current data of each sensor node, based on the Gaussian distribution assumption, the least square method is used to estimate the state of the current data to obtain the optimal state estimation value of the current data; The estimation error of the missing measurement of the sensor node is determined by the current data and the optimal state estimation value, and the estimation error is used as the state residual of the current data corresponding to the sensor node.

5. The method according to claim 1, characterized in that Extracting the transient energy of each sensor node in power measurement from the current data of each sensor node specifically includes: Preset current thresholds based on historical current data; For the current data of each sensor node, the current average value greater than the current threshold in the current data is used as the transient energy of the sensor node in power measurement.

6. The method according to claim 1, characterized in that Reconstructing the current value measured by the sensor node according to the measurement confidence specifically includes: Determining a reconstruction weight of a pre-trained data reconstruction model through the measurement confidence; The current data of the sensor node is reconstructed according to the data reconstruction model to obtain the current value after the missing measurement data is restored.

7. A low-voltage data acquisition device based on the Internet of Things, which uses the method described in any one of claims 1 to 6 to perform low-voltage data acquisition, characterized in that: The device includes: The acquisition module is used to receive the synchronous sampling instruction sent by the power Internet of Things terminal, and synchronously acquire the current data of each sensor node according to the synchronous sampling instruction; A processing module, used to construct a power grid node network according to the spatial distance relationship between each sensor node, and then determine the correlation coefficient of the topological structure between each adjacent node in the power grid node network; The processing module is further used to estimate the missing state of the current data of each sensor node, obtain the state residual of the current data corresponding to each sensor node, and then determine the spatiotemporal correlation of all sensor nodes in the power grid in power measurement through all the state residuals and the correlation coefficient of the topological structure between each adjacent node; The processing module is further used to extract the transient energy of each sensor node in the power measurement from the current data of each sensor node, and then perform confidence association on all current data of low-voltage wireless synchronous measurement according to all transient energies and the spatiotemporal correlation to obtain the measurement confidence of each sensor node; The execution module is used for reconstructing the current value measured by each sensor node according to the measurement confidence when the measurement confidence of the sensor node is less than a preset measurement confidence threshold.

8. A computer device, comprising a memory and a processor, wherein the memory stores a code, characterized in that: The processor is configured to obtain the code and execute the low-voltage data acquisition method based on the Internet of Things as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the low-voltage data acquisition method based on the Internet of Things as described in any one of claims 1 to 6 is implemented.

Images