Method, device and equipment for determining type of load node based on power distribution network

Abstract

The invention provides a method, a device and equipment for determining the type of a load node based on a power distribution network. The method comprises the following steps: acquiring electrical parameter information of a load node in a power distribution network under each moment node in a preset time period; wherein the electrical parameter information comprises at least one of voltage information, power information and impedance information; according to the impedance information corresponding to each moment node in the adjacent moments, determining connection weight information corresponding to the adjacent moments; determining target parameter information of a next moment node according to the voltage information and the power information of the load node under each moment node in a preset time period and the connection weight information corresponding to each adjacent moment; wherein the target parameter information comprises voltage information and power information of the node at the next moment; and determining the type of the load node according to the target parameter information. According to the method, the reliability of determining the type of the load node of the power distribution network is improved.

Description

Technical Field

[0001] This application relates to the field of power system technology, and in particular to a method, apparatus and equipment for determining the type of load node in a distribution network. Background Technology

[0002] In a power distribution network, there are generally many load nodes that are complexly distributed. At the same time, in the actual power grid operation environment, most load nodes do not have the conditions to measure and record operating parameters. That is, load nodes do not have the ability to measure and record operating parameters, and cannot effectively determine the line loss of power transmission under the load node.

[0003] In existing technologies, load nodes are classified and corresponding line loss calculation strategies are selected based on the category of the load node to calculate the line loss of power during transmission under that load node. However, classifying load nodes requires certain data support, and the reliability of current load node classification is poor.

[0004] Therefore, there is currently a problem with the poor reliability of determining the type of load nodes in the distribution network. Summary of the Invention

[0005] This application provides a method, apparatus, and equipment for determining the type of load nodes in a distribution network, in order to solve the technical problem of poor reliability in determining the type of load nodes in a distribution network.

[0006] Firstly, this application provides a method for determining the type of load nodes in a distribution network, including:

[0007] Obtain electrical parameter information of load nodes in the distribution network at each time point within a preset time period; wherein, the electrical parameter information includes at least one of voltage information, power information, and impedance information;

[0008] Based on the impedance information corresponding to each time node in adjacent time periods, the connection weight information corresponding to adjacent time periods is determined; whereby the connection weight information represents the probability of connection between time nodes in adjacent time periods.

[0009] Based on the voltage and power information of the load node at each time point within a preset time period, and the connection weight information corresponding to each adjacent time point, the target parameter information of the node at the next time point is determined; wherein, the target parameter information includes the voltage and power information of the node at the next time point.

[0010] Determine the type of load node based on the target parameter information.

[0011] Optionally, as described above, the connection weight information corresponding to adjacent time points is determined based on the impedance information corresponding to each node in adjacent time points, including:

[0012] Based on the impedance information of the load node at each adjacent time point, the impedance amplitude of the load node at adjacent time points is determined; whereby the impedance amplitude characterizes the magnitude of the change in impedance information.

[0013] Based on the impedance magnitude of the load node at adjacent times, the connection weight information corresponding to adjacent times is determined; whereby the connection weight information is represented as the reciprocal of the impedance magnitude.

[0014] Optionally, as described above, based on the voltage and power information of the load node at each time point within a preset time period, and the connection weight information corresponding to each adjacent time point, the target parameter information of the node at the next time point is determined, including:

[0015] Obtain the impedance sensitivity factor at each time point within a preset time period; whereby the impedance sensitivity factor characterizes the degree to which impedance is affected.

[0016] Based on the impedance sensitivity factor at each time node within the preset time period, the voltage and power information of the load node at each time node, and the connection weight information corresponding to each adjacent time node, the target parameter information of the next time node is determined.

[0017] Alternatively, as described above, the impedance sensitivity factor is characterized as follows:

[0018] ;

[0019] in, Indicates the impedance sensitivity factor. Indicates time, This represents the preset initial impedance sensitivity factor, where α is a preset parameter.

[0020] Optionally, as described above, the target parameter information for the next time node is determined based on the impedance sensitivity factor at each time node within a preset time period, the voltage and power information of the load node at each time node, and the connection weight information corresponding to each adjacent time node. This includes:

[0021] Based on the connection weight information corresponding to adjacent time points, the connection relationship information corresponding to adjacent time points is determined; whereby the connection relationship information indicates whether there is an edge connection between time nodes in adjacent time points;

[0022] Based on the connection relationship information corresponding to adjacent time points, the impedance sensitivity factor of each time point within the preset time period, and the voltage and power information of the load node at each time point, the target parameter information of the next time point node is determined.

[0023] Optionally, as described above, based on the connection relationship information corresponding to adjacent time points, the impedance sensitivity factor at each time point within a preset time period, and the voltage and power information of the load node at each time point, the target parameter information of the next time point node is determined, including:

[0024] If, based on the connection information corresponding to adjacent time points, it is determined that there is an edge connection between time nodes in adjacent time points, then the connection coefficient corresponding to adjacent time points is determined based on the impedance magnitude corresponding to adjacent time points and the impedance sensitivity factor of the time node in the next time point in adjacent time points; whereby the connection coefficient characterizes the degree of correlation between two time nodes in adjacent time points.

[0025] Based on the connection coefficients corresponding to each adjacent time point, and the voltage and power information of the load node at each time point, the target parameter information of the node at the next time point is determined.

[0026] Optionally, as described above, the type of load node is determined based on the target parameter information, including:

[0027] Based on the target parameter information, determine the probability value of the load node under each type;

[0028] The type of load node is determined based on the probability value of each type.

[0029] Alternatively, as described above, the probability value is represented as:

[0030] ;

[0031] in, Let represent the probability that the load node will be of type k at the next time step, and y represent the probability that the load node will be of type k at the next time step. This represents the frequency matrix of the k-th type for each time node within a preset time period for the load node. This represents the transpose of the frequency matrix of the k-th type for each time node of the load node within a preset time period. This represents the frequency matrix of the c-th type for each time node within a preset time period, representing the load node. This represents the transpose of the frequency matrix of type c for each time node within a preset time period for the load node. This indicates the target parameter information.

[0032] Optionally, the method described above further includes:

[0033] Based on a preset association relationship, a line loss calculation strategy corresponding to the type of load node is determined; wherein, the preset association relationship represents the relationship between the type of load node and the line loss calculation strategy, and the line loss calculation strategy is used to calculate the line loss result of the load node.

[0034] Secondly, this application provides a device for determining the type of load nodes in a distribution network, comprising:

[0035] The acquisition unit is used to acquire electrical parameter information of load nodes in the distribution network at each time node within a preset time period; wherein, the electrical parameter information includes at least one of voltage information, power information, and impedance information;

[0036] The first determining unit is used to determine the connection weight information corresponding to adjacent time points based on the impedance information of each time point in adjacent time points; wherein, the connection weight information represents the possibility of connection between time points in adjacent time points.

[0037] The second determining unit is used to determine the target parameter information of the next time node based on the voltage and power information of the load node at each time node within a preset time period, as well as the connection weight information corresponding to each adjacent time node; wherein, the target parameter information includes the voltage and power information of the next time node.

[0038] The third determining unit is used to determine the type of load node based on the target parameter information.

[0039] Thirdly, this application provides an electronic device, including: a memory and a processor;

[0040] The memory stores instructions that the computer executes;

[0041] The processor executes computer execution instructions stored in memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0042] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible embodiments of the first aspect.

[0043] Fifthly, this application provides a computer program product, comprising: a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0044] The method, apparatus, and equipment for determining the type of load nodes in a distribution network provided in this application acquire voltage, power, and impedance information of load nodes in the distribution network at each time point within a preset time period. Further, based on the impedance information corresponding to each time point in adjacent time periods, the connection weight information corresponding to adjacent time points is determined. Then, combining the voltage and power information of the load node at each time point within the preset time period, and the connection weight information corresponding to each adjacent time point, the target parameter information of the next time point node is determined. Based on the target parameter information, the type of load node is determined. The electrical parameter information includes at least one of voltage, power, and impedance information, and the target parameter information includes the voltage and power information of the next time point node. The method for determining the type of load nodes in a distribution network provided in this application uses the voltage and power information of the load node at each time point within the preset time period as the parameter information at that time point, and uses the connection weight information corresponding to each adjacent time point as the probability of connection between time points in adjacent time periods to determine the target parameter information of the next time point node. This target parameter information can then be used as the basis for determining the type of load node. The method for determining the type of load nodes in a distribution network provided in this application improves the reliability of determining the type of load nodes in a distribution network. Attached Figure Description

[0045] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0046] Figure 1 A flowchart illustrating a method for determining the type of load nodes in a distribution network, as provided in this application. Figure 1 ;

[0047] Figure 2 A flowchart illustrating a method for determining the type of load nodes in a distribution network, as provided in this application. Figure 2 ;

[0048] Figure 3 A schematic diagram of the structure of a device for determining the type of load node in a distribution network provided in this application. Figure 1 ;

[0049] Figure 4 A schematic diagram of the structure of a device for determining the type of load node in a distribution network provided in this application. Figure 2 ;

[0050] Figure 5 A schematic diagram of the structure of the electronic device provided in this application.

[0051] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0052] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0053] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with relevant laws, regulations and standards, and corresponding operation entry points are provided for users to choose to authorize or refuse.

[0054] In a power distribution network, there are generally many load nodes that are complexly distributed. At the same time, in the actual power grid operation environment, most load nodes do not have the conditions to measure and record operating parameters. That is, load nodes do not have the ability to measure and record operating parameters, and cannot effectively determine the line loss of power transmission under the load node.

[0055] In existing technologies, load nodes are classified, and corresponding line loss calculation strategies are selected based on the category of the load node to calculate the line loss of power during transmission under that load node. However, classifying load nodes requires certain data support, and existing technologies face many difficulties in obtaining this data. For example, the voltage, current, and power information of the same load node obtained may show anomalies within a short period of time, such as large fluctuations in voltage, current, and power information within a short period of time. This leads to greater difficulty in classifying load nodes and serious abrupt changes in classification results, resulting in poor reliability of load node classification.

[0056] Therefore, there is currently a problem with the poor reliability of determining the type of load nodes in the distribution network.

[0057] The method, apparatus, and equipment for determining the type of load node in a distribution network provided in this application acquire voltage, power, and impedance information of load nodes in the distribution network at each time point within a preset time period. Further, based on the impedance information corresponding to each time point in adjacent time periods, the connection weight information corresponding to adjacent time points is determined. Then, combining the voltage and power information of the load node at each time point within the preset time period with the connection weight information corresponding to each adjacent time point, the target parameter information of the next time point node is determined. Based on the target parameter information, the type of load node is determined. The electrical parameter information includes at least one of voltage, power, and impedance information, and the target parameter information includes the voltage and power information of the next time point node.

[0058] The method for determining the type of load node based on the distribution network provided in this application uses the voltage and power information of the load node at each time node within a preset time period as the parameter information at that time node, and uses the connection weight information corresponding to each adjacent time as the probability of connection between time nodes in adjacent time periods, to determine the target parameter information of the next time node, and then uses the target parameter information as the basis for determining the type of load node.

[0059] The method for determining the type of load nodes in a distribution network provided in this application improves the reliability of determining the type of load nodes in a distribution network.

[0060] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0061] Figure 1 A flowchart illustrating a method for determining the type of load nodes in a distribution network, as provided in this application. Figure 1 The execution subject of this method can be a server, host, or other device, such as... Figure 1 As shown, the method may include:

[0062] S101. Obtain electrical parameter information of load nodes in the distribution network at each time node within a preset time period; wherein, the electrical parameter information includes at least one of voltage information, power information, and impedance information.

[0063] The preset time period can refer to a period of time in which the power distribution network operates. Within this time period, multiple time nodes can be divided according to a certain time interval. For example, if the preset time period is the past minute, and the time period is divided according to a time interval of 1 second, 60 time nodes can be obtained. Under each time node, there can be corresponding electrical parameter information.

[0064] In one possible implementation, real-time measurement devices are pre-installed at load nodes in the distribution network. These devices can acquire electrical parameter information at each time point in real time. For example, the real-time measurement devices may include, but are not limited to, voltage sensors, current sensors, and power sensors.

[0065] Electrical parameter information may include at least one of voltage information, power information, and impedance information. Electrical parameter information is used to reflect the electrical operating status of the load node at different points in time.

[0066] In one possible implementation, if the real-time measuring device is unable to measure the electrical parameter information of the load node, the value of the electrical parameter information is set to a preset value, such as 0.

[0067] Voltage information can characterize the voltage status of a load node. For example, voltage information can include voltage amplitude and voltage phase, where voltage amplitude refers to the real-time voltage value of the load node and voltage phase refers to the phase angle information of the voltage. For example, the voltage amplitude can be 220 volts (V) and the voltage phase can be 30 degrees (°).

[0068] Power information can characterize the power status of a load node. For example, power information can include the load node's active power, reactive power, active power change rate, and reactive power change rate. Active power refers to the active electrical energy consumed by the load node, reactive power refers to the reactive electrical energy consumed by the load node, and the power change rate refers to the change in the load node's power over time. For example, the active power can be 5 kilowatts (kW), the reactive power can be 3 kilovars (kvar), the active power change rate can be 0.5 kilowatts per second (kW / s), and the reactive power change rate can be 0.3 kilovars per second (kvar / s).

[0069] Impedance information characterizes the resistance of a load node to alternating current. For example, impedance information can refer to impedance spectrum characteristics, which are a set of impedance values ​​measured at different frequencies. Impedance information can consist of a real part and an imaginary part; the real part represents resistance, and the imaginary part represents reactance. For example, at a frequency of 1 Hz, the real part is 80 ohms (Ω), and the imaginary part is 60 ohms (Ω).

[0070] It is understood that each time point can correspond to electrical parameter information. For example, the time interval between two adjacent time points is 1 second, and the times corresponding to two adjacent time points are 12:00:00 and 12:00:01. It is understood that the real-time measuring device measures the electrical parameters between 12:00:00 and 12:00:01 to obtain the electrical parameter information corresponding to the next time point between two adjacent time points. For example, the electrical parameter information corresponding to the next time point between two adjacent time points may include a voltage amplitude of 220 volts (V), a voltage phase of 30 degrees (°), and an active power change rate of 0.5 kilowatts per second (kW / s).

[0071] The advantage of this setup is that it enables comprehensive and accurate acquisition of electrical operating status information of load nodes in the distribution network at different times, providing sufficient data support for subsequent line loss calculation and load node type identification.

[0072] S102. Based on the impedance information corresponding to each time node in adjacent time periods, determine the connection weight information corresponding to adjacent time periods; wherein, the connection weight information represents the possibility of connection between time nodes in adjacent time periods.

[0073] Among them, the connection weight information corresponding to adjacent time points can refer to the connection weight information between two adjacent time point nodes. The connection weight information can be used to characterize the possibility of connection between time point nodes in adjacent time points.

[0074] In one possible implementation, the connection weight information corresponding to adjacent time points is determined based on the real part of the impedance information corresponding to each time point in adjacent time points.

[0075] For example, the real parts of the impedance information corresponding to each node in adjacent time intervals are 20 ohms (Ω) and 25 ohms (Ω), respectively, and the connection weight information corresponding to adjacent time intervals can be calculated.

[0076] In one alternative implementation, step S102 may include:

[0077] Based on the impedance information of the load node at each adjacent time point, the impedance amplitude of the load node at adjacent time points is determined; where the impedance amplitude represents the magnitude of the change in impedance information. Based on the impedance amplitude of the load node at adjacent time points, the connection relationship weight information at adjacent time points is determined; where the connection relationship weight information is represented as the reciprocal of the impedance amplitude.

[0078] Among them, the impedance amplitude can characterize the magnitude of the change in impedance information. For example, if the real part of the impedance information corresponding to each node in adjacent time moments is 20 ohms (Ω) and 25 ohms (Ω) respectively, then the magnitude of the change in the real part of the impedance information corresponding to the load node in adjacent time moments can be determined to be 5 ohms (Ω), that is, the impedance amplitude corresponding to the load node in adjacent time moments.

[0079] Furthermore, the connection relationship weight information corresponding to adjacent time points can be determined based on the impedance amplitude of the load nodes at adjacent time points.

[0080] It can be understood that the connection weight information can be represented as the reciprocal of the impedance amplitude. For example, if the impedance amplitude of the load node at adjacent times is 5 ohms (Ω), then the connection weight information at adjacent times can be 1 / 5.

[0081] The advantage of this setting is that it dynamically reflects the connection strength between nodes at adjacent times based on the magnitude of changes in impedance information, providing a more accurate weighting basis for determining the type of subsequent load nodes.

[0082] S103. Based on the voltage and power information of the load node at each time point within a preset time period, and the connection weight information corresponding to each adjacent time point, determine the target parameter information of the node at the next time point; wherein, the target parameter information includes the voltage and power information of the node at the next time point.

[0083] It is understandable that, based on the voltage and power information of the load node at each time point within a preset time period, as well as the connection weight information corresponding to each adjacent time point, the target parameter information of the node at the next time point after the preset time period can be determined. The target parameter information may include the voltage and power information of the node at the next time point.

[0084] For example, the target parameter information can also be understood as the feature information of the next time node, and the feature information represents voltage information and power information.

[0085] In one possible implementation, based on the voltage and power information of the load node at each time point within a preset time period, as well as the connection weight information corresponding to each adjacent time point, an adjacency matrix of a graph neural network can be constructed. This allows the target parameter information of the next time point after the preset time period to be determined based on the target adjacency matrix of the load node.

[0086] Specifically, for a given load node, methods for determining its target adjacency matrix may include:

[0087] The voltage and power information of the load node at each time point within a preset time period in the time series are obtained as the initial features of each time point in the adjacency matrix.

[0088] The connection weight information corresponding to each adjacent time point is used as the connection weight between time nodes in the adjacency matrix;

[0089] Based on the initial features of each time node and the connection weights between time nodes, an initial adjacency matrix is ​​constructed.

[0090] The initial adjacency matrix is ​​symmetrically normalized to obtain the symmetrically normalized initial adjacency matrix.

[0091] The initial adjacency matrix after symmetric normalization is weighted and aggregated to obtain the target adjacency matrix;

[0092] Based on the target adjacency matrix, determine the target parameter information of the node at the next time step.

[0093] Among them, symmetric normalization can be used to eliminate the impact of differences in the degree of time nodes on information propagation, so that the influence of each time node's neighboring time nodes on the time node is more balanced.

[0094] The steps of symmetric normalization may include: determining the degree matrix of the time node; determining the inverse square root of the degree matrix of the time node based on the degree matrix of the time node; multiplying the initial adjacency matrix with the inverse square root of the degree matrix to obtain the symmetric normalized initial adjacency matrix.

[0095] For example, the degree matrix of each time node can be represented by D, and the diagonal elements of the degree matrix are... It can represent the degree of the node at time i. satisfy ,in, This represents the connection relationship between the i-th time node and the j-th time node. A value of 1 indicates that there is an edge connecting the i-th time node and the j-th time node. A value of 0 indicates that there is no edge connection between the i-th time node and the j-th time node. The connection weight represents the connection strength between the i-th time node and the j-th time node.

[0096] For example, the initial matrix is ​​denoted by A, and the symmetric normalized initial adjacency matrix is ​​denoted by . If the expression is true, then the following conditions are met:

[0097] ;

[0098] in, This represents the inverse square root of the degree matrix.

[0099] Weighted aggregation processing can be used to aggregate information from neighboring time nodes of a current time node, thereby updating the feature representation of the current time node.

[0100] The weighted aggregation process may include: determining the information aggregation of neighboring nodes based on the initial features of each time node and the initial adjacency matrix after symmetric normalization; determining the linear transformation result of the load node based on the information aggregation of the neighboring nodes and the preset learnable weight matrix; obtaining the updated features of each time node, i.e., the target adjacency matrix, based on the linear transformation result and the nonlinear activation function; and using the features of the last time node in the target adjacency matrix as the target parameter information of the next time node; wherein, the target parameter information includes the voltage information and power information of the next time node.

[0101] For example, the initial features of each time node can be used This means that the initial adjacency matrix after symmetric normalization can be expressed as follows: This means that multiplying the initial features of each node at each time step by the symmetrically normalized initial adjacency matrix yields the information aggregation of the neighborhood nodes. This information aggregation can be used... express;

[0102] The pre-defined learnable weight matrix has the same dimension as the initial adjacency matrix. The pre-defined learnable weight matrix can be used... This means that by aggregating the information of neighboring nodes and multiplying it by a pre-defined learnable weight matrix, the linear transformation result of the load node can be obtained. The linear transformation result of the load node can be used... express;

[0103] By processing the linear transformation results using a nonlinear activation function, the updated features of each time node can be obtained, i.e., the target adjacency matrix. The features of the last time node in the target adjacency matrix are used as the target parameter information of the next time node. The target parameter information includes the voltage and power information of the next time node.

[0104] The target parameter information of the next time step node can be represented as: Where l represents the number of feature updates, This represents a non-linear activation function, such as the ReLU activation function. This represents the learnable weight matrix after processing with a non-linear activation function.

[0105] The advantage of this setup is that by constructing the adjacency matrix of a graph neural network, the target parameter information of the next node can be determined based on the voltage and power information of the load node at each time point within a preset time period, as well as the connection weight information corresponding to each adjacent time point. This provides a more accurate feature basis for determining the type of the subsequent load node.

[0106] In one alternative implementation, step S103 may include:

[0107] Obtain the impedance sensitivity factor at each time node within a preset time period; where the impedance sensitivity factor characterizes the degree of impedance influence; based on the impedance sensitivity factor at each time node within the preset time period, the voltage and power information of the load node at each time node, and the connection weight information corresponding to each adjacent time node, determine the target parameter information of the next time node.

[0108] It is understandable that the connection weight information corresponding to each adjacent time point is obtained from the impedance information. Therefore, it is necessary to introduce an impedance sensitivity factor to accurately reflect the impact of impedance changes on the connection strength between time points.

[0109] Furthermore, by combining the impedance sensitivity factor at each time node within the preset time period, the voltage and power information of the load node at each time node, and the connection weight information corresponding to each adjacent time node, the target parameter information of the next time node can be determined.

[0110] In one alternative implementation, the impedance sensitivity factor is characterized as:

[0111] ;

[0112] in, Indicates the impedance sensitivity factor. Indicates time, This represents the preset initial impedance sensitivity factor, where α is a preset parameter.

[0113] For example, the preset initial impedance sensitivity factor can be 0.1, and the preset parameter α can be 0.001.

[0114] It is understandable that at the first time point within the preset time period, the time... The impedance sensitivity factor can be 0, in which case it is zero. Equal to the preset initial impedance sensitivity factor At the second time node within the preset time period, time... The impedance sensitivity factor can be 1, in which case it can be 1. equal Similarly, at the nth time node within the preset time period, the time... It can be n-1, in which case the impedance sensitivity factor equal .

[0115] The advantage of this setting is that by linearly and dynamically adjusting the impedance sensitivity factor, the target parameter information of the next time node can be determined based on the impedance sensitivity factor at each time node within a preset time period, the voltage and power information of the load node at each time node, and the connection weight information corresponding to each adjacent time node, thereby improving the accuracy of determining the target parameter information of the next time node.

[0116] In one optional implementation, the target parameter information for the next time node is determined based on the impedance sensitivity factor at each time node within a preset time period, the voltage and power information of the load node at each time node, and the connection weight information corresponding to each adjacent time node. This may include:

[0117] Based on the connection weight information corresponding to adjacent time points, the connection relationship information corresponding to adjacent time points is determined; wherein, the connection relationship information indicates whether there is an edge connection between time nodes in adjacent time points; based on the connection relationship information corresponding to adjacent time points, the impedance sensitivity factor of each time node within a preset time period, and the voltage and power information of the load node at each time node, the target parameter information of the next time node is determined.

[0118] It is understandable that by considering whether there are edge connections between time nodes in adjacent time periods, the dynamic electrical relationships between time nodes can be captured more accurately, thereby improving the accuracy of determining the target parameter information of the next time node and thus improving the reliability of determining the type of load node in the distribution network.

[0119] For example, if the connection weight information corresponding to adjacent time points is 0, it means that there is no edge connection in the connection relationship information corresponding to adjacent time points; if the connection weight information corresponding to adjacent time points is not 0, it means that there is an edge connection in the connection relationship information corresponding to adjacent time points.

[0120] Furthermore, after determining the connection relationship information corresponding to adjacent time points, the target parameter information of the next time point node can be determined based on the connection relationship information corresponding to adjacent time points, the impedance sensitivity factor of each time point node within the preset time period, and the voltage and power information of the load node at each time point node.

[0121] In one optional implementation, the target parameter information for the next time node is determined based on the connection relationship information corresponding to adjacent time points, the impedance sensitivity factor at each time node within a preset time period, and the voltage and power information of the load node at each time node. This may include:

[0122] If, based on the connection relationship information corresponding to adjacent time points, it is determined that there is an edge connection between time points in adjacent time points, then the connection coefficient corresponding to adjacent time points is determined based on the impedance amplitude corresponding to adjacent time points and the impedance sensitivity factor of the time point in the next time point in adjacent time points; where the connection coefficient represents the degree of correlation between two time point nodes in adjacent time points; based on the connection coefficient corresponding to each adjacent time point, the voltage information and power information of the load node in each time point node, the target parameter information of the next time point node is determined.

[0123] It is understandable that if, based on the connection information corresponding to adjacent time points, it is determined that there are edge connections between time points in adjacent time points, then it can be understood that the j-th time point node is a neighbor node of the i-th time point node, that is, the connection strength between the i-th time point node and the j-th time point node is not 0, which can be expressed as: ,in, This represents all neighboring nodes of the node at time i.

[0124] The connection coefficients corresponding to adjacent times can be used For example, if there is no edge connection between the i-th time node and the j-th time node, then It can be 0;

[0125] If there is an edge connection between the i-th time node and the j-th time node, then the connection coefficient between the adjacent time nodes is determined based on the impedance magnitudes corresponding to the adjacent time nodes and the impedance sensitivity factor of the time node at the next time node in the adjacent time nodes. Specifically, It can be represented as Where t is the time corresponding to the i-th time node. This represents the impedance sensitivity factor corresponding to the i-th time node. This represents the impedance magnitude of the load node between the time corresponding to node i at time i and the time corresponding to node j at time j, where the time of node i at time i is after the time of node j at time j.

[0126] In one optional implementation, the target parameter information for the next time node is determined based on the connection coefficients corresponding to each adjacent time point, the voltage information and power information of the load node at each time point, which may include:

[0127] The voltage and power information of the load node at each time point within a preset time period in the time series are obtained as the initial features of each time point in the adjacency matrix.

[0128] The connection weight information corresponding to each adjacent time point is used as the connection weight between time nodes in the adjacency matrix;

[0129] Based on the initial features of each time node and the connection weights between time nodes, an initial adjacency matrix is ​​constructed.

[0130] The initial adjacency matrix is ​​symmetrically normalized to obtain the symmetrically normalized initial adjacency matrix.

[0131] The initial adjacency matrix after symmetric normalization is weighted and aggregated to obtain the target adjacency matrix;

[0132] Based on the target adjacency matrix, determine the target parameter information of the node at the next time step.

[0133] The target parameter information of the next time step node can satisfy:

[0134] ;

[0135] The last time point within the preset time period is the i-th time point. express Activation function This represents the target parameter information of the node at the next time point after a preset time period, where l represents the number of iterations in the weighted aggregation process. Indicates use The learnable weight matrix after activation function processing. This represents the feature information of the i-th time node during the l-th iteration of the weighted aggregation process. Let represent the feature information of the j-th time node at the l-th iteration in the weighted aggregation process. The feature information includes voltage and power information. The degree matrix of each time node can be represented by D, where the diagonal elements of the degree matrix are... The diagonal elements of the degree matrix represent the degree of the node at time i. This represents the degree of the node at time j. This represents the connection coefficients between the i-th time node and the j-th time node.

[0136] In one possible implementation, if the target parameter information does not satisfy the power balance law, gradient correction is performed to obtain new target parameter information until the new target parameter information satisfies the power balance law.

[0137] The gradient correction process may include, but is not limited to, using a pre-defined Adagrad (adaptive gradient) optimizer to adjust the target parameter information in order to obtain new target parameter information.

[0138] The advantage of this setting is that by comprehensively considering the connection coefficients corresponding to each adjacent time point, the voltage information and power information of the load node at each time point, the target parameter information of the next time point node can be determined, which improves the accuracy of determining the target parameter information of the next time point node, and thus improves the reliability of determining the type of load node in the distribution network.

[0139] S104. Determine the type of load node based on the target parameter information.

[0140] The types of load nodes can include measurement nodes, electrical quantity nodes, and capacitor nodes.

[0141] Among them, the current and / or voltage information of the measurement node can be directly measured by the preset real-time measurement device; the current and voltage information of the power node cannot be directly measured by the preset real-time measurement device, but the active power of the measurement node can be measured by the preset real-time measurement device; the current and voltage information of the capacitor node cannot be directly measured by the preset real-time measurement device, but the reactive power of the measurement node can be measured by the preset real-time measurement device.

[0142] It is understandable that the target parameter information includes voltage and power information, which can be used to determine the type of load node.

[0143] In one alternative implementation, step S104 may include:

[0144] Based on the target parameter information, determine the probability value of the load node under each type; based on the probability value under each type, determine the type of the load node.

[0145] In one alternative implementation, the probability value is characterized as:

[0146] ;

[0147] in, Let represent the probability that the load node will be of type k at the next time step, and y represent the probability that the load node will be of type k at the next time step. This represents the frequency matrix of the k-th type for each time node within a preset time period for the load node. This represents the transpose of the frequency matrix of the k-th type for each time node of the load node within a preset time period. This represents the frequency matrix of the c-th type for each time node within a preset time period, representing the load node. This represents the transpose of the frequency matrix of type c for each time node within a preset time period for the load node. This indicates the target parameter information.

[0148] in, The target parameter information includes three elements: voltage, active power, and reactive power.

[0149] For example, there are k types of load nodes, where k is 3, that is, the first type can be a measurement node, the second type can be an electrical energy node, and the third type can be a capacitor node;

[0150] The load node includes 5 time nodes within a preset time period. The frequency matrix of the load node for the first type under each time node within the preset time period can be

[00011] . It can be seen that, under the 5 time nodes, the 4th and 5th time nodes correspond to the first type. The frequency matrix of the load node for the second type under each time node within the preset time period can be

[01100] . It can be seen that, under the 5 time nodes, the 2nd and 3rd time nodes correspond to the second type. The frequency matrix of the load node for the third type under each time node within the preset time period can be

[10000] . It can be seen that, under the 5 time nodes, the 1st time node corresponds to the first type.

[0151] For example, Substituting [0, 5kW, 0] into the above expression, we can predict the probability that the load node will be of the kth type at the next time step. For example, P(y=1) = 0.1, P(y=2) = 0.85, P(y=3) = 0.05.

[0152] Choose the type with the highest probability value as the load node type, that is, choose the second type (electricity node) as the load node type.

[0153] In one possible implementation, the frequency of the k-th type under each time node within the preset time period is obtained manually and uploaded in advance. In the future time period after the preset time period, the type of the load node under the future time node does not need to be manually determined and uploaded in advance, but can be calculated by the above formula.

[0154] The advantage of this setting is that by combining the frequency of load nodes of each type at each time point within a preset time period with target parameter information, the type of load node can be determined, thereby improving the reliability of determining the type of load nodes in the distribution network.

[0155] In an optional implementation, the method for determining the type of load node in a distribution network provided in this application may further include step S105:

[0156] Based on a preset association relationship, a line loss calculation strategy corresponding to the type of load node is determined; wherein, the preset association relationship represents the relationship between the type of load node and the line loss calculation strategy, and the line loss calculation strategy is used to calculate the line loss result of the load node.

[0157] Among them, line loss can refer to synchronous line loss, and the line loss result characterizes the energy loss of load nodes during the power transmission process within a certain period of time.

[0158] For example, if the load node is a measurement node, the line loss is calculated directly based on the current and voltage information obtained from the real-time measurement device; if the load node is an energy node, the line loss is calculated based on the active power data in the target parameter information; if the load node is a capacitor node, the line loss is calculated based on the reactive power data in the target parameter information.

[0159] It should be noted that there are other implementation logics for the line loss calculation strategy, which will not be elaborated here.

[0160] The method for determining the type of load nodes in a distribution network provided in this application uses the voltage and power information of the load node at each time point within a preset time period as the parameter information at that time point, and uses the connection weight information corresponding to each adjacent time point as the probability of connection between time points in adjacent time points, to determine the target parameter information of the next time point node. This target parameter information can then be used as the basis for determining the type of load node. The method for determining the type of load nodes in a distribution network provided in this application improves the reliability of determining the type of load nodes in a distribution network.

[0161] Figure 2 A flowchart illustrating a method for determining the type of load nodes in a distribution network, as provided in this application. Figure 2 The execution subject of this method can be a server, host, or other device, such as... Figure 2 As shown, the method may include:

[0162] S201. Obtain the voltage and power information of the load node at each time point within a preset time period in the time series, and use it as the initial feature of each time point in the adjacency matrix.

[0163] S202. Based on the impedance information corresponding to each time node in adjacent time periods, determine the connection weight information corresponding to adjacent time periods, and use the connection weight information corresponding to each adjacent time period as the connection weight between time nodes in the adjacency matrix; wherein, the connection weight information represents the possibility of connection between time nodes in adjacent time periods.

[0164] S203. Construct an initial adjacency matrix based on the initial characteristics of each time node and the connection weights between time nodes.

[0165] S204. Perform symmetric normalization on the initial adjacency matrix to obtain the symmetric normalized initial adjacency matrix.

[0166] S205. Perform weighted aggregation on the symmetrically normalized initial adjacency matrix to obtain the target adjacency matrix.

[0167] S206. Based on the target adjacency matrix, determine the target parameter information of the node at the next time step; wherein, the target parameter information includes the voltage information and power information of the node at the next time step.

[0168] Specifically, the target parameter information of the next time step node can satisfy:

[0169] ;

[0170] The last time point within the preset time period is the i-th time point. express Activation function This represents the target parameter information of the node at the next time point after a preset time period, where l represents the number of iterations in the weighted aggregation process. Indicates use The learnable weight matrix after activation function processing. This represents the feature information of the i-th time node during the l-th iteration of the weighted aggregation process. Let represent the feature information of the j-th time node at the l-th iteration in the weighted aggregation process. The feature information includes voltage and power information. The degree matrix of each time node can be represented by D, where the diagonal elements of the degree matrix are... The diagonal elements of the degree matrix represent the degree of the node at time i. This represents the degree of the node at time j. This represents the connection coefficients between the i-th time node and the j-th time node.

[0171] S207. Determine the type of load node based on the target parameter information.

[0172] The method for determining the type of load nodes in a distribution network provided in this application uses the voltage and power information of the load node at each time point within a preset time period as the initial features of each time point in the adjacency matrix to determine the target parameter information of the node at the next time point. This target parameter information can then be used as the basis for determining the type of the load node. The method for determining the type of load nodes in a distribution network provided in this application improves the reliability of determining the type of load nodes in a distribution network.

[0173] Figure 3 A schematic diagram of the structure of a device for determining the type of load node in a distribution network provided in this application. Figure 1 ,like Figure 3 As shown, the device 30 for determining the type of load node in the distribution network includes: an acquisition unit 301, a first determination unit 302, a second determination unit 303, and a third determination unit 304.

[0174] The acquisition unit 301 is used to acquire electrical parameter information of load nodes in the distribution network at each time node within a preset time period; wherein, the electrical parameter information includes at least one of voltage information, power information, and impedance information;

[0175] The first determining unit 302 is used to determine the connection weight information corresponding to adjacent time points based on the impedance information corresponding to each time point in adjacent time points; wherein, the connection weight information represents the possibility of connection between time points in adjacent time points.

[0176] The second determining unit 303 is used to determine the target parameter information of the next time node based on the voltage and power information of the load node at each time node within a preset time period, and the connection weight information corresponding to each adjacent time node; wherein, the target parameter information includes the voltage and power information of the next time node.

[0177] The third determining unit 304 is used to determine the type of load node based on the target parameter information.

[0178] Figure 4 A schematic diagram of the structure of a device for determining the type of load node in a distribution network provided in this application. Figure 2 ,like Figure 4 As shown, the device 40 for determining the type of load node in the distribution network includes: an acquisition unit 401, a first determination unit 402, a second determination unit 403, and a third determination unit 404. The first determination unit 402 further includes a first processing module 4021 and a second processing module 4022, and the second determination unit 403 further includes a third processing module 4031 and a fourth processing module 4032.

[0179] The first processing module 4021 is used to determine the impedance amplitude of the load node at adjacent time points based on the impedance information of the load node at each time point in adjacent time points; wherein, the impedance amplitude represents the magnitude of the change in impedance information.

[0180] The second processing module 4022 is used to determine the connection weight information corresponding to adjacent time points based on the impedance amplitude of the load node at adjacent time points; wherein, the connection weight information is represented as the reciprocal of the impedance amplitude.

[0181] The third processing module 4031 is used to obtain the impedance sensitivity factor at each time node within a preset time period; wherein, the impedance sensitivity factor characterizes the degree to which impedance is affected.

[0182] The fourth processing module 4032 is used to determine the target parameter information of the next time node based on the impedance sensitivity factor at each time node within a preset time period, the voltage and power information of the load node at each time node, and the connection weight information corresponding to each adjacent time node.

[0183] In an optional example, the impedance sensitivity factor is characterized as:

[0184] ;

[0185] in, Indicates the impedance sensitivity factor. Indicates time, This represents the preset initial impedance sensitivity factor. These are preset parameters.

[0186] In an optional example, the fourth processing module 4032 may also include a first submodule and a second submodule;

[0187] The first submodule is used to determine the connection relationship information of adjacent time points based on the connection weight information of adjacent time points; wherein, the connection relationship information indicates whether there is an edge connection between the time nodes in adjacent time points.

[0188] The second submodule is used to determine the target parameter information of the next time node based on the connection relationship information corresponding to adjacent time points, the impedance sensitivity factor of each time node within a preset time period, and the voltage and power information of the load node at each time node.

[0189] In an optional example, the second submodule is further specifically used to determine the connection coefficient between adjacent time nodes if it is determined that there is an edge connection between the time nodes in adjacent time nodes based on the connection relationship information corresponding to adjacent time nodes; wherein, the connection coefficient characterizes the degree of correlation between two time nodes in adjacent time nodes.

[0190] Based on the connection coefficients corresponding to each adjacent time point, and the voltage and power information of the load node at each time point, the target parameter information of the node at the next time point is determined.

[0191] The third determining unit 404 is also used to determine the probability value of the load node under each type based on the target parameter information;

[0192] The type of load node is determined based on the probability value of each type.

[0193] In an optional example, the probability value is represented as:

[0194] ;

[0195] in, Let represent the probability that the load node will be of type k at the next time step, and y represent the probability that the load node will be of type k at the next time step. This represents the frequency matrix of the k-th type for each time node within a preset time period for the load node. This represents the transpose of the frequency matrix of the k-th type for each time node of the load node within a preset time period. This represents the frequency matrix of the c-th type for each time node within a preset time period, representing the load node. This represents the transpose of the frequency matrix of type c for each time node within a preset time period for the load node. This indicates the target parameter information.

[0196] In an optional example, the device 40 for determining the type of load nodes in the distribution network further includes a fourth determining unit;

[0197] The fourth determining unit is used to determine the line loss calculation strategy corresponding to the type of load node according to a preset association relationship; wherein, the preset association relationship represents the association relationship between the type of load node and the line loss calculation strategy, and the line loss calculation strategy is used to calculate the line loss result of the load node.

[0198] Figure 5 A schematic diagram of the structure of the electronic device provided in this application, such as... Figure 5 As shown, the electronic device 50 provided in this embodiment includes at least one processor 501 and a memory 502. Optionally, the device 50 further includes a communication component 503. The processor 501, memory 502, and communication component 503 are connected via a bus 504.

[0199] In one possible implementation, the communication component 503 can achieve communication and data transmission between components via a 230M private network and / or a GPRS private network.

[0200] In a specific implementation, at least one processor 501 executes computer execution instructions stored in memory 502, causing at least one processor 501 to perform the above-described method.

[0201] The specific implementation process of processor 501 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0202] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0203] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0204] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0205] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0206] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0207] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0208] It should be further noted that although the steps in the flowchart are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0209] It should be understood that the above-described device embodiments are merely illustrative, and the device of this application can also be implemented in other ways. For example, the division of units / modules in the above embodiments is only a logical functional division, and there may be other division methods in actual implementation. For example, multiple units, modules, or components may be combined, or integrated into another system, or some features may be ignored or not executed.

[0210] Furthermore, unless otherwise specified, the functional units / modules in the various embodiments of this application can be integrated into one unit / module, or each unit / module can exist physically separately, or two or more units / modules can be integrated together. The integrated units / modules described above can be implemented in hardware or as software program modules.

[0211] When integrated units / modules are implemented in hardware, the hardware can be digital circuits, analog circuits, etc. The physical implementation of the hardware structure includes, but is not limited to, transistors, memristors, etc. Unless otherwise specified, the processor can be any suitable hardware processor, such as a CPU, GPU, FPGA, DSP, and ASIC, etc. Unless otherwise specified, the storage unit can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc.

[0212] If the integrated unit / module is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0213] In the above embodiments, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments. The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as these combinations of technical features do not contradict each other, they should be considered within the scope of this specification.

[0214] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0215] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for determining the type of load nodes in a distribution network, characterized in that, include: Obtain electrical parameter information of load nodes in the distribution network at each time point within a preset time period; wherein, the electrical parameter information includes at least one of voltage information, power information, and impedance information; Based on the impedance information corresponding to each time node in adjacent time periods, the connection weight information corresponding to the adjacent time periods is determined; wherein, the connection weight information represents the probability of connection between time nodes in adjacent time periods. Based on the voltage and power information of the load node at each time point within a preset time period, and the connection weight information corresponding to each adjacent time point, the target parameter information of the node at the next time point is determined; wherein, the target parameter information includes the voltage and power information of the node at the next time point. The type of the load node is determined based on the target parameter information.

2. The method according to claim 1, characterized in that, Based on the impedance information corresponding to each node in adjacent time intervals, the connection weight information corresponding to the adjacent time intervals is determined, including: Based on the impedance information of the load node at each adjacent time point, the impedance amplitude of the load node at the adjacent time point is determined; wherein, the impedance amplitude characterizes the magnitude of the change in impedance information; Based on the impedance amplitude of the load node at the adjacent time, the connection weight information corresponding to the adjacent time is determined; wherein, the connection weight information is represented as the reciprocal of the impedance amplitude.

3. The method according to claim 2, characterized in that, Based on the voltage and power information of the load node at each time point within a preset time period, and the connection weight information corresponding to each adjacent time point, the target parameter information of the node at the next time point is determined, including: Obtain the impedance sensitivity factor at each time point within the preset time period; wherein, the impedance sensitivity factor characterizes the degree to which impedance is affected; Based on the impedance sensitivity factor at each time node within the preset time period, the voltage and power information of the load node at each time node, and the connection weight information corresponding to each adjacent time node, the target parameter information of the next time node is determined.

4. The method according to claim 3, characterized in that, The impedance sensitivity factor is characterized as follows: ； Among them, the The impedance sensitivity factor represents the impedance sensitivity factor. Indicates the time, the This represents the preset initial impedance sensitivity factor, where α is a preset parameter.

5. The method according to claim 3, characterized in that, Based on the impedance sensitivity factor at each time node within the preset time period, the voltage and power information of the load node at each time node, and the connection weight information corresponding to each adjacent time node, the target parameter information of the next time node is determined, including: Based on the connection weight information corresponding to the adjacent time points, the connection relationship information corresponding to the adjacent time points is determined; wherein, the connection relationship information indicates whether there is an edge connection between the time nodes in the adjacent time points; Based on the connection relationship information corresponding to the adjacent time points, the impedance sensitivity factor at each time point within the preset time period, and the voltage and power information of the load node at each time point, the target parameter information of the next time point node is determined.

6. The method according to claim 5, characterized in that, Based on the connection relationship information corresponding to adjacent time points, the impedance sensitivity factor at each time node within the preset time period, and the voltage and power information of the load node at each time node, the target parameter information of the next time node is determined, including: If, based on the connection relationship information corresponding to the adjacent time points, it is determined that there is an edge connection between the time nodes in the adjacent time points, then the connection coefficient corresponding to the adjacent time points is determined based on the impedance amplitude corresponding to the adjacent time points and the impedance sensitivity factor of the time node in the next time point in the adjacent time points; wherein, the connection coefficient represents the degree of correlation between the two time nodes in the adjacent time points. Based on the connection coefficients corresponding to each adjacent time point, and the voltage and power information of the load node at each time point, the target parameter information of the next time point node is determined.

7. The method according to claim 1, characterized in that, Based on the target parameter information, the type of the load node is determined, including: Based on the target parameter information, determine the probability value of the load node under each type; The type of the load node is determined based on the probability value under each type.

8. The method according to claim 7, characterized in that, The probability value is characterized as follows: ； Among them, the The y represents the probability that the load node will be of type k at the next time step, where y represents the probability that the load node will be of type k at the next time step. This indicates that the load node is a frequency matrix of type k at each time point within the preset time period. This indicates that the load node is the transpose of the frequency matrix of the k-th type at each time point within the preset time period. This indicates that the load node is a frequency matrix of type c at each time point within the preset time period. This indicates that the load node is the transpose of the frequency matrix of type c at each time point within the preset time period. This represents the target parameter information.

9. The method according to any one of claims 1-8, characterized in that, Also includes: Based on a preset association relationship, a line loss calculation strategy corresponding to the type of the load node is determined; wherein, the preset association relationship represents the relationship between the type of the load node and the line loss calculation strategy, and the line loss calculation strategy is used to calculate the line loss result of the load node.

10. A device for determining the type of load node in a distribution network, characterized in that, include: The acquisition unit is used to acquire electrical parameter information of load nodes in the distribution network at each time node within a preset time period; wherein, the electrical parameter information includes at least one of voltage information, power information, and impedance information; The first determining unit is used to determine the connection weight information corresponding to the adjacent time points based on the impedance information corresponding to each time point in the adjacent time points; wherein, the connection weight information represents the possibility of connection between time points in the adjacent time points. The second determining unit is used to determine the target parameter information of the next time node based on the voltage and power information of the load node at each time node within a preset time period, and the connection weight information corresponding to each adjacent time node; wherein, the target parameter information includes the voltage and power information of the next time node; The third determining unit is used to determine the type of the load node based on the target parameter information.

11. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-9.

13. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-9.

Images