Construction method, device and equipment of voltage segmentation and layering calculation architecture and medium

Abstract

The invention provides a construction method of a voltage segmentation and layering calculation framework. The construction method comprises the following steps: summarizing node voltage historical operation data and node active power historical operation data in a low-voltage power distribution network, and determining a daytime operation time period and a night operation time period; obtaining a daytime training data set according to the daytime operation time period, and obtaining a night training data set according to the night operation time period; according to the daytime training data set and the night training data set, constructing a base layer and a regulation and control layer of the low-voltage power distribution network in different operation periods; and acquiring basic voltages and voltage variations of the low-voltage distribution network in different time periods, and calculating actual voltages of the low-voltage distribution network in different time periods according to the basic voltages and the voltage variations. According to the technical scheme of the embodiment, the non-electrical model voltage calculation accuracy of the low-voltage active power distribution network can be improved.

Description

Technical Field

[0001] The present invention relates to the field of low-voltage distribution network computing technology, and in particular to a method, device, electronic device, and storage medium for constructing a voltage segmented and hierarchical computing architecture. Background Art

[0002] Due to complex network structures, insufficient coverage of measurement equipment, and the high cost of building accurate electrical models, low-voltage distribution networks often lack accurate topology and line parameter information. This makes traditional voltage calculation methods based on power flow calculations difficult to apply. In recent years, with the widespread deployment of smart meters and the rapid development of data-driven technologies, voltage calculation methods that do not rely on electrical models have been proposed. These methods use data-driven techniques such as least squares and machine learning to fit the mapping relationship between node power and node voltage in low-voltage distribution networks, thereby achieving voltage calculation. However, due to the mismatch between load demand and photovoltaic output in time and space, bidirectional power flow often occurs in low-voltage distribution networks, leading to safety issues such as node voltage exceeding the limit and three-phase imbalance, necessitating voltage regulation. Consequently, voltage calculation without electrical models in low-voltage active distribution networks is inaccurate even when regulated. Summary of the Invention

[0003] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a method, apparatus, device, and medium for constructing a segmented and hierarchical voltage calculation architecture, which can improve the accuracy of voltage calculation without an electrical model in a low-voltage active distribution network.

[0004] In a first aspect, an embodiment of the present invention provides a method for constructing a voltage segmented hierarchical computing architecture, comprising:

[0005] Summarize the historical operating data of node voltage and node active power in the low-voltage distribution network;

[0006] Determining a daytime operation period and a nighttime operation period according to the node voltage historical operation data and the node active power historical operation data;

[0007] Obtaining a daytime training data set according to the daytime operation period, and obtaining a nighttime training data set according to the nighttime operation period;

[0008] According to the daytime training data set, constructing a daytime basic layer and a daytime regulation layer for the daytime operation period, wherein the daytime basic layer is constructed based on the three-phase active net load matrix, the three-phase reactive net load matrix and the input-output mapping relationship of the low-voltage distribution network;

[0009] Constructing a nighttime basic layer and a nighttime control layer for the nighttime operation period according to the nighttime training data set, wherein the nighttime basic layer is constructed based on a three-phase active net load matrix, a three-phase reactive net load matrix, and an input-output mapping relationship of the low-voltage distribution network;

[0010] Obtaining a daytime base voltage and a daytime voltage change, and calculating the daytime actual voltage of the low-voltage distribution network according to the daytime base voltage and the daytime voltage change through the daytime base layer and the daytime regulation layer;

[0011] A nighttime basic voltage and a nighttime voltage change are obtained, and the nighttime actual voltage of the low-voltage distribution network is calculated according to the nighttime basic voltage and the nighttime voltage change through the nighttime basic layer and the nighttime regulation layer.

[0012] In some embodiments of the present invention, determining the daytime operation period and the nighttime operation period of the low-voltage distribution network includes:

[0013] Obtaining the start and stop output times of preset photovoltaic nodes on preset days of the low-voltage distribution network, as well as the total number of working days and the total number of photovoltaic nodes of the low-voltage distribution network;

[0014] Calculate the daytime starting working time of the low-voltage distribution network according to the processing start time, the total number of working days and the total number of photovoltaic nodes;

[0015] Calculate the daytime stop working time of the low-voltage distribution network according to the processing start time, the total number of working days and the total number of photovoltaic nodes;

[0016] The nighttime working time of the low-voltage distribution network is determined according to the daytime working start time and the daytime working stop time.

[0017] In some embodiments of the present invention, the calculating the daytime actual voltage of the low-voltage distribution network according to the daytime basic voltage and the daytime voltage change includes:

[0018] Obtaining a three-phase voltage matrix of each node when the low-voltage distribution network is operating normally according to the three-phase active net load matrix, the three-phase reactive net load matrix and the input-output mapping relationship;

[0019] The daytime basic voltage of the low-voltage distribution network is obtained according to the three-phase voltage matrix, and the daytime regulation layer obtains the daytime voltage change of the low-voltage distribution network based on the three-phase active net load matrix and reactive load matrix and the input-output mapping relationship.

[0020] In some embodiments of the present invention, the calculating the nighttime actual voltage of the low-voltage distribution network according to the nighttime basic voltage and the nighttime voltage change includes:

[0021] Obtaining a three-phase voltage matrix of each node of the low-voltage distribution network during normal operation at night according to the three-phase active net load matrix, the three-phase reactive net load matrix and the input-output mapping relationship;

[0022] The nighttime basic voltage of the low-voltage distribution network is obtained according to the three-phase voltage matrix, and the nighttime regulation layer obtains the nighttime voltage change of the low-voltage distribution network based on the three-phase active net load matrix and reactive load matrix of the low-voltage distribution network and the input-output mapping relationship.

[0023] In some embodiments of the present invention, constructing the basic layer and the control layer of the low-voltage distribution network in different operating periods includes:

[0024] Constructing a voltage calculation model for the daytime base layer according to the total number of photovoltaic nodes, the input-output mapping relationship, the three-phase active net load matrix, and the reactive load matrix;

[0025] Calculating a reference operating voltage of the daytime base layer at the current daytime voltage calculation time, wherein the reference operating voltage represents a system state when no control measures are introduced into the daytime base layer;

[0026] The basic operating state of the control equipment acting on the low-voltage distribution network in the daytime control layer is calculated, and the reference operating voltage and the voltage change are superimposed to obtain the actual daytime voltage.

[0027] In some embodiments of the present invention, obtaining a daytime training dataset according to the daytime operation period and obtaining a nighttime training dataset according to the nighttime operation period includes:

[0028] The training data of the control layer is obtained by subtracting the base layer data from different time periods;

[0029] Determining the time delay required for training data of the daytime control layer and the nighttime control layer;

[0030] Performing time difference processing on the training data of the daytime base layer and the nighttime base layer, subtracting the data of each time point from the data of the time delay amount to obtain difference data, wherein the difference data includes the three-phase active static load change data, the reactive static load change data, and the three-phase voltage change data;

[0031] The differential data is used as the daytime training data set and the nighttime training data set.

[0032] In some embodiments of the present invention, after constructing the voltage calculation model of the base layer, the method further includes:

[0033] Obtaining a three-phase voltage change matrix, a three-phase active difference matrix, a three-phase reactive difference matrix, a three-phase energy storage device active output matrix, and a three-phase photovoltaic inverter reactive output matrix of each node in the low-voltage distribution network;

[0034] Acquiring non-voltage regulation data and voltage regulation data in the low-voltage distribution network;

[0035] Constructing a three-phase voltage change matrix of each node in the control layer according to the no-voltage control data, the voltage control data, the three-phase voltage change matrix, the three-phase active difference matrix, the three-phase reactive difference matrix, the three-phase energy storage device active output matrix and the three-phase photovoltaic inverter reactive output matrix;

[0036] A segmented and hierarchical calculation architecture is constructed based on the three-phase active net load matrix, the reactive load matrix, the three-phase active difference matrix, and the three-phase reactive difference matrix.

[0037] In a second aspect, an embodiment of the present invention provides a voltage calculation device without an electrical model, comprising at least one control processor and a memory for communicating with the at least one control processor; the memory stores instructions that can be executed by the at least one control processor, and the instructions are executed by the at least one control processor so that the at least one control processor can execute the method for constructing a voltage segmented hierarchical calculation architecture as described in the first aspect above.

[0038] In a third aspect, an embodiment of the present invention provides an electronic device comprising the voltage calculation device without an electrical model as described in the second aspect above.

[0039] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are used to execute the method for constructing a voltage segmented hierarchical computing architecture as described in the first aspect above.

[0040] The method for constructing a voltage segmented hierarchical computing architecture according to an embodiment of the present invention has at least the following beneficial effects:

[0041] Summarize the node voltage historical operation data and node active power historical operation data in the low-voltage distribution network; determine the daytime operation period and the nighttime operation period based on the node voltage historical operation data and the node active power historical operation data; obtain the daytime training data set according to the daytime operation period, and obtain the nighttime training data set according to the nighttime operation period; construct the daytime basic layer and the daytime control layer of the daytime operation period based on the daytime training data set, and the daytime basic layer is constructed based on the three-phase active net load matrix, the three-phase reactive net load matrix and the input-output mapping relationship of the low-voltage distribution network; according to the nighttime training data The system constructs a nighttime base layer and a nighttime control layer for the nighttime operation period. The nighttime base layer is constructed based on the three-phase active net load matrix, the three-phase reactive net load matrix, and the input-output mapping relationship of the low-voltage distribution network. The system obtains the daytime base voltage and the daytime voltage change, and calculates the daytime actual voltage of the low-voltage distribution network based on the daytime base voltage and the daytime voltage change using the daytime base layer and the daytime control layer. The system also obtains the nighttime base voltage and the nighttime voltage change, and calculates the nighttime actual voltage of the low-voltage distribution network based on the nighttime base voltage and the nighttime voltage change using the nighttime base layer and the nighttime control layer. The technical solution of this embodiment can improve the accuracy of voltage calculation without an electrical model for low-voltage active distribution networks. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 This is a flow chart of a method for constructing a voltage segmented hierarchical computing architecture provided by one embodiment of the present invention;

[0043] Figure 2 This is a flow chart for determining the daytime operation period and the nighttime operation period of a low-voltage distribution network provided by an embodiment of the present invention;

[0044] Figure 3 This is a flow chart of calculating the daytime actual voltage of a low-voltage distribution network based on the daytime basic voltage and the daytime voltage change, provided by one embodiment of the present invention;

[0045] Figure 4 A flowchart of calculating the actual nighttime voltage of a low-voltage distribution network based on the nighttime basic voltage and the nighttime voltage change is provided in one embodiment of the present invention;

[0046] Figure 5 This is a flowchart of constructing a basic layer and a control layer for different operating periods of a low-voltage distribution network provided by an embodiment of the present invention;

[0047] Figure 6 This is a flow chart of calculating the daytime voltage change of a low-voltage distribution network under the action of a control device provided by an embodiment of the present invention;

[0048] Figure 7 This is a flow chart after constructing a voltage calculation model for a base layer, provided by one embodiment of the present invention;

[0049] Figure 8 It is a structural diagram of a voltage calculation device without an electrical model provided by another embodiment of the present invention. DETAILED DESCRIPTION

[0050] The following describes embodiments of the present invention in detail. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended only to explain the present invention and are not to be construed as limiting the present invention.

[0051] In the description of the present invention, it should be understood that descriptions involving orientations, such as up, down, front, back, left, right, etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, they cannot be understood as limitations on the present invention.

[0052] In the description of the present invention, "several" means one or more, "many" means more than two, "greater than," "less than," and "exceed" are understood to exclude the number itself, while "above," "below," and "within" are understood to include the number itself. The use of "first" and "second" in the description is solely for the purpose of distinguishing technical features and should not be construed as indicating or implying relative importance, implicitly specifying the number of the indicated technical features, or implicitly specifying the order of the indicated technical features.

[0053] In the description of the present invention, unless otherwise clearly defined, terms such as setting, installing, and connecting should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in the present invention based on the specific content of the technical solution.

[0054] An embodiment of the present invention provides a method for constructing a segmented and hierarchical voltage calculation architecture, which extends the model-free single-phase voltage calculation method in the prior art to a three-phase system, fully considering the three-phase imbalance characteristics commonly present in low-voltage distribution networks, thereby more accurately reflecting the operating status of the actual low-voltage distribution system. Furthermore, this embodiment is used to target the time period characteristics of photovoltaic power generation, using operating data from different time periods during the daytime and nighttime periods in the low-voltage distribution network for training, thereby establishing voltage calculation models for different time periods. Through a data-driven approach, the flow characteristics of different low-voltage distribution networks at different time periods are learned, thereby improving the accuracy and adaptability of the low-voltage distribution network's all-day voltage calculation.

[0055] Furthermore, based on the voltage calculation method of this embodiment, by decomposing the voltage calculation process in different time periods into the superposition of the base layer voltage and the control layer voltage changes, and by independently modeling the voltage and power mapping characteristics between different nodes in the base layer and the control layer, the problem of decreased voltage calculation accuracy in the existing technology under frequent power fluctuation scenarios is effectively solved, thereby improving the robustness of the voltage calculation model.

[0056] The control method of the embodiment of the present invention is further described below based on the accompanying drawings.

[0057] Reference Figure 1 , Figure 1 A flowchart of a method for constructing a voltage segmented hierarchical computing architecture provided by an embodiment of the present invention includes but is not limited to the following steps:

[0058] Step S11, summarizing the node voltage historical operation data and node active power historical operation data in the low-voltage distribution network;

[0059] It should be noted that historical node voltage data directly reflects the temporal changes in node voltages within the distribution network. By summarizing this data, we can understand characteristics such as the fluctuation range and amplitude distribution of node voltages under different operating conditions. Historical node active power data reflects the distribution and flow of power within the distribution network. Changes in active power affect node voltages, and summarizing this data helps analyze the inherent relationship between power and voltage, providing accurate data support for calculation methods based on the power-voltage relationship.

[0060] Step S12, determining the daytime operation period and the nighttime operation period according to the node voltage historical operation data and the node active power historical operation data;

[0061] It's important to note that in low-voltage distribution networks, photovoltaic (PV) power generation exhibits significant time-varying characteristics, generating significant power during the day and discontinuing operation at night. Furthermore, due to the high impedance of low-voltage distribution networks, fluctuations in node active power significantly impact node voltage. Consequently, the correlation between voltage and node power varies dynamically with time and operating conditions: during the day, the correlation between voltage and PV node active power is higher, while the correlation with load node active power is lower. During the night, the correlation between voltage and load node active power increases significantly. This dynamic behavior indicates that PV output has a particularly pronounced impact on the correlation between voltage and power.

[0062] However, in existing technologies, the time period characteristics of photovoltaic output are usually ignored, and a single model is used to uniformly train and calculate all data of all low-voltage distribution networks. As a result, the model pays too much attention to the characteristics of photovoltaic nodes during the day during training, while ignoring the impact of nighttime load nodes on voltage. This makes it difficult to fully capture the dynamic characteristics of grid power changes, thereby limiting the accuracy and applicability of voltage calculations.

[0063] Therefore, this embodiment performs segmented processing on the voltage calculation model according to the time period characteristics of photovoltaic output, and uses targeted models for calculation in different time periods.

[0064] Step S13, obtaining a daytime training data set according to the daytime operation period, and obtaining a nighttime training data set according to the nighttime operation period;

[0065] It's important to note that there are significant differences in power load characteristics between daytime and nighttime. During the daytime, industrial and commercial electricity consumption, as well as various household appliances, are frequently used, resulting in diverse and highly volatile loads. Meanwhile, at night, loads are relatively small and stable, primarily driven by household lighting and small appliances. By acquiring separate daytime and nighttime training datasets, we can more accurately reflect the impact of load variations at different times of day on the voltage of the low-voltage distribution network.

[0066] Step S14: constructing a base layer and a control layer for different operating periods of the low-voltage distribution network based on the daytime training data set and the nighttime training data set. The base layer is constructed based on the three-phase active net load matrix, the three-phase reactive net load matrix, and the input-output mapping relationship of the low-voltage distribution network.

[0067] It should be noted that the three-phase active net load matrix and the three-phase reactive net load matrix can comprehensively and meticulously describe the power distribution of each phase in the low-voltage distribution network. Active power determines the rate at which electrical energy is converted into other forms of energy, while reactive power is related to the energy exchange between electric and magnetic fields, directly affecting voltage quality and grid losses. The three-phase active net load matrix and the three-phase reactive net load matrix can accurately grasp the power flow state of each node and line in the low-voltage distribution network during daytime operation, providing accurate basic data for subsequent analysis and calculations. The input-output mapping relationship links the power matrix with other operating parameters of the low-voltage distribution network (such as voltage and current), thereby reflecting the dynamic changes between power input and output during daytime operation. Based on the three-phase active net load matrix, the three-phase reactive net load matrix, and the input-output mapping relationship, the daytime basic layer, daytime control layer, nighttime basic layer, and nighttime control layer of the low-voltage distribution network are established.

[0068] Step S15: constructing a nighttime base layer and a nighttime control layer for the nighttime operation period based on the nighttime training data set. The nighttime base layer is constructed based on the three-phase active net load matrix, the three-phase reactive net load matrix, and the input-output mapping relationship of the low-voltage distribution network.

[0069] Step S16, obtaining the daytime base voltage and the daytime voltage change, and calculating the daytime actual voltage of the low-voltage distribution network according to the daytime base voltage and the daytime voltage change through the daytime base layer and the daytime regulation layer;

[0070] Step S17: Obtain the nighttime basic voltage and the nighttime voltage change, and calculate the nighttime actual voltage of the low-voltage distribution network according to the nighttime basic voltage and the nighttime voltage change through the nighttime basic layer and the nighttime regulation layer.

[0071] It should be noted that the baseline normal operating voltage of the daytime base layer is first calculated. The baseline normal operating voltage reflects the system state of the low-voltage distribution network when no regulatory measures are introduced. Subsequently, the voltage change of the low-voltage distribution network due to the influence of the regulatory equipment is calculated in the daytime and nighttime regulatory layers. Finally, the baseline voltage of the daytime base layer is superimposed with the voltage change of the daytime regulatory layer, and the baseline voltage of the nighttime base layer is superimposed with the voltage change of the nighttime regulatory layer, thereby obtaining the actual daytime and nighttime voltages of the low-voltage distribution network.

[0072] It should be noted that this embodiment, by extending the existing model-free single-phase voltage calculation method to a three-phase system, fully considers the three-phase imbalance characteristics commonly found in low-voltage distribution networks, thereby more accurately reflecting the actual operating status of low-voltage distribution systems. Furthermore, this embodiment is used to target the time period characteristics of photovoltaic power generation, using operating data from different time periods during the daytime and nighttime periods in the low-voltage distribution network for training, thereby establishing voltage calculation models for different time periods. Through a data-driven approach, the power flow characteristics of different low-voltage distribution networks at different time periods are learned, thereby improving the accuracy and adaptability of the low-voltage distribution network's all-day voltage calculation.

[0073] In addition, in one embodiment, referring to Figure 2 ,exist Figure 1 Step S11 of the illustrated embodiment also includes but is not limited to the following steps:

[0074] Step S21, obtaining the start output time and stop output time of the photovoltaic nodes of the low-voltage distribution network for a preset number of days, as well as the total working days and the total number of photovoltaic nodes of the low-voltage distribution network;

[0075] Step S22, calculating the daytime starting working time of the low-voltage distribution network according to the starting output time, the total number of working days and the total number of photovoltaic nodes;

[0076] Step S23, calculating the daytime stop working time of the low-voltage distribution network according to the start output time, the total number of working days and the total number of photovoltaic nodes;

[0077] Step S24: determining the nighttime working time of the low-voltage distribution network according to the daytime working start time and the daytime working stop time.

[0078] It should be noted that the voltage segmentation rules set in this embodiment are as follows:

[0079] The node voltage history data set is obtained based on the node voltage history data, and the node active power history data set is obtained based on the node active power history data set. The time when all photovoltaic power generation starts and stops in the node voltage history data set and the node active power history data set are recorded each day. The average of the two sets is taken and rounded as the start and end time of the daytime period. Time outside the daytime period is defined as the nighttime period. This is expressed by the following first formula:

[0080]

[0081] Among them, T begin The time when the output starts during the day, T stop is the time when power output stops during the day; D is the total number of working days; M is the total number of photovoltaic nodes in the low-voltage active distribution network; is the starting output time of the mth photovoltaic node at the mth node on the dth day, is the time when the mth PV node stops outputting power on the dth day; is the floor symbol.

[0082] In addition, in one embodiment, referring to Figure 2 ,exist Figure 1 Step S11 of the illustrated embodiment also includes but is not limited to the following steps:

[0083] Step S31, obtaining a three-phase voltage matrix of each node during normal operation of the low-voltage distribution network according to the three-phase active net load matrix, the three-phase reactive net load matrix, and the input-output mapping relationship;

[0084] Step S32: obtaining the daytime basic voltage of the low-voltage distribution network according to the three-phase voltage matrix. The daytime control layer obtains the daytime voltage change of the low-voltage distribution network based on the three-phase active net load matrix, the reactive load matrix and the input-output mapping relationship.

[0085] It should be noted that, since there is mutual influence between self-impedance and mutual impedance between three-phase lines in the low-voltage distribution line, this embodiment establishes a three-phase Distflow power flow model, which is expressed by the following second formula:

[0086]

[0087] Among them, p mn The three-phase active net load matrix q on branch mn mn is the reactive power matrix on branch mn; S n is the set of child nodes of n node; u n is the square matrix of the three-phase effective voltage values ​​at node n; mn and i mn are the three-phase impedance matrix and the square matrix of the three-phase current effective value of branch mn respectively; P PV,n is the photovoltaic three-phase active net load matrix of node n; P L,n and Q L,n are the three-phase active net load matrix and three-phase reactive net load matrix of node n respectively; * represents the conjugate of the matrix. The form of the three-phase matrix is

[0088] Furthermore, mn 、r mn and x mn , expressed by the following third formula:

[0089]

[0090] in, is the self-impedance of phase A line; is the mutual impedance between phase A and phase B; α is the symmetrical component transformation matrix.

[0091] In addition, in one embodiment, referring to Figure 2 ,exist Figure 1 Step S11 of the illustrated embodiment also includes but is not limited to the following steps:

[0092] Step S41, obtaining a three-phase voltage matrix of each node during normal nighttime operation of the low-voltage distribution network according to the three-phase active net load matrix, the three-phase reactive net load matrix, and the input-output mapping relationship;

[0093] Step S42: obtaining the nighttime basic voltage of the low-voltage distribution network according to the three-phase voltage matrix; and obtaining the nighttime voltage change of the low-voltage distribution network based on the three-phase voltage active net load matrix, reactive load matrix and the input-output mapping relationship of the low-voltage distribution network by the nighttime control layer.

[0094] It should be noted that the specific calculation process of the nighttime base layer and the nighttime control layer is consistent with that of the daytime base layer and the daytime control layer. Therefore, this embodiment will not describe them in detail.

[0095] In addition, in one embodiment, referring to Figure 2 ,exist Figure 1 Step S11 of the illustrated embodiment also includes but is not limited to the following steps:

[0096] Step S51, constructing a voltage calculation model of the base layer according to the total number of photovoltaic nodes, the input-output mapping relationship, the three-phase active net load matrix and the reactive load matrix;

[0097] Step S52, calculating the reference operating voltage of the daytime base layer at the current daytime voltage calculation time, wherein the reference operating voltage represents the system state when no control measures are introduced into the daytime base layer;

[0098] Step S53 , calculating the basic operating state of the control equipment acting on the low-voltage distribution network in the control layer, and superimposing the reference operating voltage and the voltage change to obtain the actual voltage.

[0099] It should be noted that β is any one of the three phases ABC. There is an implicit functional relationship between the β-phase voltage of node n and the β-phase voltage of node m, the three-phase active power injected by node n, the three-phase reactive power, and the three-phase line loss of the mn line. In addition, the β-phase voltage of node m and the three-phase line loss of the mn line are also affected by the active power and reactive power of other nodes. Therefore, this embodiment uses LVADN historical operation data as a training set, including three-phase active load, reactive load, PV output and corresponding node voltage. The data-driven method is used to mine the potential power flow information in these data and establish a mapping relationship, thereby replacing the traditional electrical model, thereby realizing voltage calculation without network parameters.

[0100] In this embodiment, the voltage calculation model of the base layer is expressed by the following fourth formula:

[0101] U base =f base (P,Q L );

[0102] Where, U base is the three-phase voltage matrix of each node during the normal operation of the low-voltage active distribution network; f base () is the input-output mapping relationship of the basic layer model-free voltage calculation method; P and Q L are the three-phase active power and reactive load matrices of each node respectively.

[0103] The specific meaning of each variable is expressed by the following fifth formula:

[0104]

[0105] Where N is the total number of nodes; Un is the three-phase voltage matrix of n nodes during normal operation, is the phase A voltage at node n.

[0106] Furthermore, this embodiment utilizes the reactive and active power coordinated control capabilities of the photovoltaic inverter and energy storage system to achieve precise voltage regulation when a node voltage exceeds the line in the low-voltage active distribution network, thereby ensuring the safe and stable operation of the low-voltage distribution network. This embodiment takes the control of photovoltaic inverters and energy storage systems as an example. The proposed model is universal and can be extended to other types of control equipment. The power balance model under the low-voltage distribution network control state is expressed by the following sixth formula:

[0107]

[0108] Where, the superscript reg represents the variable during voltage regulation; ΔP ESS,n is the active power matrix emitted or absorbed by the n-node energy storage during voltage regulation, ΔQ PVI,n is the reactive power matrix of the n-node photovoltaic inverter during voltage regulation, and its expanded form is the same as ΔP ESS,n .

[0109] In addition, in one embodiment, referring to Figure 2 ,exist Figure 1 Step S11 of the illustrated embodiment also includes but is not limited to the following steps:

[0110] Step S61, using the base layer data of different time periods to perform subtraction to obtain the training data of the control layer;

[0111] Step S62, determining the time delay required for the training data of the daytime control layer and the nighttime control layer;

[0112] Step S63: Performing time difference processing on the training data of the daytime base layer and the nighttime base layer, subtracting the data of each time point from the data of the time delay amount to obtain difference data, wherein the difference data is the three-phase active static load change data, the reactive static load change data, and the three-phase voltage change data;

[0113] Step S64: Using the differential data as a daytime training data set and a nighttime training data set.

[0114] It's important to note that the differential data obtained through subtraction can highlight changes in three-phase active static load, reactive static load, and three-phase voltage over different time periods. This helps the model focus more on load changes rather than the absolute values ​​in the original data, thereby better capturing the patterns and trends of load changes and improving the ability to predict and control load changes. The data dimension after differential processing may be reduced, and the data volume is relatively reduced, which speeds up model training and reduces training time and computing resource consumption. Furthermore, because the data is more representative and targeted, the model can converge to a better solution more quickly during training, improving training efficiency and effectiveness.

[0115] Finally, the calculation model for regulating the incremental layer voltage change amount proposed in this embodiment can be expressed by the following seventh formula:

[0116]

[0117] Where ΔU represents the three-phase voltage change matrix of each node in the voltage control layer; ΔP and ΔQ represent the three-phase active difference matrix and reactive difference matrix of each node respectively; ΔP ESS Represents the active output matrix of the three-phase energy storage equipment at each node; ΔQ PVI Represents the reactive power output matrix of the three-phase photovoltaic inverter at each node.

[0118] In addition, in one embodiment, referring to Figure 2 ,exist Figure 1 Step S11 of the illustrated embodiment also includes but is not limited to the following steps:

[0119] Step S71, obtaining a three-phase voltage change matrix, a three-phase active power difference matrix, a three-phase reactive power difference matrix, a three-phase energy storage device active power output matrix, and a three-phase photovoltaic inverter reactive power output matrix of each node in the low-voltage distribution network;

[0120] Step S72, obtaining non-voltage regulation data and voltage regulation data in the low-voltage distribution network;

[0121] Step S73, constructing a three-phase voltage change matrix for each node in the control layer according to the voltage control data, the voltage control data, the three-phase voltage change matrix, the three-phase active difference matrix, the three-phase reactive difference matrix, the three-phase energy storage device active output matrix, and the three-phase photovoltaic inverter reactive output matrix;

[0122] Step S74: construct a segmented and hierarchical calculation architecture based on the three-phase active net load matrix, the reactive load matrix, the three-phase active difference matrix, and the three-phase reactive difference matrix.

[0123] It is noted that the relationship between the actual voltage of node n after regulation at a certain moment and the unregulated base voltage during normal operation is expressed by the following eighth formula:

[0124] U base,n +ΔU n =U n ;

[0125] Where, ΔU n is the matrix of the three-phase voltage change of n nodes during regulation; U n is the n-node three-phase voltage matrix after regulation.

[0126] By comparing Equations (3) and (7), it can be found that there are significant differences in the mapping relationship between power and voltage in the low-voltage active distribution network under normal operation and voltage regulation. Under voltage regulation, the model needs to introduce input parameters of control devices such as photovoltaic inverters and energy storage systems to accurately characterize the impact of control measures on system operating characteristics. In addition, as shown in Equation (8), the node voltage after regulation can be calculated by linearly superposing the voltage under normal operation and the voltage change.

[0127] Based on the above analysis, the present invention proposes a hierarchical voltage calculation architecture, which clearly divides the voltage calculation process of the low-voltage active distribution network into two levels: the basic layer and the control layer. First, the base layer’s reference normal operating voltage U is calculated. base,n , the reference voltage reflects the system state when no control measures are introduced. Then, in the control layer, the voltage change ΔU under the control device is calculated n Finally, the base layer reference voltage U base,n and the voltage change ΔU of the control layer n Perform superposition to complete the voltage calculation without electrical model.

[0128] Regarding ΔU in the control layer n , the voltage sensitivity matrix can usually be used to describe the impact of the output change of the control equipment on the node voltage. n The mapping relationship between the output changes of other nodes is expressed by the following ninth formula:

[0129]

[0130] According to the ninth formula, this embodiment uses the three-phase active power change, reactive power change and corresponding voltage change of the control equipment as training data, and uses the construction method of the data-driven voltage segmented and hierarchical calculation architecture to calculate the voltage change during the voltage control process.

[0131] The specific meaning of each variable is expressed by the following tenth formula:

[0132]

[0133] Among them, when there is no voltage control data, and are the difference matrices of the three-phase voltage, three-phase injected active power, and three-phase injected reactive power at n nodes at time t and time t-t_lag respectively;

[0134] In summary, this embodiment decouples the calculation of the normal operating voltage from the impact of the control measures on the voltage, and can more specifically select and process training data at different levels.

[0135] Taking the scenario without regulation data as an example, the integrated voltage segmentation and hierarchical calculation architecture can be expressed by the following eleventh formula:

[0136]

[0137] Among them, X day is the daytime training dataset, X night is the daytime training dataset, f day () is the input correspondence of the construction method of voltage segmentation and hierarchical calculation architecture, f night () is the output correspondence of the construction method of the voltage segmented and hierarchical calculation architecture.

[0138] like Figure 8 As shown, Figure 8 : is a structural diagram of a voltage calculation device without an electrical model provided by an embodiment of the present invention. The present invention also provides a voltage calculation device without an electrical model, comprising:

[0139] The processor 801 may be implemented as a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is configured to execute relevant programs to implement the technical solutions provided in the embodiments of the present application.

[0140] The memory 802 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 802 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 802 and is called by the processor 801 to execute the method for constructing a voltage segmented hierarchical computing architecture in the embodiments of this application.

[0141] Input / output interface 803, used to implement information input and output;

[0142] Communication interface 804, used to implement communication interaction between the apparatus and other devices, which can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.);

[0143] Bus 805 , which transmits information between various components of the device (e.g., processor 801 , memory 802 , input / output interface 803 , and communication interface 804 );

[0144] The processor 801 , the memory 802 , the input / output interface 803 and the communication interface 804 are connected to each other in communication within the device via a bus 805 .

[0145] An embodiment of the present application further provides an electronic device, comprising the voltage calculation device without an electrical model as described above.

[0146] An embodiment of the present application also provides a storage medium, which is a computer-readable storage medium. The storage medium stores a computer program, and when the computer program is executed by a processor, it implements the method for constructing the above-mentioned voltage segmented hierarchical computing architecture.

[0147] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory optionally includes a memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of the above-mentioned networks include but are not limited to the Internet, an intranet, a local area network, a mobile communication network and a combination thereof. The device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and are located in one place, or may be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.

[0148] Those skilled in the art will appreciate that all or some of the steps and systems in the method disclosed above can be implemented as software, firmware, hardware, and appropriate combinations thereof. Some physical components or all physical components can be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software can be distributed on a computer-readable medium, and the computer-readable medium can include computer storage media (or non-transitory media) and communication media (or temporary media). As known to those skilled in the art, the term computer storage media is included in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data) and is volatile and non-volatile, removable, and non-removable. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory, or other memory technology, CD-ROM, digital versatile disks (DVD), or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage, or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, as is well known to those skilled in the art, communication media typically includes computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0149] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the above implementation. Those skilled in the art can also make various equivalent modifications or substitutions under the shared conditions that do not violate the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. A method for constructing a voltage segmented hierarchical computing architecture, characterized in that: include: Summarize the historical operating data of node voltage and node active power in the low-voltage distribution network; Determining a daytime operation period and a nighttime operation period according to the node voltage historical operation data and the node active power historical operation data; Obtaining a daytime training data set according to the daytime operation period, and obtaining a nighttime training data set according to the nighttime operation period; According to the daytime training data set, constructing a daytime basic layer and a daytime regulation layer for the daytime operation period, wherein the daytime basic layer is constructed based on the three-phase active net load matrix, the three-phase reactive net load matrix and the input-output mapping relationship of the low-voltage distribution network; Constructing a nighttime basic layer and a nighttime control layer for the nighttime operation period according to the nighttime training data set, wherein the nighttime basic layer is constructed based on a three-phase active net load matrix, a three-phase reactive net load matrix, and an input-output mapping relationship of the low-voltage distribution network; Obtaining a daytime base voltage and a daytime voltage change, and calculating the daytime actual voltage of the low-voltage distribution network according to the daytime base voltage and the daytime voltage change through the daytime base layer and the daytime regulation layer; A nighttime basic voltage and a nighttime voltage change are obtained, and the nighttime actual voltage of the low-voltage distribution network is calculated according to the nighttime basic voltage and the nighttime voltage change through the nighttime basic layer and the nighttime regulation layer.

2. The method for constructing a voltage segmented hierarchical computing architecture according to claim 1, characterized in that: Determining the daytime operation time period and the nighttime operation time period of the low-voltage distribution network includes: Obtaining the start and stop output times of the photovoltaic nodes of the low-voltage distribution network for a preset number of days, as well as the total number of working days and the total number of photovoltaic nodes of the low-voltage distribution network; Calculate the daytime starting working time of the low-voltage distribution network according to the starting output time, the total number of working days and the total number of photovoltaic nodes; Calculate the daytime stop working time of the low-voltage distribution network according to the start output time, the total number of working days and the total number of photovoltaic nodes; The nighttime working time of the low-voltage distribution network is determined according to the daytime working start time and the daytime working stop time.

3. The method for constructing a voltage segmented hierarchical computing architecture according to claim 1, wherein: The calculating the daytime actual voltage of the low-voltage distribution network according to the daytime basic voltage and the daytime voltage change includes: Obtaining a three-phase voltage matrix of each node when the low-voltage distribution network is operating normally according to the three-phase active net load matrix, the three-phase reactive net load matrix and the input-output mapping relationship; The daytime basic voltage of the low-voltage distribution network is obtained according to the three-phase voltage matrix, and the daytime regulation layer obtains the daytime voltage change of the low-voltage distribution network based on the three-phase active net load matrix and reactive load matrix and the input-output mapping relationship.

4. The method for constructing a voltage segmented hierarchical computing architecture according to claim 1, wherein: The calculating the nighttime actual voltage of the low-voltage distribution network according to the nighttime basic voltage and the nighttime voltage change includes: Obtaining a three-phase voltage matrix of each node of the low-voltage distribution network during normal operation at night according to the three-phase active net load matrix, the three-phase reactive net load matrix and the input-output mapping relationship; The nighttime basic voltage of the low-voltage distribution network is obtained according to the three-phase voltage matrix, and the nighttime regulation layer obtains the nighttime voltage change of the low-voltage distribution network based on the three-phase active net load matrix and reactive load matrix of the low-voltage distribution network and the input-output mapping relationship.

5. The method for constructing a voltage segmented hierarchical computing architecture according to claim 1, wherein: The construction of the daytime basic layer and the daytime regulation layer for the daytime operation period includes: Constructing a voltage calculation model for the daytime base layer according to the total number of photovoltaic nodes, the input-output mapping relationship, the three-phase active net load matrix, and the reactive load matrix; Calculating a reference operating voltage of the daytime base layer at the current daytime voltage calculation time, wherein the reference operating voltage represents a system state when no control measures are introduced into the daytime base layer; The basic operating state of the control equipment acting on the low-voltage distribution network in the daytime control layer is calculated, and the reference operating voltage and the voltage change are superimposed to obtain the actual daytime voltage.

6. The method for constructing a voltage segmented hierarchical computing architecture according to claim 5, characterized in that: The step of obtaining a daytime training data set according to the daytime operation period and obtaining a nighttime training data set according to the nighttime operation period includes: The training data of the control layer is obtained by subtracting the base layer data from different time periods; Determining the time delay required for training data of the daytime control layer and the nighttime control layer; Performing time difference processing on the training data of the daytime base layer and the nighttime base layer, subtracting the data of each time point from the data of the time delay amount to obtain difference data, wherein the difference data includes the three-phase active static load change data, the reactive static load change data, and the three-phase voltage change data; The differential data is used as the daytime training data set and the nighttime training data set.

7. The method for constructing a voltage segmented hierarchical computing architecture according to claim 5, characterized in that: After constructing the voltage calculation model of the base layer, the method further includes: Obtaining a three-phase voltage change matrix, a three-phase active difference matrix, a three-phase reactive difference matrix, a three-phase energy storage device active output matrix, and a three-phase photovoltaic inverter reactive output matrix of each node in the low-voltage distribution network; Acquiring non-voltage regulation data and voltage regulation data in the low-voltage distribution network; Constructing a three-phase voltage change matrix of each node in the control layer according to the no-voltage control data, the voltage control data, the three-phase voltage change matrix, the three-phase active difference matrix, the three-phase reactive difference matrix, the three-phase energy storage device active output matrix and the three-phase photovoltaic inverter reactive output matrix; A segmented and hierarchical calculation architecture is constructed based on the three-phase active net load matrix, the reactive load matrix, the three-phase active difference matrix, and the three-phase reactive difference matrix.

8. A voltage calculation device without an electrical model, characterized in that: comprising at least one control processor and a memory for communicatively coupling with the at least one control processor; The memory stores instructions that can be executed by the at least one control processor, and the instructions are executed by the at least one control processor to enable the at least one control processor to execute the method for constructing a voltage segmented hierarchical computing architecture as described in any one of claims 1 to 7.

9. An electronic device, characterized in that: A voltage calculation device without an electrical model according to claim 8.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the method for constructing a voltage segmented hierarchical computing architecture according to any one of claims 1 to 7.

Images