Distribution line loss prediction method and device based on digital twin

Abstract

The present application provides a distribution line loss prediction method and device based on digital twins. The embodiment of the present application first determines the line loss mapping set corresponding to the target distribution line based on the three-phase load data, power supply data and power sales data of the target distribution line in a preset historical period; then determines the three-phase load of the target distribution line at the next moment based on the three-phase load state transition probability and the three-phase load state transition probability matrix corresponding to each distribution transformer connected to the target distribution line; finally, determines the line loss rate of the target distribution line at the next moment based on the three-phase load and line loss mapping set at the next moment. The embodiment of the present application deeply explores the line loss variation law of the target distribution line based on the data of the preset historical period and the current moment, and can objectively and accurately predict the line loss rate of the target distribution line, which has important guiding significance for reducing the loss of the distribution line and improving the efficiency of electric energy utilization.

Description

Technical Field

[0001] The present application relates to the technical field of distribution line line loss analysis and management, and in particular to a distribution line line loss prediction method and device based on digital twins. Background Art

[0002] my country's distribution network continues to expand, but distribution losses are becoming increasingly severe as load capacity increases. Increased line losses in distribution networks lead to increased capacity for power generation and transmission equipment, resulting in higher electricity costs and wasted power resources. my country's distribution network development structure is irrational, and there is a lack of guidance on distribution loss management. Currently, losses in medium and low voltage distribution lines account for approximately 50% of total power line losses, posing a significant challenge to the economic operation of distribution networks.

[0003] Related technologies often use machine learning to predict line losses by building computational models. Typical computational models include big data analysis and regression analysis. However, these methods require a large amount of data collection, consuming significant manpower and material resources. Furthermore, the calculation process relies heavily on data collection and accuracy, and cannot predict future distribution line losses based on existing conditions. Accurate distribution line loss prediction can help power companies understand future line loss trends, provide effective guidance for loss reduction measures, and improve the economic operation of distribution networks. Summary of the Invention

[0004] The present application provides a distribution line line loss prediction method and device based on digital twins to improve the accuracy of distribution line line loss prediction, so as to achieve the purpose of guiding distribution line line loss management and increasing efficiency operation.

[0005] In order to solve the above problems, this application adopts the following technical solutions:

[0006] In a first aspect, an embodiment of the present application provides a distribution line line loss prediction method based on digital twins, the method comprising:

[0007] Determine a line loss mapping set corresponding to the target distribution line based on the three-phase load data, power supply data, and power sales data of the target distribution line within a preset historical period; the line loss mapping set is used to characterize the mapping relationship between the three-phase load of the target distribution line and the line loss rate;

[0008] Determine the three-phase load at the next moment corresponding to each distribution transformer connected to the target distribution line based on the three-phase load state transition probability and the three-phase load state transition probability matrix corresponding to each distribution transformer at the current moment;

[0009] Determine the sum of the three-phase loads corresponding to each of the distribution transformers at the next moment as the three-phase load of the target distribution line at the next moment;

[0010] The line loss rate of the target distribution line at the next moment is determined based on the three-phase load of the target distribution line at the next moment and the line loss mapping set.

[0011] In one embodiment of the present application, the step of determining a line loss mapping set corresponding to a target distribution line based on three-phase load data, power supply data, and power sales data of the target distribution line within a preset historical period includes:

[0012] According to a preset time interval, the preset historical period is divided into n time periods, each time period corresponds to a time node; n is a positive integer greater than 1;

[0013] For any time node, obtain the three-phase load data of the target distribution line at the time node; and determine the line loss rate of the target distribution line corresponding to the time node based on the power supply data of the target distribution line in the time period corresponding to the time node and the power sales data of each distribution transformer in the time period;

[0014] Based on the three-phase load data and line loss rate corresponding to each of the n time nodes, a line loss mapping set corresponding to the target distribution line is determined.

[0015] In one embodiment of the present application, the step of determining the line loss rate of the target distribution line corresponding to the time node based on the power supply data of the target distribution line in the time period corresponding to the time node and the power sales data of each of the distribution transformers in the time period includes:

[0016] Obtain a first power indication of each distribution transformer at the time node and a second power indication at a time node next to the time node; and obtain a first checkpoint power indication of the target distribution line at the time node and a second checkpoint power indication at a time node next to the time node;

[0017] Determine the power sales data of each distribution transformer in the time period corresponding to each of the time nodes based on the first power indication, the second power indication, and the meter multiplier corresponding to each of the distribution transformers, and determine the total power sales data based on the power sales data corresponding to each of the distribution transformers;

[0018] Determine power supply data of the target distribution line within the time period corresponding to the time node based on the first gateway power indication, the second gateway power indication, and the meter multiplier corresponding to the target distribution line;

[0019] The line loss rate of the target distribution line corresponding to the time node is determined based on the total power sales data and the power supply data of the target distribution line in the time period corresponding to the time node.

[0020] In one embodiment of the present application, the step of determining the line loss rate of the target distribution line at the next moment based on the three-phase load of the target distribution line at the next moment and the line loss mapping set includes:

[0021] Determining a target three-phase load closest to the three-phase load of the target distribution line at a next moment in the line loss mapping set;

[0022] Determining a target line loss rate corresponding to the target three-phase load based on the line loss mapping set;

[0023] The target line loss rate is determined as the line loss rate of the target power distribution line at the next moment.

[0024] In one embodiment of the present application, the three-phase load state transition probability includes a three-phase active power state transition probability and a three-phase reactive power state transition probability; the three-phase load state transition probability matrix includes a three-phase active power state transition probability matrix and a three-phase reactive power state transition probability matrix;

[0025] The step of determining the three-phase load at the next moment corresponding to each distribution transformer connected to the target distribution line based on the three-phase load state transition probability at the current moment and the three-phase load state transition probability matrix includes:

[0026] Determine the three-phase active power state transition probability distribution of each distribution transformer at the next moment based on the three-phase active power state transition probability of each distribution transformer at the current moment and the three-phase active power state transition probability matrix; and determine the three-phase active power of each distribution transformer at the next moment based on the three-phase active power state transition probability distribution;

[0027] Determine the three-phase reactive power state transition probability distribution of each distribution transformer at the next moment based on the three-phase reactive power state transition probability and the three-phase reactive power state transition probability matrix of each distribution transformer at the current moment; and determine the three-phase reactive power of each distribution transformer at the next moment based on the three-phase reactive power state transition probability distribution;

[0028] Based on the three-phase active power and three-phase reactive power corresponding to each distribution transformer at the next moment, the three-phase load corresponding to each distribution transformer at the next moment is determined.

[0029] In one embodiment of the present application, the method further includes:

[0030] Based on the three-phase active power data corresponding to each of the distribution transformers at the n time nodes, determining a first value range corresponding to the sum of the three-phase active power of each of the distribution transformers at the next moment; and based on the three-phase reactive power data corresponding to each of the distribution transformers at the n time nodes, determining a second value range corresponding to the sum of the three-phase reactive power of each of the distribution transformers at the next moment;

[0031] After determining the three-phase active power of each distribution transformer at a next moment based on the three-phase active power state transition probability distribution, the method further includes:

[0032] Determining whether the sum of the three-phase active power of each distribution transformer at the next moment is within the first value range;

[0033] If not, repeating the steps of determining the three-phase active power state transition probability distribution of each distribution transformer at the next moment based on the three-phase active power state transition probability of each distribution transformer at the current moment and the three-phase active power state transition probability matrix; and determining the three-phase active power of each distribution transformer at the next moment based on the three-phase active power state transition probability distribution, until the sum of the three-phase active power of each distribution transformer at the next moment is within the first value range;

[0034] After the step of determining the three-phase reactive power of each distribution transformer at the next moment based on the three-phase reactive power state transition probability distribution, the method further includes:

[0035] Determining whether the sum of the three-phase reactive power of each distribution transformer at the next moment is within the second value range;

[0036] If not, repeat the steps of determining the three-phase reactive power state transfer probability distribution of each distribution transformer at the next moment based on the three-phase reactive power state transfer probability and the three-phase reactive power state transfer probability matrix of each distribution transformer at the current moment; and determining the three-phase reactive power of each distribution transformer at the next moment based on the three-phase reactive power state transfer probability distribution, until the sum of the three-phase reactive power of each distribution transformer at the next moment is within the second value range.

[0037] In one embodiment of the present application, the steps of determining a first value range corresponding to the sum of the three-phase active power of each distribution transformer at the next moment based on the three-phase active power data corresponding to each of the distribution transformers at the n time nodes; and determining a second value range corresponding to the sum of the three-phase reactive power of each distribution transformer at the next moment based on the three-phase reactive power data corresponding to each of the distribution transformers at the n time nodes include:

[0038] Based on the three-phase current data of each distribution transformer in a preset historical period, clustering each distribution transformer to obtain a preset number of clusters; different clusters represent different electricity usage behaviors;

[0039] Based on the preset active power fluctuation interval corresponding to each cluster, the three-phase active power corresponding to each distribution transformer in each cluster at the n time nodes is cleaned to obtain the effective three-phase active power corresponding to each distribution transformer at the n time nodes; based on the preset reactive power fluctuation interval corresponding to each cluster, the three-phase reactive power corresponding to each distribution transformer in each cluster at the n time nodes is cleaned to obtain the effective three-phase reactive power corresponding to each distribution transformer at the n time nodes;

[0040] For any time node, calculate the sum of the effective three-phase active power and the sum of the effective three-phase reactive power of each distribution transformer at the time node to obtain n overall three-phase active powers and n overall three-phase reactive powers respectively;

[0041] The first value range is determined based on the minimum value and the maximum value of the n overall three-phase active powers; and the second value range is determined based on the minimum value and the maximum value of the n overall three-phase reactive powers.

[0042] In one embodiment of the present application, based on the preset active power fluctuation interval corresponding to each cluster, the three-phase active power corresponding to each distribution transformer in each cluster at the n time nodes is cleaned to obtain the effective three-phase active power corresponding to each distribution transformer at the n time nodes; based on the preset reactive power fluctuation interval corresponding to each cluster, the three-phase reactive power corresponding to each distribution transformer in each cluster at the n time nodes is cleaned to obtain the effective three-phase reactive power corresponding to each distribution transformer at the n time nodes, including:

[0043] For any time node, when the three-phase active power corresponding to any of the distribution transformers is greater than the upper limit of the preset active power fluctuation interval corresponding to the cluster to which the distribution transformer belongs, the three-phase active power is determined as the upper limit of the interval; or, when the three-phase active power corresponding to any of the distribution transformers is less than the lower limit of the preset active power fluctuation interval corresponding to the cluster to which the distribution transformer belongs, the three-phase active power is determined as the lower limit of the interval, so as to obtain the effective three-phase active power corresponding to each distribution transformer at the n time nodes;

[0044] For any time node, when the three-phase reactive power corresponding to any of the distribution transformers is greater than the upper limit value of the preset reactive power fluctuation range corresponding to the cluster to which the distribution transformer belongs, the three-phase reactive power is determined as the upper limit value of the interval, or, when the three-phase reactive power corresponding to any of the distribution transformers is less than the lower limit value of the preset reactive power fluctuation range corresponding to the cluster to which the distribution transformer belongs, the three-phase reactive power is determined as the lower limit value of the interval, so as to obtain the effective three-phase reactive power corresponding to each distribution transformer at the n time nodes.

[0045] In a second aspect, based on the same inventive concept, an embodiment of the present application provides a distribution line line loss prediction device based on digital twins, the device comprising:

[0046] A first determination module is configured to determine a line loss mapping set corresponding to a target distribution line based on three-phase load data, power supply data, and power sales data of the target distribution line within a preset historical period; the line loss mapping set is configured to characterize a mapping relationship between the three-phase load of the target distribution line and the line loss rate;

[0047] A second determining module is configured to determine the three-phase load corresponding to each distribution transformer connected to the target distribution line at a next moment based on the three-phase load state transition probability and the three-phase load state transition probability matrix corresponding to each distribution transformer at a current moment;

[0048] A third determining module is configured to determine the sum of the three-phase loads corresponding to each of the distribution transformers at the next moment as the three-phase load of the target distribution line at the next moment;

[0049] The fourth determining module is configured to determine the line loss rate of the target distribution line at the next moment based on the three-phase load of the target distribution line at the next moment and the line loss mapping set.

[0050] In one embodiment of the present application, the first determining module includes:

[0051] A time division submodule is used to divide the preset historical period into n time periods according to a preset time interval, each time period corresponding to a time node; n is a positive integer greater than 1;

[0052] A line loss rate determination submodule is configured to obtain, for any time node, the three-phase load data of the target distribution line at the time node; and determine the line loss rate of the target distribution line corresponding to the time node based on the power supply data of the target distribution line in the time period corresponding to the time node and the power sales data of each distribution transformer in the time period;

[0053] The line loss mapping set determination submodule is used to determine the line loss mapping set corresponding to the target distribution line based on the three-phase load data and line loss rate corresponding to each of the n time nodes.

[0054] In one embodiment of the present application, the line loss rate determination submodule includes:

[0055] An electric quantity indication acquisition unit is configured to acquire a first electric quantity indication of each distribution transformer at the time node and a second electric quantity indication at a time node next to the time node; and acquire a first checkpoint electric quantity indication of the target distribution line at the time node and a second checkpoint electric quantity indication at a time node next to the time node;

[0056] a total electricity sales data determining unit, configured to determine the electricity sales data of each distribution transformer in the time period corresponding to each of the time nodes based on the first electricity indication, the second electricity indication, and the meter multiplier corresponding to each of the distribution transformers, and determine the total electricity sales data based on the electricity sales data corresponding to each of the distribution transformers;

[0057] a power supply data determining unit, configured to determine power supply data of the target distribution line in the time period corresponding to the time node based on the first gateway power indication, the second gateway power indication, and the meter multiplier corresponding to the target distribution line;

[0058] A line loss rate determining unit is configured to determine the line loss rate of the target distribution line corresponding to the time node based on the total power sales data and the power supply data of the target distribution line in the time period corresponding to the time node.

[0059] In one embodiment of the present application, the fourth determining module includes:

[0060] a target three-phase load determination submodule, configured to determine, from the line loss mapping set, a target three-phase load closest to the three-phase load of the target distribution line at the next moment;

[0061] a target line loss rate determination submodule, configured to determine a target line loss rate corresponding to the target three-phase load based on the line loss mapping set;

[0062] The line loss rate determination submodule is configured to determine the target line loss rate as the line loss rate of the target distribution line at the next moment.

[0063] In one embodiment of the present application, the three-phase load state transition probability includes a three-phase active power state transition probability and a three-phase reactive power state transition probability; the three-phase load state transition probability matrix includes a three-phase active power state transition probability matrix and a three-phase reactive power state transition probability matrix;

[0064] The second determining module includes:

[0065] A three-phase active power determination submodule is configured to determine the three-phase active power state transition probability distribution of each distribution transformer at the next moment based on the three-phase active power state transition probability of each distribution transformer at the current moment and the three-phase active power state transition probability matrix; and determine the three-phase active power of each distribution transformer at the next moment based on the three-phase active power state transition probability distribution;

[0066] A three-phase reactive power determination submodule is configured to determine the three-phase reactive power state transition probability distribution of each distribution transformer at the next moment based on the three-phase reactive power state transition probability and the three-phase reactive power state transition probability matrix of each distribution transformer at the current moment; and determine the three-phase reactive power of each distribution transformer at the next moment based on the three-phase reactive power state transition probability distribution;

[0067] The three-phase load determination submodule is used to determine the three-phase load corresponding to each distribution transformer at the next moment based on the three-phase active power and three-phase reactive power corresponding to each distribution transformer at the next moment.

[0068] In one embodiment of the present application, the device further includes:

[0069] a value range determination module, configured to determine, based on the three-phase active power data corresponding to each of the distribution transformers at the n time nodes, a first value range corresponding to the sum of the three-phase active power of each of the distribution transformers at the next moment; and to determine, based on the three-phase reactive power data corresponding to each of the distribution transformers at the n time nodes, a second value range corresponding to the sum of the three-phase reactive power of each of the distribution transformers at the next moment;

[0070] A first judgment module is used to judge whether the sum of the three-phase active power of each distribution transformer at the next moment is within the first value range;

[0071] a first repetitive calculation module, configured to, when the sum of the three-phase active power of each distribution transformer at the next moment is not within the first value range, repeatedly determine the three-phase active power state transition probability distribution of each distribution transformer at the next moment based on the three-phase active power state transition probability of each distribution transformer at the current moment and the three-phase active power state transition probability matrix; and determine the three-phase active power of each distribution transformer at the next moment based on the three-phase active power state transition probability distribution, until the sum of the three-phase active power of each distribution transformer at the next moment is within the first value range;

[0072] A second judgment module is used to judge whether the sum of the three-phase reactive power of each distribution transformer at the next moment is within the second value range;

[0073] The second repetitive calculation module is used to repeat the steps of determining the three-phase reactive power state transition probability distribution of each distribution transformer at the next moment based on the three-phase reactive power state transition probability of each distribution transformer at the current moment and the three-phase reactive power state transition probability matrix; and determining the three-phase reactive power of each distribution transformer at the next moment based on the three-phase reactive power state transition probability distribution, when the sum of the three-phase reactive power of each distribution transformer at the next moment is not within the second value range, until the sum of the three-phase reactive power of each distribution transformer at the next moment is within the second value range.

[0074] In one embodiment of the present application, the value range determination module includes:

[0075] A clustering submodule, configured to cluster each of the distribution transformers based on the three-phase current data of each distribution transformer within a preset historical period to obtain a preset number of clusters; different clusters represent different electricity usage behaviors;

[0076] A cleaning submodule is configured to clean the three-phase active power corresponding to each of the distribution transformers in each of the clusters at the n time nodes based on the preset active power fluctuation interval corresponding to each of the clusters, and obtain the effective three-phase active power corresponding to each of the distribution transformers at the n time nodes; and clean the three-phase reactive power corresponding to each of the distribution transformers in each of the clusters at the n time nodes based on the preset reactive power fluctuation interval corresponding to each of the clusters, and obtain the effective three-phase reactive power corresponding to each of the distribution transformers at the n time nodes;

[0077] A summation submodule is used to calculate the sum of the effective three-phase active power and the sum of the effective three-phase reactive power of each distribution transformer at any time node, so as to obtain n overall three-phase active powers and n overall three-phase reactive powers respectively;

[0078] The value range determination submodule is used to determine the first value range based on the minimum and maximum values of the n overall three-phase active powers; and to determine the second value range based on the minimum and maximum values of the n overall three-phase reactive powers.

[0079] In one embodiment of the present application, the cleaning submodule includes:

[0080] The three-phase active power cleaning subunit is used to, for any time node, determine the three-phase active power as the upper limit value of the interval when the three-phase active power corresponding to any of the distribution transformers is greater than the upper limit value of the preset active power fluctuation interval corresponding to the cluster to which the distribution transformer belongs, or, when the three-phase active power corresponding to any of the distribution transformers is less than the lower limit value of the preset active power fluctuation interval corresponding to the cluster to which the distribution transformer belongs, determine the three-phase active power as the lower limit value of the interval, so as to obtain the effective three-phase active power corresponding to each distribution transformer at the n time nodes;

[0081] The three-phase reactive power cleaning subunit is used to, for any time node, determine the three-phase reactive power as the upper limit value of the interval when the three-phase reactive power corresponding to any of the distribution transformers is greater than the upper limit value of the preset reactive power fluctuation interval corresponding to the cluster to which the distribution transformer belongs, or, when the three-phase reactive power corresponding to any of the distribution transformers is less than the lower limit value of the preset reactive power fluctuation interval corresponding to the cluster to which the distribution transformer belongs, determine the three-phase reactive power as the lower limit value of the interval, so as to obtain the effective three-phase reactive power corresponding to each distribution transformer at the n time nodes.

[0082] Compared with the prior art, this application has the following advantages:

[0083] An embodiment of the present application provides a distribution line loss prediction method based on digital twins, including: determining a line loss mapping set corresponding to the target distribution line based on the three-phase load data, power supply data and power sales data of the target distribution line within a preset historical period; the line loss mapping set is used to characterize the mapping relationship between the three-phase load and the line loss rate of the target distribution line; based on the three-phase load state transition probability and the three-phase load state transition probability matrix corresponding to each distribution transformer connected to the target distribution line at the current moment, determining the three-phase load corresponding to each distribution transformer at the next moment; the sum of the three-phase load corresponding to each distribution transformer at the next moment is determined as the three-phase load of the target distribution line at the next moment; based on the three-phase load of the target distribution line at the next moment and the line loss mapping set, determining the line loss rate of the target distribution line at the next moment. Compared with prediction models that require a lot of manpower and material resources and are computationally complex, the embodiments of the present application can extract valuable data closely related to the core characteristics of line loss from a large amount of data, and deeply explore the line loss variation pattern of the target distribution line based on the data of the preset historical period and the current moment. It can objectively and accurately predict the line loss rate of the target distribution line, which has important guiding significance for reducing the loss of the distribution line, improving the efficiency of power utilization, and realizing the economic operation of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0085] Figure 1 This is a flowchart of the steps of a distribution line line loss prediction method based on digital twin in one embodiment of the present application.

[0086] Figure 2 It is a structural diagram of the distribution network in one embodiment of the present application.

[0087] Figure 3 This is a functional module diagram of a distribution line line loss prediction device based on digital twin in one embodiment of the present application. DETAILED DESCRIPTION

[0088] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0089] Reference Figure 1 , shows a distribution line line loss prediction method based on digital twins in this application, which may include the following steps:

[0090] S101: Determine a line loss mapping set corresponding to a target distribution line based on the three-phase load data, power supply data, and power sales data of the target distribution line within a preset historical period; the line loss mapping set is used to characterize the mapping relationship between the three-phase load of the target distribution line and the line loss rate.

[0091] In this embodiment, referring to Figure 2 , shows a schematic diagram of the distribution network structure, where the distribution lines connect gateway meters and N distribution transformers (hereinafter referred to as distribution transformers). The gateway meters collect power supply data from the distribution lines, and the N distribution transformers transmit power from the distribution lines to users in different areas to meet their electricity needs. Each distribution transformer can be equipped with a corresponding distribution transformer smart meter to collect its own power sales data. The three-phase load data of the target distribution line refers to the sum of the three-phase loads of the N distribution transformers at a specific moment.

[0092] In this embodiment, in order to enable the line loss mapping set to accurately reflect the mapping relationship between the three-phase load and the line loss rate of the target distribution line, the preset historical period can be set to 30 days, that is, the three-phase load data, power supply data, and power sales data of the target distribution line in the last 30 days are obtained. In a specific implementation, the 30 days can be divided into several time periods, and then the line loss rate of the target distribution line corresponding to any time period is calculated based on the power supply data and power sales data of each time period. The line loss relationship mapping process is then performed on the line loss rate and three-phase load data of the target distribution line corresponding to the time period, thereby obtaining the mapping relationship between the three-phase load and the line loss rate of the target distribution line corresponding to each time period, and then obtaining the line loss mapping set.

[0093] S102: Determine the three-phase load at the next moment corresponding to each distribution transformer connected to the target distribution line based on the three-phase load state transition probability at the current moment and the three-phase load state transition probability matrix.

[0094] In this embodiment, based on digital twin technology, by obtaining the three-phase active / reactive power data set of each distribution transformer, specifically including the A-phase active / reactive power data set, the B-phase active / reactive power data set and the C-phase active / reactive power data set, the three-phase load state transition probability corresponding to each distribution transformer can be obtained; and then based on the obtained A-phase active / reactive power state transition probability set, the B-phase active / reactive power state transition probability set and the C-phase active / reactive power state transition probability set, the three-phase load state transition probability matrix of each distribution transformer can be obtained.

[0095] It should be noted that in the development process of an event, the transition from one state to another is called a state transition. The development of an event, the state transition that changes with time, or the relationship between state transition and time, is called a state transition process. In the development and change process of an event, the possibility of transitioning from a certain state to another state at the next moment is called the state transition probability. For example, if the active power of phase A of a distribution transformer exists in two states, Ei and Ej, then the state transition probability from state Ei to state Ej is Pi j; assuming that the active power of phase A has n possible states, E1, E2, ..., En, Pi j is the state transition probability from state Ei to state Ej, and the following matrix P can be obtained. Matrix P is the state transition probability matrix:

[0096]

[0097] In this embodiment, based on the three-phase load state transition probability and the three-phase load state transition probability matrix corresponding to each distribution transformer connected to the target distribution line at the current moment, the three-phase load corresponding to each distribution transformer at the next moment can be predicted.

[0098] S103: Determine the sum of the three-phase loads corresponding to each distribution transformer at the next moment as the three-phase load of the target distribution line at the next moment.

[0099] S104: Determine the line loss rate of the target distribution line at the next moment based on the three-phase load and line loss mapping set of the target distribution line at the next moment.

[0100] In this embodiment, by calculating the sum of the three-phase loads corresponding to each distribution transformer at the next moment, the three-phase load of the target distribution line at the next moment can be obtained, and based on the three-phase load of the target distribution line at the next moment, the line loss rate of the target distribution line at the next moment can be predicted.

[0101] In the specific implementation, first, the target three-phase load closest to the three-phase load of the target distribution line at the next moment is determined in the line loss mapping set; then, based on the line loss mapping set, the target line loss rate corresponding to the target three-phase load is found; finally, the target line loss rate is determined as the line loss rate of the target distribution line at the next moment.

[0102] The embodiment of the present application fully mines the historical data patterns of the target distribution line to obtain a line loss mapping set that can objectively reflect the mapping relationship between the three-phase load of the target distribution line and the line loss rate, and then accurately predicts the line loss rate by predicting the three-phase load of the target distribution line at the next moment. Compared with the prediction model that requires a lot of manpower and material resources and is complex to calculate, the embodiment of the present application can extract valuable data closely related to the core characteristics of line loss from a large amount of data, and comprehensively mine the line loss change pattern of the target distribution line based on the data of the preset historical period and the current moment, and can objectively and accurately predict the line loss rate of the target distribution line, which has important guiding significance for reducing the loss of the distribution line, improving the efficiency of power utilization, and realizing the economic operation of the power grid.

[0103] In a feasible implementation, S101 may specifically include the following steps:

[0104] S101-1: Divide the preset historical period into n time periods according to the preset time interval, each time period corresponds to a time node; n is a positive integer greater than 1.

[0105] In this embodiment, a preset time interval is set according to actual needs. For example, it can be set to 15 minutes, meaning that the readings from the gateway meter and the distribution transformer smart meter are collected every 15 minutes. Each time period includes a start time and an end time. The end time of each time period can be defined as a time node corresponding to each time period. In other words, the line loss rate corresponding to a time period is mapped to the three-phase load data at the time node corresponding to the time period.

[0106] S101-2: For any time node, obtain the three-phase load data of the target distribution line at the time node; and determine the line loss rate corresponding to the target distribution line at the time node based on the power supply data of the target distribution line in the time period corresponding to the time node and the power sales data of each distribution transformer in the time period.

[0107] In this embodiment, for any time node, the first power indication P of each distribution transformer at the time node can be obtained first. r And the second power indication bP of the next time node of the time node r ; Then based on the first power indication P corresponding to each distribution transformer r 、Second power indication bP rand meter multiplication factor μ r , determine the electricity sales data E of each distribution transformer in the time period corresponding to each time node r And by analyzing the electricity sales data E corresponding to each of N distribution transformers r By summing, we can get the total electricity sales data ∑NE r .

[0108] Specifically, at time node T n , the electricity sales data E of each distribution transformer in the time period corresponding to each time node r It can be calculated according to the following formula:

[0109] E r =μ r *(bP r -P r ) (2);

[0110] Where r represents the number of the distribution transformer, r∈{1,2,...,N}; P n Indicates that the distribution transformer numbered r is at time node T n The first power indication; bP r Indicates that the distribution transformer numbered n is at time node T n The second power reading at the next time node; μ r Indicates the meter multiplier corresponding to the distribution transformer numbered r.

[0111] In this embodiment, the first gateway power indication G of the target distribution line at the time node and the second gateway power indication bG of the time node next to the time node can be obtained through the gateway meter; then based on the first gateway power indication G, the second gateway power indication bG and the meter multiplier μ corresponding to the target distribution line G , determine the power supply data of the target distribution line in the time period corresponding to the time node.

[0112] Specifically, the target distribution line is at time node T n The power supply data e in the corresponding time period can be calculated according to the following formula:

[0113] e=μ G *(bG-G) (3);

[0114] Among them, G represents the gateway meter at time node T n The first gate power reading; bG represents the gate meter at time node T n的 The second checkpoint power reading at the next time node; μ G Indicates the meter multiplier of the gateway meter.

[0115] In this embodiment, based on the total electricity sales data ∑NE corresponding to each time period r The power supply data e of the target distribution line in each time period is used to determine the line loss rate R of the target distribution line at the time node. The specific calculation can be done according to the following formula:

[0116] R n =((e-∑NE r ) / e)*100% (4);

[0117] Among them, R n Represents time node T n Corresponding line loss rate; ∑NE r Represents time node T n The total electricity sales data for the corresponding time period; e represents the time node T n Power supply data for the corresponding time period.

[0118] S101 - 3 : Based on the three-phase load data and line loss rates corresponding to each of the n time nodes, determine a line loss mapping set corresponding to the target distribution line.

[0119] In this embodiment, based on the three-phase load data W corresponding to each of the n time nodes n and line loss rate R n , we can get the line loss mapping set Z corresponding to the target distribution line, which can be expressed by the following formula:

[0120] Z={[W1,R1],[W2,R2],...,[W n ,R n ]} (5);

[0121] Among them, W n Indicates the three-phase load data corresponding to the nth time node; R n Indicates the line loss rate corresponding to the nth time node; [W n ,R n ] represents the mapping relationship between the three-phase load data and line loss rate corresponding to the nth time node.

[0122] In this embodiment, if the same three-phase load data W n , then the same three-phase load data W n The corresponding line loss rate is calculated by arithmetic mean, and the result is used as the three-phase load data W n The corresponding line loss rate.

[0123] In a feasible implementation, the three-phase load state transition probability includes a three-phase active power state transition probability and a three-phase reactive power state transition probability; the three-phase load state transition probability matrix includes a three-phase active power state transition probability matrix and a three-phase reactive power state transition probability matrix; S102 may specifically include the following sub-steps:

[0124] S102-1: Based on the three-phase active power state transition probability of each distribution transformer at the current moment and the three-phase active power state transition probability matrix, determine the three-phase active power state transition probability distribution of each distribution transformer at the next moment; and based on the three-phase active power state transition probability distribution, determine the three-phase active power of each distribution transformer at the next moment.

[0125] S102-2: Based on the three-phase reactive power state transition probability of each distribution transformer at the current moment and the three-phase reactive power state transition probability matrix, determine the three-phase reactive power state transition probability distribution of each distribution transformer at the next moment; and based on the three-phase reactive power state transition probability distribution, determine the three-phase reactive power of each distribution transformer at the next moment.

[0126] S102-3: Determine the three-phase load corresponding to each distribution transformer at the next moment based on the three-phase active power and three-phase reactive power corresponding to each distribution transformer at the next moment.

[0127] In this embodiment, the three-phase active power of each distribution transformer at the next moment is calculated from two aspects: three-phase active power and three-phase reactive power. Firstly, from the perspective of three-phase active power, the three-phase active power of each distribution transformer at the current moment is calculated based on the three-phase active power state transition probability and the three-phase active power state transition probability matrix. Secondly, from the perspective of three-phase reactive power, the three-phase reactive power of each distribution transformer at the next moment is calculated based on the three-phase reactive power state transition probability and the three-phase reactive power state transition probability matrix. Finally, based on the principle that the square of apparent power is equal to the square of active power plus the square of reactive power, the three-phase load of each distribution transformer at the next moment is calculated.

[0128] In a feasible implementation, the distribution line line loss prediction method based on digital twins may further include the following steps:

[0129] S201: Based on the three-phase active power data corresponding to each distribution transformer at n time nodes, determine the first value range corresponding to the sum of the three-phase active power of each distribution transformer at the next moment; and based on the three-phase reactive power data corresponding to each distribution transformer at n time nodes, determine the second value range corresponding to the sum of the three-phase reactive power of each distribution transformer at the next moment.

[0130] In this embodiment, although obtaining the three-phase active power state transition probability distribution and the three-phase reactive power state transition probability distribution can relatively accurately predict the three-phase active power and three-phase reactive power of each distribution transformer at the next moment, certain prediction errors may still exist. For example, the predicted three-phase active power and / or three-phase reactive power of the distribution transformer at the next moment may be abnormal data, causing the three-phase load corresponding to each distribution transformer at the next moment to also be abnormal data. Therefore, by setting the first value range and the second value range, the predicted sum of the three-phase active power and the sum of the three-phase reactive power of each distribution transformer at the next moment can be limited to a reasonable value range.

[0131] Specifically, S201 may include the following sub-steps:

[0132] S201-1: Clustering each distribution transformer based on the three-phase current data of each distribution transformer within a preset historical period to obtain a preset number of clusters; different clusters represent different electricity usage behaviors.

[0133] In this embodiment, the phase information of the smart meter connected to the distribution transformer connected to the distribution line can be collected, and the three-phase current data of each distribution transformer within a preset historical period can be clustered and analyzed. The power consumption behavior of each distribution transformer can be analyzed based on the three-phase current data to divide the L clusters into clusters. The power consumption behavior of the distribution transformers in the same cluster is similar. For example, from a regional perspective, the power consumption behavior of the distribution transformers supplying urban electricity and the distribution transformers supplying rural electricity is different, and the power consumption behavior of new and old communities is different. From the perspective of power consumption habits, different distribution transformers have different peak power consumption periods, and distribution transformers with similar peak power consumption periods can be grouped in the same cluster. From the perspective of the phase information of the smart meter connected to the distribution transformer, distribution transformers with relatively large phase A current can be grouped in the same cluster, distribution transformers with relatively large phase B current can be grouped in the same cluster, distribution transformers with relatively large phase C current can be grouped in the same cluster, and distribution transformers with balanced three-phase current can be grouped in the same cluster.

[0134] In this implementation, N distribution transformers can be divided into L categories based on multiple dimensions and perspectives, with each category forming a single cluster. For example, if both the phase of the distribution transformer smart meter access and electricity usage habits are considered, all distribution transformers with high A-phase current and similar peak usage periods can be grouped into the same cluster.

[0135] S201-2: Based on the preset active power fluctuation range corresponding to each cluster, the three-phase active power corresponding to each distribution transformer in each cluster at n time nodes is cleaned to obtain the effective three-phase active power corresponding to each distribution transformer at n time nodes; based on the preset reactive power fluctuation range corresponding to each cluster, the three-phase reactive power corresponding to each distribution transformer in each cluster at n time nodes is cleaned to obtain the effective three-phase reactive power corresponding to each distribution transformer at n time nodes.

[0136] In this embodiment, considering that different clusters correspond to different electricity consumption behaviors, a corresponding preset active power fluctuation range and a preset reactive power fluctuation range can be set for each cluster, and the three-phase active power and three-phase reactive power of each distribution transformer are cleaned to remove invalid and abnormal data.

[0137] In the specific implementation, the preset active power fluctuation range is set to [P l , P h ], the preset reactive power fluctuation range is [Q l , Q h ].

[0138] At any time point, the three-phase active power Pz corresponding to any distribution transformer is greater than the preset active power fluctuation range [P l , P h ] the upper limit value P of the interval h When the three-phase active power Pz is determined as the upper limit value P h , or, when the three-phase active power Pz corresponding to any distribution transformer is less than the lower limit value P of the preset active power fluctuation interval corresponding to the cluster to which the distribution transformer belongs l When the three-phase active power Pz is determined as the lower limit value P l , and then realize the cleaning of all three-phase active power Pz, and then obtain the effective three-phase active power corresponding to each distribution transformer at n time nodes.

[0139] At any time point, the three-phase reactive power Qz corresponding to any distribution transformer is greater than the preset reactive power fluctuation range [Q l , Q h] the upper limit value Q of the interval h When the three-phase reactive power Qz is determined as the upper limit value Q h , or, when the three-phase reactive power Qz corresponding to any distribution transformer is less than the preset reactive power fluctuation range [Q l , Q h ] the lower limit value Q of the interval l When the three-phase reactive power Qz is determined as the lower limit value Q l , in order to obtain the effective three-phase reactive power corresponding to each distribution transformer at n time nodes.

[0140] S201-3: For any time node, calculate the sum of the effective three-phase active power and the sum of the effective three-phase reactive power of each distribution transformer at the time node to obtain n overall three-phase active powers and n overall three-phase reactive powers respectively.

[0141] In this embodiment, assuming that there are N distribution transformers, the n overall three-phase active powers corresponding to the N distribution transformers at n time nodes can be specifically represented by the following set:

[0142] P={Pz1, Pz2..., Pzn} (6);

[0143] Where n represents the nth time node; Pzn represents the overall three-phase active power of N distribution transformers corresponding to the nth time node.

[0144] In this embodiment, assuming that there are N distribution transformers, the n overall three-phase reactive powers corresponding to the N distribution transformers at n time nodes can be specifically represented by the following set:

[0145] Q={Qz1, Qz2..., Qzn} (7);

[0146] Where n represents the nth time node; Qzn represents the overall three-phase reactive power of N distribution transformers corresponding to the nth time node.

[0147] S201-4: Determine a first value range based on the minimum and maximum values of the n overall three-phase active powers; and determine a second value range based on the minimum and maximum values of the n overall three-phase reactive powers.

[0148] In this embodiment, the minimum value Pzmi n in the set P is taken as the lower limit value of the first value range, and the maximum value Pzmax in the set P is taken as the upper limit value of the first value range, then the first value range [Pzmi n, Pzmax] can be obtained; the minimum value Qzmi n in the set Q is taken as the lower limit value of the first value range, and the maximum value Qzmax in the set Q is taken as the upper limit value of the second value range, then the second value range [Qzmi n, Qzmax] can be obtained.

[0149] In this embodiment, after determining the three-phase reactive power of each distribution transformer at the next moment based on the three-phase reactive power state transition probability distribution, the distribution line loss prediction method based on digital twins may further include the following steps:

[0150] S202: Determine whether the sum of the three-phase active power of each distribution transformer at the next moment is within a first value range.

[0151] S203: If not, repeat the steps of determining the three-phase active power state transfer probability distribution of each distribution transformer at the next moment based on the three-phase active power state transfer probability and the three-phase active power state transfer probability matrix of each distribution transformer at the current moment; and determining the three-phase active power of each distribution transformer at the next moment based on the three-phase active power state transfer probability distribution, until the sum of the three-phase active power of each distribution transformer at the next moment is within the first value range.

[0152] In this embodiment, if the predicted sum of the three-phase active power of the distribution transformer at the next moment, that is, the overall three-phase active power is not within the first value range [Pzmi n, Pzmax], the three-phase active power of each distribution transformer at the next moment is re-predicted until the overall three-phase active power is recalculated and is within the first value range [Pzmi n, Pzmax], and the calculation result is output.

[0153] In this embodiment, after determining the three-phase reactive power of each distribution transformer at the next moment based on the three-phase reactive power state transition probability distribution, the distribution line loss prediction method based on digital twins may further include the following steps:

[0154] S204: Determine whether the sum of the three-phase reactive power of each distribution transformer at the next moment is within a second value range.

[0155] S205: If not, repeat the steps of determining the three-phase reactive power state transfer probability distribution of each distribution transformer at the next moment based on the three-phase reactive power state transfer probability and the three-phase reactive power state transfer probability matrix of each distribution transformer at the current moment; and determining the three-phase reactive power of each distribution transformer at the next moment based on the three-phase reactive power state transfer probability distribution, until the sum of the three-phase reactive power of each distribution transformer at the next moment is within the second value range.

[0156] In this embodiment, if the predicted sum of the three-phase reactive power of the distribution transformer at the next moment, that is, the overall three-phase reactive power is not within the second value range [Qzmi n, Qzmax], the three-phase reactive power of each distribution transformer at the next moment is re-predicted until the overall three-phase reactive power is recalculated and is within the second value range [Qzmi n, Qzmax], and the calculation result is output.

[0157] In this embodiment, based on the first value range [Pzmi n, Pzmax] and the second value range [Qzmi n, Qzmax] calculated according to the actual operating environment of different distribution transformers, the predicted sum of the three-phase active power and the sum of the three-phase reactive power of each distribution transformer at the next moment can be limited to a reasonable value range, further ensuring the rationality and accuracy of the output results and improving the prediction accuracy.

[0158] In the second aspect, based on the same inventive concept, Figure 3 The embodiment of the present application provides a distribution line line loss prediction device 300 based on digital twins, and the distribution line line loss prediction device 300 based on digital twins includes:

[0159] A first determining module 301 is configured to determine a line loss mapping set corresponding to a target distribution line based on three-phase load data, power supply data, and power sales data of the target distribution line within a preset historical period; the line loss mapping set is configured to represent a mapping relationship between the three-phase load of the target distribution line and the line loss rate;

[0160] The second determining module 302 is configured to determine the three-phase load corresponding to each distribution transformer at the next moment based on the three-phase load state transition probability and the three-phase load state transition probability matrix corresponding to each distribution transformer connected to the target distribution line at the current moment;

[0161] The third determining module 303 is configured to determine the sum of the three-phase loads corresponding to each distribution transformer at the next moment as the three-phase load of the target distribution line at the next moment;

[0162] The fourth determining module 304 is configured to determine the line loss rate of the target distribution line at the next moment based on the three-phase load and line loss mapping set of the target distribution line at the next moment.

[0163] In one embodiment of the present application, the first determining module 301 includes:

[0164] The time division submodule is used to divide the preset historical period into n time periods according to the preset time interval, each time period corresponds to a time node; n is a positive integer greater than 1;

[0165] The line loss rate determination submodule is used to obtain the three-phase load data of the target distribution line at any time node; and determine the line loss rate of the target distribution line corresponding to the time node based on the power supply data of the target distribution line in the time period corresponding to the time node and the power sales data of each distribution transformer in the time period;

[0166] The line loss mapping set determination submodule is used to determine the line loss mapping set corresponding to the target distribution line based on the three-phase load data and line loss rate corresponding to each of the n time nodes.

[0167] In one embodiment of the present application, the line loss rate determination submodule includes:

[0168] An electric quantity indication acquisition unit is used to obtain a first electric quantity indication of each distribution transformer at a time node and a second electric quantity indication at a time node next to the time node; and obtain a first checkpoint electric quantity indication of a target distribution line at a time node and a second checkpoint electric quantity indication at a time node next to the time node;

[0169] a total electricity sales data determining unit, configured to determine the electricity sales data of each distribution transformer in a time period corresponding to each time node based on the first electricity indication, the second electricity indication, and the meter multiplier corresponding to each distribution transformer, and to determine the total electricity sales data based on the electricity sales data corresponding to each distribution transformer;

[0170] A power supply data determination unit, configured to determine power supply data of a target distribution line within a time period corresponding to a time node based on the power indication at the first gateway, the power indication at the second gateway, and the meter multiplier corresponding to the target distribution line;

[0171] The line loss rate determining unit is used to determine the line loss rate of the target distribution line corresponding to the time node based on the total power sales data and the power supply data of the target distribution line in the time period corresponding to the time node.

[0172] In one embodiment of the present application, the fourth determining module 304 includes:

[0173] A target three-phase load determination submodule is used to determine a target three-phase load that is closest to the three-phase load of the target distribution line at the next moment in the line loss mapping set;

[0174] A target line loss rate determination submodule is used to determine a target line loss rate corresponding to a target three-phase load based on a line loss mapping set;

[0175] The line loss rate determination submodule is used to determine the target line loss rate as the line loss rate of the target distribution line at the next moment.

[0176] In one embodiment of the present application, the three-phase load state transition probability includes a three-phase active power state transition probability and a three-phase reactive power state transition probability; the three-phase load state transition probability matrix includes a three-phase active power state transition probability matrix and a three-phase reactive power state transition probability matrix;

[0177] The second determining module 302 includes:

[0178] The three-phase active power determination submodule is used to determine the three-phase active power state transition probability distribution of each distribution transformer at the next moment based on the three-phase active power state transition probability of each distribution transformer at the current moment and the three-phase active power state transition probability matrix; and determine the three-phase active power of each distribution transformer at the next moment based on the three-phase active power state transition probability distribution;

[0179] A three-phase reactive power determination submodule is configured to determine the three-phase reactive power state transition probability distribution of each distribution transformer at the next moment based on the three-phase reactive power state transition probability and the three-phase reactive power state transition probability matrix of each distribution transformer at the current moment; and to determine the three-phase reactive power of each distribution transformer at the next moment based on the three-phase reactive power state transition probability distribution;

[0180] The three-phase load determination submodule is used to determine the three-phase load corresponding to each distribution transformer at the next moment based on the three-phase active power and three-phase reactive power corresponding to each distribution transformer at the next moment.

[0181] In one embodiment of the present application, the digital twin distribution line loss prediction device 300 further includes:

[0182] a value range determination module, configured to determine, based on the three-phase active power data corresponding to each distribution transformer at n time nodes, a first value range corresponding to the sum of the three-phase active power of each distribution transformer at the next moment; and to determine, based on the three-phase reactive power data corresponding to each distribution transformer at n time nodes, a second value range corresponding to the sum of the three-phase reactive power of each distribution transformer at the next moment;

[0183] A first judgment module is used to judge whether the sum of the three-phase active power of each distribution transformer at the next moment is within a first value range;

[0184] a first repetitive calculation module, configured to, when the sum of the three-phase active power of each distribution transformer at the next moment is not within the first value range, repeat the steps of determining the three-phase active power state transition probability distribution of each distribution transformer at the next moment based on the three-phase active power state transition probability of each distribution transformer at the current moment and the three-phase active power state transition probability matrix; and determining the three-phase active power of each distribution transformer at the next moment based on the three-phase active power state transition probability distribution, until the sum of the three-phase active power of each distribution transformer at the next moment is within the first value range;

[0185] A second judgment module is used to judge whether the sum of the three-phase reactive power of each distribution transformer at the next moment is within a second value range;

[0186] The second repetitive calculation module is used to repeat the steps of determining the three-phase reactive power state transition probability distribution of each distribution transformer at the next moment based on the three-phase reactive power state transition probability of each distribution transformer at the current moment and the three-phase reactive power state transition probability matrix; and determining the three-phase reactive power of each distribution transformer at the next moment based on the three-phase reactive power state transition probability distribution, when the sum of the three-phase reactive power of each distribution transformer at the next moment is not within the second value range, until the sum of the three-phase reactive power of each distribution transformer at the next moment is within the second value range.

[0187] In one embodiment of the present application, the value range determination module includes:

[0188] A clustering submodule is used to cluster each distribution transformer based on the three-phase current data of each distribution transformer within a preset historical period to obtain a preset number of clusters; different clusters represent different power consumption behaviors;

[0189] The cleaning submodule is used to clean the three-phase active power corresponding to each distribution transformer in each cluster at n time nodes based on the preset active power fluctuation interval corresponding to each cluster, and obtain the effective three-phase active power corresponding to each distribution transformer at n time nodes; based on the preset reactive power fluctuation interval corresponding to each cluster, the three-phase reactive power corresponding to each distribution transformer in each cluster at n time nodes is cleaned, and obtain the effective three-phase reactive power corresponding to each distribution transformer at n time nodes;

[0190] A summation submodule is used to calculate the sum of the effective three-phase active power and the sum of the effective three-phase reactive power of each distribution transformer at any time node to obtain n overall three-phase active powers and n overall three-phase reactive powers respectively;

[0191] The value range determination submodule is used to determine a first value range based on the minimum and maximum values of the n overall three-phase active powers; and to determine a second value range based on the minimum and maximum values of the n overall three-phase reactive powers.

[0192] In one embodiment of the present application, the cleaning submodule includes:

[0193] The three-phase active power cleaning subunit is used to, for any time node, determine the three-phase active power as the upper limit of the interval when the three-phase active power corresponding to any distribution transformer is greater than the upper limit of the interval of the preset active power fluctuation interval corresponding to the cluster to which the distribution transformer belongs, or, when the three-phase active power corresponding to any distribution transformer is less than the lower limit of the interval of the preset active power fluctuation interval corresponding to the cluster to which the distribution transformer belongs, determine the three-phase active power as the lower limit of the interval, so as to obtain the effective three-phase active power corresponding to each distribution transformer at n time nodes;

[0194] The three-phase reactive power cleaning subunit is used to determine the three-phase reactive power as the upper limit value of the interval when the three-phase reactive power corresponding to any distribution transformer is greater than the upper limit value of the preset reactive power fluctuation interval corresponding to the cluster to which the distribution transformer belongs at any time node, or to determine the three-phase reactive power as the lower limit value of the interval when the three-phase reactive power corresponding to any distribution transformer is less than the lower limit value of the preset reactive power fluctuation interval corresponding to the cluster to which the distribution transformer belongs, so as to obtain the effective three-phase reactive power corresponding to each distribution transformer at n time nodes.

[0195] It should be noted that the specific implementation of the distribution line line loss prediction device 300 based on digital twin in the embodiment of the present application refers to the specific implementation of the distribution line line loss prediction method based on digital twin proposed in the first aspect of the aforementioned embodiment of the present application, and will not be repeated here.

[0196] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, apparatus, or computer program products. Thus, embodiments of the present invention may take the form of a fully hardware embodiment, a fully software embodiment, or an embodiment combining software and hardware. Furthermore, embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0197] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the process in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0198] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0199] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0200] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they become aware of the basic creative concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0201] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or terminal device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or terminal device that includes the element.

[0202] The above is a detailed introduction to the distribution line line loss prediction method and device based on digital twin provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A distribution line line loss prediction method based on digital twin, characterized in that: The method comprises: Determining a line loss mapping set corresponding to a target distribution line based on three-phase load data, power supply data, and power sales data of a target distribution line within a preset historical period; the line loss mapping set is used to characterize a mapping relationship between the three-phase load of the target distribution line and a line loss rate; wherein the step of determining the line loss mapping set corresponding to the target distribution line based on the three-phase load data, power supply data, and power sales data of the target distribution line within the preset historical period includes: According to a preset time interval, the preset historical period is divided into n time periods, each time period corresponds to a time node; n is a positive integer greater than 1; For any time node, obtain the three-phase load data of the target distribution line at the time node; and determine the line loss rate corresponding to the target distribution line at the time node based on the power supply data of the target distribution line in the time period corresponding to the time node and the power sales data of each distribution transformer in the time period; determine the line loss mapping set corresponding to the target distribution line based on the three-phase load data and line loss rate corresponding to each of the n time nodes; The step of determining the line loss rate of the target distribution line corresponding to the time node based on the power supply data of the target distribution line in the time period corresponding to the time node and the power sales data of each distribution transformer in the time period includes: Obtain a first power indication of each distribution transformer at the time node and a second power indication at a time node next to the time node; and obtain a first checkpoint power indication of the target distribution line at the time node and a second checkpoint power indication at a time node next to the time node; Determine the power sales data of each distribution transformer in the time period corresponding to each of the time nodes based on the first power indication, the second power indication, and the meter multiplier corresponding to each of the distribution transformers, and determine the total power sales data based on the power sales data corresponding to each of the distribution transformers; Determine power supply data of the target distribution line within the time period corresponding to the time node based on the first gateway power indication, the second gateway power indication, and the meter multiplier corresponding to the target distribution line; Determining a line loss rate of the target distribution line corresponding to the time node based on the total power sales data and the power supply data of the target distribution line in the time period corresponding to the time node; Determine the three-phase load at the next moment corresponding to each distribution transformer connected to the target distribution line based on the three-phase load state transition probability and the three-phase load state transition probability matrix corresponding to each distribution transformer at the current moment; Determine the sum of the three-phase loads corresponding to each of the distribution transformers at the next moment as the three-phase load of the target distribution line at the next moment; The line loss rate of the target distribution line at the next moment is determined based on the three-phase load of the target distribution line at the next moment and the line loss mapping set.

2. The distribution line line loss prediction method based on digital twin according to claim 1 is characterized in that: The step of determining the line loss rate of the target distribution line at the next moment based on the three-phase load of the target distribution line at the next moment and the line loss mapping set includes: Determining a target three-phase load closest to the three-phase load of the target distribution line at a next moment in the line loss mapping set; Determining a target line loss rate corresponding to the target three-phase load based on the line loss mapping set; The target line loss rate is determined as the line loss rate of the target power distribution line at the next moment.

3. The distribution line line loss prediction method based on digital twin according to claim 1 is characterized in that: The three-phase load state transfer probability includes a three-phase active power state transfer probability and a three-phase reactive power state transfer probability; the three-phase load state transfer probability matrix includes a three-phase active power state transfer probability matrix and a three-phase reactive power state transfer probability matrix; The step of determining the three-phase load at the next moment corresponding to each distribution transformer connected to the target distribution line based on the three-phase load state transition probability at the current moment and the three-phase load state transition probability matrix includes: Determine the three-phase active power state transition probability distribution of each distribution transformer at the next moment based on the three-phase active power state transition probability of each distribution transformer at the current moment and the three-phase active power state transition probability matrix; and determine the three-phase active power of each distribution transformer at the next moment based on the three-phase active power state transition probability distribution; Determine the three-phase reactive power state transition probability distribution of each distribution transformer at the next moment based on the three-phase reactive power state transition probability and the three-phase reactive power state transition probability matrix of each distribution transformer at the current moment; and determine the three-phase reactive power of each distribution transformer at the next moment based on the three-phase reactive power state transition probability distribution; Based on the three-phase active power and three-phase reactive power corresponding to each distribution transformer at the next moment, the three-phase load corresponding to each distribution transformer at the next moment is determined.

4. The distribution line line loss prediction method based on digital twin according to claim 3 is characterized in that: The method further comprises: Based on the three-phase active power data corresponding to each of the distribution transformers at the n time nodes, determining a first value range corresponding to the sum of the three-phase active power of each of the distribution transformers at the next moment; and based on the three-phase reactive power data corresponding to each of the distribution transformers at the n time nodes, determining a second value range corresponding to the sum of the three-phase reactive power of each of the distribution transformers at the next moment; After determining the three-phase active power of each distribution transformer at a next moment based on the three-phase active power state transition probability distribution, the method further includes: Determining whether the sum of the three-phase active power of each distribution transformer at the next moment is within the first value range; If not, repeating the steps of determining the three-phase active power state transition probability distribution of each distribution transformer at the next moment based on the three-phase active power state transition probability of each distribution transformer at the current moment and the three-phase active power state transition probability matrix; and determining the three-phase active power of each distribution transformer at the next moment based on the three-phase active power state transition probability distribution, until the sum of the three-phase active power of each distribution transformer at the next moment is within the first value range; After the step of determining the three-phase reactive power of each distribution transformer at the next moment based on the three-phase reactive power state transition probability distribution, the method further includes: Determining whether the sum of the three-phase reactive power of each distribution transformer at the next moment is within the second value range; If not, repeat the steps of determining the three-phase reactive power state transfer probability distribution of each distribution transformer at the next moment based on the three-phase reactive power state transfer probability and the three-phase reactive power state transfer probability matrix of each distribution transformer at the current moment; and determining the three-phase reactive power of each distribution transformer at the next moment based on the three-phase reactive power state transfer probability distribution, until the sum of the three-phase reactive power of each distribution transformer at the next moment is within the second value range.

5. The distribution line line loss prediction method based on digital twin according to claim 4 is characterized in that: The steps of determining a first value range corresponding to the sum of the three-phase active power of each distribution transformer at the next moment based on the three-phase active power data corresponding to each distribution transformer at the n time nodes; and determining a second value range corresponding to the sum of the three-phase reactive power of each distribution transformer at the next moment based on the three-phase reactive power data corresponding to each distribution transformer at the n time nodes, include: Based on the three-phase current data of each distribution transformer in the preset historical period, clustering each distribution transformer to obtain a preset number of clusters; different clusters represent different electricity usage behaviors; Based on the preset active power fluctuation interval corresponding to each cluster, the three-phase active power corresponding to each distribution transformer in each cluster at the n time nodes is cleaned to obtain the effective three-phase active power corresponding to each distribution transformer at the n time nodes; based on the preset reactive power fluctuation interval corresponding to each cluster, the three-phase reactive power corresponding to each distribution transformer in each cluster at the n time nodes is cleaned to obtain the effective three-phase reactive power corresponding to each distribution transformer at the n time nodes; For any time node, calculate the sum of the effective three-phase active power and the sum of the effective three-phase reactive power of each distribution transformer at the time node to obtain n overall three-phase active powers and n overall three-phase reactive powers respectively; The first value range is determined based on the minimum value and the maximum value of the n overall three-phase active powers; and the second value range is determined based on the minimum value and the maximum value of the n overall three-phase reactive powers.

6. The distribution line line loss prediction method based on digital twin according to claim 5 is characterized in that: Based on the preset active power fluctuation interval corresponding to each cluster, the three-phase active power corresponding to each distribution transformer in each cluster at the n time nodes is cleaned to obtain the effective three-phase active power corresponding to each distribution transformer at the n time nodes; based on the preset reactive power fluctuation interval corresponding to each cluster, the three-phase reactive power corresponding to each distribution transformer in each cluster at the n time nodes is cleaned to obtain the effective three-phase reactive power corresponding to each distribution transformer at the n time nodes, including: For any time node, when the three-phase active power corresponding to any of the distribution transformers is greater than the upper limit of the preset active power fluctuation interval corresponding to the cluster to which the distribution transformer belongs, the three-phase active power is determined as the upper limit of the interval; or, when the three-phase active power corresponding to any of the distribution transformers is less than the lower limit of the preset active power fluctuation interval corresponding to the cluster to which the distribution transformer belongs, the three-phase active power is determined as the lower limit of the interval, so as to obtain the effective three-phase active power corresponding to each distribution transformer at the n time nodes; For any time node, when the three-phase reactive power corresponding to any of the distribution transformers is greater than the upper limit value of the preset reactive power fluctuation range corresponding to the cluster to which the distribution transformer belongs, the three-phase reactive power is determined as the upper limit value of the interval, or, when the three-phase reactive power corresponding to any of the distribution transformers is less than the lower limit value of the preset reactive power fluctuation range corresponding to the cluster to which the distribution transformer belongs, the three-phase reactive power is determined as the lower limit value of the interval, so as to obtain the effective three-phase reactive power corresponding to each distribution transformer at the n time nodes.

7. A distribution line line loss prediction device based on digital twin, characterized in that: The device comprises: A first determination module is configured to determine a line loss mapping set corresponding to a target distribution line based on three-phase load data, power supply data, and power sales data of the target distribution line within a preset historical period; the line loss mapping set is configured to characterize a mapping relationship between the three-phase load of the target distribution line and the line loss rate; wherein the first determination module includes: A time division submodule is used to divide the preset historical period into n time periods according to a preset time interval, each time period corresponding to a time node; n is a positive integer greater than 1; A line loss rate determination submodule is configured to obtain, for any time node, the three-phase load data of the target distribution line at the time node; and determine the line loss rate of the target distribution line corresponding to the time node based on the power supply data of the target distribution line in the time period corresponding to the time node and the power sales data of each distribution transformer in the time period; A line loss mapping set determination submodule is configured to determine a line loss mapping set corresponding to the target distribution line based on the three-phase load data and line loss rate corresponding to each of the n time nodes; wherein the line loss rate determination submodule includes: An electric quantity indication acquisition unit is configured to acquire a first electric quantity indication of each distribution transformer at the time node and a second electric quantity indication at a time node next to the time node; and acquire a first checkpoint electric quantity indication of the target distribution line at the time node and a second checkpoint electric quantity indication at a time node next to the time node; a total electricity sales data determining unit, configured to determine the electricity sales data of each distribution transformer in the time period corresponding to each of the time nodes based on the first electricity indication, the second electricity indication, and the meter multiplier corresponding to each of the distribution transformers, and determine the total electricity sales data based on the electricity sales data corresponding to each of the distribution transformers; a power supply data determining unit, configured to determine power supply data of the target distribution line in the time period corresponding to the time node based on the first gateway power indication, the second gateway power indication, and the meter multiplier corresponding to the target distribution line; a line loss rate determining unit, configured to determine a line loss rate of the target distribution line corresponding to the time node based on the total power sales data and the power supply data of the target distribution line in the time period corresponding to the time node; A second determination module is configured to determine the three-phase load corresponding to each distribution transformer at the next moment based on the three-phase load state transition probability and the three-phase load state transition probability matrix corresponding to each distribution transformer connected to the target distribution line at the current moment; A third determining module is configured to determine the sum of the three-phase loads corresponding to each of the distribution transformers at the next moment as the three-phase load of the target distribution line at the next moment; The fourth determining module is configured to determine the line loss rate of the target distribution line at the next moment based on the three-phase load of the target distribution line at the next moment and the line loss mapping set.

Images