Electric power emergency resource scheduling method and system based on digital twinning

Abstract

The invention belongs to the technical field of electric power resource scheduling, and provides an electric power emergency resource scheduling method and system based on digital twinning, and the method comprises the steps: dividing a region related to a power grid into a plurality of power grid sub-regions, carrying out the analysis and comparison of each power grid sub-region, finding out a power-off fault region, and carrying out the calculation of the power-off fault region; the power generation demands of all the power failure fault areas are compared with the power generation capacity of existing power generation equipment, whether the existing power generation equipment can meet the power generation demands of all the power failure fault areas or not is judged, power utilization users in the power failure fault areas are classified, and therefore the power supply priority of all the power failure fault areas is judged; according to the method, the problem that power supply cannot be recovered in time in some power failure fault areas with higher power generation requirements due to the fact that existing power generation equipment cannot meet the power generation requirements of all the power failure fault areas is solved, and the reasonability of power emergency dispatching distribution is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of power resource scheduling, and specifically relates to a power emergency resource scheduling method and system based on digital twins. Background Art

[0002] Existing technologies have many problems in identifying power outage fault areas and dispatching power emergency resources. For example, there is a lack of effective methods to scientifically divide the areas involved in the power grid and accurately identify the power outage fault areas. This may result in areas of normal operation being misjudged as fault areas, or some real fault areas being missed, thus affecting the subsequent dispatching of emergency resources. In terms of power emergency resource dispatching, since existing power generation equipment may not meet the power generation needs of all power outage fault areas, existing technologies fail to classify electricity users in the power outage fault areas, lack a reliable basis for determining the power supply priority of each power outage fault area, and fail to allocate power generation equipment to the power outage fault areas in order of power supply priority. This may result in some power outage fault areas with higher power generation needs being unable to restore power in a timely manner, resulting in irrational dispatching and allocation of power emergency resources.

[0003] To this end, the present invention provides a method and system for dispatching power emergency resources based on digital twins. Summary of the Invention

[0004] In order to make up for the deficiencies of the prior art, at least one technical problem raised in the background technology is solved.

[0005] The technical solution adopted by the present invention to solve its technical problem is:

[0006] A method for dispatching power emergency resources based on digital twins, comprising:

[0007] Step 1: Identify the power outage fault area within the area affected by the power grid;

[0008] Step 2: Determine whether the existing power generation equipment can meet the power generation needs of all power outage areas;

[0009] Step 3: If the requirements cannot be met, identify the electricity users involved in each power outage area;

[0010] Step 4: Classify the electricity users in the power outage area into ordinary electricity users and important electricity users;

[0011] Step 5: Determine the power supply priority for each power outage area by analyzing the number and power consumption time of ordinary and important power users in the power outage area, and allocate power generation equipment to the power outage area in order of power supply priority.

[0012] Furthermore, the method of identifying the power failure area is:

[0013] Divide the area involved in the power grid into several power grid sub-areas;

[0014] Obtain the voltage amplitude and branch power of the nodes included in the power grid sub-area;

[0015] The voltage amplitude and branch power variation amplitude of the nodes in the grid sub-area are calculated by correspondingly calculating the voltage amplitude and branch power of the nodes in the grid sub-area with the normal voltage amplitude and normal branch power respectively, thereby obtaining the voltage variation amplitude and branch power variation amplitude of the nodes in the grid sub-area;

[0016] By comparing the voltage variation amplitude of nodes and the power variation amplitude of branches in the grid sub-area with the preset ranges, abnormal nodes and branches are identified;

[0017] By performing quantitative analysis on abnormal nodes and abnormal branches, the power outage fault value is obtained;

[0018] If the power outage fault value is greater than or equal to the power outage fault threshold, the power grid sub-area is a power outage fault area.

[0019] Furthermore, the method of identifying abnormal nodes and abnormal branches is:

[0020] If the voltage variation of a node in a grid sub-region is not within the preset range, the node in the grid sub-region is marked as an abnormal node; otherwise, no action is taken.

[0021] If the power variation amplitude of the branch in the power grid sub-area is not within the preset amplitude range, the branch in the power grid sub-area is marked as an abnormal branch; otherwise, no operation is performed.

[0022] Furthermore, the power failure fault value is obtained in the following manner:

[0023] The ratio of the number of abnormal nodes to all nodes in the power grid sub-area and the ratio of the number of abnormal branches to all branches are calculated, and the sums are obtained to obtain the power outage fault value.

[0024] Furthermore, the process of determining whether the existing power generation equipment can meet the power generation needs of all power outage fault areas is as follows:

[0025] According to the location, model, rated power, maximum output and operating efficiency parameters of the existing power generation equipment, the total available power P of the power generation equipment that can actually be put into operation is calculated. available ;

[0026] Summarize the power of all load nodes in the power outage fault area to obtain the final power demand P of the power outage fault area total ;

[0027] P available With P totalFor comparison, if P available ≥(1+margin)P total , it is considered that the existing power generation equipment can meet the demand; otherwise, it is considered that it cannot meet the demand.

[0028] Furthermore, the process of identifying electricity users involved in each power outage fault area includes:

[0029] Establish the corresponding relationship between electricity users and grid nodes;

[0030] According to the load nodes in the power outage fault area, through the correspondence between electricity users and grid nodes, the information of all electricity users connected to these load nodes is found, and the specific electricity users involved in each power outage fault area are clarified.

[0031] Furthermore, the process of classifying electricity users in the power outage fault area is as follows:

[0032] Collect data on electricity users in the power outage area;

[0033] Divide the electricity user data in the power outage area into a training set and a test set;

[0034] Using the CART algorithm, a decision tree is recursively constructed based on the characteristics of electricity user data to generate a decision tree model;

[0035] The decision tree model is trained and tested using the training set and the test set. After the training and testing are completed, the data of electricity users in the power outage fault area are input into the decision tree model, and the output is whether the electricity user is an ordinary electricity user or an important electricity user.

[0036] Furthermore, the process of determining the power supply priority of each power outage fault area is as follows:

[0037] Counting the number of common electricity users and the number of important electricity users in the power outage fault area, and calculating the ratio of the sum to the total number of electricity users in all power outage fault areas to obtain the ratio of the number of electricity users in the power outage fault area;

[0038] Calculate the ratio of the number of important electricity users in the power outage fault area to the total number of important electricity users in all power outage fault areas to obtain the ratio of the number of important electricity users in the power outage fault area;

[0039] The ratio of the number of electricity users in the power outage fault area is summed with the ratio of the number of important electricity users to obtain the value of electricity users in the power outage fault area;

[0040] The power consumption duration performance value in the power outage fault area is summed with the power user value in the power outage fault area to obtain the power consumption priority coefficient of the power outage fault area;

[0041] Sort all power outage fault areas according to their corresponding power priority coefficients from large to small, and determine the power supply priority of each power outage fault area.

[0042] Furthermore, the power consumption duration performance value in the power outage fault area is obtained in the following manner:

[0043] Obtain the total electricity consumption of all electricity users in the power outage fault area during the historical power consumption cycle, and calculate the ratio of the total electricity consumption of all electricity users in the power outage fault area during the historical power consumption cycle to obtain the power consumption time ratio of the electricity users in the power outage fault area;

[0044] Obtain the total electricity consumption of all important electricity users in the power outage fault area during the historical power consumption cycle, and calculate the ratio of the total electricity consumption of all important electricity users in the power outage fault area during the historical power consumption cycle to obtain the power consumption time ratio of the important electricity users in the power outage fault area;

[0045] The power consumption duration ratio of power users in the power outage fault area is summed with the power consumption duration ratio of important power users to obtain the power consumption duration performance value in the power outage fault area.

[0046] A digital twin-based power emergency resource dispatching system includes the following modules:

[0047] Power outage fault area identification module: identifies the power outage fault area within the area covered by the power grid;

[0048] Power generation demand judgment module: determines whether the existing power generation equipment can meet the power generation needs of all power outage fault areas;

[0049] Electricity user identification module: If the requirements cannot be met, identify the electricity users involved in each power outage fault area;

[0050] Electricity user classification module: classifies electricity users in the power outage area into ordinary electricity users and important electricity users;

[0051] Emergency resource scheduling module: By analyzing the number and power consumption time of ordinary and important electricity users in the power outage fault area, the power supply priority of each power outage fault area is determined, and power generation equipment is allocated to the power outage fault area in order of power supply priority.

[0052] The beneficial effects of the present invention are as follows:

[0053] By dividing the area involved in the power grid into several sub-areas to identify the power outage fault area, and by classifying the electricity users in the power outage fault area to determine the power supply priority of each power outage fault area, power is supplied to each power outage fault area in turn according to the power supply priority. This solves the problem that when the existing power generation equipment cannot meet the power generation needs of all power outage fault areas, the power outage fault areas with higher power generation needs cannot be restored in time, and improves the rationality of power emergency resource scheduling and allocation. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The present invention will be further described below with reference to the accompanying drawings.

[0055] Figure 1 This is a flowchart of the steps of a method for dispatching power emergency resources based on digital twins according to an embodiment of the present invention;

[0056] Figure 2 This is a flowchart of a digital twin-based power emergency resource dispatching system in an embodiment of the present invention. DETAILED DESCRIPTION

[0057] In order to make the technical means, creative features, objectives and effects achieved by the present invention easier to understand, the present invention is further described below in conjunction with specific implementation methods.

[0058] Example 1

[0059] See also Figure 1 As shown, a method for dispatching power emergency resources based on digital twins according to an embodiment of the present invention includes the following steps:

[0060] Step 1: Identify the power outage fault area within the area affected by the power grid;

[0061] In step 1, the grid area refers to a geographical area with a specific power supply relationship defined by the production, transmission, distribution and use of electricity, taking into account multiple factors such as power source, transmission, distribution and load;

[0062] In step 1, the process of identifying the power outage fault area within the area involved in the power grid includes:

[0063] Divide the area involved in the power grid into several power grid sub-areas;

[0064] The division of power grid sub-regions includes but is not limited to geographical location and spatial location, for example:

[0065] Division based on administrative boundaries: Taking the town-level power grid as an example, the town-level power grid is divided into several large sub-areas based on the administrative boundaries of streets and townships. If there are multiple streets in the town, each street can be divided into an independent power grid sub-area; for townships, the power grid sub-areas are also divided based on their administrative boundaries. Within each street or township power grid sub-area, it is further subdivided into smaller power grid sub-areas based on the administrative boundaries of the village.

[0066] Based on grid hierarchy: The grid is divided according to the voltage level and the hierarchical relationship of power transmission. It can usually be divided into high-voltage transmission sub-areas, medium-voltage distribution sub-areas, and low-voltage distribution sub-areas. With substations of different voltage levels as the core, the transmission lines, distribution lines, and power users within their power supply range are divided into a grid sub-area;

[0067] Based on any power grid sub-area, obtaining operating data of nodes included in the power grid sub-area, wherein the operating data includes voltage amplitude and branch power;

[0068] The voltage amplitudes of the nodes and the branch powers of the branches included in the grid sub-area are compared with the voltage amplitudes and branch powers of the nodes and branches included in the grid sub-area under normal operation power flow distribution. The specific process is as follows:

[0069] The voltage amplitude and branch power of the nodes included in the power grid sub-area under normal operating power flow distribution are marked as normal voltage amplitude and normal branch power respectively;

[0070] The voltage amplitude and branch power variation amplitude of the nodes in the grid sub-area are calculated by correspondingly calculating the voltage amplitude and branch power of the nodes in the grid sub-area with the normal voltage amplitude and normal branch power respectively, thereby obtaining the voltage variation amplitude and branch power variation amplitude of the nodes in the grid sub-area;

[0071] The voltage variation is the difference between the node voltage and the normal voltage, and the branch power variation is the difference between the branch power and the normal branch power.

[0072] Compare the voltage variation amplitudes and branch power variation amplitudes of the nodes in the grid sub-area with the corresponding preset amplitude ranges respectively;

[0073] If the voltage variation of a node in a grid sub-region is not within the preset range, the node in the grid sub-region is marked as an abnormal node; otherwise, no action is taken.

[0074] If the power variation of a branch in the power grid sub-area is not within the preset range, the branch in the power grid sub-area is marked as an abnormal branch. Otherwise, no operation is performed.

[0075] Calculate the ratio of the number of abnormal nodes to all nodes in the power grid sub-area and the ratio of the number of abnormal branches to all branches, and sum them up to obtain the power outage fault value;

[0076] comparing the power outage fault value with a power outage fault value threshold;

[0077] If the power outage fault value is greater than or equal to the power outage fault threshold, it means that there are multiple abnormal nodes and multiple abnormal branches in the power grid sub-area, which means that the power grid sub-area is a power outage fault area;

[0078] If the power outage fault value is less than the power outage fault value threshold, it means that there are a small number of abnormal nodes and a small number of abnormal branches in the power grid sub-area, which means that the power grid sub-area is a non-power outage fault area;

[0079] In step 1, the process of calculating the voltage amplitude and branch power of the nodes included in the grid sub-area under normal operating power flow distribution includes:

[0080] Number all nodes in the power grid and nodes within the divided sub-regions. Create an index table that maps the overall node numbers of the power grid to the node numbers within the sub-regions, clarifying which overall node numbers belong to specific sub-regions. Create a branch list, where each element represents a branch and contains the branch's starting and ending node information. For the divided sub-regions, traverse the nodes within the sub-regions to find all branches connecting these nodes. Number the branches within the overall power grid and establish a correspondence between the overall branch numbers and the branches within the sub-regions.

[0081] The power flow calculation of the entire power grid is carried out, taking the Newton-Raphson method as an example, according to the node power balance equation of the power grid Establish the power flow equations of the entire power grid, where P i and Q i are the injected active power and reactive power of node i, U i and U j Represents the voltage phasors of nodes i and j, Y ij Represents the admittance matrix element between nodes i and j, and establishes the power flow equations for the entire power grid. After linearizing the nonlinear power flow equations through Taylor series expansion, the voltage phasor U of all nodes in the entire power grid is obtained by iterative solution. i =U i ∠δ i , and then get the voltage amplitude U of all nodes i At the same time, according to the node voltages at both ends of the branch and the branch parameters, the formula and Calculate the active power P of all branches ij and reactive power Q ij, that is, branch power, where G ij is the conductance of branch ij, B ij is the susceptance of branch ij, δ ij is the voltage phase angle difference between node i and node j;

[0082] After the overall power flow calculation is completed, the node number list of the power grid sub-area is traversed, and the voltage phasor of the corresponding node is extracted from the overall power flow calculation result according to the corresponding overall node number, and then its voltage amplitude U is obtained. i ,According to the number index of the branch in the overall branch of the power grid sub-area, the branch power of the corresponding branch is extracted from the overall power flow calculation results;

[0083] For example, assuming that the number of grid nodes is 5 and the divided grid sub-area includes three of these nodes, the specific demonstration process of calculating the voltage amplitude and branch power of the nodes included in the grid sub-area under normal operating power flow distribution is as follows:

[0084] All five nodes in the power grid are numbered as node 1, node 2, node 3, node 4, and node 5. The divided power grid sub-areas include node 1, node 2, and node 3. The nodes in these three power grid sub-areas are marked and indexed as follows:

[0085] |Grid sub-area number|Node number within the sub-area|Corresponding overall node number|;

[0086] |1|1|1|;

[0087] |1|2|2|;

[0088] |1|3|3|;

[0089] Assume that the branches of the power grid are connected as follows: branch 1 connects nodes 1 and 2; branch 2 connects nodes 2 and 3; branch 3 connects nodes 3 and 4; and branch 4 connects nodes 4 and 5. Create a branch list, where each element contains the starting and ending node information of the branch:

[0090] Branch 1: [1,2];

[0091] Branch 2: [2,3];

[0092] Branch 3: [3,4];

[0093] Branch 4: [4,5];

[0094] For the divided power grid sub-area (including nodes 1, 2, and 3), traverse the nodes in the power grid sub-area and find the branches connecting these nodes as branch 1 and branch 2. Number the four branches in the entire power grid, setting branch 1 to 1, branch 2 to 2, branch 3 to 3, and branch 4 to 4. The corresponding relationship between the overall branch number and the branches in the power grid sub-area is established as follows:

[0095] |Grid sub-area number|Branch number within the sub-area|Corresponding overall branch number|;

[0096] |1|1|1|;

[0097] |1|2|2|;

[0098] Using the Newton-Raphson method, according to the node power balance equation of the power grid (where n=5, P i and Q i are the injected active power and reactive power of node i, Y ij is the node admittance matrix element, is the conjugate of the voltage phasor at node j), and the power flow equations for the entire power grid are established;

[0099] Assuming that the parameters such as the injected power of each node and the node admittance matrix elements are known, the nonlinear power flow equation is linearized by Taylor series expansion and then solved iteratively. Assuming that the voltage phasors of all nodes in the entire power grid are obtained through iterative calculation, they are:

[0100] Node 1: U1 = 1.05∠0°;

[0101] Node 2: U2 = 1.03∠-5°;

[0102] Node 3: U3 = 1.02∠-8°;

[0103] Node 4: U4 = 1.00∠-12°;

[0104] Node 5: U5 = 0.98∠-15°;

[0105] Then the voltage amplitudes of all nodes are obtained as follows: U1 = 1.05, U2 = 1.03, U3 = 1.02, U4 = 1.00, U5 = 0.98;

[0106] Known branch parameters (assuming branch 1 has a conductivity of G 12 、Susceptance B 12 , the conductance G of branch 2 23 、Susceptance B 23 etc.), according to the formula and Calculate the active power and reactive power of all branches (where δij =δ i -δ j is the voltage phase angle difference between nodes i and j). Assume that the calculation result is:

[0107] Branch 1: Active power P 12 =0.2, reactive power Q 12 =0.1;

[0108] Branch 2: Active power P 23 =0.15, reactive power Q 23 =0.08;

[0109] Branch 3: Active power P 34 =0.1, reactive power Q 34 =0.05;

[0110] Branch 4: Active power P 45 =0.08, reactive power Q 45 =0.04;

[0111] After the overall power flow calculation is completed, the node number list of the power grid sub-area (node 1, node 2, node 3) is traversed. According to the corresponding overall node number, the voltage phasor of the corresponding node is extracted from the overall power flow calculation result, and then the voltage amplitude of the corresponding node is obtained:

[0112] The voltage amplitude at node 1 is 1.05;

[0113] The voltage amplitude at node 2 is 1.03;

[0114] The voltage amplitude at node 3 is 1.02;

[0115] According to the number index of the branch in the overall branch of the power grid sub-area (branch 1 and branch 2 correspond to overall branch numbers 1 and 2), the branch power of the corresponding branch is extracted from the overall power flow calculation results:

[0116] Active power P of branch 1 12 =0.2, reactive power Q 12 =0.1;

[0117] Active power P of branch 2 23 =0.15, reactive power Q 23 =0.08;

[0118] Step 2: Determine whether the existing power generation equipment can meet the power generation needs of all power outage areas;

[0119] In step 2, the process of determining whether the existing power generation equipment can meet the power generation needs of all power outage fault areas is as follows:

[0120] Obtain the location, model, rated power, maximum output, operating efficiency and other parameters of the existing power generation equipment, and calculate the total available power P of the power generation equipment that can actually be put into operation available ;

[0121] Summarize the power of all load nodes in the power outage fault area to obtain the final power demand P of the area total ;

[0122] P available With P total For comparison, while considering a certain margin (such as 10%-20%), if P available ≥(1+margin)P total , it is considered that the existing power generation equipment can meet the demand; otherwise, it is considered that it cannot meet the demand.

[0123] For example, assume that a power grid identifies a power outage area and there are four power generation devices available around the area. The parameters of these four devices are:

[0124] (location, rated power, maximum output coefficient, operating efficiency, available power generation P available-i )

[0125] Equipment 1: (Substation A, 5MW, 0.9 (derating 10%), 0.85, 5×0.9×0.85=3.825MW);

[0126] Equipment 2: (wind farm B, 3MW, 0.7 (insufficient wind speed), 0.9, 3×0.7×0.9=1.89MW);

[0127] Equipment 3: (PV power station C, 2MW, 0.6 (cloudy day), 0.88, 2×0.6×0.88=1.056MW);

[0128] Equipment 4: (Gas power plant D, 4MW, 1.0 (full power), 0.92, 4×1.0×0.92=3.68MW);

[0129] Total available power generation P available calculate:

[0130]

[0131] The power outage fault area contains three types of load nodes, and the aggregate power is as follows:

[0132] (Load type, number of nodes, single node power, total power P type );

[0133] (Residential load, 100 households, 5kW / household, 100×5kW=0.5MW);

[0134] (commercial load, 20 households, 50kW / household, 20×50kW=1MW);

[0135] (Industrial load, 5 companies, 1MW / company, 5×1MW=5MW);

[0136] Final electricity demand calculation:

[0137] P total =0.5+1+5=6.5MW

[0138] Set the margin coefficient k = 0.15 and calculate the demand threshold:

[0139] (1+k)×P total =(1+0.15)×6.5MW=7.475MW

[0140] The total available power generation power P of the power generation equipment that can actually be put into operation available The final power demand P in the power outage fault area total To compare:

[0141] P available =10.451MW>7.475MW

[0142] Therefore, it is determined that the existing power generation equipment can meet the power generation demand of the power outage fault area.

[0143] Step 3: If the requirements cannot be met, identify the electricity users involved in each power outage area;

[0144] In step three, the process of identifying electricity users involved in each power outage fault area includes:

[0145] Establish the corresponding relationship between electricity users and grid nodes;

[0146] Based on the load nodes within the identified power outage fault area, the corresponding relationship between electricity users and grid nodes is used to find out the information of all electricity users connected to these load nodes, including user name, address, electricity usage type, etc., so as to clarify the specific electricity users involved in each power outage fault area.

[0147] In step three, the correspondence between electricity users and grid nodes is established in the following manner:

[0148] Collect user information and the topology of the power grid, the number, location, and type information of each load node, determine which load node each user is connected to, and thus establish a corresponding relationship between electricity users and power grid nodes.

[0149] Step 4: Classify the electricity users in the power outage area into ordinary electricity users and important electricity users;

[0150] The process of classifying the electricity users in the power outage area into ordinary electricity users and important electricity users in step 4 includes:

[0151] Collect data on electricity users in the power outage area, including historical electricity consumption, user characteristics, and predicted power outage losses;

[0152] Divide the electricity user data in the power outage area into training sets and test sets according to a certain ratio;

[0153] Using the CART algorithm, a decision tree is recursively constructed based on three features: historical power consumption, user characteristics, and predicted power outage losses, generating a decision tree model.

[0154] The decision tree model is trained using the training set and test set. The model performance is evaluated using the test set data. Accuracy, precision, recall, and F1 value are calculated as evaluation indicators. Accuracy refers to the ratio of correctly classified samples to the total number of samples. Precision refers to the ratio of samples predicted to a certain category that actually belong to that category. Recall refers to the ratio of samples actually belonging to a certain category that are correctly predicted to that category. F1 value refers to the harmonic mean of precision and recall, which is used to comprehensively measure the performance of the model.

[0155] The constructed decision tree model is deployed in practical applications. The data of electricity users in the new power outage fault area is input into the model. The model will classify the electricity user based on the rules learned during training, historical electricity consumption, user nature and predicted power outage losses, and output the prediction result of whether the electricity user is an ordinary electricity user or an important electricity user.

[0156] In step 4, the process of building a decision tree model using the CART algorithm includes:

[0157] Analyze the relationship between historical electricity consumption and power outage losses, and use a linear regression model to predict the power outage losses based on historical electricity consumption;

[0158] For the three features of historical electricity consumption, user nature, and predicted power outage loss, the Gini coefficient of each feature is calculated. The feature with the smallest Gini coefficient is selected as the root node partition feature, and the partition threshold is determined. The Gini coefficient is an indicator used to measure data purity and is used as the basis for decision tree node splitting.

[0159] Repeatedly calculate the Gini coefficient for each child node, select the feature with the smallest Gini coefficient, and determine the threshold for partitioning until the tree is built.

[0160] For example, let's assume there's a power supply area that contains data on various types of electricity users. We collected information about 1,000 electricity users, including their nature (residential, commercial, industrial, and public service), their average annual electricity consumption over the past three years (in megawatt-hours, MWh), and the losses caused by a 24-hour power outage (in 10,000 yuan).

[0161] By analyzing historical data, we found a certain linear relationship between power outage losses and historical electricity consumption. Using a linear regression model, we used historical electricity consumption as the independent variable and power outage losses as the dependent variable to train the model. For example, the regression equation we obtained is: power outage losses = 0.25 × historical annual average electricity consumption - 0.1;

[0162] Calculate the Gini coefficient for each feature for the classification (critical electricity users and ordinary electricity users). Assume that the calculation shows that the Gini coefficient for historical average annual electricity consumption is the smallest. Use historical average annual electricity consumption as the first dividing feature and 50MWh as the threshold to divide electricity users into two groups: those with historical average annual electricity consumption less than 50MWh and those with historical average annual electricity consumption greater than or equal to 50MWh.

[0163] For branches with historical annual average electricity consumption less than 50MWh, we further calculated the Gini coefficient of user nature and predicted power outage losses. If we found that the Gini coefficient of user nature was small, we would use user nature as the classification feature. Residential and public service users were classified as ordinary electricity users; commercial and industrial users were classified as important electricity users.

[0164] For branches with historical annual average electricity consumption greater than or equal to 50MWh, the predicted power outage loss is used as the classification feature. Assuming a threshold of 100,000 yuan, users with predicted power outage losses greater than or equal to 100,000 yuan are classified as important electricity users, and those with predicted power outage losses less than 100,000 yuan are classified as ordinary electricity users.

[0165] The data from 1,000 electricity users is divided into 70% as a training set and 30% as a test set. The decision tree model is trained using the training set data, and the model performance is evaluated using the test set data. Accuracy, precision, recall, and F1 value are selected as evaluation metrics. Assuming the accuracy is 82%, the precision is 80%, the recall is 85%, and the F1 value is 82.5%, indicating that the model has a certain degree of reliability and effectiveness.

[0166] Consider a new electricity user, identified as an industrial user with a historical average annual electricity consumption of 80 MWh. First, a linear regression model predicts the power outage loss as: 0.25 × 80 - 0.1 = 199,000 yuan. This user's data is then encoded and fed into a trained decision tree model. The model first determines whether the historical average annual electricity consumption is greater than or equal to 50 MWh. It then determines whether the predicted power outage loss of 199,000 yuan is greater than or equal to 100,000 yuan, ultimately classifying the user as a critical user.

[0167] Step 5: Determine the power supply priority for each power outage area by analyzing the number of common and important power users within the power outage area and their power consumption time. Allocate power generation equipment to each power outage area in order of power supply priority.

[0168] The process of determining the power supply priority of each power outage fault area in step 5 includes:

[0169] Based on any power outage fault area;

[0170] Count the number of ordinary electricity users and the number of important electricity users in the power outage fault area, add them up, and get the total number of electricity users in the power outage fault area. Then calculate the ratio of the number of electricity users in the power outage fault area to the total number of electricity users in all power outage fault areas to get the ratio of the number of electricity users in the power outage fault area.

[0171] Calculate the ratio of the number of important electricity users in the power outage fault area to the total number of important electricity users in all power outage fault areas to obtain the ratio of the number of important electricity users in the power outage fault area;

[0172] The ratio of the number of electricity users in the power outage fault area is summed with the ratio of the number of important electricity users to obtain the value of electricity users in the power outage fault area;

[0173] Based on any power outage fault area;

[0174] Obtain the electricity usage duration of all electricity users in the power outage fault area during the historical power usage cycle, and calculate the ratio of the electricity usage duration of all electricity users in the power outage fault area to the electricity usage duration ratio of the electricity users in the power outage fault area;

[0175] Obtain the electricity usage duration of all important electricity users in the power outage fault area during the historical power usage cycle, and calculate the ratio of the electricity usage duration of all important electricity users in the power outage fault area to the electricity usage duration ratio of important electricity users in the power outage fault area;

[0176] The power consumption duration ratio of power users in the power outage fault area is summed with the power consumption duration ratio of important power users to obtain the power consumption duration performance value in the power outage fault area;

[0177] The power consumption duration performance value in the power outage fault area is summed with the power user value in the power outage fault area to obtain the power consumption priority coefficient of the power outage fault area;

[0178] Sort all power outage fault areas according to their corresponding power priority coefficients from large to small, and determine the power supply priority of each power outage fault area;

[0179] In step 5, the method of allocating power generation equipment to the power outage fault area in order of power supply priority is as follows:

[0180] According to the power supply priority of each power outage fault area, power generation equipment is allocated to the power outage fault area in turn. For example, power generation equipment is allocated first to the power outage fault area with the highest power supply priority. After the allocated power generation equipment can meet the power demand of the power outage fault area with the highest power supply priority, power generation equipment is allocated to the next power outage fault area according to the power supply priority until all power generation equipment are allocated.

[0181] The technical solutions and benefits of the embodiments of the present application are: identifying the power outage fault areas within the area involved in the power grid, judging whether the existing power generation equipment can meet the power generation needs of all power outage fault areas, and if not, identifying the electricity users involved in each power outage fault area, classifying the electricity users in the power outage fault area, and classifying the electricity users into ordinary electricity users and important electricity users. By performing a quantity analysis and a power consumption time analysis on ordinary electricity users and important electricity users in the power outage fault area, the power supply priority of each power outage fault area is determined, and power generation equipment is allocated to the power outage fault area in order according to the power supply priority. The present application identifies the power outage fault areas by dividing the area involved in the power grid into several power grid sub-areas, and determines the power supply priority of each power outage fault area by classifying the electricity users in the power outage fault area, and supplies power to each power outage fault area in order according to the power supply priority, thereby solving the problem that when the existing power generation equipment cannot meet the power generation needs of all power outage fault areas, the power outage fault areas with higher power generation needs cannot be restored in time, thereby improving the rationality of the scheduling and allocation of power emergency resources.

[0182] Example 2

[0183] See also Figure 2 As shown, a digital twin-based power emergency resource dispatching system according to an embodiment of the present invention includes:

[0184] Power outage fault area identification module: identifies the power outage fault area within the area covered by the power grid;

[0185] The grid area refers to a geographical area with a specific power supply relationship defined by the production, transmission, distribution and use of electricity, taking into account multiple factors such as power source, transmission, distribution and load;

[0186] The process of identifying the power outage fault area in the area involved in the power grid includes:

[0187] Divide the area involved in the power grid into several power grid sub-areas;

[0188] The division of power grid sub-regions includes but is not limited to geographical location and spatial location;

[0189] Based on any power grid sub-area, obtaining operating data of nodes included in the power grid sub-area, wherein the operating data includes voltage amplitude and branch power;

[0190] The voltage amplitudes of the nodes and the branch powers of the branches included in the grid sub-area are compared with the voltage amplitudes and branch powers of the nodes and branches included in the grid sub-area under normal operation power flow distribution. The specific process is as follows:

[0191] The voltage amplitude and branch power of the nodes included in the power grid sub-area under normal operating power flow distribution are marked as normal voltage amplitude and normal branch power respectively;

[0192] The voltage amplitude and branch power variation amplitude of the nodes in the grid sub-area are calculated by correspondingly calculating the voltage amplitude and branch power of the nodes in the grid sub-area with the normal voltage amplitude and normal branch power respectively, thereby obtaining the voltage variation amplitude and branch power variation amplitude of the nodes in the grid sub-area;

[0193] The voltage variation is the difference between the node voltage and the normal voltage, and the branch power variation is the difference between the branch power and the normal branch power.

[0194] Compare the voltage variation amplitudes and branch power variation amplitudes of the nodes in the grid sub-area with the corresponding preset amplitude ranges respectively;

[0195] If the voltage variation of a node in a grid sub-region is not within the preset range, the node in the grid sub-region is marked as an abnormal node; otherwise, no action is taken.

[0196] If the power variation of a branch in the power grid sub-area is not within the preset range, the branch in the power grid sub-area is marked as an abnormal branch. Otherwise, no operation is performed.

[0197] Calculate the ratio of the number of abnormal nodes to all nodes in the power grid sub-area and the ratio of the number of abnormal branches to all branches, and sum them up to obtain the power outage fault value;

[0198] comparing the power outage fault value with a power outage fault value threshold;

[0199] If the power outage fault value is greater than or equal to the power outage fault threshold, it means that there are multiple abnormal nodes and multiple abnormal branches in the power grid sub-area, which means that the power grid sub-area is a power outage fault area;

[0200] If the power outage fault value is less than the power outage fault value threshold, it means that there are a small number of abnormal nodes and a small number of abnormal branches in the power grid sub-area, which means that the power grid sub-area is a non-power outage fault area;

[0201] Power generation demand judgment module: determines whether the existing power generation equipment can meet the power generation needs of all power outage fault areas;

[0202] The process of determining whether the existing power generation equipment can meet the power generation needs of all power outage fault areas is as follows:

[0203] Obtain the location, model, rated power, maximum output, operating efficiency and other parameters of the existing power generation equipment, and calculate the total available power P of the power generation equipment that can actually be put into operation available ;

[0204] Summarize the power of all load nodes in the power outage fault area to obtain the final power demand P of the area total ;

[0205] P available With P total For comparison, while considering a certain margin (such as 10%-20%), if P available ≥(1+margin)P total , it is considered that the existing power generation equipment can meet the demand; otherwise, it is considered that it cannot meet the demand;

[0206] Electricity user identification module: If the requirements cannot be met, identify the electricity users involved in each power outage fault area;

[0207] The process of identifying electricity users involved in each power outage fault area includes:

[0208] Establish the corresponding relationship between electricity users and grid nodes;

[0209] Based on the identified load nodes within the power outage fault area, the corresponding relationship between electricity users and grid nodes is used to find all the electricity user information connected to these nodes, including user name, address, electricity type, etc., so as to clarify the specific electricity users involved in each power outage fault area;

[0210] The method of establishing the correspondence between electricity users and grid nodes is:

[0211] Collect user information and the topology of the power grid, the number, location, and type information of each load node, determine which load node each user is connected to, and thus establish a corresponding relationship between electricity users and power grid nodes.

[0212] Electricity user classification module: classifies electricity users in the power outage area into ordinary users and important users;

[0213] Collect relevant data on electricity users in the power outage area, including historical electricity consumption, user characteristics, and predicted power outage losses;

[0214] Divide the electricity user data in the power outage area into training sets and test sets according to a certain ratio;

[0215] Using the CART algorithm, a decision tree is recursively constructed based on three features: historical power consumption, user characteristics, and predicted power outage losses, generating a decision tree model.

[0216] The decision tree model is trained using the training set data, and the model performance is evaluated using the test set data. Accuracy, precision, recall, and F1 value are calculated as evaluation indicators. Accuracy refers to the ratio of correctly classified samples to the total number of samples, precision refers to the ratio of samples predicted to a certain category that actually belong to that category, recall refers to the ratio of samples actually belonging to a certain category that are correctly predicted to that category, and F1 value refers to the harmonic mean of precision and recall, which is used to comprehensively measure the performance of the model.

[0217] The constructed decision tree model is deployed in real-world applications. The model inputs data about electricity users in a new outage area. The model then uses the learned rules to classify the user based on historical electricity consumption, user attributes, and predicted outage losses, and outputs a prediction of whether the user is a regular or critical user.

[0218] Emergency resource scheduling module: By analyzing the number and power consumption time of ordinary and important power users in the power outage fault area, the power supply priority of each power outage fault area is determined, and power generation equipment is allocated to the power outage fault area in order of power supply priority;

[0219] The process of determining the power supply priority for each power outage fault area includes:

[0220] Based on any power outage fault area;

[0221] Count the number of ordinary electricity users and the number of important electricity users in the power outage fault area, add them up, and get the total number of electricity users in the power outage fault area. Then calculate the ratio of the number of electricity users in the power outage fault area to the total number of electricity users in all power outage fault areas to get the ratio of the number of electricity users in the power outage fault area.

[0222] Calculate the ratio of the number of important electricity users in the power outage fault area to the total number of important electricity users in all power outage fault areas to obtain the ratio of the number of important electricity users in the power outage fault area;

[0223] The ratio of the number of electricity users in the power outage fault area is summed with the ratio of the number of important electricity users to obtain the value of electricity users in the power outage fault area;

[0224] Based on any power outage fault area;

[0225] Obtain the electricity usage duration of all electricity users in the power outage fault area during the historical power usage cycle, and calculate the ratio of the electricity usage duration of all electricity users in the power outage fault area to the electricity usage duration ratio of the electricity users in the power outage fault area;

[0226] Obtain the electricity usage duration of all important electricity users in the power outage fault area during the historical power usage cycle, and calculate the ratio of the electricity usage duration of all important electricity users in the power outage fault area to the electricity usage duration ratio of important electricity users in the power outage fault area;

[0227] The power consumption duration ratio of power users in the power outage fault area is summed with the power consumption duration ratio of important power users to obtain the power consumption duration performance value in the power outage fault area;

[0228] The power consumption duration performance value in the power outage fault area is summed with the power user value in the power outage fault area to obtain the power consumption priority coefficient of the power outage fault area;

[0229] Sort all power outage fault areas according to their corresponding power priority coefficients from large to small, and determine the power supply priority of each power outage fault area;

[0230] The method of allocating power generation equipment to power outage fault areas in order of power supply priority is as follows:

[0231] According to the power supply priority of each power outage fault area, power generation equipment is allocated to the power outage fault area in turn. For example, power generation equipment is allocated first to the power outage fault area with the highest power supply priority. After the allocated power generation equipment can meet the power demand of the power outage fault area with the highest power supply priority, power generation equipment is allocated to the next power outage fault area according to the power supply priority until all power generation equipment are allocated.

[0232] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the foregoing embodiments. The foregoing embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for dispatching power emergency resources based on digital twins, characterized by: include: Step 1: Identify the power outage fault area within the area affected by the power grid; Step 2: Determine whether the existing power generation equipment can meet the power generation needs of all power outage areas; Step 3: If the requirements cannot be met, identify the electricity users involved in each power outage area; Step 4: Classify the electricity users in the power outage area into ordinary electricity users and important electricity users; Step 5: Determine the power supply priority for each power outage area by analyzing the number and power consumption time of ordinary and important power users in the power outage area, and allocate power generation equipment to the power outage area in order of power supply priority.

2. The method for dispatching power emergency resources based on digital twins according to claim 1, characterized in that: The power failure area identification method is: Divide the area involved in the power grid into several power grid sub-areas; Obtain the voltage amplitude and branch power of the nodes included in the power grid sub-area, and calculate the voltage change amplitude and branch power change amplitude corresponding to the normal value; Compare the voltage variation amplitude of nodes and branch power variation amplitude in the grid sub-area with the preset ranges to identify abnormal nodes and branches; By performing quantitative analysis on abnormal nodes and abnormal branches, the power outage fault value is obtained; If the power outage fault value is greater than or equal to the power outage fault threshold, the power grid sub-area is a power outage fault area.

3. The method for dispatching power emergency resources based on digital twins according to claim 2, characterized in that: The method for identifying abnormal nodes and abnormal branches is: If the voltage variation amplitude of a node in the power grid sub-area is not within the preset amplitude range, the node in the power grid sub-area is marked as an abnormal node; If the power variation amplitude of a branch in the power grid sub-area is not within a preset amplitude range, the branch in the power grid sub-area is marked as an abnormal branch.

4. The method for dispatching power emergency resources based on digital twins according to claim 2, characterized in that: The method for obtaining the power failure fault value is as follows: The ratio of the number of abnormal nodes to all nodes in the power grid sub-area and the ratio of the number of abnormal branches to all branches are calculated, and the sums are obtained to obtain the power outage fault value.

5. The method for dispatching power emergency resources based on digital twins according to claim 1, characterized in that: The process of determining whether the existing power generation equipment can meet the power generation needs of all power outage fault areas is as follows: According to the location, model, rated power, maximum output and operating efficiency parameters of the existing power generation equipment, the total available power P of the power generation equipment that can actually be put into operation is calculated. available ; Summarize the power of all load nodes in the power outage fault area to obtain the final power demand P of the power outage fault area total ; P available With P total For comparison, if P available ≥(1+margin)P total , then the existing power generation equipment can meet the demand; otherwise it cannot be met.

6. The method for dispatching power emergency resources based on digital twins according to claim 1, characterized in that: The process of identifying electricity users involved in each power outage fault area includes: Establish the corresponding relationship between electricity users and grid nodes; According to the load nodes in the power outage fault area, through the correspondence between electricity users and grid nodes, the information of all electricity users connected to these load nodes is found, and the specific electricity users involved in each power outage fault area are clarified.

7. The method for dispatching power emergency resources based on digital twins according to claim 1, characterized in that: The process of classifying electricity users in the power outage fault area is as follows: Collect data on electricity users in the power outage area; Divide the electricity user data in the power outage area into a training set and a test set; Using the CART algorithm, a decision tree is recursively constructed based on the characteristics of electricity user data to generate a decision tree model; The decision tree model is trained and tested using the training set and the test set. After the training and testing are completed, the data of electricity users in the power outage fault area are input into the decision tree model, and the output is whether the electricity user is an ordinary electricity user or an important electricity user.

8. The method for dispatching power emergency resources based on digital twins according to claim 1, characterized in that: The process of determining the power supply priority of each power outage fault area is as follows: Counting the number of common electricity users and the number of important electricity users in the power outage fault area, and calculating the ratio of the sum to the total number of electricity users in all power outage fault areas to obtain the ratio of the number of electricity users in the power outage fault area; Calculate the ratio of the number of important electricity users in the power outage fault area to the total number of important electricity users in all power outage fault areas to obtain the ratio of the number of important electricity users in the power outage fault area; The power user value in the power outage fault area is obtained by summing the power user number ratio in the power outage fault area and the important power user number ratio; The power consumption duration performance value in the power outage fault area is summed with the power user value in the power outage fault area to obtain the power consumption priority coefficient of the power outage fault area; Sort all power outage fault areas according to their corresponding power priority coefficients from large to small, and determine the power supply priority of each power outage fault area.

9. The method for dispatching power emergency resources based on digital twins according to claim 8, characterized in that: The method for obtaining the power consumption duration performance value in the power outage fault area is as follows: Obtain the power consumption duration of all power users and all important power users in the power outage fault area during the historical power consumption cycle; Calculate the ratio of the power consumption time of all power users in the power outage fault area to the power consumption time of all power users in the power outage fault area in the historical power consumption cycle to obtain the power consumption time ratio of the power users in the power outage fault area; Calculate the ratio of the power consumption time of all important power users in the power outage fault area to the power consumption time of all important power users in the power outage fault area in the historical power consumption cycle to obtain the power consumption time ratio of the important power users in the power outage fault area; The power consumption duration ratio of power users in the power outage fault area is summed with the power consumption duration ratio of important power users to obtain the power consumption duration performance value in the power outage fault area.

10. A power emergency resource dispatching system based on digital twins, characterized by: Includes the following modules: Power outage fault area identification module: identifies the power outage fault area within the area covered by the power grid; Power generation demand judgment module: determines whether the existing power generation equipment can meet the power generation needs of all power outage fault areas; Electricity user identification module: If the requirements cannot be met, identify the electricity users involved in each power outage fault area; Electricity user classification module: classifies electricity users in the power outage area into ordinary electricity users and important electricity users; Emergency resource scheduling module: By analyzing the number and power consumption time of ordinary and important electricity users in the power outage fault area, the power supply priority of each power outage fault area is determined, and power generation equipment is allocated to the power outage fault area in order of power supply priority.

Images