Key power transmission section identification method and system in new energy transmission blocking scene

By calculating the load rate of the power grid section and dimensionality reduction analysis of influencing factors, we can identify the key transmission sections that are blocked from new energy transmission, solve the problem of impossible to achieve optimal control in the existing technology, optimize the scheduling strategy of new energy consumption and transmission, and improve the The stability and efficiency of grid operation.

CN118970929APending Publication Date: 2024-11-15CHINA ELECTRIC POWER RESEARCH INSTITUTE CO LTD +3
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411065887.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-05
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

The existing technology cannot effectively identify key transmission sections in scenarios where new energy transmission is blocked, resulting in the inability to achieve optimal control and cannot meet the optimization scheduling needs of new energy consumption and delivery, especially when the complexity and uncertainty of the power grid are increasing.

Method used

By obtaining the historical, real-time or future trend operation values ​​and limit information of regional power grid transmission lines and sections, the section load rate is calculated, and the k-means clustering and random forest algorithm are used to perform dimensionality reduction analysis of influencing factors, combined with FP-growth algorithm mining The correlation between the state quantity and the data of key influencing factors is to identify the key transmission sections that hinder the delivery of new energy.

Benefits of technology

Implement the identification of key transmission sections under the conditions of new energy hindered, optimize subsequent scheduling control, generate the optimal intraday scheduling strategy for stations, reduce the scale of network constraints, and support intraday regulating decisions, avoiding the generation of candidate sets when data volume increases. , realizes efficient computing.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118970929A_ABST
    Figure CN118970929A_ABST
Patent Text Reader

Abstract

The invention discloses a key power transmission section identification method and system in a new energy transmission hindered scene, and the method comprises the steps: obtaining historical, real-time or future power flow operation values and limit information of a regional power grid power transmission line and a section, and carrying out the calculation to obtain a section load rate; classifying the section load rates, finding out the section load rate of a target interval, and extracting a power grid operation section at a corresponding moment as a correlation analysis sample; on the basis of the power grid operation section in the correlation analysis sample, performing influence factor dimension reduction analysis on pre-acquired power grid operation state data to obtain key influence factor data; whether the power grid operation section is heavy, full and overloaded is taken as a state quantity, an incidence relation between the state quantity and key influence factor data is mined, and a key power transmission section hindering new energy transmission is found out. According to the invention, under the condition that new energy is blocked, delivery channel resources can be analyzed, the delivery capacity of a key section is judged, the subsequent scheduling control calculation process is optimized, and the generation of an optimal scheduling strategy is assisted.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of power system automation, and specifically relates to a method and system for identifying key transmission sections in a scenario where the transmission of new energy is blocked. Background Art

[0002] The new power system shows a trend of rapid development of high-proportion new energy grid connection and rapid increase in the proportion of flexible loads such as distributed power sources, energy storage, and power electronic equipment. The uncertainty of system operation has significantly increased, and it is easy to reconstruct the power supply side and load side, and the complexity of operation data has greatly increased. In order to ensure the power supply capacity of the entire network, the operation of the power spot market, and the green power trading needs, the dispatching strategy involved in large-scale new energy consumption and transmission is relatively complex.

[0003] In the existing technology, the emergence of regional energy storage power stations cannot completely solve and smooth the regulatory risks brought to the power grid by the fluctuation of local renewable energy in the region. The obstruction of renewable energy transmission is usually caused by factors such as market absorption capacity, transmission capacity of power grid transmission channels, insufficient peak-shaving capacity, and power loss caused by power grid failures.

[0004] In order to realize large-scale consumption and transmission of new energy, it is necessary to judge the transmission capacity of the transmission channel. Currently, automatic control software usually allocates power based on fixed strategies and cannot achieve optimal control.

[0005] With the digital evolution of the power grid, social environmental data are connected to the power grid, the types and number of dispatch objects are growing exponentially, and the number of internal and external uncertainty factors influencing the power grid is increasing. The decision-making feasibility and computational efficiency of the currently widely used deterministic and model-driven optimization methods cannot fully meet the requirements for optimized dispatching to promote the consumption and transmission of new energy. Summary of the invention

[0006] The purpose of the present invention is to address the problems in the above-mentioned prior art and provide a method and system for identifying key transmission sections in a scenario where new energy transmission is blocked, analyze the external transmission channel resources under the condition that new energy is blocked, judge the transmission capacity of key sections, optimize the subsequent scheduling control calculation process, and assist in generating the optimal station intraday scheduling strategy.

[0007] In order to achieve the above object, the present invention has the following technical solutions:

[0008] In the first aspect, a method for identifying key transmission sections in a scenario where new energy transmission is blocked is provided, including:

[0009] Obtain historical, real-time or future power flow operation values ​​and limit information of regional power grid transmission lines and sections, and calculate the section load rate;

[0010] Classify the section load rate, find the section load rate in the target interval, and extract the grid operation section at the corresponding time as the correlation analysis sample;

[0011] Based on the power grid operation section in the correlation analysis sample, the pre-acquired power grid operation status data is subjected to dimensionality reduction analysis of influencing factors to obtain key influencing factor data;

[0012] Whether the grid operating section is heavy, full or overloaded is used as the state quantity, and the correlation between the state quantity and the key influencing factor data is explored. Based on the correlation, the key transmission section that hinders the transmission of new energy is found.

[0013] As a preferred solution, the cross-sectional load rate is calculated according to the following expression:

[0014]

[0015] Where n line Indicates the number of lines, I i represents the current running value of the ith line, T i represents the thermal stability limit of the i-th line, and j represents the transmission section number.

[0016] As a preferred solution, the step of classifying the section load rate and finding the section load rate of the target interval adopts k-means cluster analysis method for classification, including:

[0017] Set the number of clusters K and randomly select K scenes from n scenes as the initial cluster centers Z k ;

[0018] Calculate each scene X m The distance D to each cluster center i,k , the categories are divided according to the minimum distance principle;

[0019] Calculate the new cluster center as follows:

[0020]

[0021] In the formula, C k N is all objects of the kth class; k is the number of objects contained in the kth class;

[0022] Repeat the above steps until the classification no longer changes and obtain the classification result.

[0023] As a preferred solution, the pre-acquired power grid operation status data includes data corresponding to the upper and lower limits of new energy power, generator power, load power, interconnection line power and equipment maintenance status.

[0024] As a preferred solution, the step of performing dimensionality reduction analysis of influencing factors on the pre-acquired power grid operation status data based on the power grid operation section in the association analysis sample to obtain key influencing factor data adopts a random forest algorithm to perform dimensionality reduction analysis of influencing factors, including:

[0025] Select the same number of sample data as the original data set by random sampling with replacement each time from the original data set to construct a data subset;

[0026] Each data subset randomly selects a set number of optimal features from all the features to be selected as the input features of the decision tree, i.e., the influencing factors;

[0027] Each decision tree is obtained according to each data subset, and multiple decision trees together form a random forest.

[0028] As a preferred solution, in the step of taking whether the grid operation section is heavy, full, or overloaded as a state quantity, mining the correlation between the state quantity and the key influencing factor data, and finding the key transmission section that hinders the transmission of new energy according to the correlation, the FP-growth algorithm is used to mine the correlation between the state quantity and the key influencing factor data, including:

[0029] Obtain the grid operation data, the grid operation section corresponding to the target interval section load rate, and the key influencing factor data, and generate a correlation database;

[0030] First, scan the association database, record the support of the grid operation section corresponding to the characteristic quantity of each influencing factor and the load rate of the target section under the condition of blocked new energy transmission, select the items that meet the support conditions, list the items in each transaction in descending order according to the support size, and construct the corresponding conditional projection database and projection FP-tree;

[0031] The association database is scanned for the second time to construct a new FP-tree, traversing the filtered and reordered volatility characteristic values ​​and risk indicator status items in each transaction, compressing the information represented by each item into the FP-tree structure, and retaining the association between the data; repeat the above process until the newly constructed FP-tree is empty or contains only one path;

[0032] Frequent item sets are found through the constructed FP-tree, and the key transmission sections that hinder the transmission of new energy are found based on the frequent item sets.

[0033] As a preferred solution, in the second scanning of the association database, a new FP-tree is constructed, the fluctuation characteristic values ​​and risk indicator status items that have been screened and reordered in each transaction are traversed, the information represented by each item is compressed into the FP-tree structure, and in the step of retaining the association between the data, the items in the association database whose status changes and the number of occurrences of the items with status changes on the corresponding paths are determined, and the sum of the number of occurrences of a certain item on all paths is equal to the frequency of occurrence of this item in the database.

[0034] As a preferred solution, in the step of searching for frequent item sets through the constructed FP-tree, the conditional pattern base of each item is found, and the items that do not meet the minimum support are deleted by recursively calling the tree structure. If there is only one path left in the final tree structure, all combinations are exhausted. If the tree structure is not a single path, the tree structure is continued to be recursively called until only a single path remains. When the constructed FP-tree is empty, the prefix of the corresponding FP-tree is the frequent pattern. When the constructed FP-tree contains only one path, the frequent pattern is obtained by enumerating all possible combinations and connecting them with the prefix of the corresponding FP-tree.

[0035] As a preferred solution, in the step of searching for frequent item sets through the constructed FP-tree, after the construction of the FP-tree is completed, the FP-tree is mined in a bottom-up order based on the tail item of the tree, and frequent item sets of different paths are obtained in turn. By taking the union of the frequent item sets of different paths, all frequent item sets in the association relationship database are obtained.

[0036] Secondly, a key transmission section identification system is provided in the scenario where the transmission of new energy is blocked, including:

[0037] The section load rate calculation module is used to obtain the historical, real-time or future power flow operation values ​​and limit information of the regional power grid transmission lines and sections, and calculate the section load rate;

[0038] The correlation analysis sample extraction module is used to classify the section load rate, find the section load rate in the target interval, and extract the grid operation section at the corresponding time as the correlation analysis sample;

[0039] The key influencing factor data analysis module is used to perform influencing factor dimensionality reduction analysis on the pre-acquired power grid operation status data based on the power grid operation section in the association analysis sample to obtain key influencing factor data;

[0040] The key transmission section determination module is used to take whether the power grid operating section is heavy, full, or overloaded as a state quantity, explore the correlation between the state quantity and the key influencing factor data, and find out the key transmission section that hinders the transmission of new energy based on the correlation.

[0041] As a preferred solution, the section load rate calculation module calculates the section load rate according to the following expression:

[0042]

[0043] Where n line Indicates the number of lines, I i represents the current running value of the ith line, T i represents the thermal stability limit of the i-th line, and j represents the transmission section number.

[0044] As a preferred solution, the association analysis sample extraction module uses k-means cluster analysis method for classification, including:

[0045] Set the number of clusters K and randomly select K scenes from n scenes as the initial cluster centers Z k ;

[0046] Calculate each scene X m The distance D to each cluster center i,k , the categories are divided according to the minimum distance principle;

[0047] Calculate the new cluster center as follows:

[0048]

[0049] In the formula, C k N is all objects of the kth class; k is the number of objects contained in the kth class;

[0050] Repeat the above steps until the classification no longer changes and obtain the classification result.

[0051] As a preferred solution, the pre-acquired power grid operation status data includes data corresponding to the upper and lower limits of new energy power, the upper and lower limits of generator power, the upper and lower limits of load power, the upper and lower limits of tie line power, and the equipment maintenance status;

[0052] The key influencing factor data analysis module uses a random forest algorithm to perform dimensionality reduction analysis of influencing factors, including:

[0053] Select the same number of sample data as the original data set by random sampling with replacement each time from the original data set to construct a data subset;

[0054] Each data subset randomly selects a set number of optimal features from all the features to be selected as the input features of the decision tree, i.e., the influencing factors;

[0055] Each decision tree is obtained according to each data subset, and multiple decision trees together form a random forest.

[0056] As a preferred solution, the key transmission section determination module uses the FP-growth algorithm to mine the correlation between the state quantity and the key influencing factor data, including:

[0057] Obtain the grid operation data, the grid operation section corresponding to the target interval section load rate, and the key influencing factor data, and generate a correlation database;

[0058] First, scan the association database, record the support of the grid operation section corresponding to the characteristic quantity of each influencing factor and the load rate of the target section under the condition of blocked new energy transmission, select the items that meet the support conditions, list the items in each transaction in descending order according to the support size, and construct the corresponding conditional projection database and projection FP-tree;

[0059] The association database is scanned for the second time to construct a new FP-tree, traversing the filtered and reordered volatility characteristic values ​​and risk indicator status items in each transaction, compressing the information represented by each item into the FP-tree structure, and retaining the association between the data; repeat the above process until the newly constructed FP-tree is empty or contains only one path;

[0060] Frequent item sets are found through the constructed FP-tree, and the key transmission sections that hinder the transmission of new energy are found based on the frequent item sets.

[0061] As a preferred solution, when the key transmission section determination module scans the association database for the second time and constructs a new FP-tree, it determines the items with state changes in the association database and the number of times the items with state changes appear on the corresponding paths. The sum of the number of times an item appears on all paths is equal to the frequency of appearance of the item in the database.

[0062] As a preferred solution, when searching for frequent item sets through the constructed FP-tree, the key transmission section determination module finds the conditional pattern base of each item, and deletes the items that do not meet the minimum support by recursively calling the tree structure. If there is only one path left in the final tree structure, all combinations are exhausted. If the tree structure is not a single path, the tree structure is continued to be recursively called until only a single path remains. When the constructed FP-tree is empty, the prefix of the corresponding FP-tree is the frequent pattern. When the constructed FP-tree contains only one path, the frequent pattern is obtained by enumerating all possible combinations and connecting them with the prefix of the corresponding FP-tree.

[0063] As a preferred solution, when the key transmission section determination module searches for frequent item sets through the constructed FP-tree, after completing the construction of the FP-tree, the FP-tree is mined in a bottom-up order based on the tail item of the tree, and frequent item sets of different paths are obtained in turn. By taking the union of the frequent item sets of different paths, all frequent item sets in the association relationship database are obtained.

[0064] In a third aspect, an electronic device is provided, comprising a processor and a memory, wherein the processor is used to execute a computer program stored in the memory to implement the method for identifying key transmission sections in a scenario where new energy transmission is blocked as described in the first aspect.

[0065] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by a processor, a method for identifying key transmission sections in a scenario where new energy transmission is blocked as described in the first aspect is implemented.

[0066] Compared with the prior art, the first aspect of the present invention has at least the following beneficial effects:

[0067] Based on the historical, real-time or future flow operation values ​​and limit information of the regional power grid transmission lines and sections, the section load rate is calculated, and the section load rate is divided into three levels of "high, medium and low". The grid operation sections with high congestion are analyzed and statistically analyzed to provide a data basis for extracting the typical characteristics of the blocked grid operation sections. The influencing factors are reduced in dimension analysis of the grid operation section congestion and the pre-acquired grid operation status data to obtain the key influencing factor data. Through the correlation degree analysis method, the identification of the key transmission section of the grid operation corresponding to the occurrence of congestion is realized. The key transmission section identification method in the scenario of new energy transmission obstruction of the present invention realizes the analysis of the external transmission channel resources under the condition of new energy obstruction, and judges the transmission capacity of the key transmission section. It can be used for the generation of the "energy storage + new energy" station intraday scheduling strategy based on the optimization algorithm, and serves for the subsequent optimization calculation and scheduling control. It can provide technical support for reducing the scale of network constraints in the optimization solution of intraday regulation auxiliary decision-making.

[0068] Furthermore, the present invention adopts a random forest algorithm to perform a dimensionality reduction analysis of influencing factors on the pre-acquired power grid operation status data based on the power grid operation sections in the association analysis samples, and obtains key influencing factor data. It can perform feature compression on the influencing factors of new energy obstruction, and realize dimensionality reduction analysis of the reasons that affect the absorption capacity of key new energy transmission sections by extracting operation data, thereby providing support for the association analysis of the absorption capacity of key new energy transmission sections.

[0069] Furthermore, the present invention utilizes the frequent item set search FP-growth algorithm to mine the correlation between the state quantity and the key influencing factor data, analyzes the main factors affecting the obstruction of key transmission sections, and provides support for optimal scheduling and power regulation under the condition of new energy obstruction. It can avoid the generation of a large number of candidate item sets when the data volume increases, and only needs to scan the association relationship database twice to quickly find the frequent item sets, thereby achieving efficient calculation.

[0070] It can be understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0072] Figure 1 Flow chart of a method for identifying key power transmission sections in a scenario where new energy transmission is blocked according to an embodiment of the present invention;

[0073] Figure 2 A schematic diagram of the principle of using a random forest algorithm to perform dimensionality reduction analysis of influencing factors in an embodiment of the present invention;

[0074] Figure 3 A schematic diagram of the principle of using the FP-growth algorithm to mine the association relationship between state quantities and key influencing factor data in an embodiment of the present invention. DETAILED DESCRIPTION

[0075] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0076] In the scenario where the transmission of renewable energy is blocked, the identification of critical transmission sections is crucial to ensure the stable and safe operation of the power system. Generally, by collecting real-time operating data of renewable energy power stations, transmission networks, load centers, etc., including voltage, current, power, frequency, etc., the reasons for the obstruction of renewable energy transmission are analyzed in detail, which may be due to network congestion, equipment failure, weather conditions, etc. In this process, the critical transmission section is the main line collection that undertakes power interaction in the power system. Disconnecting these lines may cause the system to be divided into independent subsystems. In the scenario where the transmission of renewable energy is blocked, the critical transmission sections may be those lines that connect renewable energy power stations with major load centers and transmit a large amount of power. The identification of critical transmission sections is a complex and important issue. Once the critical transmission sections are identified, corresponding countermeasures need to be formulated to ensure the stable and safe operation of the power system when the transmission of renewable energy is blocked. These measures may include adjusting the output of renewable energy power stations, optimizing the operation mode of the transmission network, and strengthening the monitoring and protection of critical transmission sections.

[0077] See also Figure 1 The method for identifying key transmission sections in a scenario where new energy transmission is blocked according to an embodiment of the present invention includes:

[0078] S1. Obtain the historical, real-time or future power flow operation values ​​and limit information of the regional power grid transmission lines and sections, and calculate the section load rate;

[0079] S2. Classify the section load rate, find the section load rate in the target interval, and extract the grid operation section at the corresponding time as the correlation analysis sample;

[0080] S3. Based on the power grid operation section in the association analysis sample, perform dimensionality reduction analysis on the pre-acquired power grid operation status data to obtain key influencing factor data;

[0081] S4. Take whether the grid operation section is heavy, full or overloaded as the state quantity, explore the correlation between the state quantity and the key influencing factor data, and find out the key transmission section that hinders the delivery of new energy based on the correlation.

[0082] More specifically, the cross-sectional load rate in step S1 is calculated according to the following expression:

[0083]

[0084] Where n line Indicates the number of lines, I i represents the current running value of the ith line, T i represents the thermal stability limit of the i-th line, i=1,2,...n; j represents the transmission section number, j=1,2,...m.

[0085] Step S2 uses the k-means cluster analysis method to classify the section load rate into three levels: "high, medium and low", find the interval of "high" section load rate, and extract the grid operation section at the corresponding time as the sample D for correlation analysis. t , specifically:

[0086] 1) Set the number of clusters K and randomly select K scenes from n scenes as the initial cluster centers Z k (k=1, 2, ..., K);

[0087] 2) Calculate each scene X according to the cluster center according to the formula m (m=1, 2, ..., n) The distance D to each cluster center i,k =|X i -Z k |, classify according to the minimum distance principle;

[0088] 3) Calculate the new cluster center, that is: Among them, C k N is all objects of the kth class; k is the number of objects contained in the kth class;

[0089] 4) Repeat steps 2) and 3) until the classification no longer changes and obtain the classification result.

[0090] In a possible implementation, the grid operation status data pre-acquired in step S3 includes but is not limited to data corresponding to the upper and lower limits of new energy power, generator power, load power, tie line power, and equipment maintenance status. tFirst, the random forest algorithm is used to perform impact dimensionality reduction analysis on the aforementioned power grid operation status data to obtain the key influencing factor data E t ,like Figure 2 As shown, specifically including:

[0091] 1) Randomly select the same number of sample data as the original data set each time with replacement from the original data set to construct a data subset;

[0092] 2) Each data subset randomly selects a certain number of optimal features from all the features to be selected as the input features of the decision tree, i.e., the influencing factors;

[0093] 3) Each decision tree is obtained according to each data subset, and multiple decision trees together form a random forest.

[0094] Step S4 takes whether the grid operation section is heavy, full, or overloaded as the state quantity S t , using the frequent itemset search FP-growth algorithm to mine the state quantity S t Data on key influencing factors t The correlation relationship between them.

[0095]

[0096] The verification of the section load rate clustering results can refer to the above table. The clustering results can filter out heavy-loaded, fully-loaded, and overloaded sections as high-load rate sections, which are determined as key information that hinders the delivery of new energy.

[0097] Set the confidence and support thresholds, and remove those that do not meet the thresholds. Support reflects the importance of the generated rules, and confidence reflects the reliability of the rules. Both affect the size of the generated rule base. In order to ensure the reliability of the generated association rule recognition model, the minimum confidence threshold is set to C%, and the minimum support is S%.

[0098] See also Figure 3 The steps of mining association relationships using the frequent item set search FP-growth algorithm in the embodiment of the present invention include:

[0099] 1) Obtain the grid operation data, high load rate sections and key sections influencing factors, and after data processing, form the association database D between the two. When using the FP-growth algorithm to mine frequent item sets, the association database D is scanned for the first time to record the support of each feature quantity (influencing factor) and each section with high load rate under the condition of obstruction of new energy transmission, and select the items that meet the support conditions, and then list the items in each transaction in descending order according to the support size.

[0100] First, scan and traverse the experimental data set, propose the item sets that do not meet the conditions according to the set minimum support, obtain the frequent 1-item set, and sort the experimental data set in descending order. For each frequent item, construct its conditional projection database and projection FP-tree;

[0101] 2) Scan the original data set for the second time to create the item header table and FP-tree. Repeat this process for each newly constructed FP-tree until the constructed new FP-tree is empty or contains only one path;

[0102] The second scan of the association database D is used to construct the FP-tree. The root node "NULL" is created first, and the fluctuation characteristic values ​​and risk indicator status items after screening and reordering in each transaction are traversed. The information represented by each item is compressed into the FP-tree structure, while retaining the correlation between the data. i is the state change element item appearing in the database, t j is the number of times the item appears on the path. The sum of the number of times an item appears on all paths is equal to the frequency of occurrence of the item in the database.

[0103] 3) Search for frequent item sets through the constructed FP-tree, find the conditional pattern base of each item, and delete items that do not meet the minimum support by recursively calling the tree structure. If there is only one path left in the final tree structure, you only need to exhaustively enumerate all combinations. If the tree structure is not a single path, continue to recursively call the tree structure until only a single path remains. When the constructed FP-tree is empty, its prefix is ​​the frequent pattern; when it contains only one path, the frequent pattern can be obtained by enumerating all possible combinations and connecting them with the prefix of this tree.

[0104] After scanning the association database D twice and completing the FP-tree construction, the FP-tree is mined from bottom to top based on the tail item of the tree, and frequent item sets of different paths are obtained in turn. By taking their union, all frequent item sets in the database can be obtained.

[0105] The method for identifying key transmission sections in a scenario where new energy transmission is blocked in an embodiment of the present invention is based on a random forest algorithm, and can perform feature compression on factors affecting new energy blocking, and realize dimensionality reduction analysis of the reasons that affect the absorption capacity of key new energy transmission sections by extracting operating data, thereby providing support for correlation analysis of absorption capacity of key new energy transmission sections; at the same time, the method of the present invention uses a frequent item set search FP-growth algorithm to analyze the main factors affecting the obstruction of key transmission sections, and provides support for optimal scheduling and power regulation under the condition of new energy blocking, which can avoid the generation of a large number of candidate item sets when the amount of data increases, and only needs to scan the database twice to quickly find frequent item sets, thereby achieving efficient calculation.

[0106] Another embodiment of the present invention further provides a key transmission section identification system in a scenario where new energy transmission is blocked, comprising:

[0107] The section load rate calculation module is used to obtain the historical, real-time or future power flow operation values ​​and limit information of the regional power grid transmission lines and sections, and calculate the section load rate;

[0108] The correlation analysis sample extraction module is used to classify the section load rate, find the section load rate in the target interval, and extract the grid operation section at the corresponding time as the correlation analysis sample;

[0109] The key influencing factor data analysis module is used to perform influencing factor dimensionality reduction analysis on the pre-acquired power grid operation status data based on the power grid operation section in the association analysis sample to obtain key influencing factor data;

[0110] The key transmission section determination module is used to take whether the power grid operating section is heavy, full, or overloaded as a state quantity, explore the correlation between the state quantity and the key influencing factor data, and find out the key transmission section that hinders the transmission of new energy based on the correlation.

[0111] In a possible implementation, the section load rate calculation module calculates the section load rate according to the following expression:

[0112]

[0113] Where n line Indicates the number of lines, I i represents the current running value of the ith line, T i represents the thermal stability limit of the i-th line, and j represents the transmission section number.

[0114] In a possible implementation, the association analysis sample extraction module uses a k-means cluster analysis method for classification, and the k-means cluster analysis method includes:

[0115] Set the number of clusters K and randomly select K scenes from n scenes as the initial cluster centers Z k ;

[0116] Calculate each scene X m The distance D to each cluster center i,k , the categories are divided according to the minimum distance principle;

[0117] Calculate the new cluster center as follows:

[0118]

[0119] In the formula, C kN is all objects of the kth class; k is the number of objects contained in the kth class;

[0120] Repeat the above steps until the classification no longer changes and obtain the classification result.

[0121] In a possible implementation, the pre-acquired power grid operation status data includes data corresponding to the upper and lower limits of new energy power, the upper and lower limits of generator power, the upper and lower limits of load power, the upper and lower limits of tie line power, and the equipment maintenance status;

[0122] The key influencing factor data analysis module uses the random forest algorithm to perform dimensionality reduction analysis of influencing factors, including:

[0123] Select the same number of sample data as the original data set by random sampling with replacement each time from the original data set to construct a data subset;

[0124] Each data subset randomly selects a set number of optimal features from all the features to be selected as the input features of the decision tree, i.e., the influencing factors;

[0125] Each decision tree is obtained according to each data subset, and multiple decision trees together form a random forest.

[0126] In a possible implementation, the key transmission section determination module uses the FP-growth algorithm to mine the association between the state quantity and the key influencing factor data, including the following steps:

[0127] Obtain the grid operation data, the grid operation section corresponding to the target interval section load rate, and the key influencing factor data, and generate a correlation database;

[0128] First, scan the association database, record the support of the grid operation section corresponding to the characteristic quantity of each influencing factor and the load rate of the target section under the condition of blocked new energy transmission, select the items that meet the support conditions, list the items in each transaction in descending order according to the support size, and construct the corresponding conditional projection database and projection FP-tree;

[0129] The association database is scanned for the second time to construct a new FP-tree, traversing the filtered and reordered volatility characteristic values ​​and risk indicator status items in each transaction, compressing the information represented by each item into the FP-tree structure, and retaining the association between the data; repeat the above process until the newly constructed FP-tree is empty or contains only one path;

[0130] Frequent item sets are found through the constructed FP-tree, and the key transmission sections that hinder the transmission of new energy are found based on the frequent item sets.

[0131] In a possible implementation, when the critical transmission section determination module scans the association database for the second time and constructs a new FP-tree, it determines the items with state changes in the association database and the number of times the items with state changes appear on the corresponding paths. The sum of the number of times an item appears on all paths is equal to the frequency of appearance of the item in the database.

[0132] In a possible implementation, when the key transmission section determination module searches for frequent item sets through the constructed FP-tree, it finds the conditional pattern base of each item, deletes the items that do not meet the minimum support by recursively calling the tree structure, and if there is only one path left in the final tree structure, all combinations are exhausted. If the tree structure is not a single path, the tree structure is continued to be recursively called until only a single path remains; when the constructed FP-tree is empty, the prefix of the corresponding FP-tree is the frequent pattern; when the constructed FP-tree contains only one path, the frequent pattern is obtained by enumerating all possible combinations and connecting them with the prefix of the corresponding FP-tree.

[0133] In a possible implementation, when the key transmission section determination module searches for frequent item sets through the constructed FP-tree, after the construction of the FP-tree is completed, the FP-tree is mined in a bottom-up order based on the tail item of the tree, and frequent item sets of different paths are obtained in turn. By taking the union of the frequent item sets of different paths, all the frequent item sets in the association relationship database are obtained.

[0134] Another embodiment of the present invention further proposes an electronic device, including a processor and a memory, wherein the processor is used to execute a computer program stored in the memory to implement a method for identifying key transmission sections in the scenario where the transmission of new energy is blocked.

[0135] Another embodiment of the present invention further proposes a computer-readable storage medium, which stores at least one instruction. When the at least one instruction is executed by a processor, a method for identifying key transmission sections in the scenario where the transmission of new energy is blocked is implemented.

[0136] The computer program includes computer program code, which may be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium may include: any entity or device, medium, USB flash drive, mobile hard disk, disk, optical disk, computer memory, read-only memory, random access memory, electric carrier signal, telecommunication signal and software distribution medium, etc. that can carry the computer program code. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals. For ease of explanation, the above content only shows the part related to the embodiment of the present invention. For specific technical details not disclosed, please refer to the method part of the embodiment of the present invention. The computer-readable storage medium is non-temporary and can be stored in a storage device formed by various electronic devices, which can realize the execution process recorded in the method of the embodiment of the present invention.

[0137] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, 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 disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0138] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to 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 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 device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the flowchart. 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.

[0139] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0140] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0141] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method for identifying key transmission sections in a scenario where new energy transmission is blocked, characterized in that: include: Obtain historical, real-time or future power flow operation values ​​and limit information of regional power grid transmission lines and sections, and calculate the section load rate; Classify the section load rate, find the section load rate in the target interval, and extract the grid operation section at the corresponding time as the correlation analysis sample; Based on the power grid operation section in the correlation analysis sample, the pre-acquired power grid operation status data is subjected to dimensionality reduction analysis of influencing factors to obtain key influencing factor data; Whether the grid operating section is heavy, full or overloaded is used as the state quantity, and the correlation between the state quantity and the key influencing factor data is explored. Based on the correlation, the key transmission section that hinders the transmission of new energy is found.

2. The method for identifying key power transmission sections in a scenario where new energy transmission is blocked according to claim 1 is characterized in that: The cross-sectional load rate is calculated according to the following expression: Where n line Indicates the number of lines, I i represents the current running value of the ith line, T i represents the thermal stability limit of the i-th line, and j represents the transmission section number.

3. The method for identifying key transmission sections in a scenario where new energy transmission is blocked according to claim 1 is characterized in that: The step of classifying the section load rate and finding the section load rate of the target interval adopts the k-means cluster analysis method for classification, including: Set the number of clusters K and randomly select K scenes from n scenes as the initial cluster centers Z k ; Calculate each scene X m The distance D to each cluster center i,k , the categories are divided according to the minimum distance principle; Calculate the new cluster center as follows: In the formula, C k N is all objects of the kth class; k is the number of objects contained in the kth class; Repeat the above steps until the classification no longer changes and obtain the classification result.

4. The method for identifying key transmission sections in a scenario where new energy transmission is blocked according to claim 1 is characterized in that: The pre-acquired power grid operation status data includes data corresponding to the upper and lower limits of new energy power, the upper and lower limits of generator power, the upper and lower limits of load power, the upper and lower limits of tie line power, and equipment maintenance status.

5. The method for identifying key transmission sections in a scenario where new energy transmission is blocked according to claim 4 is characterized in that: The step of performing dimensionality reduction analysis of influencing factors on the pre-acquired power grid operation status data based on the power grid operation section in the association analysis sample to obtain key influencing factor data adopts a random forest algorithm to perform dimensionality reduction analysis of influencing factors, including: Select the same number of sample data as the original data set by random sampling with replacement each time from the original data set to construct a data subset; Each data subset randomly selects a set number of optimal features from all the features to be selected as the input features of the decision tree, i.e., the influencing factors; Each decision tree is obtained according to each data subset, and multiple decision trees together form a random forest.

6. The method for identifying key transmission sections in a scenario where new energy transmission is blocked according to claim 1 is characterized in that: In the step of taking whether the grid operation section is heavy, full, or overloaded as a state quantity, mining the correlation between the state quantity and the key influencing factor data, and finding the key transmission section that hinders the transmission of new energy according to the correlation, the FP-growth algorithm is used to mine the correlation between the state quantity and the key influencing factor data, including: Obtain the grid operation data, the grid operation section corresponding to the target interval section load rate, and the key influencing factor data, and generate a correlation database; First, scan the association database, record the support of the grid operation section corresponding to the characteristic quantity of each influencing factor and the load rate of the target section under the condition of blocked new energy transmission, select the items that meet the support conditions, list the items in each transaction in descending order according to the support size, and construct the corresponding conditional projection database and projection FP-tree; The association database is scanned for the second time to construct a new FP-tree, traversing the filtered and reordered volatility characteristic values ​​and risk indicator status items in each transaction, compressing the information represented by each item into the FP-tree structure, and retaining the association between the data; repeat the above process until the newly constructed FP-tree is empty or contains only one path; Frequent item sets are found through the constructed FP-tree, and the key transmission sections that hinder the transmission of new energy are found based on the frequent item sets.

7. The method for identifying key transmission sections in a scenario where new energy transmission is blocked according to claim 6 is characterized in that: In the second scanning of the association database, a new FP-tree is constructed, the fluctuation characteristic values ​​and risk indicator status items that have been screened and reordered in each transaction are traversed, the information represented by each item is compressed into the FP-tree structure, and the correlation between the data is retained. The items in the association database whose status changes and the number of occurrences of the items with status changes on the corresponding paths are determined. The sum of the number of occurrences of a certain item on all paths is equal to the frequency of occurrence of this item in the database.

8. The method for identifying key transmission sections in a scenario where new energy transmission is blocked according to claim 7 is characterized in that: In the step of searching for frequent item sets through the constructed FP-tree, the conditional pattern base of each item is found, and the items that do not meet the minimum support are deleted by recursively calling the tree structure. If there is only one path left in the final tree structure, all combinations are exhausted. If the tree structure is not a single path, the tree structure is continued to be recursively called until only a single path remains. When the constructed FP-tree is empty, the prefix of the corresponding FP-tree is the frequent pattern. When the constructed FP-tree contains only one path, the frequent pattern is obtained by enumerating all possible combinations and connecting them with the prefix of the corresponding FP-tree.

9. The method for identifying key transmission sections in a scenario where new energy transmission is blocked according to claim 8 is characterized in that: In the step of searching for frequent item sets through the constructed FP-tree, after the construction of the FP-tree is completed, the FP-tree is mined in a bottom-up order based on the tail item of the tree, and frequent item sets of different paths are obtained in turn. By taking the union of the frequent item sets of different paths, all the frequent item sets in the association relationship database are obtained.

10. A key transmission section identification system in the scenario where new energy transmission is blocked, characterized in that: include: The section load rate calculation module is used to obtain the historical, real-time or future power flow operation values ​​and limit information of the regional power grid transmission lines and sections, and calculate the section load rate; The correlation analysis sample extraction module is used to classify the section load rate, find the section load rate in the target interval, and extract the grid operation section at the corresponding time as the correlation analysis sample; The key influencing factor data analysis module is used to perform influencing factor dimensionality reduction analysis on the pre-acquired power grid operation status data based on the power grid operation section in the association analysis sample to obtain key influencing factor data; The key transmission section determination module is used to take whether the power grid operating section is heavy, full, or overloaded as a state quantity, explore the correlation between the state quantity and the key influencing factor data, and find out the key transmission section that hinders the transmission of new energy based on the correlation.

11. The key transmission section identification system in the scenario of obstructed transmission of new energy according to claim 10 is characterized in that: The section load rate calculation module calculates the section load rate according to the following expression: Where n line Indicates the number of lines, I i represents the current running value of the ith line, T i represents the thermal stability limit of the i-th line, and j represents the transmission section number.

12. The key transmission section identification system in the scenario of obstructed transmission of new energy according to claim 10 is characterized in that: The association analysis sample extraction module uses k-means cluster analysis method for classification, including: Set the number of clusters K and randomly select K scenes from n scenes as the initial cluster centers Z k ; Calculate each scene X m The distance D to each cluster center i,k , the categories are divided according to the minimum distance principle; Calculate the new cluster center as follows: In the formula, C k N is all objects of the kth class; k is the number of objects contained in the kth class; Repeat the above steps until the classification no longer changes and obtain the classification result.

13. The key transmission section identification system in the scenario of obstructed transmission of new energy according to claim 10 is characterized in that: The pre-acquired power grid operation status data includes data corresponding to the upper and lower limits of new energy power, upper and lower limits of generator power, upper and lower limits of load power, upper and lower limits of tie line power, and equipment maintenance status; The key influencing factor data analysis module uses a random forest algorithm to perform dimensionality reduction analysis of influencing factors, including: Select the same number of sample data as the original data set by random sampling with replacement each time from the original data set to construct a data subset; Each data subset randomly selects a set number of optimal features from all the features to be selected as the input features of the decision tree, i.e., the influencing factors; Each decision tree is obtained according to each data subset, and multiple decision trees together form a random forest.

14. The key transmission section identification system in the scenario of obstructed transmission of new energy according to claim 10 is characterized in that: The key transmission section determination module uses the FP-growth algorithm to mine the correlation between the state quantity and the key influencing factor data, including: Obtain the grid operation data, the grid operation section corresponding to the target interval section load rate, and the key influencing factor data, and generate a correlation database; First, scan the association database, record the support of the grid operation section corresponding to the characteristic quantity of each influencing factor and the load rate of the target section under the condition of blocked new energy transmission, select the items that meet the support conditions, list the items in each transaction in descending order according to the support size, and construct the corresponding conditional projection database and projection FP-tree; The association database is scanned for the second time to construct a new FP-tree, traversing the filtered and reordered volatility characteristic values ​​and risk indicator status items in each transaction, compressing the information represented by each item into the FP-tree structure, and retaining the association between the data; repeat the above process until the newly constructed FP-tree is empty or contains only one path; Frequent item sets are found through the constructed FP-tree, and the key transmission sections that hinder the transmission of new energy are found based on the frequent item sets.

15. The key transmission section identification system in the scenario of obstructed transmission of new energy according to claim 14 is characterized in that: When the key transmission section determination module scans the association database for the second time and constructs a new FP-tree, it determines the items in the association database whose states have changed, and the number of times the items whose states have changed on the corresponding paths appear. The sum of the number of times an item appears on all paths is equal to the frequency of appearance of the item in the database.

16. The key transmission section identification system in the scenario of obstructed transmission of new energy according to claim 15 is characterized in that: When searching for frequent item sets through the constructed FP-tree, the key transmission section determination module finds the conditional pattern base of each item, deletes the items that do not meet the minimum support by recursively calling the tree structure, and if there is only one path left in the final tree structure, all combinations are exhausted. If the tree structure is not a single path, the tree structure is continuously recursively called until only a single path remains; when the constructed FP-tree is empty, the prefix of the corresponding FP-tree is the frequent pattern; when the constructed FP-tree contains only one path, the frequent pattern is obtained by enumerating all possible combinations and connecting them with the prefix of the corresponding FP-tree.

17. The key transmission section identification system in the scenario of obstructed transmission of new energy according to claim 16 is characterized in that: When the key transmission section determination module searches for frequent item sets through the constructed FP-tree, after completing the construction of the FP-tree, the FP-tree is mined in a bottom-up order based on the tail item of the tree, and frequent item sets of different paths are obtained in turn. By taking the union of the frequent item sets of different paths, all the frequent item sets in the association relationship database are obtained.

18. An electronic device, characterized in that: It comprises a processor and a memory, wherein the processor is used to execute a computer program stored in the memory to implement a method for identifying a key transmission section in a scenario where the transmission of new energy is blocked as described in any one of claims 1 to 9.

19. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by the processor, it implements the key transmission section identification method in the scenario where the transmission of new energy is blocked as described in any one of claims 1 to 9.

Citation Information

Cited By

  • Power system multi-scene key section identification method and system considering flexible resource transmission limitation

    CN120847534A