Load resource regulation capability analysis method based on knowledge graph and data fusion

Abstract

The invention discloses a load resource regulation capability analysis method based on knowledge graph and data fusion, and relates to the technical field of power load regulation capability analysis, and the method comprises the following steps: collecting historical data of multi-source data; establishing a knowledge graph of the power system, and searching influence factors; based on the influence factors, performing data fusion on historical data of the multi-source data to obtain fused data; extracting load characteristics from the fused data, and analyzing the influence of influence factors on the power load; analyzing the load resource adjustment capability of the power system based on the influence of the influence factors on the power load; the method is used for solving the problem that an existing power load regulation capability analysis technology is not comprehensive enough in power load analysis, so that the error of an evaluation result of the power resource regulation capability is relatively large.

Description

Technical Field

[0001] The present invention relates to the technical field of power load regulation capability analysis, and specifically to a load resource regulation capability analysis method based on knowledge graph and data fusion. Background Art

[0002] Power load regulation capability analysis technology refers to the use of various data analysis methods, models and technologies to evaluate and analyze the loads in the power system to determine the load regulation capability of the system. This technology is designed to help power system operators and planners better understand and manage the regulation capability of various loads in the power system, thereby ensuring the stable and efficient operation of the system.

[0003] Existing power load regulation capability analysis technologies usually evaluate the load regulation capability of a single power plant. The power system is usually composed of a national grid and a grid-connected power plant. Ordinary power plants and new energy power plants will participate in power load regulation. Therefore, considering only the load regulation capability of a single power plant is relatively one-sided, and it is impossible to obtain the accurate upper limit of the load regulation of the power system, and thus it is impossible to evaluate whether the power plant setting is reasonable. For example, in a patent application with publication number CN115018362A, a method and device for evaluating regional resource regulation capability in a source-load interaction scenario are disclosed. This scheme does not consider the load data between different power plants, resulting in large errors in the evaluation results of the power resource regulation capability, and cannot be used to evaluate whether the power plant setting is reasonable. The existing power load regulation capability analysis technology also has the problem that the analysis of the power load is not comprehensive enough, resulting in large errors in the evaluation results of the power resource regulation capability. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems in the prior art to a certain extent, by collecting historical data from multiple sources, establishing a knowledge graph of the power system, searching for factors affecting the power load in the knowledge graph, marking them as influencing factors, and then based on the influencing factors, performing data fusion on the historical data of the multiple sources to obtain fused data, and then constructing a load characteristic graph based on the fused data, analyzing the load characteristic graph to obtain the influence function of the influencing factors on the power load, and finally analyzing the load resource regulation capability of the power system based on the influence of the influencing factors on the power load, so as to solve the problem that the existing power load regulation capability analysis technology is not comprehensive enough when analyzing the power load, resulting in large errors in the evaluation results of the power resource regulation capability.

[0005] To achieve the above objectives, in a first aspect, the present application provides a load resource regulation capability analysis method based on knowledge graph and data fusion, comprising the following steps:

[0006] Collect historical data from multiple sources;

[0007] Establish a knowledge graph of the power system, find the factors that affect the power load in the knowledge graph, and mark them as influencing factors;

[0008] Based on the influencing factors, the historical data of multi-source data is fused to obtain fused data;

[0009] Extract load characteristics from fused data and analyze the impact of influencing factors on power load;

[0010] Based on the impact of influencing factors on power load, the load resource regulation capability of the power system is analyzed.

[0011] Furthermore, collecting historical data from multiple sources includes the following sub-steps:

[0012] The multi-source data includes ordinary power plant data and new energy power plant data, and the historical data includes historical load data and historical weather data. The historical load data is the power load of the power system at a certain moment in the historical records, and the historical weather data is the ambient temperature at a certain moment in the historical records;

[0013] Marking the historical data in the ordinary power plant data as ordinary historical data, where the ordinary historical data includes ordinary historical load data and ordinary historical weather data;

[0014] Mark the historical data in the new energy power plant data as new energy historical data, which includes new energy historical load data and new energy historical weather data;

[0015] The common historical data is recorded by a common historical database, and the new energy historical data is recorded by a new energy historical database.

[0016] Furthermore, establishing the knowledge graph of the power system includes the following sub-steps:

[0017] Take power equipment, users and environment as entities, and build a knowledge graph based on the relationship between them;

[0018] The power equipment includes new energy equipment and ordinary equipment;

[0019] Find the factors that affect power load in the knowledge graph and mark them as influencing factors.

[0020] Furthermore, based on the influencing factors, the historical data of the multi-source data is fused to obtain the fused data, which includes the following sub-steps:

[0021] Find the influencing factors and the corresponding historical load data in the general historical database, and mark them as general historical factors and general historical loads respectively;

[0022] Find the influencing factors and the corresponding historical load data in the new energy historical database, and mark them as new energy historical factors and new energy historical load respectively;

[0023] Find the maximum value in the common historical load and mark it as the common maximum historical load; find the maximum value in the new energy historical load and mark it as the new energy maximum historical load;

[0024] Data fusion is performed on multi-source data based on normal historical load, new energy historical load, normal maximum historical load and new energy maximum historical load.

[0025] Furthermore, based on different common historical factors and new energy historical factors, data fusion is performed on common historical load and new energy maximum load;

[0026] Sort and number the common historical factors in ascending order, using the symbol T n Indicates, where n is a positive integer and n is the serial number of T; the new energy historical factors are sorted and numbered in ascending order, and the symbol H m represents, where m is a positive integer and m is the serial number of H;

[0027] The common history factor is T n All common historical loads are integrated and numbered, represented by the symbol A(n,i), where n is equal to T n The n in the figure corresponds to that in which i is a positive integer and (n,i) is the serial number of A; the new energy historical factor is H m All the historical loads of renewable energy are integrated and numbered, represented by the symbol B(m,j), where m and H m In the equation, m corresponds to j, which is a positive integer and (m,j) is the serial number of B;

[0028] When data fusion is performed on the common historical load and the common maximum historical load, the common historical load is fused and calculated using the common historical fusion formula to obtain the common load ratio, and then the new energy historical load is fused and calculated using the new energy historical fusion formula to obtain the new energy load ratio;

[0029] The general history fusion formula is configured as: Among them, RT n The common historical factor is T n The normal load ratio at that time, max(n) is the maximum value of n, and Tmax is the normal maximum historical load;

[0030] The new energy history fusion formula is configured as: Among them, RH m The historical factor for new energy is H mThe new energy load ratio at that time, max(m) is the maximum value of m, and Hmax is the maximum historical load of new energy;

[0031] The common historical factors and the corresponding common load ratios are marked as a set of fusion data, that is, (T n ,RT n ) is marked as a set of fusion data, and the new energy historical factors and the corresponding new energy load ratio are marked as a set of fusion data, that is, (H m ,RH m ) is marked as a set of fused data, and several fused data are obtained through data fusion.

[0032] Furthermore, extracting load characteristics from the fused data and analyzing the impact of influencing factors on power load includes the following sub-steps:

[0033] Construct load characteristic diagram based on fused data;

[0034] The load characteristic diagram is analyzed to obtain the influence function of the influencing factors on the power load.

[0035] Furthermore, constructing a load characteristic diagram based on the fused data includes the following sub-steps:

[0036] Marking common historical factors and new energy historical factors in the fusion data as fusion historical factors;

[0037] The common load ratio and the new energy load ratio in the fused data are marked as fused load ratios;

[0038] A plane rectangular coordinate system is established with the fused historical factor as the X-axis and the fused load ratio as the Y-axis, named as the load characteristic diagram, and the fused data is entered into the load characteristic diagram.

[0039] Further, analyzing the load characteristic diagram to obtain the influence function of the influencing factors on the power load includes the following sub-steps:

[0040] Perform polynomial fitting on the load characteristic diagram;

[0041] The fitted function is marked as an influence function, and the format of the influence function is Y=a×X 2 +b×X+c, where Y is the fusion load ratio, X is the fusion history factor, and a, b, and c are all constants that influence the function.

[0042] Furthermore, based on the influence of the influencing factors on the power load, analyzing the load resource regulation capability of the power system includes the following sub-steps:

[0043] Obtain the influence function and the maximum amount of electricity that can be uploaded by the power system, marked as the maximum uploaded electricity;

[0044] Calculate the maximum load ratio of the power system through the maximum load ratio calculation formula;

[0045] The maximum load ratio calculation formula is configured as: Among them, E is the maximum load ratio, UE is the maximum upload power, and 1h is one hour, which is used to convert the unit of UE from kWh to kW;

[0046] Based on the influence function and the maximum load ratio, the load resource regulation capability of the power system is analyzed.

[0047] Furthermore, based on the influence function and the maximum load ratio, analyzing the load resource regulation capability of the power system includes the following sub-steps:

[0048] Let Y equal E, substitute it into the influence function, and mark the solved X as the upper limit of factor adjustment;

[0049] The factor adjustment upper limit means that after the influencing factor reaches the factor adjustment upper limit, the load resource adjustment capacity of the power system reaches the upper limit. If the power load increases further, the power system cannot meet all the power loads.

[0050] Beneficial effects of the present invention: The present invention collects historical data from multiple sources, establishes a knowledge graph of the power system, searches for factors that affect the power load in the knowledge graph, marks them as influencing factors, and then fuses the historical data of the multiple sources based on the influencing factors to obtain fused data. The advantage is that the power plants participating in the load resource regulation in the power system are not unified, but multiple power plants participate together, and the multiple power plants have different power generation methods. Therefore, it is necessary to fuse their data to achieve the purpose of data unification, facilitate subsequent analysis, and improve the accuracy and rationality of the load resource regulation capability analysis;

[0051] The present invention fuses historical data of multi-source data based on influencing factors to obtain fused data, then constructs a load characteristic diagram based on the fused data, analyzes the load characteristic diagram to obtain the influence function of the influencing factors on the power load, and finally analyzes the load resource regulation capability of the power system based on the influence of the influencing factors on the power load. The advantage is that the load characteristic diagram and the influence function reflect the influence of the influencing factors on the power load of the power system, and then evaluates the load resource regulation capability of different power plants according to their power supply capabilities, thereby improving the accuracy and effectiveness of the load resource regulation capability analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 is a flow chart of the steps of the method of the present invention;

[0053] Figure 2 is the knowledge graph of the present invention;

[0054] Figure 3 This is the load characteristic diagram of the present invention. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] Example 1, please refer to Figure 1 As shown, the present application provides a load resource regulation capability analysis method based on knowledge graph and data fusion, comprising the following steps:

[0057] Step S1, collecting historical data from multiple sources; Step S1 includes the following sub-steps:

[0058] Step S101, the multi-source data includes ordinary power plant data and new energy power plant data, the historical data includes historical load data and historical weather data, the historical load data is the power load of the power system at a certain moment in the historical records, and the historical weather data is the ambient temperature at a certain moment in the historical records;

[0059] Step S102, marking the historical data in the ordinary power plant data as ordinary historical data, where the ordinary historical data includes ordinary historical load data and ordinary historical weather data;

[0060] Step S103, marking the historical data in the new energy power plant data as new energy historical data, where the new energy historical data includes new energy historical load data and new energy historical weather data;

[0061] Step S104, ordinary historical data is recorded by the ordinary historical database, and new energy historical data is recorded by the new energy historical database;

[0062] In specific implementation, when collecting historical weather data, it is usually necessary to collect solar radiation, ambient temperature and wind force. In this embodiment, only ambient temperature is used as an example to explain the specific analysis process, and other historical weather data are omitted in this embodiment. Part of the data of the general historical database is shown in Table 1 below:

[0063] Table 1 Partial data of common historical database

[0064] Recording time General historical load data General historical weather data 2024.3.26 13:00:00 237844kW 34℃ 2024.3.26 14:00:00 227938kW 33℃ 2024.3.26 15:00:00 215849kW 32℃ 2024.3.26 16:00:00 213988kW 32℃

[0065] The format of the data recorded in the new energy history database is the same as that of the data recorded in the common history database, so it will not be specifically demonstrated in this embodiment.

[0066] Step S2, establishing a knowledge graph of the power system, searching for factors influencing the power load in the knowledge graph, and marking them as influencing factors; Step S2 includes the following sub-steps:

[0067] See also Figure 2 As shown, in step S201, power equipment, users and environment are taken as entities, and a knowledge graph is constructed based on the relationship between them;

[0068] Step S202, the power equipment includes new energy equipment and common equipment;

[0069] Step S203, searching the knowledge graph for factors that affect power load and marking them as influencing factors;

[0070] In the specific implementation, the knowledge graph constructed is as follows Figure 2 As shown, the construction of the knowledge graph is implemented using existing technologies, and from the knowledge graph it can be obtained that the main factor affecting the power load is the ambient temperature, that is, the influencing factor is the ambient temperature.

[0071] Step S3, based on the influencing factors, data fusion is performed on the historical data of the multi-source data to obtain fused data; Step S3 includes the following sub-steps:

[0072] Step S301, searching for influencing factors and corresponding historical load data in a common historical database, marking them as common historical factors and common historical loads respectively;

[0073] Step S302, searching for influencing factors and corresponding historical load data in a new energy history database, and marking them as new energy history factors and new energy history loads respectively;

[0074] Step S303, finding the maximum value in the common historical load, marking it as the common maximum historical load, finding the maximum value in the new energy historical load, marking it as the new energy maximum historical load;

[0075] In the specific implementation, the common historical load data in Table 1 is the common historical load, and the common historical weather data is the common historical factor; the new energy historical factor and the new energy historical load are similarly the new energy historical factor and the new energy historical load in the new energy historical database, and the common maximum historical load is 271862kW, and the new energy maximum historical load is 124743kW;

[0076] Step S304, fusing multi-source data based on common historical load, new energy historical load, common maximum historical load and new energy maximum historical load;

[0077] Step S304 includes the following sub-steps:

[0078] Step S3041, based on different common historical factors and new energy historical factors, data fusion of common historical load and new energy maximum load;

[0079] Sort and number the common historical factors in ascending order, using the symbol T n Indicates, where n is a positive integer and n is the serial number of T; the new energy historical factors are sorted and numbered in ascending order, and the symbol H m represents, where m is a positive integer and m is the serial number of H;

[0080] The common history factor is T n All common historical loads are integrated and numbered, represented by the symbol A(n,i), where n is equal to T n The n in the figure corresponds to that in which i is a positive integer and (n,i) is the serial number of A; the new energy historical factor is H m All the historical loads of renewable energy are integrated and numbered, represented by the symbol B(m,j), where m and H m In the equation, m corresponds to j, which is a positive integer and (m,j) is the serial number of B;

[0081] In the specific implementation, the numbers T1 to T are obtained by sorting. 46 , 1≤n≤47, and similarly, H1 to H 46 , 1≤m≤47, because they are in the same area, so usually, the range of n and m is the same; 40 For example, T 40 The temperature is 30°C, and all common historical loads with a common historical factor of 30°C are obtained, a total of 436 data items are obtained, and A(30,1) to A(30,436) are obtained by numbering. The process of obtaining B(m,j) is the same as that of A(n,i), so it will not be specifically demonstrated in this embodiment;

[0082] When data fusion is performed on the common historical load and the common maximum historical load, the common historical load is fused and calculated using the common historical fusion formula to obtain the common load ratio, and then the new energy historical load is fused and calculated using the new energy historical fusion formula to obtain the new energy load ratio;

[0083] The general history fusion formula is configured as: Among them, RT n The common historical factor is T n The normal load ratio at that time, max(n) is the maximum value of n, and Tmax is the normal maximum historical load;

[0084] The new energy history fusion formula is configured as: Among them, RH m The historical factor for new energy is H m The new energy load ratio at that time, max(m) is the maximum value of m, and Hmax is the maximum historical load of new energy;

[0085] The common historical factors and the corresponding common load ratios are marked as a set of fusion data, that is, (T n ,RT n ) is marked as a set of fusion data, and the new energy historical factors and the corresponding new energy load ratio are marked as a set of fusion data, that is, (H m ,RH m ) is marked as a set of fused data, and several fused data are obtained by data fusion;

[0086] In the specific implementation, due to the large amount of data, the values ​​of A(n,i) and B(m,j) are not specifically displayed in this embodiment, and the calculated RT n and RH m The number of them is too large, and their calculation results are omitted in this embodiment. The purpose of calculating the ordinary load ratio and the new energy load ratio is to unify the measurement standards between them. Since the power generation capacity of ordinary power plants is much higher than that of new energy power plants, the data gap between them is large, and there will be large deviations in the analysis. Therefore, their data are fused by calculating the ratio to achieve the purpose of unifying the measurement standards.

[0087] Step S4, extracting load characteristics from the fused data and analyzing the impact of influencing factors on the power load; Step S4 includes the following sub-steps:

[0088] Step S401, constructing a load characteristic diagram based on fused data;

[0089] Step S401 includes the following sub-steps:

[0090] Step S4011, marking common historical factors and new energy historical factors in the fusion data as fusion historical factors;

[0091] Step S4012, marking the common load ratio and the new energy load ratio in the fused data as fused load ratio;

[0092] See also Figure 3 As shown, in step S4013, a plane rectangular coordinate system is established with the fused historical factor as the X-axis and the fused load ratio as the Y-axis, named as the load characteristic diagram, and the fused data is entered into the load characteristic diagram;

[0093] In the specific implementation, taking the fusion data (34℃, 0.8749) as an example, 34℃ is the fusion history factor, 0.8749 is the fusion load ratio, and the load characteristic diagram is constructed as follows: Figure 3 As shown;

[0094] Step S402, analyzing the load characteristic diagram to obtain an influence function of the influencing factors on the power load;

[0095] Step S402 includes the following sub-steps:

[0096] Step S4021, performing polynomial fitting on the load characteristic diagram;

[0097] Step S4022: mark the fitted function as an influence function. The format of the influence function is Y=a×X 2 +b×X+c, where Y is the fusion load ratio, X is the fusion history factor, and a, b, and c are constants that come with the influencing function;

[0098] In the specific implementation, the influence function obtained by fitting is Y=0.0007×X 2 -0.0197×X+0.7639, where a=0.0007, b=-0.0197, c=0.7639.

[0099] Step S5, based on the influence of the influencing factors on the power load, analyzing the load resource regulation capability of the power system; Step S5 includes the following sub-steps:

[0100] Step S501, obtaining an influence function and simultaneously obtaining the maximum amount of electricity that can be uploaded by the power system, which is marked as the maximum uploaded electricity;

[0101] Step S502, calculating the maximum load ratio of the power system by using the maximum load ratio calculation formula;

[0102] The maximum load ratio calculation formula is configured as: Among them, E is the maximum load ratio, UE is the maximum upload power, and 1h is one hour, which is used to convert the unit of UE from kWh to kW;

[0103] In the specific implementation, the maximum uploaded power is 420000kWh, the maximum common historical load is 271862kW, the maximum new energy historical load is 124743kW, and the maximum load ratio E is calculated to be 1.0590. The calculation result is rounded to four decimal places;

[0104] Step S503, analyzing the load resource regulation capability of the power system based on the influence function and the maximum load ratio;

[0105] Step S503 includes the following sub-steps:

[0106] Step S5031, let Y be equal to E, substitute it into the influence function, and mark the solved X as the upper limit of factor adjustment;

[0107] Step S5032, the factor adjustment upper limit means that after the influencing factor reaches the factor adjustment upper limit, the load resource adjustment capacity of the power system reaches the upper limit. If the power load increases further, the power system cannot meet all the power loads;

[0108] In the specific implementation, Y = 1.0590 is substituted into Y = 0.0007 × X 2 -0.0197×X+0.7639, the solution is X=39 or -11, the calculation result is rounded to an integer, and the upper limit of the factor adjustment is 39°C and -11°C, which means that when the ambient temperature exceeds 39°C or is lower than -11°C, the load resource adjustment capacity of the power system reaches the upper limit.

[0109] In addition, the logic instructions in the above-mentioned memory can be implemented in the form of software functional units and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art, and the computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.

[0110] Through the description of the above implementation methods, the embodiments of the present invention can be provided as methods, systems or computer program products. Based on such an understanding, the above technical solutions can be essentially or partly contributed to the prior art in the form of software products, which can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and include several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0111] In the embodiments provided in the present application, it should be understood that the disclosed system or method can be implemented in other ways. The embodiments described above are merely schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of systems, modules and units can be electrical, mechanical or other forms.

[0112] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A load resource regulation capability analysis method based on knowledge graph and data fusion, characterized in that: The steps include: Collect historical data from multiple sources; Establish a knowledge graph of the power system, find the factors that affect the power load in the knowledge graph, and mark them as influencing factors; Based on the influencing factors, the historical data of multi-source data is fused to obtain fused data; Extract load characteristics from fused data and analyze the impact of influencing factors on power load; Based on the impact of influencing factors on power load, the load resource regulation capability of the power system is analyzed.

2. The load resource regulation capability analysis method based on knowledge graph and data fusion according to claim 1 is characterized in that: Collecting historical data from multiple sources includes the following sub-steps: The multi-source data includes ordinary power plant data and new energy power plant data, and the historical data includes historical load data and historical weather data. The historical load data is the power load of the power system at a certain moment in the historical records, and the historical weather data is the ambient temperature at a certain moment in the historical records; Marking the historical data in the ordinary power plant data as ordinary historical data, where the ordinary historical data includes ordinary historical load data and ordinary historical weather data; Mark the historical data in the new energy power plant data as new energy historical data, which includes new energy historical load data and new energy historical weather data; The common historical data is recorded by a common historical database, and the new energy historical data is recorded by a new energy historical database.

3. The load resource regulation capability analysis method based on knowledge graph and data fusion according to claim 2 is characterized in that: Building a knowledge graph for the power system includes the following sub-steps: Take power equipment, users and environment as entities, and build a knowledge graph based on the relationship between them; The power equipment includes new energy equipment and ordinary equipment; Find the factors that affect power load in the knowledge graph and mark them as influencing factors.

4. The load resource regulation capability analysis method based on knowledge graph and data fusion according to claim 3 is characterized in that: Based on the influencing factors, the historical data of multi-source data is fused to obtain the fused data, which includes the following sub-steps: Find the influencing factors and the corresponding historical load data in the general historical database, and mark them as general historical factors and general historical loads respectively; Find the influencing factors and the corresponding historical load data in the new energy historical database, and mark them as new energy historical factors and new energy historical load respectively; Find the maximum value in the common historical load and mark it as the common maximum historical load; find the maximum value in the new energy historical load and mark it as the new energy maximum historical load; Data fusion is performed on multi-source data based on normal historical load, new energy historical load, normal maximum historical load and new energy maximum historical load.

5. The load resource regulation capability analysis method based on knowledge graph and data fusion according to claim 4 is characterized in that: The data fusion of multi-source data based on common historical load, new energy historical load, common maximum historical load and new energy maximum historical load includes the following sub-steps: Based on different common historical factors and new energy historical factors, data fusion is performed on common historical load and new energy maximum load; Sort and number the common historical factors in ascending order, using the symbol T n Indicates, where n is a positive integer and n is the serial number of T; the new energy historical factors are sorted and numbered in ascending order, and the symbol H m represents, where m is a positive integer and m is the serial number of H; The common history factor is T n All common historical loads are integrated and numbered, represented by the symbol A(n,i), where n is equal to T n The n in the figure corresponds to that in which i is a positive integer and (n,i) is the serial number of A; the new energy historical factor is H m All the historical loads of renewable energy are integrated and numbered, represented by the symbol B(m,j), where m and H m In the equation, m corresponds to j, which is a positive integer and (m,j) is the serial number of B; When data fusion is performed on the common historical load and the common maximum historical load, the common historical load is fused and calculated using the common historical fusion formula to obtain the common load ratio, and then the new energy historical load is fused and calculated using the new energy historical fusion formula to obtain the new energy load ratio; The general history fusion formula is configured as: Among them, RT n The common historical factor is T n The normal load ratio at that time, max(n) is the maximum value of n, and Tmax is the normal maximum historical load; The new energy history fusion formula is configured as: Among them, RH m The historical factor for new energy is H m The new energy load ratio at that time, max(m) is the maximum value of m, and Hmax is the maximum historical load of new energy; The common historical factors and the corresponding common load ratios are marked as a set of fusion data, that is, (T n ,RT n ) is marked as a set of fusion data, and the new energy historical factors and the corresponding new energy load ratio are marked as a set of fusion data, that is, (H m ,RH m ) is marked as a set of fused data, and several fused data are obtained through data fusion.

6. The load resource regulation capability analysis method based on knowledge graph and data fusion according to claim 5 is characterized in that: Extracting load characteristics from fused data and analyzing the impact of influencing factors on power load include the following sub-steps: Construct load characteristic diagram based on fused data; The load characteristic diagram is analyzed to obtain the influence function of the influencing factors on the power load.

7. The load resource regulation capability analysis method based on knowledge graph and data fusion according to claim 6 is characterized in that: Constructing a load characteristic diagram based on fused data includes the following sub-steps: Marking common historical factors and new energy historical factors in the fusion data as fusion historical factors; The common load ratio and the new energy load ratio in the fused data are marked as fused load ratios; A plane rectangular coordinate system is established with the fused historical factor as the X-axis and the fused load ratio as the Y-axis, named as the load characteristic diagram, and the fused data is entered into the load characteristic diagram.

8. The load resource regulation capability analysis method based on knowledge graph and data fusion according to claim 7 is characterized in that: Analyzing the load characteristic diagram to obtain the influence function of the influencing factors on the power load includes the following sub-steps: Perform polynomial fitting on the load characteristic diagram; The fitted function is marked as an influence function, and the format of the influence function is Y=a×X 2 +b×X+c, where Y is the fusion load ratio, X is the fusion history factor, and a, b, and c are all constants that influence the function.

9. The load resource regulation capability analysis method based on knowledge graph and data fusion according to claim 8 is characterized in that: Based on the impact of influencing factors on power load, analyzing the load resource regulation capability of the power system includes the following sub-steps: Obtain the influence function and the maximum amount of electricity that can be uploaded by the power system, marked as the maximum uploaded electricity; Calculate the maximum load ratio of the power system through the maximum load ratio calculation formula; The maximum load ratio calculation formula is configured as: Among them, E is the maximum load ratio, UE is the maximum upload power, and 1h is one hour, which is used to convert the unit of UE from kWh to kW; Based on the influence function and the maximum load ratio, the load resource regulation capability of the power system is analyzed.

10. The load resource regulation capability analysis method based on knowledge graph and data fusion according to claim 9 is characterized in that: Based on the influence function and the maximum load ratio, the analysis of the load resource regulation capability of the power system includes the following sub-steps: Let Y equal E, substitute it into the influence function, and mark the solved X as the upper limit of factor adjustment; The factor adjustment upper limit means that after the influencing factor reaches the factor adjustment upper limit, the load resource adjustment capacity of the power system reaches the upper limit. If the power load increases further, the power system cannot meet all the power loads.

Images