Historical data-based power grid operation mode intelligent generation method and system

Abstract

The invention provides a power grid operation mode intelligent generation method and system based on historical data, and the method comprises the steps: extracting operation mode characteristics in the historical operation data of a power grid based on a pre-constructed artificial intelligence model; generating target features according to the operation mode features; carrying out load flow calculation on the first operation mode data of the power grid, and verifying a calculation result and the target characteristics; if not, the artificial intelligence model modifies the first operation mode data of the power grid according to the target features to obtain second operation mode data of the power grid, and when the calculation result of the second operation mode data of the power grid is consistent with the target features, the adjustment of the artificial intelligence model on the operation mode data of the power grid is finished; checking the branch range to generate a plurality of pieces of check data; and performing load flow calculation on the check data, if the load flow calculation result of the check data is converged, passing the check, and taking the running mode passing the check as the running mode of the current power grid. And the working efficiency of generating the power grid operation mode is improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent simulation analysis and calculation of power systems, specifically to a method and system for intelligently generating power grid operation modes based on historical data. Background Technology

[0002] Power grid simulation analysis is widely used in power grid operation, planning, and security defense, serving as a fundamental supporting technology for large power grids. Conducting power grid simulation analysis requires first preparing power grid operation mode data, which must meet key indicators such as power flow convergence, qualified voltage levels at critical nodes, compliant cross-sectional power, and compliant DC power. In preparing this data, manual intervention is necessary to determine targets for key node voltage levels, load targets, cross-sectional target power, and DC target power based on past experience with actual power grid operation. This data is then manually modified, calculated, and verified to confirm compliance with requirements. In this process, human experience is a crucial factor in generating power grid operation modes; different personnel with varying experience will produce different key indicators for the generated operation modes, highlighting the significant influence of subjective factors. Summary of the Invention

[0003] To address the aforementioned technical problems, this invention provides a method for intelligently generating power grid operation modes based on historical data, comprising:

[0004] Based on a pre-built artificial intelligence model, the operating mode characteristics of the power grid are extracted from historical power grid operation data; and target characteristics of the power grid operating mode are generated based on the operating mode characteristics.

[0005] Power flow calculation is performed on the current power grid first operating mode data, and the power flow calculation result is verified with the indicators in the target feature; if the verification fails, the artificial intelligence model modifies the current power grid first operating mode data according to the target feature and obtains the current power grid second operating mode data until the power flow calculation result of the current power grid second operating mode data is verified with the indicators in the target feature, at which point the adjustment of the power grid operating mode data by the artificial intelligence model ends.

[0006] The branch range of the selected second operating mode data is verified to generate multiple operating mode verification data; power flow calculation is performed on the multiple operating mode verification data. If the power flow calculation results of the multiple operating mode verification data converge, the second operating mode data passes the verification, and the operating mode that passes the verification is taken as the current power grid operating mode.

[0007] Furthermore, the artificial intelligence model is constructed based on historical power grid operation data.

[0008] Furthermore, after performing power flow calculations on the current power grid's first operating mode data and verifying the calculation results against the indicators in the target characteristics, the method further includes:

[0009] If the verification is successful, the branch range of the current power grid first operating mode data is checked to generate multiple operating mode check data; power flow calculation is performed on the multiple operating mode check data. If the power flow calculation results of the multiple operating mode check data converge, the first operating mode data passes the verification, and the operating mode that passes the verification is taken as the current power grid operating mode.

[0010] Furthermore, the power flow calculation results are verified against the indicators in the target features, including:

[0011] Based on the power flow calculation results and the power flow convergence, key node voltage level, generation level, load level, cross-sectional power, and DC power indices in the target characteristics, the power flow index F of historical operating data and the current power grid operating mode data F' are calculated. Let α be the allowable error range. If the current power grid operation data is considered to conform to the characteristics of historical operation data, the verification is passed; otherwise, the verification fails.

[0012] Furthermore, based on the power flow calculation results and the power flow convergence, key node voltage level, generation level, load level, cross-sectional power, and DC power indices in the target characteristics, the power flow index F of historical operating data and the current power grid operating mode data F' are calculated, including:

[0013] Let the power flow convergence index be F0, the power generation level index be F1, the load level index be F2, the cross-sectional power index be F3, the DC power index be F4, and the critical node voltage level index be F5 in the target characteristics.

[0014] F=F0×(a1×F1+a2×F2+a3×F3+a4×F4+a5×F5)

[0015] F is the power flow index of historical operating data, and a1, a2, a3, a4, and a5 are the power generation level coefficient, load level coefficient, cross-sectional power coefficient, DC power coefficient, and critical node voltage level coefficient, respectively, and a1+a2+a3+a4+a5=1;

[0016] In the power flow calculation results, the current power flow convergence index is F0, the power generation level index is F1', the load level index is F2', the cross-sectional power index is F3', the DC power index is F4', and the critical node voltage level index is F5'.

[0017] F'=F0×(a1×F1'+a2×F2'+a3×F3'+a4×F4'+a5×F5')

[0018] F' represents the index of the current power grid operation mode data, and a1, a2, a3, a4, and a5 are the power generation level coefficient, load level coefficient, cross-sectional power coefficient, DC power coefficient, and key node voltage level coefficient, respectively, and a1+a2+a3+a4+a5=1.

[0019] Furthermore, the power generation level indicator F1,

[0020] F1=b1*F11+b2*F12+b3*F13+b4*F14+b5*F15+b6*F16;

[0021] b1, b2, b3, b4, b5, and b6 are the power generation level coefficients for wind power, photovoltaic power, energy storage power, thermal power, hydropower, and other power generation types, respectively, and b1+b2+b3+b4+b5+b6=1.

[0022] Furthermore,

[0023] In the section power index F3, the power grid includes k sections, and the power of each section is F31, F32, ..., F3k respectively. Then F3 = d1*F31 + d2*F32 + ... + dk*F3k, where d1, d2, ..., dk are the weighting coefficients of each section, and d1 + d2 + ... + dk = 1.

[0024] Furthermore,

[0025] In the DC power index F4, the power grid includes i DC lines, and the power of each DC line is F41, F42, ..., F4i, respectively. Then F4 = e1*F41 + e2*F42 + ... + ei*F4i, where e1, e2, ..., ei are the weighting coefficients of each DC line, and e1 + e2 + ... + ei = 1.

[0026] Furthermore,

[0027] In the critical node voltage level F5, the power grid includes j nodes, and the voltages of each node are F51, F52, ..., F5j. Then F5 = f1*F51 + f2*F52 + ... + fk*F5j, where f1, f2, ..., fk are the weighting coefficients of each critical node voltage level, and f1 + f2 + ... + fk = 1.

[0028] Furthermore, the branch range of the selected second operating mode data is verified, generating multiple operating mode verification data, including:

[0029] The branch range of the selected second operating mode data is verified by sequentially cutting off each branch within the branch range to form multiple operating mode verification data.

[0030] This invention also provides an intelligent power grid operation mode generation system based on historical data, comprising:

[0031] The target feature generation module is used to extract the operating mode features of the power grid from historical power grid operation data based on a pre-built artificial intelligence model; and generate target features of the power grid operation mode based on the operating mode features.

[0032] The operation data adjustment module is used to perform power flow calculation on the current power grid first operation mode data, and verify the power flow calculation result with the indicators in the target feature; if the verification fails, the artificial intelligence model modifies the current power grid first operation mode data according to the target feature, obtains the current power grid second operation mode data, and the adjustment of the power grid operation mode data by the artificial intelligence model ends when the power flow calculation result of the current power grid second operation mode data passes the verification with the indicators in the target feature.

[0033] The operation mode determination module is used to verify the branch range of the selected second operation mode data and generate multiple operation mode verification data; perform power flow calculation on the multiple operation mode verification data; if the power flow calculation results of the multiple operation mode verification data converge, the second operation mode data passes the verification, and the operation mode that passes the verification is taken as the current power grid operation mode.

[0034] Furthermore, the artificial intelligence model is constructed based on historical power grid operation data.

[0035] Furthermore, it also includes:

[0036] The data verification module is used to verify the branch range of the current power grid first operating mode data if the verification is successful, and generate multiple operating mode verification data; perform power flow calculation on the multiple operating mode verification data; if the power flow calculation results of the multiple operating mode verification data converge, the first operating mode data passes the verification, and the verified operating mode is taken as the current power grid operating mode.

[0037] Furthermore, the runtime data adjustment module includes:

[0038] The historical operating data feature determination submodule is used to calculate the historical operating data's power flow index F and the current grid operating mode data F' based on the power flow calculation results and the target features, including power flow convergence, key node voltage level, generation level, load level, cross-sectional power, and DC power index. Let α be the allowable error range. If the current power grid operation data is considered to conform to the characteristics of historical operation data, the verification is passed; otherwise, the verification fails.

[0039] Furthermore, the historical operational data characteristic determination submodule includes:

[0040] The first power flow index calculation submodule is used to set the power flow convergence index as F0, the power generation level index as F1, the load level index as F2, the cross-sectional power index as F3, the DC power index as F4, and the critical node voltage level index as F5 in the target features.

[0041] F=F0×(a1×F1+a2×F2+a3×F3+a4×F4+a5×F5)

[0042] F is the power flow index of historical operating data, and a1, a2, a3, a4, and a5 are the power generation level coefficient, load level coefficient, cross-sectional power coefficient, DC power coefficient, and critical node voltage level coefficient, respectively, and a1+a2+a3+a4+a5=1;

[0043] The first power flow index calculation submodule is used to set the power flow convergence index as F0, the power generation level index as F1', the load level index as F2', the cross-sectional power index as F3', the DC power index as F4', and the critical node voltage level index as F5' in the current power flow calculation results.

[0044] F'=F0×(a1×F1'+a2×F2'+a3×F3'+a4×F4'+a5×F5')

[0045] F' represents the index of the current power grid operation mode data, and a1, a2, a3, a4, and a5 are the power generation level coefficient, load level coefficient, cross-sectional power coefficient, DC power coefficient, and key node voltage level coefficient, respectively, and a1+a2+a3+a4+a5=1.

[0046] Furthermore, the power generation level indicator F1,

[0047] F1=b1*F11+b2*F12+b3*F13+b4*F14+b5*F15+b6*F16;

[0048] b1, b2, b3, b4, b5, and b6 are the power generation level coefficients for wind power, photovoltaic power, energy storage power, thermal power, hydropower, and other power generation types, respectively, and b1+b2+b3+b4+b5+b6=1.

[0049] Furthermore,

[0050] In the section power index F3, the power grid includes k sections, and the power of each section is F31, F32, ..., F3k respectively. Then F3 = d1*F31 + d2*F32 + ... + dk*F3k, where d1, d2, ..., dk are the weighting coefficients of each section, and d1 + d2 + ... + dk = 1.

[0051] Furthermore,

[0052] In the DC power index F4, the power grid includes i DC lines, and the power of each DC line is F41, F42, ..., F4i, respectively. Then F4 = e1*F41 + e2*F42 + ... + ei*F4i, where e1, e2, ..., ei are the weighting coefficients of each DC line, and e1 + e2 + ... + ei = 1.

[0053] Furthermore,

[0054] In the critical node voltage level F5, the power grid includes j nodes, and the voltages of each node are F51, F52, ..., F5j. Then F5 = f1*F51 + f2*F52 + ... + fk*F5j, where f1, f2, ..., fk are the weighting coefficients of each critical node voltage level, and f1 + f2 + ... + fk = 1.

[0055] Furthermore, the operation mode determination module includes:

[0056] The verification submodule is used to verify the branch range of the selected second operating mode data. It sequentially disconnects each branch within the branch range to form multiple operating mode verification data.

[0057] This invention also provides a computer device, comprising: one or more processors;

[0058] The processor is used to store one or more programs;

[0059] When the one or more programs are executed by the one or more processors, the intelligent generation method for power grid operation modes based on historical data as described in any of the preceding claims is implemented.

[0060] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed, it implements the intelligent generation method for power grid operation mode based on historical data as described in any one of the preceding claims.

[0061] The present invention provides a method and system for intelligently generating power grid operation modes based on historical data. It eliminates the need for matching power grid component names, and the adjustment of operation modes is performed by an artificial intelligence model. The verification of operation modes is also completed automatically, which greatly reduces the time required to generate operation mode data that meets the requirements, saves manpower, material resources and time, and significantly improves work efficiency. Attached Figure Description

[0062] Figure 1 This is a flowchart illustrating a method for intelligently generating power grid operation modes based on historical data, provided in an embodiment of the present invention.

[0063] Figure 2 This is a schematic diagram of the structure of an intelligent power grid operation mode generation system based on historical data provided in an embodiment of the present invention. Detailed Implementation

[0064] Numerous specific details are set forth in the following description to provide a full understanding of the invention. However, the invention can be practiced in many other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0065] Example 1

[0066] This invention provides a method and system for intelligently generating power grid operation modes based on historical data, such as... Figure 1 As shown, this addresses the problem of heavy reliance on human experience mentioned in the background art.

[0067] To achieve the above objectives, the present invention provides the following technical solution:

[0068] Step S101: Based on the pre-built artificial intelligence model, extract the operating mode characteristics of the power grid from the historical operating data of the power grid; and generate target characteristics of the power grid operating mode according to the operating mode characteristics.

[0069] This invention acquires historical power grid operation data and power grid operation mode data, and generates an artificial intelligence (AI) model based on this data. It also allows for the management of the AI ​​model, including its name, function, number of calls, and call success rate. The AI ​​model in this invention is not limited to a specific implementation process; multiple AI models are possible, as long as they conform to the input / output interfaces of the AI ​​model described in this invention. The function of this AI model is to extract the power grid operation mode characteristics from historical power grid operation data to generate power grid operation data.

[0070] Then, the operation mode characteristics are intelligently extracted and generated. Specifically, one or more historical power grid operation data are selected, and the artificial intelligence model extracts the power grid operation mode characteristics and generates the target characteristics of the power grid operation mode (key node voltage level, power generation level, load level, cross-sectional power and DC power). Combined with the selected power grid operation data, the power grid operation data is modified to form new power grid operation data.

[0071] Step S102: Perform power flow calculation on the current power grid first operating mode data, and verify the power flow calculation result with the indication in the target feature; if the verification fails, the artificial intelligence model modifies the current power grid first operating mode data according to the target feature, obtains the current power grid second operating mode data, and the adjustment of the power grid operating mode data by the artificial intelligence model ends when the power flow calculation result of the current power grid second operating mode data passes the verification with the indicator in the target feature.

[0072] Intelligent adjustment of operating modes refers to invoking a power flow calculation program to perform power flow calculations on new power grid operating data and verifying whether the calculation results are consistent with the target characteristics. If they are inconsistent, the power flow adjustment AI model modifies the power grid operating data according to the target characteristics of the power grid operating mode, and then invokes the power flow calculation program again to perform power flow calculations to verify whether the target characteristics are met. This process of modifying the power grid operating data is repeated until the target characteristics are achieved. Specifically, power flow calculations are performed on the current first power grid operating mode data, and the results are verified against the target characteristics. If the verification passes, the branch range of the current first power grid operating mode data is checked. If the verification fails, the AI ​​model modifies the current first power grid operating mode data according to the target characteristics and obtains the current second power grid operating mode data. The adjustment of the power grid operating mode data by the AI ​​model ends when the power flow calculation results of the current second power grid operating mode data are consistent with the target characteristics.

[0073] An artificial intelligence (AI) model extracts features from historical operating data and combines them with power grid operation mode data to generate a new power grid operation mode. This new operation mode requires calculation by a power flow calculation program to verify whether the features of the new operation mode are consistent with the features extracted by the AI ​​model. If they are inconsistent, the operation mode adjustment AI model needs to be adjusted until the new operation mode features are consistent with the features extracted by the AI ​​model. The two types of AI models involved in this invention are: one for extracting features from historical operating data, and the other for adjusting power grid operation modes.

[0074] Verifying whether the power flow calculation results are consistent with the target characteristics involves verifying them using six indicators: power flow convergence, critical node voltage level, generation level, load level, cross-sectional power, and DC power. Let F0 be the power flow convergence indicator, F1 be the generation level indicator, F2 be the load level indicator, F3 be the cross-sectional power indicator, F4 be the DC power indicator, and F5 be the critical node voltage level indicator.

[0075] Calculate the power flow index F based on historical operating data and the current power grid operating mode index F'. Let α be the allowable error range. If the current power grid operation data is considered to conform to the characteristics of historical operation data, the verification is passed; otherwise, the verification fails.

[0076] Let the power flow convergence index be F0, the power generation level index be F1, the load level index be F2, the cross-sectional power index be F3, the DC power index be F4, and the critical node voltage level index be F5 in the target characteristics.

[0077] F=F0×(a1×F1+a2×F2+a3×F3+a4×F4+a5×F5)

[0078] F is the power flow index of historical operating data, and a1, a2, a3, a4, and a5 are the power generation level coefficient, load level coefficient, cross-sectional power coefficient, DC power coefficient, and critical node voltage level coefficient, respectively, and a1+a2+a3+a4+a5=1;

[0079] In the power flow calculation results, the current power flow convergence index is F0, the power generation level index is F1', the load level index is F2', the cross-sectional power index is F3', the DC power index is F4', and the critical node voltage level index is F5'.

[0080] F'=F0×(a1×F1'+a2×F2'+a3×F3'+a4×F4'+a5×F5')

[0081] F' represents the index of the current power grid operation mode data, and a1, a2, a3, a4, and a5 are the power generation level coefficient, load level coefficient, cross-sectional power coefficient, DC power coefficient, and key node voltage level coefficient, respectively, and a1+a2+a3+a4+a5=1.

[0082] Power generation level index F1, F1=b1*F11+b2*F12+b3*F13+b4*F14+b5*F15+b6*F16;

[0083] b1, b2, b3, b4, b5, and b6 are the power generation level coefficients for wind power, photovoltaic power, energy storage power, thermal power, hydropower, and other power generation types, respectively, and b1+b2+b3+b4+b5+b6=1.

[0084] The power generation level F1 can be composed of wind power generation level F11, photovoltaic power generation level F12, energy storage power generation level F13, thermal power generation level F14, hydropower generation level F15, and other power generation type level F16.

[0085] F1=b1*F11+b2*F12+b3*F13+b4*F14+b5*F15+b6*F16

[0086] b1, b2, b3, b4, b5, and b6 are the power generation level coefficients for wind power, photovoltaic power, energy storage power, thermal power, hydropower, and other power generation types, respectively, and b1+b2+b3+b4+b5+b6=1.

[0087] In the section power index F3, the power grid includes k sections, and the power of each section is F31, F32, ..., F3k respectively. Then F3 = d1*F31 + d2*F32 + ... + dk*F3k, where d1, d2, ..., dk are the weighting coefficients of each section, and d1 + d2 + ... + dk = 1.

[0088] In the DC power index F4, the power grid includes i DC lines, and the power of each DC line is F41, F42, ..., F4i, respectively. Then F4 = e1*F41 + e2*F42 + ... + ei*F4i, where e1, e2, ..., ei are the weighting coefficients of each DC line, and e1 + e2 + ... + ei = 1.

[0089] In the critical node voltage level F5, the power grid includes j nodes, and the voltages of each node are F51, F52, ..., F5j. Then F5 = f1*F51 + f2*F52 + ... + fk*F5j, where f1, f2, ..., fk are the weighting coefficients of each critical node voltage level, and f1 + f2 + ... + fk = 1.

[0090] Step S103: Verify the branch range of the selected second operating mode data to generate multiple operating mode verification data; perform power flow calculation on the multiple operating mode verification data; if the power flow calculation results of the multiple operating mode verification data converge, the second operating mode data passes the verification, and the operating mode that passes the verification is taken as the current power grid operating mode.

[0091] Automatic verification of operating modes refers to the process of selecting a range of branches to be verified based on the intelligent adjustment of operating modes to generate operating mode data, sequentially disconnecting each branch within the range to form multiple operating mode verification data, and then calling a power flow calculation program to perform power flow calculation on the multiple operating mode verification data to determine whether the verification data converges. After selecting the branch range, based on the second operating mode data, the selected branches are sequentially disconnected to form multiple operating mode data. That is, if the number of selected branches is N, based on the second operating data, the selected branches are sequentially disconnected (one branch at a time) to form N operating mode data. If all operating mode verification data within the selected verification branch range converges in power flow calculation, then the operating mode data passes the automatic verification; otherwise, it fails the automatic verification. In this invention, the branch range of the selected second operating mode data is verified by sequentially disconnecting each branch within the branch range to form multiple operating mode verification data. After verification, the system outputs the operation mode data generated by the historical operation mode feature intelligent extraction and generation function, the target features of this data, the new operation mode data after intelligent adjustment of the operation mode, and the automatic verification result of the new operation mode data. The automatic verification result of the new operation mode data indicates whether the new operation mode data passes the automatic verification. If it passes the automatic verification, the result will be "Passed all verifications"; if it fails, the result will be "Failed verification", and the name of the branch that failed the verification will be output.

[0092] Example 2

[0093] In this embodiment of the invention, a method and system for intelligently generating power grid operation modes based on historical data includes data management, intelligent model management, intelligent extraction and generation of historical operation mode features, intelligent adjustment of operation modes, automatic verification of operation modes, and result output.

[0094] Step 1: Upload historical operation mode data and power grid operation mode data to the data management module.

[0095] Step 2: Upload the AI ​​model for intelligent extraction of historical operation mode features and the AI ​​model for intelligent adjustment of operation mode flow to the intelligent model management module. There can be multiple AI models for both the intelligent extraction of historical operation mode features and the intelligent adjustment of operation mode flow.

[0096] Step 3: Select one historical operation mode data and one power grid operation mode data from the data management module.

[0097] Step 4: Select a historical operation mode intelligent extraction model and an operation mode power flow intelligent adjustment model from the intelligent model management module.

[0098] Step 5: Based on the selected historical operation mode data, run the historical operation mode intelligent extraction model to obtain the power flow characteristics F and its sub-features of the historical operation mode data, namely, the power generation level index is F1, the load level index is F2, the cross-sectional power index is F3, the DC power index is F4, and the key node voltage level index is F5.

[0099] Step 6: Using the power flow characteristics F and its sub-characteristics of historical operation mode data as the target, and based on the selected power grid operation mode data, generate new power grid operation mode data using the intelligent power flow adjustment model.

[0100] Step 7: Based on the new power grid operation mode data, call the power flow calculation program to obtain the power flow calculation results of the new power grid operation mode data, and calculate its power flow characteristics F' and its sub-characteristics, namely, the generation level index is F1', the load level index is F2', the cross-sectional power index is F3', the DC power index is F4', and the critical node voltage level index is F5'.

[0101] Step 8: Set the method to generate the allowable error α, and verify whether it is satisfied. If the conditions are met, proceed to step 9; otherwise, return to step 6, generate new power grid operation mode data, and proceed to step 7, until the conditions are met. Alternatively, if the maximum number of calculations is reached, proceed to step 11.

[0102] Step 9: Select the branch range to be verified, disconnect each branch within the range sequentially to generate multiple operation mode verification data, and call the power flow calculation program to perform power flow calculation on the multiple operation mode verification data to determine whether the verification data converges. If the power flow calculation of all operation mode verification data within the selected verification branch range converges, then the operation mode data passes the automatic verification; otherwise, it fails the automatic verification.

[0103] Step 10: Generate the product from step 8 that satisfies... The system stores the results of the power grid operation mode data, as well as the verification status, including the scope of the verified branch and whether it has passed the automatic verification.

[0104] Step 11: If step 8 cannot generate a result that satisfies... If the power grid operation mode data is not available, the result will be stored with the message "Unable to generate power grid operation mode data based on this historical operation mode".

[0105] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

[0106] Example 3

[0107] Based on the same inventive concept, this invention also provides a smart power grid operation mode generation system 200 based on historical data, such as... Figure 2 As shown, it includes:

[0108] The target feature generation module 210 is used to extract the operating mode features of the power grid from the historical operating data of the power grid based on a pre-built artificial intelligence model; and generate target features of the power grid operating mode based on the operating mode features.

[0109] The data adjustment module 220 is used to perform power flow calculation on the current power grid first operating mode data, and verify the power flow calculation result with the indicators in the target feature; if the verification fails, the artificial intelligence model modifies the current power grid first operating mode data according to the target feature, and obtains the current power grid second operating mode data, until the power flow calculation result of the current power grid second operating mode data passes the verification with the indicators in the target feature, at which point the artificial intelligence model ends the adjustment of the power grid operating mode data;

[0110] The operation mode determination module 230 is used to verify the branch range of the selected second operation mode data and generate multiple operation mode verification data; perform power flow calculation on the multiple operation mode verification data; if the power flow calculation results of the multiple operation mode verification data converge, the second operation mode data passes the verification, and the operation mode that passes the verification is taken as the current power grid operation mode.

[0111] Furthermore, the artificial intelligence model is constructed based on historical power grid operation data.

[0112] Furthermore, it also includes:

[0113] The data verification module is used to verify the branch range of the current power grid first operating mode data if the verification is successful, and generate multiple operating mode verification data; perform power flow calculation on the multiple operating mode verification data; if the power flow calculation results of the multiple operating mode verification data converge, the first operating mode data passes the verification, and the verified operating mode is taken as the current power grid operating mode.

[0114] Furthermore, the runtime data adjustment module includes:

[0115] The historical operating data feature determination submodule is used to calculate the historical operating data's power flow index F and the current grid operating mode data F' based on the power flow calculation results and the target features, including power flow convergence, key node voltage level, generation level, load level, cross-sectional power, and DC power index. Let α be the allowable error range. If the current power grid operation data is considered to conform to the characteristics of historical operation data, the verification is passed; otherwise, the verification fails.

[0116] Furthermore, the historical operational data characteristic determination submodule includes:

[0117] The first power flow index calculation submodule is used to set the power flow convergence index as F0, the power generation level index as F1, the load level index as F2, the cross-sectional power index as F3, the DC power index as F4, and the critical node voltage level index as F5 in the target features.

[0118] F=F0×(a1×F1+a2×F2+a3×F3+a4×F4+a5×F5)

[0119] F is the power flow index of historical operating data, and a1, a2, a3, a4, and a5 are the power generation level coefficient, load level coefficient, cross-sectional power coefficient, DC power coefficient, and critical node voltage level coefficient, respectively, and a1+a2+a3+a4+a5=1;

[0120] The first power flow index calculation submodule is used to set the power flow convergence index as F0, the power generation level index as F1', the load level index as F2', the cross-sectional power index as F3', the DC power index as F4', and the critical node voltage level index as F5' in the current power flow calculation results.

[0121] F'=F0×(a1×F1'+a2×F2'+a3×F3'+a4×F4'+a5×F5')

[0122] F' represents the index of the current power grid operation mode data, and a1, a2, a3, a4, and a5 are the power generation level coefficient, load level coefficient, cross-sectional power coefficient, DC power coefficient, and key node voltage level coefficient, respectively, and a1+a2+a3+a4+a5=1.

[0123] Furthermore, the power generation level indicator F1,

[0124] F1=b1*F11+b2*F12+b3*F13+b4*F14+b5*F15+b6*F16;

[0125] b1, b2, b3, b4, b5, and b6 are the power generation level coefficients for wind power, photovoltaic power, energy storage power, thermal power, hydropower, and other power generation types, respectively, and b1+b2+b3+b4+b5+b6=1.

[0126] Furthermore,

[0127] In the section power index F3, the power grid includes k sections, and the power of each section is F31, F32, ..., F3k respectively. Then F3 = d1*F31 + d2*F32 + ... + dk*F3k, where d1, d2, ..., dk are the weighting coefficients of each section, and d1 + d2 + ... + dk = 1.

[0128] Furthermore,

[0129] In the DC power index F4, the power grid includes i DC lines, and the power of each DC line is F41, F42, ..., F4i, respectively. Then F4 = e1*F41 + e2*F42 + ... + ei*F4i, where e1, e2, ..., ei are the weighting coefficients of each DC line, and e1 + e2 + ... + ei = 1.

[0130] Furthermore,

[0131] In the critical node voltage level F5, the power grid includes j nodes, and the voltages of each node are F51, F52, ..., F5j. Then F5 = f1*F51 + f2*F52 + ... + fk*F5j, where f1, f2, ..., fk are the weighting coefficients of each critical node voltage level, and f1 + f2 + ... + fk = 1.

[0132] Furthermore, the operation mode determination module includes:

[0133] The verification submodule is used to verify the branch range of the selected second operating mode data. It sequentially disconnects each branch within the branch range to form multiple operating mode verification data.

[0134] This invention also provides a computer device, comprising: one or more processors;

[0135] The processor is used to store one or more programs;

[0136] When the one or more programs are executed by the one or more processors, the intelligent generation method for power grid operation modes based on historical data as described in any of the preceding claims is implemented.

[0137] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed, it implements the intelligent generation method for power grid operation mode based on historical data as described in any one of the preceding claims.

[0138] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied 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.

[0139] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0140] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0141] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0142] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of the claims of the present invention.

Claims

1. A method for intelligently generating power grid operation modes based on historical data, characterized in that, include: Based on a pre-built artificial intelligence model, the characteristics of the power grid's operation mode are extracted from the historical operation data of the power grid; Based on the aforementioned operating mode characteristics, target characteristics of the power grid operating mode are generated; Power flow calculation is performed on the current power grid first operating mode data, and the power flow calculation result is verified with the indicators in the target feature; if the verification fails, the artificial intelligence model modifies the current power grid first operating mode data according to the target feature and obtains the current power grid second operating mode data until the power flow calculation result of the current power grid second operating mode data is verified with the indicators in the target feature, at which point the adjustment of the power grid operating mode data by the artificial intelligence model ends. The branch range of the selected second operating mode data is verified to generate multiple operating mode verification data; power flow calculation is performed on the multiple operating mode verification data. If the power flow calculation results of the multiple operating mode verification data converge, the second operating mode data passes the verification, and the operating mode that passes the verification is taken as the current power grid operating mode.

2. The method according to claim 1, characterized in that, The artificial intelligence model is built based on historical power grid operation data.

3. The method according to claim 1, characterized in that, After performing power flow calculations on the current power grid's first operating mode data and verifying the calculation results against the indicators in the target characteristics, the method further includes: If the verification is successful, the branch range of the current power grid first operating mode data is checked to generate multiple operating mode check data; power flow calculation is performed on the multiple operating mode check data. If the power flow calculation results of the multiple operating mode check data converge, the first operating mode data passes the verification, and the operating mode that passes the verification is taken as the current power grid operating mode.

4. The method according to claim 1, characterized in that, The power flow calculation results are verified against the indicators in the target features, including: Based on the power flow calculation results and the power flow convergence, key node voltage level, generation level, load level, cross-sectional power, and DC power indices in the target characteristics, the power flow index F of historical operating data and the current power grid operating mode data F' are calculated. Let α be the allowable error range, when... If the current power grid operation data is considered to conform to the characteristics of historical operation data, the verification is passed; otherwise, the verification fails.

5. The method according to claim 4, characterized in that, Based on the power flow calculation results and the power flow convergence, key node voltage level, generation level, load level, cross-sectional power, and DC power indices in the target characteristics, calculate the power flow index F of historical operating data and the current power grid operating mode data F', including: Let the power flow convergence index be F0, the power generation level index be F1, the load level index be F2, the cross-sectional power index be F3, the DC power index be F4, and the critical node voltage level index be F5 in the target characteristics. F=F0×(a1×F1+a2×F2+a3×F3+a4×F4+a5×F5) F is the power flow index of historical operating data, and a1, a2, a3, a4, and a5 are the power generation level coefficient, load level coefficient, cross-sectional power coefficient, DC power coefficient, and critical node voltage level coefficient, respectively, and a1+a2+a3+a4+a5=1; In the power flow calculation results, the current power flow convergence index is F0, the power generation level index is F1', the load level index is F2', the cross-sectional power index is F3', the DC power index is F4', and the critical node voltage level index is F5'. F'=F0×(a1×F1'+a2×F2'+a3×F3'+a4×F4'+a5×F5') F' represents the index of the current power grid operation mode data, and a1, a2, a3, a4, and a5 are the power generation level coefficient, load level coefficient, cross-sectional power coefficient, DC power coefficient, and key node voltage level coefficient, respectively, and a1+a2+a3+a4+a5=1.

6. The method according to claim 4, characterized in that, Power generation level index F1, F1=b1*F11+b2*F12+b3*F13+b4*F14+b5*F15+b6*F16; b1, b2, b3, b4, b5, and b6 are the power generation level coefficients for wind power, photovoltaic power, energy storage power, thermal power, hydropower, and other power generation types, respectively, and b1+b2+b3+b4+b5+b6=1.

7. The method according to claim 4, characterized in that, In the section power index F3, the power grid includes k sections, and the power of each section is F31, F32, ..., F3k respectively. Then F3 = d1*F31 + d2*F32 + ... + dk*F3k, where d1, d2, ..., dk are the weighting coefficients of each section, and d1 + d2 + ... + dk = 1.

8. The method according to claim 4, characterized in that, In the DC power index F4, the power grid includes i DC lines, and the power of each DC line is F41, F42, ..., F4i, respectively. Then F4 = e1*F41 + e2*F42 + ... + ei*F4i, where e1, e2, ..., ei are the weighting coefficients of each DC line, and e1 + e2 + ... + ei = 1.

9. The method according to claim 4, characterized in that, In the critical node voltage level F5, the power grid includes j nodes, and the voltages of each node are F51, F52, ..., F5j. Then F5 = f1*F51 + f2*F52 + ... + fk*F5j, where f1, f2, ..., fk are the weighting coefficients of each critical node voltage level, and f1 + f2 + ... + fk = 1.

10. The method according to claim 1, characterized in that, The branch range of the selected second operating mode data is verified, generating multiple operating mode verification data, including: The branch range of the selected second operating mode data is verified by sequentially cutting off each branch within the branch range to form multiple operating mode verification data.

11. A smart power grid operation mode generation system based on historical data, characterized in that, include: The target feature generation module is used to extract the operating mode features of the power grid from historical power grid operation data based on a pre-built artificial intelligence model. Based on the aforementioned operating mode characteristics, target characteristics of the power grid operating mode are generated; The operation data adjustment module is used to perform power flow calculation on the current power grid first operation mode data and verify the power flow calculation results with the indicators in the target characteristics; If the verification fails, the artificial intelligence model modifies the current power grid first operating mode data according to the target feature and obtains the current power grid second operating mode data. The adjustment of the power grid operating mode data by the artificial intelligence model ends when the power flow calculation result of the current power grid second operating mode data passes the verification with the indicators in the target feature. The operation mode determination module is used to verify the branch range of the selected second operation mode data and generate multiple operation mode verification data; perform power flow calculation on the multiple operation mode verification data; if the power flow calculation results of the multiple operation mode verification data converge, the second operation mode data passes the verification, and the operation mode that passes the verification is taken as the current power grid operation mode.

12. The system according to claim 11, characterized in that, The artificial intelligence model is built based on historical power grid operation data.

13. The system according to claim 11, characterized in that, Also includes: The data verification module is used to verify the branch range of the current power grid first operating mode data if the verification is successful, and generate multiple operating mode verification data. Power flow calculations are performed on the multiple operating mode verification data. If the power flow calculation results of the multiple operating mode verification data converge, the first operating mode data passes the verification, and the operating mode that passes the verification is taken as the current power grid operating mode.

14. The system according to claim 11, characterized in that, The runtime data adjustment module includes: The historical operating data feature determination submodule is used to calculate the historical operating data's power flow index F and the current grid operating mode data F' based on the power flow calculation results and the target features, including power flow convergence, key node voltage level, generation level, load level, cross-sectional power, and DC power index. Let α be the allowable error range. If the current power grid operation data is considered to conform to the characteristics of historical operation data, the verification is passed; otherwise, the verification fails.

15. The system according to claim 14, characterized in that, The historical operational data characteristic determination submodule includes: The first power flow index calculation submodule is used to set the power flow convergence index as F0, the power generation level index as F1, the load level index as F2, the cross-sectional power index as F3, the DC power index as F4, and the critical node voltage level index as F5 in the target features. F=F0×(a1×F1+a2×F2+a3×F3+a4×F4+a5×F5) F is the power flow index of historical operating data, and a1, a2, a3, a4, and a5 are the power generation level coefficient, load level coefficient, cross-sectional power coefficient, DC power coefficient, and critical node voltage level coefficient, respectively, and a1+a2+a3+a4+a5=1; The first power flow index calculation submodule is used to set the power flow convergence index as F0, the power generation level index as F1', the load level index as F2', the cross-sectional power index as F3', the DC power index as F4', and the critical node voltage level index as F5' in the current power flow calculation results. F'=F0×(a1×F1'+a2×F2'+a3×F3'+a4×F4'+a5×F5') F' represents the index of the current power grid operation mode data, and a1, a2, a3, a4, and a5 are the power generation level coefficient, load level coefficient, cross-sectional power coefficient, DC power coefficient, and key node voltage level coefficient, respectively, and a1+a2+a3+a4+a5=1.

16. The system according to claim 14, characterized in that, Power generation level index F1, F1=b1*F11+b2*F12+b3*F13+b4*F14+b5*F15+b6*F16; b1, b2, b3, b4, b5, and b6 are the power generation level coefficients for wind power, photovoltaic power, energy storage power, thermal power, hydropower, and other power generation types, respectively, and b1+b2+b3+b4+b5+b6=1.

17. The system according to claim 14, characterized in that, In the section power index F3, the power grid includes k sections, and the power of each section is F31, F32, ..., F3k respectively. Then F3 = d1*F31 + d2*F32 + ... + dk*F3k, where d1, d2, ..., dk are the weighting coefficients of each section, and d1 + d2 + ... + dk = 1.

18. The system according to claim 14, characterized in that, In the DC power index F4, the power grid includes i DC lines, and the power of each DC line is F41, F42, ..., F4i, respectively. Then F4 = e1*F41 + e2*F42 + ... + ei*F4i, where e1, e2, ..., ei are the weighting coefficients of each DC line, and e1 + e2 + ... + ei = 1.

19. The system according to claim 14, characterized in that, In the critical node voltage level F5, the power grid includes j nodes, and the voltages of each node are F51, F52, ..., F5j. Then F5 = f1*F51 + f2*F52 + ... + fk*F5j, where f1, f2, ..., fk are the weighting coefficients of each critical node voltage level, and f1 + f2 + ... + fk = 1.

20. The system according to claim 11, characterized in that, The operation mode determination module includes: The verification submodule is used to verify the branch range of the selected second operating mode data. It sequentially disconnects each branch within the branch range to form multiple operating mode verification data.

21. A computer device, characterized in that, include: One or more processors; The processor is used to store one or more programs; When the one or more programs are executed by the one or more processors, the intelligent generation method for power grid operation modes based on historical data as described in any one of claims 1 to 10 is implemented.

22. A computer-readable storage medium, characterized in that, It contains a computer program, which, when executed, implements the intelligent generation method for power grid operation modes based on historical data as described in any one of claims 1 to 10.

Images