Distribution network operation mode optimization method and device based on big data analysis

Abstract

The invention discloses a distribution network operation mode optimization method and device based on big data analysis, and the method comprises the steps: obtaining the distribution network operation data of a target power grid and the power grid multi-source data of the target power grid, carrying out the data processing operation of the distribution network operation data and the power grid multi-source data, and obtaining a data processing result, based on the data processing result, constructing a distribution network operation state big data evaluation model, and based on the distribution network operation state big data evaluation model and the distribution network operation data, determining an operation evaluation result of the target power grid; and determining a power grid optimization target corresponding to the target power grid according to the operation evaluation result, and generating distribution network optimization parameters of the target power grid according to the distribution network operation state big data evaluation model and the power grid optimization target. Therefore, the current distribution network mode can be optimized intelligently, the utilization rate of the distribution network equipment and the operation efficiency of the distribution network can be improved, and the power supply reliability of the distribution network can be improved.

Description

Technical Field

[0001] The present invention relates to the field of Internet technology, and in particular to a method and device for optimizing a distribution network operation mode based on big data analysis. Background Art

[0002] With the continuous development of science and technology, people's requirements for the quality of power supply are also constantly increasing. The operating efficiency and reliability of distribution networks have become key issues in the power system. The distribution network is an important component of the power system, directly serving electricity users. Its operating status directly affects the quality and reliability of power supply to users. The traditional distribution network operation mode mainly relies on manual experience and fixed scheduling rules. This operation mode has many shortcomings when facing complex grid structures and dynamically changing load demands. For example, it cannot effectively balance the load distribution of the distribution network, and is prone to local overloads and equipment overheating, which affects equipment life and power supply quality, and has the problem of low power supply reliability.

[0003] It can be seen that it is particularly important to provide a new distribution network operation optimization method to optimize the operation mode of distribution network equipment and thus improve power supply reliability. Summary of the Invention

[0004] The present invention provides a method and device for optimizing the distribution network operation mode based on big data analysis, which can intelligently optimize the current distribution network mode, which is beneficial to improving the utilization rate of distribution network equipment and improving the distribution network operation efficiency, and further beneficial to improving the power supply reliability of the distribution network.

[0005] In order to solve the above technical problems, the first aspect of the present invention discloses a method for optimizing the distribution network operation mode based on big data analysis, the method comprising:

[0006] Obtaining distribution network operation data of a target power grid and multi-source power grid data of the target power grid, wherein the distribution network operation data includes one or more of the following: topological structure data of the target power grid, power grid equipment operation data, power grid operation load data, historical power grid fault data, and power grid environmental factor data; and the multi-source power grid data includes one or more of the following: communication status data, operation record data, and historical measurement data of the target power grid;

[0007] performing data processing operations on the distribution network operation data and the multi-source data of the power grid to obtain data processing results, constructing a distribution network operation status big data evaluation model based on the data processing results, and determining an operation evaluation result of the target power grid based on the distribution network operation status big data evaluation model and the distribution network operation data;

[0008] According to the operation evaluation result, the power grid optimization target corresponding to the target power grid is determined, and the distribution network optimization parameters of the target power grid are generated according to the distribution network operation status big data evaluation model and the power grid optimization target.

[0009] As an optional embodiment, in the first aspect of the present invention, the method further comprises:

[0010] Performing a distribution network optimization operation on the target power grid according to the distribution network optimization parameters to obtain a distribution network optimization result;

[0011] Performing a data comparison operation on the distribution network optimization result and the power grid optimization target to obtain a data comparison result;

[0012] Acquiring real-time monitoring information corresponding to the target power grid, and determining a target operating state corresponding to the target power grid based on the real-time monitoring information;

[0013] According to the target operating state and the data comparison result, dynamic optimization parameters of the target power grid are generated, and the distribution network optimization parameters are updated according to the dynamic optimization parameters.

[0014] As an optional embodiment, in the first aspect of the present invention, before generating the distribution network optimization parameters of the target power grid based on the distribution network operation status big data evaluation model and the power grid optimization target, the method further includes:

[0015] Obtaining grid location information corresponding to the target grid, and obtaining current environment information corresponding to the target grid based on the grid location information;

[0016] Determining target environment information of the target power grid based on the power grid location information and the current environment information, and judging whether there are influencing parameters in the target environment information that have an impact on the operating state of the target power grid;

[0017] When it is determined that the target environment information contains influencing parameters that affect the operating state of the target power grid, generating an influencing optimization parameter based on all the influencing parameters;

[0018] The step of generating the distribution network optimization parameters of the target power grid according to the distribution network operation status big data evaluation model and the power grid optimization target includes:

[0019] The distribution network optimization parameters of the target power grid are generated according to the distribution network operation status big data evaluation model, the power grid optimization target and the influencing optimization parameters.

[0020] As an optional embodiment, in the first aspect of the present invention, generating the distribution network optimization parameters of the target power grid according to the distribution network operation status big data evaluation model, the power grid optimization target, and the influencing optimization parameters includes:

[0021] Extracting a first target parameter of the power grid optimization target and extracting a second target parameter affecting the optimization parameter, and generating a target evaluation parameter according to the first target parameter and the second target parameter;

[0022] The target evaluation parameters are input into the distribution network operation status big data evaluation model to perform parameter evaluation operations on the target evaluation parameters through the distribution network operation status big data evaluation model to obtain parameter evaluation results, and based on the parameter evaluation results, at least one optimization parameter that matches the parameter evaluation result is determined from a predetermined optimization parameter library, and the distribution network optimization parameters of the target power grid are generated based on all the optimization parameters.

[0023] As an optional implementation manner, in the first aspect of the present invention, performing data processing operations on the distribution network operation data and the power grid multi-source data to obtain data processing results includes:

[0024] Performing a data cleaning operation on the distribution network operation data and the multi-source power grid data to obtain a data cleaning result, wherein the data cleaning result at least includes the distribution network operation data and the multi-source power grid data after performing the data cleaning operation;

[0025] Determining a data integrity parameter corresponding to the data cleaning result, and judging whether the data integrity parameter satisfies a preset data integrity condition;

[0026] When it is determined that the data integrity parameter does not satisfy the preset data integrity condition, performing a data filling operation on the data corresponding to the data cleaning result according to the data integrity parameter and the preset data integrity condition to obtain target filled data, and generating a data processing result based on the target filled data;

[0027] When it is determined that the data integrity parameter meets the preset data integrity condition, a data processing result is generated according to the data corresponding to the data cleaning result.

[0028] As an optional implementation manner, in the first aspect of the present invention, determining the power grid optimization target corresponding to the target power grid according to the operation evaluation result includes:

[0029] Extracting multi-dimensional feature data corresponding to the operation evaluation result, and determining a feature association relationship corresponding to the multi-dimensional feature data based on the multi-dimensional feature data;

[0030] performing a feature classification operation on all feature data corresponding to the multi-dimensional feature data according to the feature association relationship to obtain at least one feature category, wherein each feature category includes at least one feature data;

[0031] Based on each of the feature categories and all the feature data included in each of the feature categories, a feature data fusion operation is performed to obtain a data fusion result; wherein the data fusion result includes the operating state impact data corresponding to the target power grid;

[0032] According to the data fusion result, a power grid optimization target corresponding to the target power grid is determined.

[0033] As an optional embodiment, in the first aspect of the present invention, before performing the distribution network optimization operation on the target power grid according to the distribution network optimization parameters and obtaining the distribution network optimization result, the method further includes:

[0034] Performing a simulation optimization operation on the target power grid according to the distribution network optimization parameters of the target power grid to obtain a simulation optimization result;

[0035] Determine, based on the simulation optimization results, the feasible optimization parameters corresponding to the distribution network optimization parameters, and judge whether the feasible optimization parameters meet the preset operation optimization conditions;

[0036] When it is determined that the optimization feasible parameters meet the preset operation optimization conditions, triggering the execution of the operation of performing the distribution network optimization operation on the target power grid according to the distribution network optimization parameters to obtain the distribution network optimization result;

[0037] When it is determined that the optimization feasible parameters do not meet the preset operation optimization conditions, the distribution network optimization parameters are updated by a preset deep reinforcement algorithm to obtain optimized scheduling parameters;

[0038] The step of performing a distribution network optimization operation on the target power grid according to the distribution network optimization parameters to obtain a distribution network optimization result includes:

[0039] According to the optimized scheduling parameters, a distribution network optimization operation is performed on the target power grid to obtain a distribution network optimization result.

[0040] A second aspect of the present invention discloses a device for optimizing a distribution network operation mode based on big data analysis, the device comprising:

[0041] an acquisition module, configured to acquire distribution network operation data of a target power grid and multi-source power grid data of the target power grid, wherein the distribution network operation data includes one or more of the topological structure data of the target power grid, power grid equipment operation data, power grid operation load data, power grid historical fault data, and power grid environmental factor data; and the multi-source power grid data includes one or more of the communication status data, operation record data, and historical measurement data of the target power grid;

[0042] a processing module, configured to perform data processing operations on the distribution network operation data and the multi-source data of the power grid to obtain data processing results;

[0043] A construction module is used to construct a distribution network operation status big data evaluation model based on the data processing results;

[0044] A determination module, configured to determine an operation evaluation result of the target power grid based on the distribution network operation status big data evaluation model and the distribution network operation data; and determine a power grid optimization target corresponding to the target power grid according to the operation evaluation result;

[0045] A generation module is used to generate distribution network optimization parameters of the target power grid based on the distribution network operation status big data evaluation model and the power grid optimization target.

[0046] As an optional embodiment, in the second aspect of the present invention, the device further includes:

[0047] An optimization module, configured to perform a distribution network optimization operation on the target power grid according to the distribution network optimization parameters to obtain a distribution network optimization result;

[0048] A comparison module, configured to perform a data comparison operation on the distribution network optimization result and the power grid optimization target to obtain a data comparison result;

[0049] The acquisition module is further configured to acquire real-time monitoring information corresponding to the target power grid;

[0050] The determining module is further configured to determine a target operating state corresponding to the target power grid based on the real-time monitoring information;

[0051] The generating module is further configured to generate dynamic optimization parameters of the target power grid according to the target operating state and the data comparison result;

[0052] An updating module is used to update the distribution network optimization parameters according to the dynamic optimization parameters.

[0053] As an optional embodiment, in the second aspect of the present invention, the acquisition module is further configured to obtain grid location information corresponding to the target grid before the generation module generates the distribution network optimization parameters of the target grid based on the distribution network operation status big data evaluation model and the grid optimization target, and obtain current environment information corresponding to the target grid based on the grid location information;

[0054] The determining module is further configured to determine target environment information of the target power grid based on the power grid location information and the current environment information;

[0055] The device further comprises:

[0056] A first judgment module is used to judge whether there is an influencing parameter that affects the operating state of the target power grid in the target environment information;

[0057] The generating module is further configured to generate an impact optimization parameter based on all the impact parameters when the first judging module judges that the target environment information contains impact parameters that affect the operating state of the target power grid;

[0058] The specific manner in which the generation module generates the distribution network optimization parameters of the target power grid according to the distribution network operation status big data evaluation model and the power grid optimization target includes:

[0059] The distribution network optimization parameters of the target power grid are generated according to the distribution network operation status big data evaluation model, the power grid optimization target and the influencing optimization parameters.

[0060] As an optional embodiment, in the second aspect of the present invention, the specific manner in which the generation module generates the distribution network optimization parameters of the target power grid according to the distribution network operation status big data evaluation model, the power grid optimization target, and the influencing optimization parameters includes:

[0061] Extracting a first target parameter of the power grid optimization target and extracting a second target parameter affecting the optimization parameter, and generating a target evaluation parameter according to the first target parameter and the second target parameter;

[0062] The target evaluation parameters are input into the distribution network operation status big data evaluation model to perform parameter evaluation operations on the target evaluation parameters through the distribution network operation status big data evaluation model to obtain parameter evaluation results, and based on the parameter evaluation results, at least one optimization parameter that matches the parameter evaluation result is determined from a predetermined optimization parameter library, and the distribution network optimization parameters of the target power grid are generated based on all the optimization parameters.

[0063] As an optional embodiment, in the second aspect of the present invention, the processing module performs data processing operations on the distribution network operation data and the power grid multi-source data, and a specific manner of obtaining the data processing results includes:

[0064] Performing a data cleaning operation on the distribution network operation data and the multi-source power grid data to obtain a data cleaning result, wherein the data cleaning result at least includes the distribution network operation data and the multi-source power grid data after performing the data cleaning operation;

[0065] Determining a data integrity parameter corresponding to the data cleaning result, and judging whether the data integrity parameter satisfies a preset data integrity condition;

[0066] When it is determined that the data integrity parameter does not satisfy the preset data integrity condition, performing a data filling operation on the data corresponding to the data cleaning result according to the data integrity parameter and the preset data integrity condition to obtain target filled data, and generating a data processing result based on the target filled data;

[0067] When it is determined that the data integrity parameter meets the preset data integrity condition, a data processing result is generated according to the data corresponding to the data cleaning result.

[0068] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the determination module determines the power grid optimization target corresponding to the target power grid according to the operation evaluation result includes:

[0069] Extracting multi-dimensional feature data corresponding to the operation evaluation result, and determining a feature association relationship corresponding to the multi-dimensional feature data based on the multi-dimensional feature data;

[0070] performing a feature classification operation on all feature data corresponding to the multi-dimensional feature data according to the feature association relationship to obtain at least one feature category, wherein each feature category includes at least one feature data;

[0071] Based on each of the feature categories and all the feature data included in each of the feature categories, a feature data fusion operation is performed to obtain a data fusion result; wherein the data fusion result includes the operating state impact data corresponding to the target power grid;

[0072] According to the data fusion result, a power grid optimization target corresponding to the target power grid is determined.

[0073] As an optional embodiment, in the second aspect of the present invention, the device further includes:

[0074] a simulation module, configured to perform a simulated optimization operation on the target power grid according to the distribution network optimization parameters of the target power grid to obtain a simulated optimization result before the optimization module performs the distribution network optimization operation on the target power grid according to the distribution network optimization parameters to obtain a distribution network optimization result;

[0075] The determination module is further configured to determine feasible optimization parameters corresponding to the distribution network optimization parameters based on the simulation optimization results;

[0076] a second judgment module, configured to judge whether the feasible optimization parameters satisfy preset operation optimization conditions; and when it is judged that the feasible optimization parameters satisfy the preset operation optimization conditions, triggering the optimization module to execute the distribution network optimization operation on the target power grid according to the distribution network optimization parameters to obtain a distribution network optimization result;

[0077] The updating module is further configured to, when the second judging module determines that the feasible optimization parameters do not meet the preset operation optimization conditions, perform an updating operation on the distribution network optimization parameters using a preset deep reinforcement algorithm to obtain optimized scheduling parameters;

[0078] The optimization module performs a distribution network optimization operation on the target power grid according to the distribution network optimization parameters, and obtains a distribution network optimization result in the following specific manners:

[0079] According to the optimized scheduling parameters, a distribution network optimization operation is performed on the target power grid to obtain a distribution network optimization result.

[0080] A third aspect of the present invention discloses another device for optimizing distribution network operation mode based on big data analysis, the device comprising:

[0081] a memory storing executable program code;

[0082] a processor coupled to the memory;

[0083] The processor calls the executable program code stored in the memory to execute the method for optimizing the distribution network operation mode based on big data analysis disclosed in the first aspect of the present invention.

[0084] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute the optimization method of the distribution network operation mode based on big data analysis disclosed in the first aspect of the present invention.

[0085] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0086] In an embodiment of the present invention, the distribution network operation data of the target power grid and the power grid multi-source data of the target power grid are obtained, data processing operations are performed on the distribution network operation data and the power grid multi-source data to obtain data processing results, and based on the data processing results, a distribution network operation status big data evaluation model is constructed. Based on the distribution network operation status big data evaluation model and the distribution network operation data, the operation evaluation results of the target power grid are determined; according to the operation evaluation results, the power grid optimization target corresponding to the target power grid is determined, and according to the distribution network operation status big data evaluation model and the power grid optimization target, the distribution network optimization parameters of the target power grid are generated. It can be seen that the implementation of the present invention can intelligently optimize the current distribution network mode, which is beneficial to improving the utilization rate of distribution network equipment and improving the distribution network operation efficiency, and further beneficial to improving the power supply reliability of the distribution network. BRIEF DESCRIPTION OF THE DRAWINGS

[0087] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0088] Figure 1 This is a flow chart of a method for optimizing a distribution network operation mode based on big data analysis disclosed in an embodiment of the present invention;

[0089] Figure 2 This is a flow chart of another method for optimizing a distribution network operation mode based on big data analysis disclosed in an embodiment of the present invention;

[0090] Figure 3 This is a schematic structural diagram of a device for optimizing a distribution network operation mode based on big data analysis disclosed in an embodiment of the present invention;

[0091] Figure 4 This is a schematic structural diagram of another device for optimizing a distribution network operation mode based on big data analysis disclosed in an embodiment of the present invention;

[0092] Figure 5 This is a structural diagram of another device for optimizing distribution network operation mode based on big data analysis disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0093] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of 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. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0094] The terms "first," "second," and so on, in the description and claims of the present invention and the accompanying drawings are used to distinguish between different items, not to describe a specific order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product, or end comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed therein, or may optionally include other steps or elements inherent to such process, method, product, or end.

[0095] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0096] The present invention discloses a method and device for optimizing distribution network operation based on big data analysis. This method can intelligently optimize the current distribution network mode, thereby improving the utilization rate of distribution network equipment and the efficiency of distribution network operation, thereby further improving the power supply reliability of the distribution network. These methods are described in detail below.

[0097] Example 1

[0098] See also Figure 1 , Figure 1 This is a flow chart of a method for optimizing the distribution network operation mode based on big data analysis disclosed in an embodiment of the present invention. Figure 1 The described method for optimizing the distribution network operation mode based on big data analysis can be applied to an optimization device for the distribution network operation mode based on big data analysis, wherein the optimization device for the distribution network operation mode based on big data analysis can be integrated in a local server or a cloud server, which is not limited in the embodiment of the present invention. Figure 1 As shown, the method for optimizing the distribution network operation mode based on big data analysis may include the following operations:

[0099] 101. Obtain distribution network operation data of the target power grid and multi-source power grid data of the target power grid.

[0100] In an embodiment of the present invention, the distribution network operation data includes one or more of the target power grid's topological structure data, power grid equipment operation data, power grid operation load data, power grid historical fault data, and power grid environmental factor data; the power grid multi-source data includes one or more of the target power grid's communication status data, operation record data, and historical measurement data.

[0101] In an embodiment of the present invention, optionally, the topology data of the target power grid may include one or more of the node information, line information, connection relationship information, and network layer information of the target power grid; wherein the network layer information includes the distribution network layer structure of the target power grid, such as the hierarchical relationship of the high-voltage distribution network, the medium-voltage distribution network, and the low-voltage distribution network; the power grid equipment operation data may include one or more of the transformer operation data, line operation data, switchgear operation data, and smart device operation data of the distribution network, wherein the switchgear operation data includes the status (closing / opening), number of operations, number of faults, etc. of the circuit breaker, disconnector, and fuse; the smart device operation data includes the equipment operation parameters and fault alarm information collected by the smart meter and smart sensor; the power grid operation load data includes the real-time load data of the target power grid, the load curve data of the target power grid within a preset time period, and the load preset data; the power grid historical fault data includes the fault time data, fault location data, fault type data, fault cause data, fault processing time data, and fault processing method data of the target power grid; the power grid environmental factor data includes the meteorological data, geographic location information, and environmental monitoring data of the current environment where the target power grid is located.

[0102] In an embodiment of the present invention, optionally, the communication status data of the target power grid includes one or more of the communication link data, communication equipment status data, data transmission data, and communication protocol data of the target power grid; wherein the communication link data may include the connection status (normal, interrupted, degraded), bandwidth utilization, signal strength, bit error rate, etc. of the communication link; the operation record data of the target power grid may include one or more of the operator data, operation log data, operation instruction data, and operation feedback data of the target power grid; the historical measurement data of the target power grid includes one or more of the measurement time series data, measurement quality assessment data, and measurement abnormality data of the target power grid, wherein the measurement time series data may include measurement data records at different time points, including long-term change trends of voltage, current, power, frequency, etc.; the measurement quality assessment data may include quality assessment records of measurement data, including data accuracy, completeness, consistency, etc.; the measurement abnormality data may include records of abnormal points in the measurement data, including detection of abnormal values, cause analysis, and treatment measures, etc.

[0103] 102. Perform data processing operations on the distribution network operation data and the multi-source data of the power grid to obtain data processing results. Based on the data processing results, construct a distribution network operation status big data evaluation model. Based on the distribution network operation status big data evaluation model and the distribution network operation data, determine the operation evaluation results of the target power grid.

[0104] In the embodiment of the present invention, optionally, the data processing operation includes at least a data cleaning operation.

[0105] In an embodiment of the present invention, optionally, constructing a distribution network operation status big data evaluation model based on the data processing results may include:

[0106] Extracting distribution network operation data associated with the distribution network operation status from the data processing results, wherein the distribution network operation data includes one or more of equipment operation data, load change data, and fault frequency data of the target power grid;

[0107] Perform data clustering operations on the extracted distribution network operation data according to a preset data clustering algorithm to obtain data clustering results, and build a distribution network operation status big data evaluation model based on the data clustering results;

[0108] Among them, the preset data clustering algorithm includes the K-Means clustering algorithm.

[0109] In an embodiment of the present invention, optionally, determining the operation evaluation result of the target power grid based on the distribution network operation status big data evaluation model and the distribution network operation data may include:

[0110] The distribution network operation data is input into the distribution network operation status big data evaluation model, so as to perform data evaluation operations on the distribution network operation data through the distribution network operation status big data evaluation model to obtain the operation evaluation results of the target power grid.

[0111] 103. Based on the operation evaluation results, determine the grid optimization target corresponding to the target grid, and generate the distribution network optimization parameters of the target grid based on the distribution network operation status big data evaluation model and the grid optimization target.

[0112] In the embodiment of the present invention, optionally, determining the power grid optimization target corresponding to the target power grid according to the operation evaluation result may include:

[0113] Determine the grid index parameters of the target grid, and determine the operation difference parameters between the operation state corresponding to the target grid and the grid index parameters based on the operation evaluation results and the grid index parameters;

[0114] Determine the grid optimization target corresponding to the target grid based on the operation difference parameters;

[0115] Among them, the grid optimization targets corresponding to the target grid may include one or more of grid loss targets, power quality targets, grid equipment operating efficiency targets, operating cost targets, and power supply stability targets.

[0116] It can be seen that implementation Figure 1 The described method for optimizing distribution network operation mode based on big data analysis can obtain distribution network operation data and multi-source data of a target power grid and perform data processing operations to obtain data processing results. Based on the data processing results, a distribution network operation status big data evaluation model is constructed to thereby determine the operation evaluation results of the target power grid. Based on the operation evaluation results, corresponding power grid optimization targets are determined and distribution network optimization parameters for the target power grid are generated. By comprehensively analyzing the distribution network operation data and multi-source data, a comprehensive analysis of the data corresponding to the target power grid can be achieved by combining multiple data. This is conducive to improving the accuracy and reliability of the data processing results and the determination of the operation evaluation results, and is also conducive to the accuracy and reliability of the subsequent generation of distribution network optimization parameters. By analyzing the power grid operation data, the operating parameters of the voltage regulation equipment can be optimized to achieve intelligent optimization of the target power grid. The power grid operation parameters can be dynamically adjusted based on real-time data and prediction results to ensure that the power grid always operates in an optimal state. Based on the operation evaluation results, the load response capability of the power grid is optimized, and the flexibility and adaptability of the power grid are improved, thereby intelligently optimizing the current distribution network mode, which is conducive to improving the utilization rate of distribution network equipment and the distribution network operation efficiency, and thus also conducive to improving the power supply reliability of the distribution network.

[0117] Example 2

[0118] See also Figure 2 , Figure 2 This is a flow chart of a method for optimizing the distribution network operation mode based on big data analysis disclosed in an embodiment of the present invention. Figure 2 The described method for optimizing the distribution network operation mode based on big data analysis can be applied to an optimization device for the distribution network operation mode based on big data analysis, wherein the optimization device for the distribution network operation mode based on big data analysis can be integrated in a local server or a cloud server, which is not limited in the embodiment of the present invention. Figure 2 As shown, the method for optimizing the distribution network operation mode based on big data analysis may include the following operations:

[0119] 201. Obtain distribution network operation data of a target power grid and multi-source power grid data of the target power grid.

[0120] 202. Perform data processing operations on the distribution network operation data and the multi-source data of the power grid to obtain data processing results. Based on the data processing results, construct a distribution network operation status big data evaluation model. Based on the distribution network operation status big data evaluation model and the distribution network operation data, determine the operation evaluation results of the target power grid.

[0121] 203. Determine the grid optimization target corresponding to the target grid based on the operation evaluation results, and generate the distribution network optimization parameters of the target grid based on the distribution network operation status big data evaluation model and the grid optimization target.

[0122] In the embodiment of the present invention, for the detailed description of steps 201 to 203 , please refer to the other descriptions of steps 101 to 103 in the first embodiment, and the embodiment of the present invention will not be repeated.

[0123] 204. Perform distribution network optimization operations on the target power grid according to the distribution network optimization parameters to obtain distribution network optimization results.

[0124] In the embodiment of the present invention, optionally, performing the distribution network optimization operation on the target power grid according to the distribution network optimization parameters to obtain the distribution network optimization result may include:

[0125] A distribution network optimization operation matching the distribution network optimization parameters is performed on the target power grid to obtain a distribution network optimization result corresponding to the target power grid, wherein the distribution network optimization result includes data operation data corresponding to the target power grid after the target power grid performs the distribution network optimization operation matching the distribution network optimization parameters.

[0126] 205. Perform a data comparison operation on the distribution network optimization result and the power grid optimization target to obtain a data comparison result.

[0127] In an embodiment of the present invention, optionally, the data comparison result includes at least difference information between the distribution network optimization result and the power grid optimization target. For example, the data comparison result may include one or more of power supply reliability difference information, power grid loss difference information, power quality difference information, and equipment utilization difference information. Further, the power supply reliability difference information may include power outage time difference information and power outage frequency difference information. The power grid loss difference information may include line loss rate difference information, transformer loss difference information, and line loss difference information. The power quality difference information may include voltage qualification rate difference information and voltage fluctuation difference information. The equipment utilization difference information may include equipment utilization efficiency difference information.

[0128] 206. Obtain real-time monitoring information corresponding to the target power grid, and determine a target operating state corresponding to the target power grid based on the real-time monitoring information.

[0129] In an embodiment of the present invention, optionally, the real-time monitoring information corresponding to the target power grid may include one or more of the real-time voltage value, real-time current value, real-time power value, equipment operating status, and equipment load value of the target power grid.

[0130] In the embodiment of the present invention, optionally, determining the target operating state corresponding to the target power grid based on the real-time monitoring information may include:

[0131] Determine the equipment operating parameters of the target power grid based on the real-time monitoring information, wherein the equipment operating parameters include one or more of the operating voltage, operating current, operating power, and operating temperature of the equipment corresponding to the target power grid;

[0132] Determine the target operating state of the target power grid based on the evaluation index information predetermined by the equipment operating parameters of the target power grid;

[0133] Among them, the predetermined evaluation index information may include power supply reliability indicators (such as SAIDI, SAIFI), grid loss indicators (such as line loss rate), power quality indicators (such as voltage compliance rate), equipment utilization rate, load balance, etc.

[0134] 207. Generate dynamic optimization parameters of the target power grid according to the target operating state and the data comparison result, and update the distribution network optimization parameters according to the dynamic optimization parameters.

[0135] In the embodiment of the present invention, optionally, generating the dynamic optimization parameters of the target power grid according to the target operating state and the data comparison result may include:

[0136] According to the target operating state and the data comparison result, the state difference parameters are determined, and according to the state difference parameters and the real-time monitoring information, and in combination with the preset optimization algorithm, the dynamic optimization parameters of the target power grid are generated; wherein, the preset optimization algorithm includes a linear programming algorithm or a nonlinear programming algorithm; wherein, the linear programming algorithm includes one of the dual simplex method, the network simplex method, and the interior point method, and the nonlinear programming algorithm includes one of the gradient descent method and the conjugate gradient method.

[0137] It can be seen that implementation Figure 2The described optimization method for distribution network operation mode based on big data analysis can perform distribution network optimization operations on the target power grid according to the distribution network optimization parameters to obtain distribution network optimization results, perform data comparison operations on the distribution network optimization results and the power grid optimization targets to obtain data comparison results, and obtain real-time monitoring information to determine the target operation state, generate dynamic optimization parameters of the target power grid according to the target operation state and the data comparison results, and update the distribution network optimization parameters. By performing optimization operations on the target power grid according to the distribution network optimization parameters, it is beneficial to improve the operation efficiency of the target power grid, and also to improve the operation reliability and stability of the target power grid. In addition, it dynamically generates optimization parameters according to the real-time monitoring information and the data comparison results, and updates the distribution network optimization parameters, so that the power grid can be adjusted in time according to the actual operation conditions, which is beneficial to improving the control of the target power grid. The intelligent optimization of the operation mode of the network. By obtaining real-time monitoring information of the target power grid, the operation status of the power grid can be grasped in time, which is conducive to improving the adaptability and flexibility of the power grid operation. Dynamic optimization parameters are generated based on real-time monitoring information and data comparison results, so that the power grid optimization strategy can be dynamically adjusted according to the actual operation status, which is conducive to improving the intelligence and real-time performance of optimizing the operation status of the target power grid, thereby further improving the reliability and stability of the power grid. By optimizing distribution network operations and dynamically adjusting parameters, the reasonable allocation and efficient utilization of energy can be better achieved, the energy utilization efficiency can be improved and the sustainability of the power grid can be enhanced, thereby intelligently optimizing the current distribution network mode, which is conducive to improving the utilization rate of distribution network equipment and improving the distribution network operation efficiency, and further conducive to improving the power supply reliability of the distribution network.

[0138] In an optional embodiment, before generating the distribution network optimization parameters of the target power grid based on the distribution network operation status big data evaluation model and the power grid optimization target, the method further includes:

[0139] Obtaining the grid location information corresponding to the target grid, and obtaining the current environment information corresponding to the target grid based on the grid location information;

[0140] Based on the power grid location information and the current environment information, determining the target environment information of the target power grid, and judging whether there are influencing parameters in the target environment information that have an impact on the operating state of the target power grid;

[0141] When it is determined that the target environment information contains influencing parameters that affect the operating state of the target power grid, generating influencing optimization parameters based on all influencing parameters;

[0142] Among them, based on the distribution network operation status big data evaluation model and the power grid optimization goals, the distribution network optimization parameters of the target power grid are generated, including:

[0143] Based on the distribution network operation status big data evaluation model, power grid optimization objectives and parameters affecting optimization, the distribution network optimization parameters of the target power grid are generated.

[0144] In this optional embodiment, optionally, the grid location information includes the location information of the target grid and the device location information of each grid device included in the target grid; the current environmental information includes the geographic coordinate information of the current location of the target grid, environmental temperature information, environmental humidity information, environmental lightning activity information, environmental load demand information, environmental power supply demand information, and environmental energy demand information.

[0145] In this optional embodiment, the target environment information optionally includes at least power grid location information and current environment information.

[0146] In this optional embodiment, further optionally, when it is determined that there are no influencing parameters that affect the operating status of the target power grid in the target environmental information, an operation of generating distribution network optimization parameters of the target power grid based on the distribution network operating status big data evaluation model and the power grid optimization target is directly triggered.

[0147] In this optional embodiment, optionally, the determining whether the target environment information contains an influencing parameter that affects the operating state of the target power grid may include:

[0148] Extracting a first state parameter from the target environment information and a second state parameter from the operating state of the target power grid, and calculating a parameter similarity between the first state parameter and the second state parameter;

[0149] Determine whether the parameter similarity is greater than or equal to a preset parameter similarity threshold;

[0150] When it is determined that the parameter similarity is greater than or equal to a preset parameter similarity threshold, it is determined that there are influencing parameters in the target environment information that have an impact on the operating state of the target power grid; when it is determined that the parameter similarity is less than the preset parameter similarity threshold, it is determined that there are no influencing parameters in the target environment information that have an impact on the operating state of the target power grid.

[0151] In this optional embodiment, optionally, the generation of distribution network optimization parameters of the target power grid based on the distribution network operation status big data evaluation model, the power grid optimization target, and the parameters affecting the optimization may include:

[0152] The power grid optimization objectives and the parameters affecting the optimization are input into the distribution network operation status big data evaluation model, so as to perform analysis operations on the power grid optimization objectives and the parameters affecting the optimization through the distribution network operation status big data evaluation model to generate the distribution network optimization parameters of the target power grid.

[0153] It can be seen that the implementation of this optional embodiment can obtain the grid location information and current environmental information of the target grid, determine the target environmental information of the target grid based on the grid location information and the current environmental information, and judge whether there are influencing parameters in the target environmental information that affect the operating state of the target grid. If so, the influencing optimization parameters are generated according to all the influencing parameters, and the distribution network optimization parameters of the target grid are generated according to the distribution network operating state big data evaluation model, the grid optimization target and the influencing optimization parameters. By obtaining the grid location information and current environmental information of the target grid, the external conditions of the grid operation can be fully understood, and the actual operating state of the target grid can be comprehensively generated based on the comprehensive information, which is conducive to improving the accuracy and reliability of determining the operating state of the target grid and judging whether there are influencing parameters. It can also generate influencing optimization parameters through the environmental information obtained in real time, which can make the distribution network optimization parameters The network optimization parameters dynamically adapt to environmental changes, which is conducive to improving the real-time performance of the subsequent generation of distribution network optimization parameters and the matching degree with the real-time status of the target power grid. When the influencing parameters are identified, the generated influencing optimization parameters can adjust the power grid operation strategy in a targeted manner, thereby improving the reliability of the power grid in a complex environment. It can also more reasonably allocate power grid resources by comprehensively considering the power grid location information and current environmental information. Through the generation of optimization parameters driven by real-time data, it can also automatically adjust the optimization strategy according to the real-time environmental information and power grid status, thereby improving the intelligence level of the power grid. The optimization parameters generated based on the prediction results can dynamically adjust the power grid operation strategy, which is also conducive to improving the prediction ability and operation efficiency of the power grid, thereby intelligently optimizing the current distribution network mode, which is conducive to improving the utilization rate of distribution network equipment and improving the distribution network operation efficiency, and thus also conducive to improving the power supply reliability of the distribution network.

[0154] In another optional embodiment, the distribution network optimization parameters of the target power grid are generated according to the distribution network operation status big data evaluation model, the power grid optimization target, and the parameters affecting the optimization, including:

[0155] Extracting a first target parameter of a power grid optimization target and a second target parameter affecting the optimization parameter, and generating a target evaluation parameter based on the first target parameter and the second target parameter;

[0156] The target evaluation parameters are input into the distribution network operation status big data evaluation model to perform parameter evaluation operations on the target evaluation parameters through the distribution network operation status big data evaluation model to obtain parameter evaluation results, and based on the parameter evaluation results, at least one optimization parameter that matches the parameter evaluation results is determined from a predetermined optimization parameter library, and the distribution network optimization parameters of the target power grid are generated based on all the optimization parameters.

[0157] In this optional embodiment, optionally, the first target parameter may include one or more of the equipment loss target parameter, the power quality target parameter, and the equipment utilization target parameter in the power grid optimization target; the second target parameter may include one or more of the equipment status target parameter and the equipment load characteristic parameter.

[0158] In this optional embodiment, optionally, the target evaluation parameters include at least a first target parameter and a second target parameter.

[0159] In this optional embodiment, the parameter evaluation result may optionally include an output result corresponding to the evaluation of the target evaluation parameter. Further, the parameter evaluation result may include an evaluation result of the operating mode of the target power grid. For example, the evaluation result of the operating mode of the target power grid may include one or more of the distribution network operating status and the degree of matching between the operating status and the optimization target.

[0160] In this optional embodiment, optionally, determining at least one optimization parameter that matches the parameter evaluation result from a predetermined optimization parameter library based on the parameter evaluation result may include:

[0161] According to the parameter evaluation results, the evaluation matching degree between each parameter contained in the predetermined optimization parameter library and the parameter evaluation result is calculated, and the target evaluation matching degree with an evaluation matching degree greater than or equal to the preset matching degree threshold is set, and the parameter corresponding to each target judgment matching degree is determined as the optimization parameter matching the parameter evaluation result.

[0162] In this optional embodiment, the distribution network optimization parameters may optionally include at least all optimization parameters that match the parameter evaluation results.

[0163] It can be seen that the implementation of this optional embodiment can extract the first target parameter of the power grid optimization target and the second target parameter that affects the optimization parameter, generate a target evaluation parameter based on the first target parameter and the second target parameter, input the target evaluation parameter into the distribution network operation status big data evaluation model to perform a parameter evaluation operation on the target evaluation parameter to obtain a parameter evaluation result and then determine at least one matching optimization parameter, generate the distribution network optimization parameter of the target power grid based on all the optimization parameters, and can evaluate the target evaluation parameter through the distribution network operation status big data evaluation model, which can more accurately reflect the difference parameter between the current power grid operation status and the optimization target, which is conducive to improving the accuracy and reliability of the parameter evaluation result. By comprehensively considering multiple parameters and factors, the power grid operation status can be optimized as a whole, and the operation efficiency and performance of the power grid can be comprehensively improved. By optimizing the power grid operation parameters, the power outage time and frequency can be reduced, and the power supply reliability can be improved. The optimization parameters can be dynamically adjusted according to the real-time changes in the power grid operation status, so that the power grid can better adapt to the influence of load change factors, which is conducive to improving the operation reliability and operation stability of the target power grid, thereby intelligently optimizing the current distribution network mode, improving the utilization rate of the distribution network equipment and improving the distribution network operation efficiency, and further improving the power supply reliability of the distribution network.

[0164] In yet another optional embodiment, performing data processing operations on the distribution network operation data and the power grid multi-source data to obtain data processing results includes:

[0165] Performing a data cleaning operation on the distribution network operation data and the multi-source data of the power grid to obtain a data cleaning result, wherein the data cleaning result at least includes the distribution network operation data and the multi-source data of the power grid after the data cleaning operation is performed;

[0166] Determine the data integrity parameters corresponding to the data cleaning results, and judge whether the data integrity parameters meet the preset data integrity conditions;

[0167] When it is determined that the data integrity parameter does not meet the preset data integrity condition, a data filling operation is performed on the data corresponding to the data cleaning result according to the data integrity parameter and the preset data integrity condition to obtain target filled data, and a data processing result is generated based on the target filled data;

[0168] When it is determined that the data integrity parameters meet the preset data integrity conditions, a data processing result is generated based on the data corresponding to the data cleaning result.

[0169] In this optional embodiment, the data cleaning operation may optionally include one or more of a noise removal processing operation, a data format unification processing operation, a duplicate data removal processing operation, and an outlier processing operation.

[0170] In this optional embodiment, optionally, determining the data integrity parameter corresponding to the data cleaning result and judging whether the data integrity parameter satisfies a preset data integrity condition may include:

[0171] Determine a data integrity parameter corresponding to the data cleaning result, determine the data integrity level corresponding to the data cleaning result based on the data integrity parameter, and determine whether the data integrity level is greater than or equal to a integrity level threshold corresponding to a preset data integrity condition;

[0172] When it is determined that the data integrity level is greater than or equal to the integrity level threshold corresponding to the preset data integrity condition, it is determined that the data integrity parameter meets the preset data integrity condition; when it is determined that the data integrity level is less than the integrity level threshold corresponding to the preset data integrity condition, it is determined that the data integrity parameter does not meet the preset data integrity condition.

[0173] In this optional embodiment, optionally, performing a data filling operation on the data corresponding to the data cleaning result according to the data integrity parameter and the preset data integrity condition to obtain target filled data, and generating a data processing result based on the target filled data may include:

[0174] The data to be filled corresponding to the data cleaning result is determined according to the data integrity parameters, and the filling information corresponding to the data to be filled is determined according to the preset data integrity conditions, and a data filling operation is performed on the data corresponding to the data cleaning result based on the filling information to obtain target filling data, and the target filling data is determined as the data processing result; wherein, the target filling data includes data that meets the preset data integrity conditions after performing the data filling operation on the data corresponding to the data cleaning result.

[0175] It can be seen that the implementation of this optional embodiment can perform data cleaning operations on the distribution network operation data and the multi-source data of the power grid to obtain data cleaning results, determine the data integrity parameters corresponding to the data cleaning results and judge whether the preset data integrity conditions are met. If not, the data filling operation is performed on the data corresponding to the data cleaning results according to the data integrity parameters and the data integrity conditions to obtain the target filling data and then generate the data processing results. If it is met, the data processing results are generated according to the data corresponding to the data cleaning results. By removing noise data, unifying data formats and other operations, the accuracy and consistency of the data can be effectively improved. By checking the data integrity parameters and the data filling operation, the integrity of the data is ensured, and the actual operation of the target power grid can be more accurately reflected. Status, through a systematic data processing process, is conducive to improving the efficiency and accuracy of data processing, and through data filling operations, it fills in missing data, makes the data more complete, and improves the availability of data. It can also ensure data consistency through data cleaning operations, avoiding analysis deviations caused by inconsistent data formats or erroneous data, which is conducive to improving the accuracy and reliability of subsequent data processing results, so that it can optimize the power grid operating parameters to reduce losses and energy consumption, and can reasonably allocate power grid resources based on complete and accurate data to improve equipment utilization, thereby intelligently optimizing the current distribution network mode, which is conducive to improving the utilization rate of distribution network equipment and improving the distribution network operation efficiency, and thus also conducive to improving the power supply reliability of the distribution network.

[0176] In yet another optional embodiment, determining a power grid optimization target corresponding to the target power grid according to the operation evaluation result includes:

[0177] Extracting multi-dimensional feature data corresponding to the operation evaluation results, and determining feature correlation relationships corresponding to the multi-dimensional feature data based on the multi-dimensional feature data;

[0178] Performing a feature classification operation on all feature data corresponding to the multi-dimensional feature data according to the feature association relationship to obtain at least one feature category, wherein each feature category includes at least one feature data;

[0179] Based on each feature category and all feature data included in each feature category, a feature data fusion operation is performed to obtain a data fusion result; wherein the data fusion result includes operating state impact data corresponding to the target power grid;

[0180] According to the data fusion results, the grid optimization target corresponding to the target grid is determined.

[0181] In this optional embodiment, the multi-dimensional feature data optionally includes one or more of power quality feature data, loss feature data, equipment status feature data, load feature data, and environmental feature data.

[0182] In this optional embodiment, optionally, determining the feature association relationship corresponding to the multi-dimensional feature data based on the multi-dimensional feature data may include:

[0183] Based on the multi-dimensional feature data, a feature correlation coefficient between features is calculated, and based on the feature correlation coefficient, a feature association relationship corresponding to the multi-dimensional feature data is determined; wherein the feature correlation coefficient can be used to represent the degree of correlation between features.

[0184] In this optional embodiment, optionally, the above-mentioned performing a feature classification operation on all feature data corresponding to the multi-dimensional feature data according to the feature association relationship to obtain at least one feature category may include: performing a feature classification operation on all feature data corresponding to the multi-dimensional feature data according to the feature association relationship and a preset clustering algorithm to obtain at least one feature category; for example, dividing the feature data into multiple categories through the K-means algorithm.

[0185] In this optional embodiment, optionally, performing the feature data fusion operation based on each feature category and all feature data included in each feature category to obtain a data fusion result may include:

[0186] Based on each feature category and all feature data included in each feature category, combined with a preset target fusion network, a feature data fusion operation is performed to obtain a data fusion result; wherein the preset target fusion network may include one of a linear regression network and a neural network; the data fusion result may be one or more of the equipment health index of the target power grid, the comprehensive loss rate of the power grid equipment of the target power grid, and the power outage index of the target power grid.

[0187] In this optional embodiment, optionally, the above-mentioned determination of the grid optimization target corresponding to the target grid based on the data fusion result may include: determining the grid business demand corresponding to the target grid based on the data fusion result, and determining the grid optimization target that matches the grid business demand based on the grid business demand. For example, the grid business demand may include reducing the duration of power outages, reducing the equipment loss rate, and improving the utilization rate of grid equipment. The grid optimization target may include improving power supply reliability by optimizing the health status of equipment, reducing the power outage time and frequency; improving power supply reliability by optimizing the health status of equipment, reducing the power outage time and frequency; improving power quality by optimizing indicators such as voltage qualification rate and harmonic content; and improving the operating efficiency and life of equipment by optimizing the operating parameters and maintenance strategies of the equipment.

[0188] It can be seen that the implementation of this optional embodiment can extract the multi-dimensional feature data corresponding to the operation evaluation result and determine the corresponding feature association relationship. According to the feature association relationship, a feature classification operation is performed on the feature data corresponding to the multi-dimensional feature data to obtain at least one feature category. Based on each feature category and all feature data included in each feature category, a feature data fusion operation is performed to obtain a data fusion result. By extracting the multi-dimensional feature data corresponding to the operation evaluation result, all aspects of the power grid operation can be fully covered, including reliability, power quality, loss, and equipment status. A comprehensive analysis operation can be performed on the multi-faceted data of the target power grid. By analyzing multiple feature categories and their fusion results, multiple optimization objectives can be considered at the same time, which is conducive to improving the comprehensive analysis of the target power grid to improve the accuracy and reliability of the data fusion results. Through feature classification and data fusion, the feature categories and feature data that have the greatest impact on the operation of the power grid can be identified, thereby performing personalized optimization processing operations on the target power grid, which is conducive to improving the intelligence of subsequent optimization of the target power grid, thereby intelligently optimizing the current distribution network mode, and improving the utilization rate of distribution network equipment and improving the distribution network operation efficiency, and further improving the power supply reliability of the distribution network.

[0189] In yet another optional embodiment, before performing a distribution network optimization operation on the target power grid according to the distribution network optimization parameters and obtaining a distribution network optimization result, the method further includes:

[0190] According to the distribution network optimization parameters of the target power grid, a simulation optimization operation is performed on the target power grid to obtain a simulation optimization result;

[0191] According to the simulation optimization results, determine the optimization feasible parameters corresponding to the distribution network optimization parameters, and judge whether the optimization feasible parameters meet the preset operation optimization conditions;

[0192] When it is determined that the optimization feasible parameters meet the preset operation optimization conditions, the operation of performing distribution network optimization operations on the target power grid according to the distribution network optimization parameters is triggered to obtain the distribution network optimization results;

[0193] When it is determined that the optimization feasible parameters do not meet the preset operation optimization conditions, the distribution network optimization parameters are updated through the preset deep reinforcement algorithm to obtain the optimized scheduling parameters;

[0194] Among them, according to the distribution network optimization parameters, the distribution network optimization operation is performed on the target power grid to obtain the distribution network optimization results, including:

[0195] According to the optimized dispatching parameters, the distribution network optimization operation is performed on the target power grid to obtain the distribution network optimization results.

[0196] In this optional embodiment, optionally, performing a simulation optimization operation on the target power grid according to the distribution network optimization parameters of the target power grid to obtain a simulation optimization result may include:

[0197] The distribution network optimization parameters of the target power grid are input into a predetermined power grid model to perform simulated optimization operations on the target power grid through the power grid simulation model to obtain simulated optimization results; wherein the simulated optimization results may include the simulated optimization loss rate, simulated power supply reliability, and simulated power quality obtained after performing the simulated optimization operations on the target power grid.

[0198] In this optional embodiment, optionally, the optimization feasibility parameter corresponding to the distribution network optimization parameter includes the distribution network feasibility corresponding to the distribution network optimization parameter.

[0199] In this optional embodiment, optionally, the above-mentioned determination of whether the optimization feasible parameters meet the preset operation optimization conditions may include:

[0200] Determine whether the feasibility level corresponding to the optimized feasible parameter is greater than or equal to the feasibility level threshold corresponding to the preset operation optimization condition;

[0201] When it is determined that the feasibility degree corresponding to the optimized feasible parameter is greater than or equal to the feasibility degree threshold corresponding to the preset operation optimization condition, it is determined that the optimized feasible parameter meets the preset operation optimization condition; when it is determined that the feasibility degree corresponding to the optimized feasible parameter is less than the feasibility degree threshold corresponding to the preset operation optimization condition, it is determined that the optimized feasible parameter does not meet the preset operation optimization condition.

[0202] In this optional embodiment, the deep strength algorithm may optionally include a deep Q-network (DQN) or a policy gradient method; wherein the deep Q-network (DQN) algorithm is a value function-based reinforcement learning algorithm that combines deep learning and Q-learning. The goal of DQN is to learn an optimal Q-value function Q(s,a), which represents the expected reward of taking action a in state s; the policy gradient method is a policy-based reinforcement learning algorithm whose goal is to directly optimize the agent's policy π(a|s) rather than learning a value function. The policy π(a|s) represents the probability distribution of selecting action a in state s.

[0203] In this optional embodiment, optionally, performing the distribution network optimization operation on the target power grid according to the optimized scheduling parameters to obtain the distribution network optimization result may include:

[0204] According to the optimized dispatching parameters, the optimized dispatching execution parameters that match the optimized dispatching parameters are determined, and the distribution network optimization operation that matches the optimized dispatching execution parameters is performed on the target power grid to obtain the distribution network optimization results.

[0205] It can be seen that the implementation of this optional embodiment can perform simulated optimization operations on the target power grid according to the distribution network optimization parameters of the target power grid to obtain simulated optimization results, determine the optimization feasible parameters corresponding to the distribution network optimization parameters and judge whether the preset operation optimization conditions are met. If so, it triggers the execution of the operation of performing distribution network optimization operations on the target power grid according to the distribution network optimization parameters to obtain distribution network optimization results. If not, the distribution network optimization parameters are updated through the preset deep reinforcement algorithm to obtain optimized scheduling parameters, and the distribution network optimization operations are performed on the target power grid according to the optimized scheduling parameters to obtain distribution network optimization results. By performing simulated optimization operations before the actual optimization operation, the effect of the distribution network optimization parameters can be evaluated in advance, and through the simulated optimization results, it can be verified whether the distribution network optimization parameters meet the preset operation. Optimize conditions and ensure the validity of parameters. When the optimized feasible parameters do not meet the conditions, the deep reinforcement algorithm is used to automatically update the parameters and generate optimized scheduling parameters, which is conducive to improving the intelligence and efficiency of optimizing the operation mode of the target power grid. The deep reinforcement algorithm can dynamically adjust parameters according to the simulation optimization results, which is conducive to improving the accuracy and reliability of the optimization results. By optimizing the scheduling parameters, the power grid resources can be more reasonably allocated, the operating costs can be reduced, and the economic benefits of the power grid operation can be improved. It can also help to improve the stability and reliability of the power grid operation, as well as improve the power supply quality of the power grid, thereby intelligently optimizing the current distribution network mode, which is conducive to improving the utilization rate of the distribution network equipment and improving the distribution network operation efficiency, and further helping to improve the power supply reliability of the distribution network.

[0206] Example 3

[0207] See also Figure 3 , Figure 3 This is a schematic diagram of the structure of a device for optimizing the distribution network operation mode based on big data analysis disclosed in an embodiment of the present invention. Figure 3 As shown, the device for optimizing the distribution network operation mode based on big data analysis may include:

[0208] An acquisition module 301 is configured to acquire distribution network operation data of a target power grid and multi-source power grid data of the target power grid, wherein the distribution network operation data includes one or more of the following: topological structure data of the target power grid, power grid equipment operation data, power grid operation load data, historical power grid fault data, and power grid environmental factor data; and the multi-source power grid data includes one or more of the following: communication status data, operation record data, and historical measurement data of the target power grid.

[0209] The processing module 302 is used to perform data processing operations on the distribution network operation data and the multi-source data of the power grid to obtain data processing results;

[0210] A construction module 303 is used to construct a distribution network operation status big data evaluation model based on the data processing results;

[0211] The determination module 304 is configured to determine an operation evaluation result of the target power grid based on the distribution network operation status big data evaluation model and the distribution network operation data; and determine a power grid optimization target corresponding to the target power grid according to the operation evaluation result;

[0212] The generation module 305 is used to generate distribution network optimization parameters of the target power grid according to the distribution network operation status big data evaluation model and the power grid optimization target.

[0213] It can be seen that implementation Figure 3 The described device can obtain distribution network operation data and multi-source data of a target power grid and perform data processing operations to obtain data processing results. Based on the data processing results, a distribution network operation status big data evaluation model is constructed to thereby determine the operation evaluation results of the target power grid. Based on the operation evaluation results, corresponding power grid optimization targets are determined and distribution network optimization parameters for the target power grid are generated. By comprehensively analyzing the distribution network operation data and multi-source data, a comprehensive analysis of the data corresponding to the target power grid can be achieved by combining multiple data. This is beneficial for improving the accuracy and reliability of the data processing results and the determination of the operation evaluation results, and is also beneficial for the accuracy and reliability of the subsequent generation of distribution network optimization parameters. By analyzing the power grid operation data, the operating parameters of the voltage regulation equipment can be optimized to achieve intelligent optimization of the target power grid. The power grid operation parameters can be dynamically adjusted based on real-time data and prediction results to ensure that the power grid always operates in an optimal state. Based on the operation evaluation results, the load response capability of the power grid is optimized, and the flexibility and adaptability of the power grid are improved. Thus, the current distribution network mode is intelligently optimized, which is beneficial for improving the utilization rate of distribution network equipment and the distribution network operation efficiency, thereby improving the power supply reliability of the distribution network.

[0214] In an optional embodiment, if Figure 4 As shown, the device also includes:

[0215] The optimization module 306 is used to perform a distribution network optimization operation on the target power grid according to the distribution network optimization parameters to obtain a distribution network optimization result;

[0216] The comparison module 307 is used to perform a data comparison operation on the distribution network optimization result and the power grid optimization target to obtain a data comparison result;

[0217] The acquisition module 301 is also used to obtain real-time monitoring information corresponding to the target power grid;

[0218] The determination module 304 is further configured to determine a target operating state corresponding to the target power grid based on the real-time monitoring information;

[0219] The generation module 305 is further used to generate dynamic optimization parameters of the target power grid according to the target operating state and the data comparison result;

[0220] The updating module 308 is configured to update the distribution network optimization parameters according to the dynamic optimization parameters.

[0221] It can be seen that implementation Figure 4 The described device can perform distribution network optimization operations on the target power grid according to the distribution network optimization parameters to obtain distribution network optimization results, perform data comparison operations on the distribution network optimization results and the power grid optimization targets to obtain data comparison results, and obtain real-time monitoring information to determine the target operating state, generate dynamic optimization parameters of the target power grid according to the target operating state and the data comparison results, and update the distribution network optimization parameters. By performing optimization operations on the target power grid according to the distribution network optimization parameters, it is beneficial to improve the operating efficiency of the target power grid, and also to improve the operating reliability and stability of the target power grid. In addition, it dynamically generates optimization parameters according to the real-time monitoring information and the data comparison results, and updates the distribution network optimization parameters, so that the power grid can be adjusted in time according to the actual operating conditions, which is beneficial to improving the operation mode of the target power grid. The intelligence of optimization can timely grasp the operating status of the power grid through the real-time monitoring information of the target power grid obtained, which is conducive to improving the adaptability and flexibility of the power grid operation. Dynamic optimization parameters are generated based on real-time monitoring information and data comparison results, so that the power grid optimization strategy can be dynamically adjusted according to the actual operating status, which is conducive to improving the intelligence and real-time performance of optimizing the operating status of the target power grid, thereby further improving the reliability and stability of the power grid. By optimizing the distribution network operation and dynamically adjusting the parameters, the reasonable allocation and efficient utilization of energy can be better achieved, the energy utilization efficiency can be improved and the sustainability of the power grid can be enhanced, thereby intelligently optimizing the current distribution network mode, which is conducive to improving the utilization rate of the distribution network equipment and improving the distribution network operation efficiency, and further helping to improve the power supply reliability of the distribution network.

[0222] In another optional embodiment, as Figure 4 As shown, the acquisition module 301 is further used to obtain the grid location information corresponding to the target grid before the generation module 305 generates the distribution network optimization parameters of the target grid according to the distribution network operation status big data evaluation model and the grid optimization target, and obtain the current environment information corresponding to the target grid according to the grid location information;

[0223] The determination module 304 is further configured to determine target environmental information of the target power grid based on the power grid location information and the current environmental information;

[0224] The device also includes:

[0225] The first judgment module 309 is used to judge whether there are any influencing parameters in the target environment information that have an impact on the operating state of the target power grid;

[0226] The generating module 305 is further configured to generate an impact optimization parameter based on all the impact parameters when the first judging module 309 judges that the target environment information contains impact parameters that affect the operating state of the target power grid;

[0227] The specific method in which the generation module 305 generates the distribution network optimization parameters of the target power grid according to the distribution network operation status big data evaluation model and the power grid optimization target includes:

[0228] Based on the distribution network operation status big data evaluation model, power grid optimization objectives and parameters affecting optimization, the distribution network optimization parameters of the target power grid are generated.

[0229] It can be seen that implementation Figure 4 The described device can obtain the grid location information and current environmental information of the target grid, determine the target environmental information of the target grid based on the grid location information and the current environmental information, and judge whether there are influencing parameters in the target environmental information that affect the operating state of the target grid. If so, the influencing optimization parameters are generated according to all the influencing parameters, and the distribution network optimization parameters of the target grid are generated according to the distribution network operating state big data evaluation model, the grid optimization target and the influencing optimization parameters. By obtaining the grid location information and the current environmental information of the target grid, the external conditions of the grid operation can be fully understood, and the actual operating state of the target grid can be comprehensively generated based on the comprehensive information, which is conducive to improving the accuracy and reliability of determining the operating state of the target grid and judging whether there are influencing parameters. It can also generate influencing optimization parameters through the environmental information obtained in real time, which can optimize the distribution network. Parameters dynamically adapt to environmental changes, which is conducive to improving the real-time performance of subsequent generation of distribution network optimization parameters and the matching degree with the real-time status of the target power grid. When the influencing parameters are identified, the generated influencing optimization parameters can adjust the power grid operation strategy in a targeted manner, thereby improving the reliability of the power grid in complex environments. It can also more reasonably allocate power grid resources by comprehensively considering the power grid location information and current environmental information. Through the generation of optimization parameters driven by real-time data, it can also automatically adjust the optimization strategy according to the real-time environmental information and power grid status, thereby improving the intelligence level of the power grid. The optimization parameters generated based on the prediction results can dynamically adjust the power grid operation strategy, which is also conducive to improving the prediction ability and operation efficiency of the power grid, thereby intelligently optimizing the current distribution network mode, which is conducive to improving the utilization rate of distribution network equipment and improving the distribution network operation efficiency, and thus also conducive to improving the power supply reliability of the distribution network.

[0230] In another optional embodiment, Figure 4 As shown, the generation module 305 generates the distribution network optimization parameters of the target power grid according to the distribution network operation status big data evaluation model, the power grid optimization target and the influencing optimization parameters, including:

[0231] Extracting a first target parameter of a power grid optimization target and a second target parameter affecting the optimization parameter, and generating a target evaluation parameter based on the first target parameter and the second target parameter;

[0232] The target evaluation parameters are input into the distribution network operation status big data evaluation model to perform parameter evaluation operations on the target evaluation parameters through the distribution network operation status big data evaluation model to obtain parameter evaluation results, and based on the parameter evaluation results, at least one optimization parameter that matches the parameter evaluation results is determined from a predetermined optimization parameter library, and the distribution network optimization parameters of the target power grid are generated based on all the optimization parameters.

[0233] It can be seen that implementation Figure 4 The described device can extract a first target parameter of a power grid optimization target and a second target parameter that affects the optimization parameter, generate a target evaluation parameter based on the first and second target parameters, input the target evaluation parameter into a distribution network operation status big data evaluation model to perform a parameter evaluation operation on the target evaluation parameter to obtain a parameter evaluation result, and then determine at least one matching optimization parameter. The distribution network optimization parameter of the target power grid is generated based on all the optimization parameters. The target evaluation parameter can be evaluated using the distribution network operation status big data evaluation model, which can more accurately reflect the difference parameters between the current power grid operation status and the optimization target, thereby improving the accuracy and reliability of the parameter evaluation results. By comprehensively considering multiple parameters and factors, the power grid operation status can be optimized as a whole, achieving comprehensive improvement in the operation efficiency and performance of the power grid. By optimizing the power grid operation parameters, the power outage duration and frequency can be reduced, and power supply reliability can be improved. The optimization parameters can be dynamically adjusted according to real-time changes in the power grid operation status, enabling the power grid to better adapt to the influence of load change factors, thereby improving the operation reliability and stability of the target power grid. Thus, the current distribution network mode can be intelligently optimized, which can improve the utilization rate of distribution network equipment and the operation efficiency of the distribution network, thereby improving the power supply reliability of the distribution network.

[0234] In another optional embodiment, Figure 4 As shown, the processing module 302 performs data processing operations on the distribution network operation data and the multi-source data of the power grid, and the specific methods of obtaining the data processing results include:

[0235] Performing a data cleaning operation on the distribution network operation data and the multi-source data of the power grid to obtain a data cleaning result, wherein the data cleaning result at least includes the distribution network operation data and the multi-source data of the power grid after the data cleaning operation is performed;

[0236] Determine the data integrity parameters corresponding to the data cleaning results, and judge whether the data integrity parameters meet the preset data integrity conditions;

[0237] When it is determined that the data integrity parameter does not meet the preset data integrity condition, a data filling operation is performed on the data corresponding to the data cleaning result according to the data integrity parameter and the preset data integrity condition to obtain target filled data, and a data processing result is generated based on the target filled data;

[0238] When it is determined that the data integrity parameters meet the preset data integrity conditions, a data processing result is generated based on the data corresponding to the data cleaning result.

[0239] It can be seen that implementation Figure 4 The described device can perform data cleaning operations on distribution network operation data and multi-source data of the power grid to obtain data cleaning results, determine the data integrity parameters corresponding to the data cleaning results and judge whether the preset data integrity conditions are met. If not, the data corresponding to the data cleaning results are subjected to data filling operations according to the data integrity parameters and the data integrity conditions to obtain target filling data and then generate data processing results. If satisfied, the data processing results are generated according to the data corresponding to the data cleaning results. By removing noise data, unifying data formats and other operations, the accuracy and consistency of the data can be effectively improved. By checking the data integrity parameters and the data filling operations, the integrity of the data is ensured, and the actual operating status of the target power grid can be more accurately reflected. Through a systematic data processing process, it is beneficial to improve the efficiency and accuracy of data processing, and through data filling operations, missing data can be filled to make the data more complete and improve the availability of data. Data cleaning operations can also ensure data consistency and avoid analysis deviations caused by inconsistent data formats or erroneous data, which is beneficial to improve the accuracy and reliability of subsequent data processing results, thereby optimizing power grid operating parameters to reduce losses and energy consumption, and reasonably allocating power grid resources based on complete and accurate data to improve equipment utilization, thereby intelligently optimizing the current distribution network mode, which is beneficial to improving the utilization rate of distribution network equipment and improving the distribution network operation efficiency, and further helping to improve the power supply reliability of the distribution network.

[0240] In another optional embodiment, Figure 4 As shown, the specific manner in which the determination module 304 determines the power grid optimization target corresponding to the target power grid according to the operation evaluation result includes:

[0241] Extracting multi-dimensional feature data corresponding to the operation evaluation results, and determining feature correlation relationships corresponding to the multi-dimensional feature data based on the multi-dimensional feature data;

[0242] Performing a feature classification operation on all feature data corresponding to the multi-dimensional feature data according to the feature association relationship to obtain at least one feature category, wherein each feature category includes at least one feature data;

[0243] Based on each feature category and all feature data included in each feature category, a feature data fusion operation is performed to obtain a data fusion result; wherein the data fusion result includes operating state impact data corresponding to the target power grid;

[0244] According to the data fusion results, the grid optimization target corresponding to the target grid is determined.

[0245] It can be seen that implementation Figure 4 The described device can extract multi-dimensional feature data corresponding to the operation evaluation results and determine the corresponding feature associations. Based on the feature associations, it performs a feature classification operation on the feature data corresponding to the multi-dimensional feature data to obtain at least one feature category. It then performs a feature data fusion operation based on each feature category and all feature data included in each feature category to obtain a data fusion result. By extracting the multi-dimensional feature data corresponding to the operation evaluation results, it can comprehensively cover all aspects of power grid operation, including reliability, power quality, loss, and equipment status. It can also perform comprehensive analysis operations on multiple aspects of the target power grid data. By analyzing multiple feature categories and their fusion results, it can simultaneously consider multiple optimization objectives, which is conducive to improving the comprehensive analysis of the target power grid and improving the accuracy and reliability of the data fusion results. Through feature classification and data fusion, it can identify the feature categories and feature data that have the greatest impact on power grid operation, thereby performing personalized optimization processing operations on the target power grid, which is conducive to improving the intelligence of subsequent optimization of the target power grid, thereby intelligently optimizing the current distribution network mode, and facilitating the improvement of the utilization rate of distribution network equipment and the efficiency of distribution network operation, thereby also facilitating the improvement of the power supply reliability of the distribution network.

[0246] In another optional embodiment, Figure 4 As shown, the device also includes:

[0247] The simulation module 310 is configured to perform a simulated optimization operation on the target power grid according to the distribution network optimization parameters of the target power grid to obtain a simulated optimization result before the optimization module 306 performs the distribution network optimization operation on the target power grid according to the distribution network optimization parameters to obtain the distribution network optimization result;

[0248] The determination module 304 is further configured to determine feasible optimization parameters corresponding to the distribution network optimization parameters based on the simulation optimization results;

[0249] The second judgment module 311 is used to judge whether the optimization feasible parameters meet the preset operation optimization conditions; when it is judged that the optimization feasible parameters meet the preset operation optimization conditions, the optimization module 306 is triggered to perform the distribution network optimization operation on the target power grid according to the distribution network optimization parameters to obtain the distribution network optimization result;

[0250] The updating module 308 is further configured to, when the second judging module 311 judges that the optimization feasible parameters do not meet the preset operation optimization conditions, perform an updating operation on the distribution network optimization parameters using a preset deep reinforcement algorithm to obtain optimized scheduling parameters;

[0251] The optimization module 306 performs the distribution network optimization operation on the target power grid according to the distribution network optimization parameters, and obtains the distribution network optimization result in the following specific ways:

[0252] According to the optimized dispatching parameters, the distribution network optimization operation is performed on the target power grid to obtain the distribution network optimization results.

[0253] It can be seen that implementation Figure 4 The described device can perform simulated optimization operations on the target power grid according to the distribution network optimization parameters of the target power grid to obtain simulated optimization results, determine the optimization feasible parameters corresponding to the distribution network optimization parameters and judge whether the preset operation optimization conditions are met. If so, it triggers the execution of the operation of performing distribution network optimization operations on the target power grid according to the distribution network optimization parameters to obtain distribution network optimization results. If not, it performs an update operation on the distribution network optimization parameters through a preset deep reinforcement algorithm to obtain optimized scheduling parameters, and performs distribution network optimization operations on the target power grid according to the optimized scheduling parameters to obtain distribution network optimization results. By performing simulated optimization operations before the actual optimization operation, the effect of the distribution network optimization parameters can be evaluated in advance, and through the simulated optimization results, it can be verified whether the distribution network optimization parameters meet the preset operation optimization conditions. To ensure the validity of the parameters, when the optimized feasible parameters do not meet the conditions, the deep reinforcement algorithm is used to automatically update the parameters and generate optimized dispatching parameters, which is conducive to improving the intelligence and efficiency of optimizing the operation mode of the target power grid. The deep reinforcement algorithm can dynamically adjust the parameters according to the simulation optimization results, which is conducive to improving the accuracy and reliability of the optimization results. By optimizing the dispatching parameters, the power grid resources can be more reasonably allocated, the operating costs can be reduced, and the economic benefits of the power grid operation can be improved. It can also help to improve the stability and reliability of the power grid operation, as well as the power supply quality of the power grid, thereby intelligently optimizing the current distribution network mode, which is conducive to improving the utilization rate of the distribution network equipment and improving the distribution network operation efficiency, and further helping to improve the power supply reliability of the distribution network.

[0254] Example 4

[0255] See also Figure 5 , Figure 5 This is a structural diagram of another device for optimizing the distribution network operation mode based on big data analysis disclosed in an embodiment of the present invention. Figure 5 As shown, the device for optimizing the distribution network operation mode based on big data analysis may include:

[0256] A memory 401 storing executable program code;

[0257] a processor 402 coupled to the memory 401;

[0258] The processor 402 calls the executable program code stored in the memory 401 to execute the steps of the method for optimizing the distribution network operation mode based on big data analysis described in the first embodiment of the present invention or the second embodiment of the present invention.

[0259] Example 5

[0260] An embodiment of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute the steps of the method for optimizing the distribution network operation mode based on big data analysis described in Example 1 or Example 2 of the present invention.

[0261] Example 6

[0262] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the method for optimizing the distribution network operation mode based on big data analysis described in Example 1 or Example 2.

[0263] The device embodiments described above are merely illustrative, wherein the modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, i.e., they may be located in one place or distributed across multiple network modules. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Those skilled in the art can understand and implement the present invention without inventive effort.

[0264] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus the necessary general hardware platform, or of course, by means of hardware. Based on this understanding, the above technical solution, in essence, or the portion that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0265] Finally, it should be noted that the method and device for optimizing the distribution network operation mode based on big data analysis disclosed in the embodiment of the present invention only disclose the preferred embodiments of the present invention, which are only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, ordinary technicians in this field should understand that it is still possible to modify the technical solutions recorded in the aforementioned embodiments, or to 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 various embodiments of the present invention.

Claims

1. A method for optimizing distribution network operation mode based on big data analysis, characterized in that: The method comprises: Obtaining distribution network operation data of a target power grid and multi-source power grid data of the target power grid, wherein the distribution network operation data includes one or more of the following: topological structure data of the target power grid, power grid equipment operation data, power grid operation load data, historical power grid fault data, and power grid environmental factor data; and the multi-source power grid data includes one or more of the following: communication status data, operation record data, and historical measurement data of the target power grid; performing data processing operations on the distribution network operation data and the multi-source data of the power grid to obtain data processing results, constructing a distribution network operation status big data evaluation model based on the data processing results, and determining an operation evaluation result of the target power grid based on the distribution network operation status big data evaluation model and the distribution network operation data; According to the operation evaluation result, the power grid optimization target corresponding to the target power grid is determined, and the distribution network optimization parameters of the target power grid are generated according to the distribution network operation status big data evaluation model and the power grid optimization target.

2. The method for optimizing distribution network operation mode based on big data analysis according to claim 1, characterized in that: The method further comprises: Performing a distribution network optimization operation on the target power grid according to the distribution network optimization parameters to obtain a distribution network optimization result; Performing a data comparison operation on the distribution network optimization result and the power grid optimization target to obtain a data comparison result; Acquiring real-time monitoring information corresponding to the target power grid, and determining a target operating state corresponding to the target power grid based on the real-time monitoring information; According to the target operating state and the data comparison result, dynamic optimization parameters of the target power grid are generated, and the distribution network optimization parameters are updated according to the dynamic optimization parameters.

3. The method for optimizing distribution network operation mode based on big data analysis according to claim 1, characterized in that: Before generating the distribution network optimization parameters of the target power grid according to the distribution network operation status big data evaluation model and the power grid optimization target, the method further includes: Obtaining grid location information corresponding to the target grid, and obtaining current environment information corresponding to the target grid based on the grid location information; Determining target environment information of the target power grid based on the power grid location information and the current environment information, and judging whether there are influencing parameters in the target environment information that have an impact on the operating state of the target power grid; When it is determined that the target environment information contains influencing parameters that affect the operating state of the target power grid, generating an influencing optimization parameter based on all the influencing parameters; The step of generating the distribution network optimization parameters of the target power grid according to the distribution network operation status big data evaluation model and the power grid optimization target includes: The distribution network optimization parameters of the target power grid are generated according to the distribution network operation status big data evaluation model, the power grid optimization target and the influencing optimization parameters.

4. The method for optimizing the distribution network operation mode based on big data analysis according to claim 3 is characterized in that: The step of generating the distribution network optimization parameters of the target power grid according to the distribution network operation status big data evaluation model, the power grid optimization target, and the influencing optimization parameters includes: Extracting a first target parameter of the power grid optimization target and extracting a second target parameter affecting the optimization parameter, and generating a target evaluation parameter according to the first target parameter and the second target parameter; The target evaluation parameters are input into the distribution network operation status big data evaluation model to perform parameter evaluation operations on the target evaluation parameters through the distribution network operation status big data evaluation model to obtain parameter evaluation results, and based on the parameter evaluation results, at least one optimization parameter that matches the parameter evaluation result is determined from a predetermined optimization parameter library, and the distribution network optimization parameters of the target power grid are generated based on all the optimization parameters.

5. The method for optimizing distribution network operation mode based on big data analysis according to claim 1, characterized in that: The performing of data processing operations on the distribution network operation data and the power grid multi-source data to obtain data processing results includes: Performing a data cleaning operation on the distribution network operation data and the multi-source power grid data to obtain a data cleaning result, wherein the data cleaning result at least includes the distribution network operation data and the multi-source power grid data after performing the data cleaning operation; Determining a data integrity parameter corresponding to the data cleaning result, and judging whether the data integrity parameter satisfies a preset data integrity condition; When it is determined that the data integrity parameter does not satisfy the preset data integrity condition, performing a data filling operation on the data corresponding to the data cleaning result according to the data integrity parameter and the preset data integrity condition to obtain target filled data, and generating a data processing result based on the target filled data; When it is determined that the data integrity parameter meets the preset data integrity condition, a data processing result is generated according to the data corresponding to the data cleaning result.

6. The method for optimizing distribution network operation mode based on big data analysis according to claim 1, characterized in that: Determining a power grid optimization target corresponding to the target power grid according to the operation evaluation result includes: Extracting multi-dimensional feature data corresponding to the operation evaluation result, and determining a feature association relationship corresponding to the multi-dimensional feature data based on the multi-dimensional feature data; performing a feature classification operation on all feature data corresponding to the multi-dimensional feature data according to the feature association relationship to obtain at least one feature category, wherein each feature category includes at least one feature data; Based on each of the feature categories and all the feature data included in each of the feature categories, a feature data fusion operation is performed to obtain a data fusion result; wherein the data fusion result includes the operating state impact data corresponding to the target power grid; According to the data fusion result, a power grid optimization target corresponding to the target power grid is determined.

7. The method for optimizing distribution network operation mode based on big data analysis according to claim 2, characterized in that: Before performing the distribution network optimization operation on the target power grid according to the distribution network optimization parameters and obtaining the distribution network optimization result, the method further includes: Performing a simulation optimization operation on the target power grid according to the distribution network optimization parameters of the target power grid to obtain a simulation optimization result; Determine, based on the simulation optimization results, the feasible optimization parameters corresponding to the distribution network optimization parameters, and judge whether the feasible optimization parameters meet the preset operation optimization conditions; When it is determined that the optimization feasible parameters meet the preset operation optimization conditions, triggering the execution of the operation of performing the distribution network optimization operation on the target power grid according to the distribution network optimization parameters to obtain the distribution network optimization result; When it is determined that the optimization feasible parameters do not meet the preset operation optimization conditions, the distribution network optimization parameters are updated by a preset deep reinforcement algorithm to obtain optimized scheduling parameters; The step of performing a distribution network optimization operation on the target power grid according to the distribution network optimization parameters to obtain a distribution network optimization result includes: According to the optimized scheduling parameters, a distribution network optimization operation is performed on the target power grid to obtain a distribution network optimization result.

8. A device for optimizing distribution network operation mode based on big data analysis, characterized in that: The device comprises: an acquisition module, configured to acquire distribution network operation data of a target power grid and multi-source power grid data of the target power grid, wherein the distribution network operation data includes one or more of the topological structure data of the target power grid, power grid equipment operation data, power grid operation load data, power grid historical fault data, and power grid environmental factor data; and the multi-source power grid data includes one or more of the communication status data, operation record data, and historical measurement data of the target power grid; a processing module, configured to perform data processing operations on the distribution network operation data and the multi-source data of the power grid to obtain data processing results; A construction module is used to construct a distribution network operation status big data evaluation model based on the data processing results; A determination module, configured to determine an operation evaluation result of the target power grid based on the distribution network operation status big data evaluation model and the distribution network operation data; and determine a power grid optimization target corresponding to the target power grid according to the operation evaluation result; A generation module is used to generate distribution network optimization parameters of the target power grid based on the distribution network operation status big data evaluation model and the power grid optimization target.

9. A device for optimizing distribution network operation mode based on big data analysis, characterized in that: The device comprises: a memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the method for optimizing the distribution network operation mode based on big data analysis as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that The computer storage medium stores computer instructions, which, when called, are used to execute the method for optimizing the distribution network operation mode based on big data analysis as described in any one of claims 1 to 7.

Images