Power distribution network management method and device, computer equipment and readable storage medium

Abstract

The invention relates to a power distribution network management method and device, computer equipment and a readable storage medium. The method comprises the following steps: acquiring real-time operation data of a power distribution network; obtaining a service quality evaluation result of the power distribution network according to the real-time operation data, a preset resource configuration index and a pre-constructed service quality model; and under the condition that the service quality evaluation result does not meet a preset condition, determining a resource configuration strategy according to the service quality evaluation result and the real-time operation data. The method can improve the utilization rate of power grid resources.

Description

Technical Field

[0001] The present application relates to the field of smart grid technology, and in particular to a distribution network management method, apparatus, computer equipment and readable storage medium. Background Art

[0002] In the power grid system, as the degree of intelligence continues to increase, the performance requirements for perception, transmission, and computing are becoming increasingly complex. On the one hand, it is necessary to ensure the accuracy of data in order to achieve accurate monitoring and control of the power grid operation status; on the other hand, real-time requirements are also crucial to respond to various changes in the power grid in a timely manner.

[0003] The power grid in related technologies often adopts a fixed resource allocation method, which makes it difficult to achieve effective utilization of resources. Summary of the invention

[0004] Based on this, it is necessary to provide a distribution network management method, device, computer equipment and readable storage medium that can improve the utilization rate of power grid resources in response to the above technical problems.

[0005] In a first aspect, the present application provides a distribution network management method, the method comprising:

[0006] Obtain real-time operation data of the distribution network;

[0007] Obtaining a service quality evaluation result of the distribution network according to the real-time operation data and a pre-built service quality model;

[0008] In the case that the service quality evaluation result does not meet the preset conditions, a resource configuration strategy is determined according to the service quality evaluation result, the preset resource configuration index and the real-time operation data.

[0009] In one embodiment, before acquiring the real-time operation data of the distribution network, the method further includes:

[0010] Obtain historical operation data of the distribution network within a preset time period;

[0011] Determining a resource adjustment strategy according to the real-time operation data of the distribution network and the historical operation data;

[0012] According to the resource adjustment strategy, the working status of at least part of the resource equipment in the distribution network is adjusted.

[0013] In one embodiment, the service quality model is constructed by the following method:

[0014] Obtain historical operation data of the distribution network within a preset time period;

[0015] Preprocessing the historical operation data to form a sample data set;

[0016] The model to be trained is trained according to the sample data set until a preset training stop condition is met to obtain a service quality model.

[0017] In one embodiment, the preprocessing of the historical operation data to form a sample data set includes:

[0018] Determining a candidate data set from the historical operation data according to a preset target data volume;

[0019] A sample data set is determined according to a preset thinning rule and the candidate data set.

[0020] In one embodiment, determining the candidate data set from the historical operation data according to a preset target data volume includes:

[0021] Assign a data number to each historical operation data, and different historical operation data are assigned different data numbers;

[0022] Obtain multiple random numbers, wherein the maximum value among the random numbers is not less than the maximum value among the data numbers;

[0023] According to the random number and the data serial number of each of the historical operation data, candidate data are determined from a plurality of historical operation data until the number of the candidate data reaches the total target data volume, thereby forming the candidate data set.

[0024] In one embodiment, the sample data set includes a training set and a validation set; training the model to be trained according to the sample data set until a preset training stop condition is met to obtain the service quality model includes:

[0025] Iteratively training the model to be trained using the training set;

[0026] After iteratively training the model to be trained using the training set each time, verifying the trained model to be trained using the verification set to obtain a verification loss;

[0027] When the verification loss obtained for the i-th time is greater than or equal to the verification loss obtained for the (i-1)th time, the iterative training of the model to be trained is stopped to obtain a service quality model.

[0028] In a second aspect, the present application provides a distribution network management device, the device comprising:

[0029] A first acquisition module is used to acquire real-time operation data of the distribution network;

[0030] A second acquisition module is used to obtain a service quality evaluation result of the distribution network according to the real-time operation data, the preset resource configuration index and the pre-built service quality model;

[0031] The first determination module is used to determine a resource configuration adjustment strategy according to the service quality evaluation result and the real-time operation data when the service quality evaluation result does not meet a preset condition.

[0032] In a third aspect, the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the distribution network management method described in any one of the above embodiments when executing the computer program.

[0033] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the distribution network management method described in any one of the above embodiments are implemented.

[0034] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the distribution network management method described in any of the above embodiments.

[0035] The above-mentioned distribution network management method, device, computer equipment and readable storage medium first obtain the real-time operation data of the distribution network, and then input the real-time operation data of the distribution network and the preset resource configuration indicators into a pre-built service quality model, and the service quality model outputs the service quality evaluation result of the distribution network under the current resource configuration state. If the service quality evaluation result does not meet the preset conditions, the resource configuration strategy of the distribution network is adjusted according to the service quality evaluation result and the real-time operation data, so that the resources of the distribution network can be effectively utilized. The distribution network management method of the present application can further evaluate the resource configuration of the distribution network, and then adjust the resource configuration strategy of the distribution network to adapt to the complex and changeable operating environment and demand fluctuations of the distribution network, and improve the flexibility of resource scheduling of the distribution network and the resource utilization rate of the distribution network. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0037] FIG1 is a schematic diagram of a flow chart of a distribution network management method in one embodiment;

[0038] FIG2 is a schematic diagram of a flow chart of a distribution network management method in another embodiment;

[0039] FIG3 is a flow chart of a method for constructing a service quality model in one embodiment;

[0040] FIG4 is a schematic diagram of a flow chart of step S302 in one embodiment;

[0041] FIG5 is a schematic diagram of a flow chart of step S401 in one embodiment;

[0042] FIG6 is a schematic diagram of a flow chart of step S303 in one embodiment;

[0043] FIG7 is a structural block diagram of a distribution network management device in one embodiment;

[0044] FIG. 8 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0046] In an exemplary embodiment, referring to FIG. 1 , the present application provides a distribution network management method, which includes steps S101 to S103 .

[0047] S101: Acquire real-time operation data of the distribution network.

[0048] The distribution network refers to a power grid that receives electric energy from the transmission network or regional power plant and distributes it locally or step by step according to voltage to various users through distribution facilities. It can be understood that the distribution network includes power supply equipment, distribution equipment, control equipment, protection equipment and auxiliary equipment. Specifically, the power supply equipment may include power generation equipment and power input equipment. The power generation equipment, such as a generator, can convert mechanical energy into electrical energy. The power input equipment involves related equipment for obtaining electrical energy from the power grid, such as high-voltage circuit breakers and power transformers. The task of the distribution equipment is to distribute electrical energy to various power consumption points, which may include various circuit breakers, disconnectors, load switches, distribution lines, cables, distribution cabinets and distribution boards. The control equipment is used to control the distribution and use of electrical energy, including various controllers, contactors and motors. These devices can ensure the stable operation of the power system and adjust the distribution of electrical energy according to actual needs. Protection equipment is equipment that ensures the safety of the power supply and distribution network. When the system fails or is abnormal, the protection equipment can quickly cut off the circuit or reduce the current intensity to protect the safety of electrical equipment and personnel. Common protection equipment includes lightning arresters, fuses, leakage protectors, etc. Auxiliary equipment refers to various auxiliary facilities and equipment related to the distribution network, such as power capacitors, cable accessories, monitoring systems, etc. Although the equipment is not directly involved in the transmission and distribution of electric energy, it plays an important auxiliary role in ensuring the stable operation and safety of the power system.

[0049] In applications, sensors can be set on these devices to detect the status of each device in the distribution network in real time, such as the load change status of each device, etc., to obtain the real-time operation data of these devices and upload it to the control terminal of the distribution network.

[0050] S102: Obtain a service quality evaluation result of the distribution network according to the real-time operation data and a pre-built service quality model.

[0051] After the control terminal of the distribution network receives the real-time operation data of each device in the distribution network, it can analyze the real-time operation data, extract the current resource configuration parameters of the distribution network, and input these parameters into the pre-built service quality model to obtain the service quality evaluation result that represents the service quality mapping relationship between the distribution network in the current environment and demand.

[0052] S103: When the service quality evaluation result does not meet the preset conditions, a resource allocation strategy is determined according to the service quality evaluation result, preset resource allocation indicators and real-time operation data.

[0053] If the service quality assessment result indicates that the current service quality of the distribution network is poor, then the resource allocation strategy can be determined based on the various service quality indicators included in the output service quality results, such as perception accuracy, transmission real-time, calculation accuracy, etc., combined with the preset resource allocation indicators, and the resource configuration parameters can be dynamically adjusted. These adjusted resource configuration parameters are input into the service quality model to obtain a service quality mapping relationship that adapts to the current environment and needs, providing a basis for optimal resource allocation.

[0054] The above-mentioned distribution network management method, device, computer equipment and readable storage medium first obtain the real-time operation data of the distribution network, and then input the real-time operation data of the distribution network and the preset resource configuration indicators into a pre-built service quality model, and the service quality model outputs the service quality evaluation result of the distribution network under the current resource configuration state. If the service quality evaluation result does not meet the preset conditions, the resource configuration strategy of the distribution network is adjusted according to the service quality evaluation result and the real-time operation data, so that the resources of the distribution network can be effectively utilized. The distribution network management method of the present application can further evaluate the resource configuration of the distribution network, and then adjust the resource configuration strategy of the distribution network to adapt to the complex and changeable operating environment and demand fluctuations of the distribution network, and improve the flexibility of resource scheduling of the distribution network and the resource utilization rate of the distribution network.

[0055] In an exemplary embodiment, referring to FIG. 2 , the distribution network management method further includes steps S201 to S203 .

[0056] S201: Obtain historical operation data of the distribution network within a preset time period.

[0057] In one example, the control terminal can continuously obtain and record the historical operation data of each device in the distribution network during a preset time period to analyze and record the historical data of various resources in the distribution network, such as computing power, transmission bandwidth, etc.

[0058] S202: Determine a resource adjustment strategy based on the real-time operation data and historical operation data of the distribution network.

[0059] The control terminal can also pre-set the load threshold of each resource. For example, the safety threshold of the CPU utilization of the server in the control device is set to 70%. When this threshold is exceeded, it is considered that the computing resources may be under pressure and a resource adjustment strategy needs to be determined. The dynamic state of each resource can be analyzed based on the historical data and real-time data of each resource in the distribution network, and whether each resource has undergone sudden changes, such as sudden increases or decreases, can be detected. In combination with the set load thresholds of each resource, it can be determined whether the resources in the distribution network need to be adjusted, and how to specify the resource adjustment strategy.

[0060] S203: Adjust the working status of at least part of the resource equipment in the distribution network according to the resource adjustment strategy.

[0061] For the case of load reduction, in one example, assuming that the load threshold of the CPU utilization of the server in the control device is 30%, when the CPU utilization of the server continues to be lower than 30% for a period of time, some idle computing resources can be recycled or allocated to other low-priority tasks for background processing.

[0062] In the case of load increase, if there are idle resources, priority is given to increasing idle resources, dynamically allocating spare resources, and adjusting resource allocation according to task priority. For example, when the transmission bandwidth occupancy rate continues to rise and approaches the set threshold, the spare bandwidth is preferentially allocated to the business data transmission with high real-time requirements. It can be seen that the elastic resource adjustment strategy solves the problem of inflexible resource allocation. The elastic resource adjustment strategy can effectively respond to sudden load changes, ensure the stable operation of the power grid system, and improve the reliability and adaptability of the system.

[0063] In an exemplary embodiment, referring to FIG. 3 , the service quality model is constructed using the following method, and the service quality model construction method includes steps S301 to S303 .

[0064] S301: Obtain historical operation data of the distribution network within a preset time period.

[0065] In this embodiment, the historical operation data may be relevant data of sensing, transmission, calculation and the like under different load conditions within a preset time period of the distribution network.

[0066] S302: Preprocess the historical operation data to form a sample data set.

[0067] After the historical operation data is collected, it can be pre-processed by cleaning and removing noise points to reduce the amount of historical operation data while retaining key information in the historical operation data, and finally form a sample data set.

[0068] S303: Train the model to be trained according to the sample data set until a preset training stop condition is met to obtain a service quality model.

[0069] The model to be trained can be a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), or a special network structure designed according to the characteristics of the power grid system data. The number of input layer nodes of the model to be trained corresponds to the number of features related to resource configuration, and the number of output layer nodes matches the number of service quality indicators.

[0070] For example, the sample data set can be divided into a training set, a validation set, and a test set. All samples in the training set are trained multiple times iteratively until a preset training stop condition is met, such as reaching a maximum number of training rounds, the loss on the validation set no longer decreasing, or reaching a predetermined threshold, etc., to obtain a service quality model.

[0071] In an exemplary embodiment, please refer to FIG. 4 , step S302 , preprocessing the historical operation data to form a sample data set, including step S401 and step S402 .

[0072] S401: Determine a candidate data set from historical operation data according to a preset target data volume.

[0073] In one example, in order to reduce the amount of historical operation data while retaining key information in the historical operation data, first, a portion of unnecessary historical operation data can be filtered out from the historical operation data. Specifically, a target total amount of data can be set, and the target total amount of data is less than the total amount of historical operation data. The historical operation data is filtered according to the target total amount of data to form a candidate data set.

[0074] S402: Determine a sample data set according to a preset sparsification rule and candidate data sets.

[0075] In the application, after obtaining the historical operation data, the distribution, correlation and other characteristics of the historical operation data can be used to formulate the sparseness rules. Then, the sparse sampling method can be used to check whether each data in the candidate data set meets the selection conditions according to the defined sparseness rules. The data that meets the sparseness rules is retained, and the data that does not meet the rules is discarded. The retained data forms the sample data set.

[0076] In an exemplary embodiment, please refer to FIG. 5 , step S401 , determining a candidate data set from historical operation data according to a preset target data volume, including steps S501 to S503 .

[0077] S501: Allocate a data number to each historical operation data, and different historical operation data are allocated different data numbers.

[0078] In this embodiment, a data number may be assigned to each collected historical operation data.

[0079] S502: Obtain multiple random numbers, wherein the maximum value among the random numbers is not less than the maximum value among the data numbers.

[0080] Next, a random number generator is used to generate a series of random numbers, and the range of the random numbers should cover the range of data numbers of the historical running data.

[0081] S503: Determine candidate data from multiple historical operation data according to the random number and the data serial number of each historical operation data, until the number of candidate data reaches the total target data, to form a candidate data set.

[0082] Specifically, the historical running data whose data numbers are consistent with the random numbers are determined as candidate data, and real-time statistics are conducted to see whether the number of candidate data reaches the total target data. When the number of candidate data reaches the total target data, the historical running data whose data numbers are consistent with the random numbers are stopped from being determined as candidate data to form a candidate data set.

[0083] In an exemplary embodiment, please refer to FIG. 6 , step S303 , training the model to be trained according to the sample data set until a preset training stop condition is met, and obtaining a service quality model, including steps S601 to S603 .

[0084] S601: Perform iterative training on the model to be trained using the training set.

[0085] It can be understood that the sample data set is divided into a training set, a validation set, and a test set, and the data in the training set is used to iteratively train the model to be trained.

[0086] S602: After each iterative training of the model to be trained using the training set, the trained model to be trained is verified using the verification set to obtain the verification loss.

[0087] The loss function is used to measure the gap between the predicted results of the neural network and the actual results. After each iterative training of the model to be trained using the training set, the data in the validation set can be input into the model to be trained, and the gap between the output of the model to be trained and the actual results can be calculated using the preset loss function to obtain the validation loss.

[0088] S603: When the verification loss obtained for the i-th time is greater than or equal to the verification loss obtained for the (i-1)-th time, stop iterative training of the model to be trained and obtain a service quality model.

[0089] The training goal of the model to be trained is to minimize the loss function so that the output of the model to be trained is as close to the actual result as possible. Therefore, when the verification loss no longer decreases, the iterative training of the model to be trained can be stopped to obtain the service quality model. In another example, a loss threshold can also be set. When the verification loss reaches the set loss threshold, the iterative training of the model to be trained is stopped to obtain the service quality model.

[0090] In the application, after obtaining the service quality model, you can continue to use the validation set to evaluate the performance of the service quality model, monitor indicators such as accuracy, recall, F1 value, mean square error, etc., and observe whether the service quality model is overfitting or underfitting. If overfitting is found, regularization techniques (such as L1 regularization, L2 regularization, Dropout, etc.) can be used to adjust the complexity of the service quality model to prevent the service quality model from excessively memorizing training data and losing its generalization ability. And optimize the model according to the evaluation results, such as adjusting the service quality model structure (increasing or decreasing the number of hidden layers, changing the type of layer, etc.), adjusting hyperparameters (learning rate, regularization coefficient, etc.), and then training and evaluating again until satisfactory service quality model performance is obtained.

[0091] In one example, by inputting the actual operation data of the distribution network into the trained service quality model, the current service quality of the distribution network can be accurately evaluated, and then the service quality evaluation results can be used to dynamically adjust the distribution network resource configuration parameters. These adjusted resource configuration parameters are input into the service quality model to obtain a service quality mapping relationship that adapts to the current environment and needs, providing a basis for optimal resource allocation, overcoming the problem of the existing technology lacking a multi-indicator trade-off mechanism, and achieving comprehensive optimization of multi-indicators such as accuracy and real-time through reasonable mapping of resource configuration and service quality.

[0092] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0093] Based on the same inventive concept, the embodiment of the present application also provides a distribution network management device for implementing the distribution network management method involved above. The implementation solution provided by the device to solve the problem is similar to the implementation solution recorded in the above method, so the specific limitations in one or more distribution network management device embodiments provided below can refer to the limitations of the distribution network management method above, and will not be repeated here.

[0094] In an exemplary embodiment, as shown in FIG7 , a distribution network management device is provided, including: a first acquisition module 701, a second acquisition module 702 and a first determination module 703. Wherein:

[0095] The first acquisition module 701 is used to acquire real-time operation data of the distribution network.

[0096] The second acquisition module 702 is used to obtain the service quality evaluation result of the distribution network according to the real-time operation data, the preset resource configuration index and the pre-built service quality model.

[0097] The first determination module 703 is used to determine a resource configuration strategy according to the service quality evaluation result and the real-time operation data when the service quality evaluation result does not meet the preset condition.

[0098] In an exemplary embodiment, the distribution network management device further includes: a third acquisition module, a second determination module and a first adjustment module.

[0099] The third acquisition module is used to acquire historical operation data of the distribution network within a preset time period.

[0100] The second determination module is used to determine a resource adjustment strategy based on the real-time operation data and historical operation data of the distribution network.

[0101] The first adjustment module is used to adjust the working state of at least part of the resource equipment in the distribution network according to the resource adjustment strategy.

[0102] In an exemplary embodiment, the distribution network management device further includes a fourth acquisition module, a first processing module and a first training module.

[0103] The fourth acquisition module is used to acquire historical operation data of the distribution network within a preset time period.

[0104] The first processing module is used to pre-process the historical operation data to form a sample data set.

[0105] The first training module is used to train the model to be trained according to the sample data set until a preset training stop condition is met to obtain a service quality model.

[0106] In an exemplary embodiment, the first processing module includes: a first determination submodule and a second determination submodule.

[0107] The first determination submodule is used to determine a candidate data set from the historical operation data according to a preset target data volume.

[0108] The second determination submodule is used to determine the sample data set according to the preset sparsification rule and the candidate data set.

[0109] In an exemplary embodiment, the first determination submodule includes: a first allocation unit, a first acquisition unit and a first determination unit.

[0110] The first allocation unit is used to allocate a data number to each historical operation data, and different historical operation data are allocated with different data numbers.

[0111] The first acquisition unit is used to acquire multiple random numbers, wherein the maximum value among the random numbers is not less than the maximum value among the data numbers.

[0112] The first determining unit is used to determine a candidate data set from a plurality of historical operation data according to a random number and a data serial number of each historical operation data.

[0113] In an exemplary embodiment, the sample data set includes a training set and a validation set; the first training module includes: a first training submodule, a first validation submodule and a first acquisition submodule.

[0114] The first training submodule is used to iteratively train the model to be trained using the training set.

[0115] The first verification submodule is used to verify the trained model to be trained using the verification set after each iterative training of the model to be trained using the training set, and obtain the verification loss.

[0116] The first acquisition submodule is used to stop iterative training of the model to be trained and obtain the service quality model when the verification loss obtained for the i-th time is greater than or equal to the verification loss obtained for the i-1th time.

[0117] Each module in the above-mentioned distribution network management device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0118] In an exemplary embodiment, the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the distribution network management method described in any of the above embodiments are implemented.

[0119] The computer device may be a terminal, and its internal structure diagram may be shown in FIG8. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, the memory, and the input / output interface are connected via a system bus, and the communication interface, the display unit, and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a distribution network management method is implemented. The display unit of the computer device is used to form a visually visible picture, which may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0120] Those skilled in the art will understand that the structure shown in FIG. 8 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0121] In an exemplary embodiment, the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the distribution network management method described in any of the above embodiments are implemented.

[0122] In an exemplary embodiment, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the distribution network management method described in any of the above embodiments.

[0123] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0124] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0125] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0126] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A distribution network management method, characterized in that: The method comprises: Obtain real-time operation data of the distribution network; Obtaining a service quality evaluation result of the distribution network according to the real-time operation data and a pre-built service quality model; In the case that the service quality evaluation result does not meet the preset conditions, a resource configuration strategy is determined according to the service quality evaluation result, the preset resource configuration index and the real-time operation data.

2. The method according to claim 1, characterized in that Before acquiring the real-time operation data of the distribution network, the method further includes: Obtain historical operation data of the distribution network within a preset time period; Determining a resource adjustment strategy according to the real-time operation data of the distribution network and the historical operation data; According to the resource adjustment strategy, the working status of at least part of the resource equipment in the distribution network is adjusted.

3. The method according to claim 1, characterized in that The service quality model is constructed using the following method: Obtain historical operation data of the distribution network within a preset time period; Preprocessing the historical operation data to form a sample data set; The model to be trained is trained according to the sample data set until a preset training stop condition is met to obtain a service quality model.

4. The method according to claim 3, characterized in that The preprocessing of the historical operation data to form a sample data set includes: Determining a candidate data set from the historical operation data according to a preset target data volume; A sample data set is determined according to a preset thinning rule and the candidate data set.

5. The method according to claim 4, characterized in that The step of determining the candidate data set from the historical operation data according to the preset target data volume includes: Assign a data number to each historical operation data, and different historical operation data are assigned different data numbers; Obtain multiple random numbers, wherein the maximum value among the random numbers is not less than the maximum value among the data numbers; According to the random number and the data serial number of each of the historical operation data, candidate data are determined from a plurality of historical operation data until the number of the candidate data reaches the total target data volume, thereby forming the candidate data set.

6. The method according to claim 3, characterized in that The sample data set includes a training set and a validation set; the training model is trained according to the sample data set until a preset training stop condition is met to obtain a service quality model, including: Iteratively training the model to be trained using the training set; After iteratively training the model to be trained using the training set each time, verifying the trained model to be trained using the verification set to obtain a verification loss; When the verification loss obtained for the i-th time is greater than or equal to the verification loss obtained for the (i-1)th time, the iterative training of the model to be trained is stopped to obtain a service quality model.

7. A distribution network management device, characterized in that: The device comprises: A first acquisition module is used to acquire real-time operation data of the distribution network; A second acquisition module is used to obtain a service quality evaluation result of the distribution network according to the real-time operation data, the preset resource configuration index and the pre-built service quality model; The first determination module is used to determine a resource configuration adjustment strategy according to the service quality evaluation result and the real-time operation data when the service quality evaluation result does not meet a preset condition.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the distribution network management method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the distribution network management method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the distribution network management method according to any one of claims 1 to 6 are implemented.

Images