Power metering asset management method, device, equipment and storage medium

Abstract

The present invention provides a method, device, equipment and storage medium for power metering asset management. The method includes: obtaining power data of the power metering assets to be managed, where the power data includes warehousing information, historical fault data, open-source meteorological data, calendar data and regional historical load data; and inputting the warehousing information and historical fault data into a trained hierarchical clustering model to obtain a first asset category, where the first asset category is the asset category to which the power metering assets to be managed belong; inputting the historical fault data, open-source meteorological data, calendar data and regional historical load data into a metering asset regression prediction model of the trained first asset category to obtain the predicted quantity of the power metering assets to be managed; and scheduling the power metering assets to be managed based on the inventory quantity and predicted quantity of the power metering assets to be managed. The present invention can achieve efficient management of power metering assets.

Description

Technical Field

[0001] The present invention relates to the technical field of power metering, and in particular to a power metering asset management method, device, equipment and storage medium. Background Art

[0002] With the proposal of active distribution networks and smart supply chains, and the rapid development of new-generation technologies such as the Internet of Things and artificial intelligence, high requirements are put forward for the warehousing management mode of power metering assets in the power industry.

[0003] At present, although a certain degree of automation has been achieved in the warehousing management of power metering assets, there are a wide variety of objects for power metering asset management, and there is a lack of clear overall management goals, resulting in a rough classification method and poor pertinence, and it cannot meet the current requirements of power metering assets in terms of procurement, dispatching management, demand response, etc., thus increasing the difficulty and workload of metering asset management. Therefore, there is an urgent need for an efficient management method for power metering assets. Summary of the Invention

[0004] Embodiments of the present invention provide a power metering asset management method, device, equipment and storage medium to solve the problem of low efficiency of current power metering asset management.

[0005] In a first aspect, embodiments of the present invention provide a power metering asset management method, including:

[0006] Obtain power data of power metering assets to be managed, where the power data includes warehousing information, historical fault data, open-source meteorological data, calendar data and regional historical load data; and input the warehousing information and historical fault data into a trained hierarchical clustering model to obtain a first asset category, where the first asset category is the asset category to which the power metering assets to be managed belong;

[0007] Input the historical fault data, open-source meteorological data, calendar data and regional historical load data into a metering asset regression prediction model of the trained first asset category to obtain the predicted quantity of the power metering assets to be managed;

[0008] Schedule the power metering assets to be managed based on the inventory quantity and predicted quantity of the power metering assets to be managed.

[0009] In a possible implementation manner, scheduling the power metering assets to be managed based on the inventory quantity and predicted quantity of the power metering assets to be managed includes:

[0010] Determine the inventory adequacy rate of the power metering assets to be managed based on the inventory quantity and predicted quantity of the power metering assets to be managed;

[0011] Schedule the power metering assets to be managed based on the inventory abundance rate and the preset inventory rate threshold.

[0012] In a possible implementation, scheduling the power metering assets to be managed based on the inventory abundance rate and the preset inventory rate threshold includes:

[0013] Based on the preset inventory rate threshold, classify the inventory metrics into four categories, namely excess, abundance, normal, and abnormal;

[0014] Schedule the metering assets to be managed according to the inventory abundance rate and the inventory metrics.

[0015] In a possible implementation, the hierarchical clustering model uses warehousing information and historical failure data as feature vectors and the metering assets of four asset categories as output results; among them, the metering assets of the four asset categories are conventional low-failure-rate metering assets, conventional high-failure-rate metering assets, special low-failure-rate metering assets, and special high-failure-rate metering assets.

[0016] In a possible implementation, different preset inventory rate thresholds are set for the metering assets of the four asset categories, and the preset inventory rate threshold of the conventional high-failure-rate metering assets is greater than that of the conventional low-failure-rate metering assets, and the preset inventory rate threshold of the special high-failure-rate metering assets is greater than that of the special low-failure-rate metering assets.

[0017] In a possible implementation, the metering assets of the four asset categories respectively correspond to four categories of metering asset regression prediction models. The metering asset regression prediction model is a multiple linear fractional regression model of the predicted quantity of the metering assets and the metering asset data, and the metering asset data is the historical failure data, open-source meteorological data, calendar data, and regional historical load data of the metering assets.

[0018] In a possible implementation, the warehousing information includes the user type of the metering assets, the price of a single metering asset, and the quantity of the metering assets; the historical failure data includes the number of failures occurring within a unit time, the failure occurrence frequency, and the high-failure time period; the open-source meteorological data includes the weather temperature based on time series and special weather; the calendar data is the holiday data; the regional historical load data is the load data within each time period and time segment in the region.

[0019] In a second aspect, an embodiment of the present invention provides a power metering asset management device, including:

[0020] A power data acquisition module, configured to acquire the power data of the power metering assets to be managed, where the power data includes warehousing information, historical failure data, open-source meteorological data, calendar data, and regional historical load data;

[0021] A hierarchical clustering module for inputting warehousing information and historical fault data into a trained hierarchical clustering model to obtain a first asset category, where the first asset category is the asset category to which the power metering assets to be managed belong;

[0022] A determination of predicted quantity module for inputting historical fault data, open-source meteorological data, calendar data, and regional historical load data into a trained regression prediction model for metering assets of the first asset category to obtain the predicted quantity of the power metering assets to be managed;

[0023] An asset scheduling module for scheduling the power metering assets to be managed based on the inventory quantity and predicted quantity of the power metering assets to be managed.

[0024] In a possible implementation, the asset scheduling module is specifically used for:

[0025] Determining the inventory adequacy rate of the power metering assets to be managed based on the inventory quantity and predicted quantity of the power metering assets to be managed;

[0026] Scheduling the power metering assets to be managed based on the inventory adequacy rate and a preset inventory rate threshold.

[0027] In a possible implementation, the asset scheduling module is also specifically used for:

[0028] Based on the preset inventory rate threshold, classifying the inventory metrics into four categories, namely overstocked, adequate, normal, and abnormal;

[0029] Scheduling the metering assets to be managed according to the inventory adequacy rate and the inventory metrics.

[0030] In a possible implementation, the hierarchical clustering model uses warehousing information and historical fault data as feature vectors and the metering assets of four asset categories as output results; among them, the metering assets of the four asset categories are respectively conventional metering assets with low failure rates, conventional metering assets with high failure rates, special metering assets with low failure rates, and special metering assets with high failure rates.

[0031] In a possible implementation, different preset inventory rate thresholds are set for the metering assets of the four asset categories, and the preset inventory rate threshold of the conventional metering assets with high failure rates is greater than that of the conventional metering assets with low failure rates, and the preset inventory rate threshold of the special metering assets with high failure rates is greater than that of the special metering assets with low failure rates.

[0032] In a possible implementation, the measurement assets of the four asset categories respectively correspond to four types of measurement asset regression prediction models. The measurement asset regression prediction model is a multiple linear fractional regression model of the predicted quantity of the measurement asset and the measurement asset data, and the measurement asset data is the historical failure data, open-source meteorological data, calendar data, and regional historical load data of the measurement asset.

[0033] In a possible implementation, the warehousing information includes the user type of the measurement asset, the price of a single measurement asset, and the quantity of the measurement asset; the historical failure data includes the number of failures occurring within a unit time, the failure occurrence frequency, and the high-failure time period; the open-source meteorological data includes the weather temperature and special weather based on time series; the calendar data is the festival and holiday data; and the regional historical load data is the load data within each time period and time segment in the region.

[0034] In a third aspect, an embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method described in the first aspect or any possible implementation manner of the first aspect above are implemented.

[0035] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect or any possible implementation manner of the first aspect above are implemented.

[0036] An embodiment of the present invention provides a method, device, equipment, and storage medium for power measurement asset management. First, power data of the power measurement assets to be managed is obtained. Then, the warehousing information and historical failure data are input into a trained hierarchical clustering model to obtain the first asset category. Next, the historical failure data, open-source meteorological data, calendar data, and regional historical load data are input into the measurement asset regression prediction model of the trained first asset category to obtain the predicted quantity of the power measurement assets to be managed. Finally, based on the inventory quantity and predicted quantity of the power measurement assets to be managed, the power measurement assets to be managed are scheduled. Thus, after the obtained power data is input into the trained hierarchical clustering model and measurement asset regression prediction model, the power measurement assets to be managed can be scheduled to achieve reasonable replenishment of power measurement assets, efficient utilization of warehousing capacity, and optimal warehousing efficiency. Description of the Drawings

[0037] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for use in the embodiments or the description of the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0038] Figure 1 is the implementation flowchart of the power metering asset management method provided by the embodiment of the present invention;

[0039] Figure 2 is the process block diagram of the power metering asset management method provided by the embodiment of the present invention;

[0040] Figure 3 is the process block diagram of establishing a hierarchical clustering model provided by the embodiment of the present invention;

[0041] Figure 4 is the process block diagram of calculating the regression parameters of four metering asset regression prediction models provided by the embodiment of the present invention;

[0042] Figure 5 is the block diagram of the power metering asset management device provided by the embodiment of the present invention;

[0043] Figure 6 is the schematic diagram of the electronic device provided by the embodiment of the present invention. Specific Embodiments

[0044] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present invention. However, those skilled in the art should clearly understand that the present invention can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present invention.

[0045] To make the purpose, technical solutions, and advantages of the present invention clearer, the following will be described through specific embodiments in conjunction with the accompanying drawings.

[0046] As described in the background art, at present, there are various types of power metering asset management objects, and there is a lack of clear overall management goals, resulting in low management efficiency of power metering assets. Therefore, there is an urgent need for an efficient power metering asset management method.

[0047] To solve the problems of the prior art, the embodiments of the present invention provide a power metering asset management method, device, equipment, and storage medium. First, the power metering asset management method provided by the embodiments of the present invention will be introduced below.

[0048] The entity that executes the power metering asset management method can be a power metering asset management device, which can be an electronic device with a processor and a memory, such as a mobile electronic device or a non-mobile electronic device. The embodiments of the present invention do not make specific limitations.

[0049] Please refer to Figure 1 and Figure 2 simultaneously, which shows the implementation flowchart of the power metering asset management method provided by the embodiments of the present invention, and is described in detail as follows:

[0050] Step S110: Obtain the power data of the power metering assets to be managed.

[0051] Among them, the power data includes warehousing information, historical fault data, open-source meteorological data, calendar data, and regional historical load data.

[0052] Specifically, the warehousing information includes the user type of the metering assets, the price of a single metering asset, and the quantity of the metering assets. The historical fault data includes the number of faults occurring within a unit time, the fault occurrence frequency, and the high-fault period. The open-source meteorological data includes the weather temperature based on time series and special weather. The calendar data is holiday data. The regional historical load data is the load data within each time period and time segment in the region.

[0053] Step S120: Input the warehousing information and historical fault data into the trained hierarchical clustering model to obtain the first asset category.

[0054] Among them, the first asset category is the asset category to which the power metering assets to be managed belong.

[0055] In some embodiments, before inputting the data, it is necessary to first construct and train the hierarchical clustering model. The hierarchical clustering model in this embodiment performs hierarchical clustering based on the regularity and failure rate characteristics of power metering assets. Hierarchical clustering is performed on the power metering asset management objects based on two factors: regularity and failure rate. The regularity is reflected in the user type corresponding to the power metering assets, the price of a single metering asset, and the quantity of the metering assets. The failure rate refers to the historical fault data based on time series, including the number of fault events occurring within a unit time, the fault occurrence frequency, the high-fault period, etc.

[0056] The characteristic of hierarchical clustering is that the data set needs to go through two rounds of clustering: global and local hierarchical clustering. The local clustering labels are updated according to the global clustering results to achieve the purpose of stratification. Further subdivision and data dynamic monitoring can be realized based on the results of local clustering and the actual types of power metering assets.

[0057] Such as Figure 3As shown in the figure, to ensure that the features of clustering are both typical and meet the actual needs of the power industry, the K-means clustering algorithm is used for hierarchical clustering. The warehousing information and historical fault data are used as feature vectors, and the output result is the metering assets of four asset categories.

[0058] First, select the user type of metering assets, the price of a single metering asset, and the quantity of metering assets as feature vectors for overall data clustering. The number of clustering centers is set to 2, and the power metering assets are divided into conventional and special metering devices through global clustering. On the basis of overall data clustering, local clustering is performed on the local clustering sub-datasets. Considering historical fault data as feature vectors, global secondary clustering is carried out. When the clustering centers no longer change, local clustering labels are output, and the local clustering labels are updated according to the membership relationship of the clustering labels obtained from global clustering, so as to obtain the metering assets of four asset categories: conventional metering assets with low failure rates, conventional metering assets with high failure rates, special metering assets with low failure rates, and special metering assets with high failure rates. The category subordination relationship of the power metering assets to be managed can be divided through the results of the hierarchical clustering model.

[0059] After training the constructed hierarchical clustering model with training data, the trained hierarchical clustering model can be used to classify the power metering assets to be managed. Input the warehousing information and historical fault data of the power metering assets to be managed into the trained hierarchical clustering model, and the asset category of the power metering asset can be obtained, which is one of the conventional metering assets with low failure rates, conventional metering assets with high failure rates, special metering assets with low failure rates, and special metering assets with high failure rates.

[0060] Step S130: Input the historical fault data, open-source meteorological data, calendar data, and regional historical load data into the regression prediction model of the metering assets of the first asset category that has been trained, and obtain the predicted quantity of the power metering assets to be managed.

[0061] Comprehensively considering the influence of factors such as weather and grid load on power metering assets, quantile regression prediction model training is carried out on the metering assets of four asset categories respectively by combining open-source meteorological data, calendar data, regional load data, and historical failure rate data, and the regression prediction models of metering assets corresponding to different categories of metering assets are obtained.

[0062] Specifically, the regression prediction model of metering assets is a multiple linear fractional regression model of the predicted quantity of metering assets and metering asset data, and the metering asset data is the historical fault data, open-source meteorological data, calendar data, and regional historical load data of metering assets.

[0063] The quantile regression prediction model is a prediction model that applies the quantile regression method. Quantile regression is different from traditional linear regression solved based on the least squares method. By solving the quantile loss function at different quantiles, the values of the target variable at different quantiles are fitted, so as to achieve the goal of characterizing the data distribution of the target variable. Traditional least squares estimation needs to be based on the assumption that the errors are independently and identically distributed in a normal distribution. However, it is difficult to ensure that the error distribution meets the assumptions of the least squares method in actual application scenarios. Different from traditional linear regression, quantile regression makes no assumptions about the error distribution. Even if the errors do not follow a normal distribution, quantile regression is still applicable and has strong robustness.

[0064] The specific implementation steps of quantile regression are as follows:

[0065] First, assume that the random variable X follows the distribution function:

[0066] F(x) = P(X ≤ x);

[0067] where X is the measurement asset data, namely the historical failure data, open-source meteorological data, calendar data, and regional historical load data of the measurement asset respectively.

[0068] Secondly, the τ - quantile of the random variable X is:

[0069] F -1 (τ) = inf{x : F(x) ≥ τ};

[0070] where τ ∈ (0, 1).

[0071] Then, define the quantile loss function as:

[0072] ρ τ (u) = u(τ - I(u < 0)), τ ∈ (0, 1);

[0073] The expected value of the corresponding quantile loss function can be expressed as:

[0074]

[0075] The process of training the measurement asset regression prediction model is to substitute the random variable X in the training set and solve the regression parameters when the loss function is minimized. To minimize the loss function, there is:

[0076]

[0077] The regression coefficient can be obtained by the following formula:

[0078]

[0079] Let Therefore, the predicted value estimated by the τ - quantile loss function That is the τ - quantile estimate of the target variable y.

[0080] In the generalized linear model of the quantile loss function, y is the predicted quantity of the metering assets, and x is a p - dimensional independent variable, in the form of X i =(X i1 , X i2 ,..., X ip ), where X ip represents the historical failure data, open - source meteorological data, calendar data, and regional historical load data of the metering assets after normalization.

[0081] As Figure 4 shown, according to the above process, the regression coefficients of the regression prediction models of four categories of metering assets can be obtained. Based on the regression coefficients of the regression prediction models of four categories of metering assets obtained, the regression prediction models of four categories of metering assets can be obtained.

[0082] After obtaining the regression prediction models of four categories of metering assets, input the historical failure data, open - source meteorological data, calendar data, and regional historical load data of the power metering assets to be managed into the trained metering asset regression prediction model corresponding to this asset category, and the predicted quantity of the power metering assets to be managed can be obtained.

[0083] Step S140: Schedule the power metering assets to be managed based on the inventory quantity and predicted quantity of the power metering assets to be managed.

[0084] In some embodiments, based on the inventory quantity and predicted quantity of the power metering assets to be managed, determine the inventory abundance rate of the power metering assets to be managed. That is, based on the predicted quantity of the metering asset regression prediction model, compare the inventory quantities of various types of power metering assets, and the inventory abundance rate of the power metering assets to be managed can be calculated. Thus, the power metering assets to be managed can be scheduled based on the inventory abundance rate and the preset inventory rate threshold.

[0085] Specifically, based on the preset inventory rate threshold, the inventory indicators are divided into four categories: over - quantity, abundance, normal, and abnormal. Schedule the metering assets to be managed according to the inventory abundance rate and inventory indicators. It can provide a reference for power enterprises to replace, purchase, and schedule power metering assets, achieve active response to the demand side, and promote the improvement of the operation efficiency of power enterprises.

[0086] In some embodiments, when classifying inventory metrics into four categories based on a preset inventory rate threshold, different preset inventory rate thresholds need to be set for the measured assets of the four asset categories respectively. Moreover, the preset inventory rate threshold for the measured assets with regular high failure rates is greater than that for the measured assets with regular low failure rates, and the preset inventory rate threshold for the special high failure rate measured assets is greater than that for the special low failure rate measured assets. By reasonably replenishing the measured assets, the costs in the procurement and scheduling links of the measuring equipment can be saved, so as to improve the lean management level.

[0087] In the embodiments of the present invention, first, the power data of the power measurement assets to be managed is obtained. Then, the warehousing information and historical failure data are input into the trained hierarchical clustering model to obtain the first asset category. Next, the historical failure data, open-source meteorological data, calendar data, and regional historical load data are input into the regression prediction model of the measured assets of the trained first asset category to obtain the predicted quantity of the power measurement assets to be managed. Finally, based on the inventory quantity and the predicted quantity of the power measurement assets to be managed, the power measurement assets to be managed are scheduled. Thus, after the obtained power data is input into the trained hierarchical clustering model and the regression prediction model of the measured assets, the power measurement assets to be managed can be scheduled, so as to reasonably replenish the power measurement assets, efficiently utilize the warehousing capacity, and achieve the optimal warehousing efficiency. And by evaluating the abundance of the power measurement assets in the warehouse, a health evaluation system for the power measurement assets is established to guide the scheduling of the power measurement assets.

[0088] The method provided by the present invention can realize the intelligent classification of power measurement assets and improve the management efficiency of power measurement assets. Taking the regularity and failure rate of power measurement assets as the main classification indicators, it aims to reduce the supply risk of emergency supplies in case of emergencies and reduce the risk losses caused by emergencies. In view of the characteristics of a large number of management objects of power measurement assets, the overall management goal is clarified, and the two core elements of regularity and failure rate in power measurement asset management are highlighted in a hierarchical classification manner, so as to improve the warehousing management efficiency in a targeted manner. On the basis of hierarchical clustering, classification prediction of various types of measured assets is realized based on the regression prediction model of the measured assets, which can not only improve the demand response, efficiently utilize the warehousing capacity, but also improve the warehousing efficiency, reduce costs and increase efficiency.

[0089] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0090] Based on the power measurement asset management method provided in the above embodiments, correspondingly, the present invention also provides a specific implementation manner of a power measurement asset management device applied to the power measurement asset management method. Please refer to the following embodiments.

[0091] As shown Figure 5 in the figure, a power metering asset management device 500 is provided, which includes:

[0092] A power data acquisition module 510, configured to acquire power data of the power metering assets to be managed, where the power data includes warehousing information, historical fault data, open-source meteorological data, calendar data, and regional historical load data;

[0093] A hierarchical clustering module 520, configured to input the warehousing information and historical fault data into a trained hierarchical clustering model to obtain a first asset category, where the first asset category is the asset category to which the power metering assets to be managed belong;

[0094] A predicted quantity determination module 530, configured to input the historical fault data, open-source meteorological data, calendar data, and regional historical load data into a trained regression prediction model of the metering assets of the first asset category to obtain the predicted quantity of the power metering assets to be managed;

[0095] An asset scheduling module 540, configured to schedule the power metering assets to be managed based on the inventory quantity and predicted quantity of the power metering assets to be managed.

[0096] In a possible implementation manner, the asset scheduling module 540 is specifically configured to:

[0097] Determine the inventory adequacy rate of the power metering assets to be managed based on the inventory quantity and predicted quantity of the power metering assets to be managed;

[0098] Schedule the power metering assets to be managed based on the inventory adequacy rate and a preset inventory rate threshold.

[0099] In a possible implementation manner, the asset scheduling module 540 is further specifically configured to:

[0100] Based on the preset inventory rate threshold, divide the inventory metrics into four categories, namely excess, adequacy, normal, and abnormal;

[0101] Schedule the metering assets to be managed according to the inventory adequacy rate and inventory metrics.

[0102] In a possible implementation manner, the hierarchical clustering model uses the warehousing information and historical fault data as feature vectors and the metering assets of four asset categories as output results; among them, the metering assets of the four asset categories are respectively conventional low-failure-rate metering assets, conventional high-failure-rate metering assets, special low-failure-rate metering assets, and special high-failure-rate metering assets.

[0103] In a possible implementation, different preset inventory rate thresholds are set for the measurement assets of the four asset categories, and the preset inventory rate threshold of the measurement assets with regular high failure rates is greater than that of the measurement assets with regular low failure rates, and the preset inventory rate threshold of the measurement assets with special high failure rates is greater than that of the measurement assets with special low failure rates.

[0104] In a possible implementation, the measurement assets of the four asset categories respectively correspond to four categories of measurement asset regression prediction models. The measurement asset regression prediction model is a multiple linear fractional regression model of the predicted quantity of the measurement asset and the measurement asset data, and the measurement asset data is the historical failure data, open-source meteorological data, calendar data, and regional historical load data of the measurement asset.

[0105] In a possible implementation, the warehousing information includes the user type of the measurement asset, the price of a single measurement asset, and the quantity of the measurement asset; the historical failure data includes the number of failures occurring within a unit time, the failure occurrence frequency, and the high-failure time period; the open-source meteorological data includes the weather temperature and special weather based on time series; the calendar data is the holiday data; the regional historical load data is the load data within each time period and time segment in the region.

[0106] Figure 6 is a schematic diagram of the electronic device provided by the embodiments of the present invention. As Figure 6 shown, the electronic device 6 of this embodiment includes: a processor 60, a memory 61, and a computer program 62 stored in the memory 61 and executable on the processor 60. When the processor 60 executes the computer program 62, the steps in the above-mentioned embodiments of the monitoring method for each transformer riser and bushing are implemented, such as Figure 1 the steps 110 to 140 shown. Alternatively, when the processor 60 executes the computer program 62, the functions of each module in the above-mentioned device embodiments are implemented, such as Figure 5 the functions of the modules 510 to 540 shown.

[0107] Exemplarily, the computer program 62 can be divided into one or more modules. The one or more modules are stored in the memory 61 and executed by the processor 60 to complete the present invention. The one or more modules can be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program 62 in the electronic device 6. For example, the computer program 62 can be divided into Figure 5 the modules 510 to 540 shown.

[0108] The electronic device 6 may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art can understand,Figure 6 These are merely examples of the electronic device 6 and do not constitute a limitation thereto. It may include more or fewer components than those shown, or combine certain components, or have different components. For example, the electronic device may further include input / output devices, network access devices, buses, etc.

[0109] The so-called processor 60 may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0110] The memory 61 may be an internal storage unit of the electronic device 6, such as the hard disk or memory of the electronic device 6. The memory 61 may also be an external storage device of the electronic device 6, such as a plug-in hard disk equipped on the electronic device 6, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory 61 may also include both the internal storage unit and the external storage device of the electronic device 6. The memory 61 is used to store the computer program and other programs and data required by the electronic device. The memory 61 may also be used to temporarily store data that has been output or is to be output.

[0111] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above functions can be assigned to different functional units and modules according to needs, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiments can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0112] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0113] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in the form of hardware or software depends on the specific application and design constraints of the technical solution. A professional technician can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0114] In the embodiments provided by the present invention, it should be understood that the disclosed device / electronic device and method can be implemented in other ways. For example, the device / electronic device embodiments described above are only illustrative. For example, the division of the module or unit is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical, mechanical or other form.

[0115] The unit described as a separated component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit, that is, it can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0116] In addition, in each embodiment of the present invention, each functional unit can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0117] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-mentioned embodiment methods of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various embodiments of the power metering asset management method can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0118] The above-mentioned embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for managing electric power measurement assets, characterized in that, it includes: Obtain the electric power data of the electric power measurement assets to be managed, where the electric power data includes warehousing information, historical fault data, open-source meteorological data, calendar data, and regional historical load data; and input the warehousing information and the historical fault data into the trained hierarchical clustering model to obtain the first asset category, where the first asset category is the asset category to which the electric power measurement assets to be managed belong; Input the historical fault data, the open-source meteorological data, the calendar data, and the regional historical load data into the regression prediction model of the measurement assets of the trained first asset category to obtain the predicted quantity of the electric power measurement assets to be managed; Schedule the electric power measurement assets to be managed based on the inventory quantity and the predicted quantity of the electric power measurement assets to be managed; Among them, the hierarchical clustering model uses the warehousing information and the historical fault data as feature vectors, and the measurement assets of four asset categories are the output results; the measurement assets of the four asset categories are respectively conventional measurement assets with low failure rates, conventional measurement assets with high failure rates, special measurement assets with low failure rates, and special measurement assets with high failure rates; the measurement assets of the four asset categories respectively correspond to four types of regression prediction models for measurement assets, and the regression prediction model for measurement assets is a multiple linear fractional regression model of the predicted quantity of measurement assets and measurement asset data, and the measurement asset data is the historical fault data, open-source meteorological data, calendar data, and regional historical load data of the measurement assets.

2. The method according to claim 1, characterized in that, The scheduling of the electric power measurement assets to be managed based on the inventory quantity and the predicted quantity of the electric power measurement assets to be managed includes: Determine the inventory adequacy rate of the electric power measurement assets to be managed based on the inventory quantity and the predicted quantity of the electric power measurement assets to be managed; Schedule the electric power measurement assets to be managed based on the inventory adequacy rate and the preset inventory rate threshold.

3. The method according to claim 2, characterized in that, The scheduling of the electric power measurement assets to be managed based on the inventory adequacy rate and the preset inventory rate threshold includes: Based on the preset inventory rate threshold, divide the inventory indicators into four categories, namely excess, adequacy, normal, and abnormal; Schedule the measurement assets to be managed according to the inventory adequacy rate and the inventory indicators.

4. The method according to claim 1, characterized in that, The preset inventory rate thresholds of the measurement assets of the four asset categories are set differently, and the preset inventory rate threshold of the conventional measurement assets with high failure rates is greater than the preset inventory rate threshold of the conventional measurement assets with low failure rates, and the preset inventory rate threshold of the special measurement assets with high failure rates is greater than the preset inventory rate threshold of the special measurement assets with low failure rates.

5. The method according to any one of claims 1 to 4, characterized in that, The storage information includes the user type of the metering assets, the price of a single metering asset, and the quantity of the metering assets; the historical fault data includes the number of faults occurring within a unit time, the fault occurrence frequency, and the high-fault period; the open-source meteorological data includes the weather temperature based on a time series and special weather; the calendar data is festival and holiday data; the regional historical load data is the load data within each time period and time segment in the region.

6. An electric metering asset management device, characterized in that, it includes: a power data acquisition module, configured to acquire the power data of the electric metering assets to be managed, wherein the power data includes storage information, historical fault data, open-source meteorological data, calendar data, and regional historical load data; a hierarchical clustering module, configured to input the storage information and the historical fault data into a trained hierarchical clustering model to obtain a first asset category, wherein the first asset category is the asset category to which the electric metering assets to be managed belong; a predicted quantity determination module, configured to input the historical fault data, the open-source meteorological data, the calendar data, and the regional historical load data into the metering asset regression prediction model of the trained first asset category to obtain the predicted quantity of the electric metering assets to be managed; an asset scheduling module, configured to schedule the electric metering assets to be managed based on the inventory quantity and the predicted quantity of the electric metering assets to be managed; wherein, the hierarchical clustering model uses the storage information and the historical fault data as feature vectors, and the metering assets of four asset categories are the output results; the metering assets of the four asset categories are respectively conventional metering assets with low failure rates, conventional metering assets with high failure rates, special metering assets with low failure rates, and special metering assets with high failure rates; the metering assets of the four asset categories respectively correspond to four types of metering asset regression prediction models, and the metering asset regression prediction model is a multiple linear fractional regression model of the predicted quantity of the metering assets and the metering asset data, and the metering asset data is the historical fault data, open-source meteorological data, calendar data, and regional historical load data of the metering assets.

7. An electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, when the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium, storing a computer program, characterized in that, when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images