Intelligent distribution network optimization dispatching method and system

Abstract

The present invention discloses an intelligent distribution network optimization scheduling method and system, which relates to the field of power distribution. The method includes: traversing the user side list to predict the load in a preset time zone; grouping the user predicted load list according to the access voltage level label list; traversing the access substation label list to predict the split power generation in a preset time zone; conducting transmission loss assessment; traversing the access substation label list to predict the split power generation carbon emissions; optimizing the split power generation list and the split power predicted load based on the split power transmission loss ratio list and the split power predicted carbon emissions list; and performing intelligent power distribution according to the user side power distribution plan. The method solves the technical problem that the existing power distribution scheduling lacks power distribution optimization according to the actual situation of the voltage level and the substation, resulting in insufficient refinement of the power distribution control, and achieves the technical effect of improving the refined management level of the distribution network through split power consideration and power distribution optimization.

Description

Technical Field

[0001] The present application relates to power distribution related fields, and in particular to a method and system for optimizing and dispatching a smart distribution network. Background Art

[0002] With the continuous development of smart grid technology, the intelligence and automation level of distribution networks are increasing, which puts forward higher requirements for the safe, reliable and economical operation of power systems. The traditional distribution network dispatching method is mainly based on the unified dispatching of the overall load forecast and power generation plan of the power grid, and fails to carry out refined distribution optimization according to the actual situation of voltage level and substation. Due to the lack of refined dispatching, some areas have excess or insufficient electricity, which increases the operation cost and carbon emissions of the power grid. Due to the unbalanced distribution, some users will also face problems such as voltage fluctuations and reduced power supply reliability, which will affect user satisfaction.

[0003] In the current relevant technologies, power distribution dispatching lacks the technical problem of optimizing power distribution according to the voltage level and the actual situation of the substation, resulting in insufficient refinement of power distribution control. Summary of the invention

[0004] The present application provides a smart distribution network optimization and scheduling method and system, which adopts load forecasting and power generation forecasting for preset time zones respectively, groups user predicted loads according to voltage levels to form voltage-divided predicted loads, predicts carbon emissions of voltage-divided power generation, evaluates voltage-divided transmission losses, comprehensively considers voltage-divided transmission loss ratios and voltage-divided carbon emissions, optimizes distribution of voltage-divided predicted power generation and voltage-divided predicted loads, and other technical means, thereby achieving the technical effect of improving the level of refined management of distribution networks through voltage-divided considerations and distribution optimization.

[0005] This application provides a smart distribution network optimization scheduling method, including:

[0006] Traverse the user side list to perform load forecasting for a preset time zone and generate a user forecast load list, wherein the user forecast load list has an access voltage level label list and an access substation label list; group the user forecast load list according to the access voltage level label list to generate a voltage-divided forecast load; traverse the access substation label list to perform voltage-divided power generation forecasting for a preset time zone and generate a voltage-divided forecast power generation list; perform transmission loss assessment based on the access substation label list and the user side list to generate a voltage-divided transmission loss ratio list; traverse the access substation label list to perform voltage-divided power generation carbon emissions forecasting and generate a voltage-divided forecast carbon emissions list; based on the voltage-divided transmission loss ratio list and the voltage-divided forecast carbon emissions list, perform power distribution optimization on the voltage-divided forecast power generation list and the voltage-divided forecast load to generate a user side power distribution plan; perform intelligent power distribution according to the user side power distribution plan.

[0007] In a possible implementation, the user side list is traversed to perform load forecasting in a preset time zone, and a user forecast load list is generated, wherein the user forecast load list has an access voltage level label list and an access substation label list, and the following processing is performed:

[0008] According to the user-side list, extract the first user basic information, wherein the first user basic information includes a first electricity consumption industry, a first access capacity, a first commissioning time, a first user scale, a first access voltage level, and a first access substation; perform load forecasting according to the first electricity consumption industry, the first access capacity, the first commissioning time, and the first user scale to generate a first user predicted load; add the first user predicted load to the user predicted load list, add the first access voltage level to the access voltage level label list, and add the first access substation to the access substation label list.

[0009] In a possible implementation, load forecasting is performed according to the first electricity consumption industry, the first access capacity, the first commissioning time, and the first user scale to generate a first user forecast load, and the following processing is performed:

[0010] The first electricity consumption industry is set as the first fixed constraint condition; based on the access capacity deviation threshold, the production time deviation threshold and the user scale deviation threshold, the first fuzzy constraint condition is configured for the first access capacity, the first production time and the first user scale; historical backtracking is performed according to the first fixed constraint condition and the first fuzzy constraint condition to obtain a data set of electricity consumption records of users in the same cluster, wherein the data set of electricity consumption records of users in the same cluster represents user load record data that meets the first fixed constraint condition and the first fuzzy constraint condition; mode fitting is performed on the data set of electricity consumption records of users in the same cluster to generate the predicted load of the first user.

[0011] In a possible implementation, the access substation tag list is traversed to perform a prediction of the voltage-divided power generation in a preset time zone, a voltage-divided predicted power generation list is generated, and the following processing is performed:

[0012] According to the access substation label list, extract the basic information of the first access substation, wherein the basic information of the first access substation includes a first installed capacity, a first power type, a first access voltage level, a first commissioning year, a first unit capacity, a first number of units and a preset time zone step; take the first power type and the first access voltage level as the second fixed constraint; based on the installed capacity deviation threshold, the commissioning year deviation threshold, the unit capacity deviation threshold, the unit number deviation threshold and the time zone step deviation threshold, configure the second fuzzy constraint in combination with the first installed capacity, the first commissioning year, the first unit capacity, the first number of units and the preset time zone step; perform historical backtracking according to the second fixed constraint and the second fuzzy constraint to obtain a data set of power generation records of substations in the same cluster; perform mode fitting on the data set of power generation records of substations in the same cluster to generate a predicted power generation of the first access substation; group the predicted power generation of the first access substation according to the first access voltage level and add it to the voltage-dividing predicted power generation list.

[0013] In a possible implementation, a transmission loss assessment is performed based on the access substation tag list and the user side list, a voltage-dividing transmission loss ratio list is generated, and the following processing is performed:

[0014] According to the access substation label list, extract the first access substation; according to the user side list, extract the first user side, wherein the first access substation belongs to the first user side access substation label; obtain the transmission line model list and the transmission line length list from the first access substation to the first user side; according to the access voltage label, traverse the transmission line model list and the transmission line length list to perform transmission loss prediction, obtain the first voltage-dividing transmission loss ratio, and add it to the voltage-dividing transmission loss ratio list.

[0015] In a possible implementation, according to the access voltage tag, the transmission line model list and the transmission line length list are traversed to perform transmission loss prediction, a first voltage division transmission loss ratio is obtained, and the following processing is performed:

[0016] A transmission line model data set, a transmission line length data set, a transmission voltage data set and a transmission loss ratio identification data set are collected to configure a transmission loss ratio prediction network; according to the transmission loss ratio prediction network and the access voltage label, the transmission line model list and the transmission line length list are traversed to perform transmission loss prediction to obtain a first voltage-dividing initial transmission loss ratio sequence; the first voltage-dividing initial transmission loss ratio sequence is fitted to generate the first voltage-dividing transmission loss ratio.

[0017] In a possible implementation, based on the partial pressure transmission loss ratio list and the partial pressure predicted carbon emission list, the partial pressure predicted power generation list and the partial pressure predicted load are optimized for distribution, a user-side distribution plan is generated, and the following processing is performed:

[0018] With the voltage-divided predicted power generation list, the voltage-divided predicted load and the voltage-divided transmission loss ratio list as constraints, random distribution of power distribution is performed to obtain a number of power distribution allocation schemes; power transmission loss statistics are performed according to the several power distribution allocation schemes to obtain a number of power transmission loss amounts; based on the several power transmission loss amounts, the several power distribution allocation schemes are sorted from small to large to obtain a first sorting result, wherein the first sorting result has a first weight; based on the voltage-divided predicted carbon emission list, a number of total carbon emissions of the several power distribution allocation schemes are counted; based on the several total carbon emissions, the several power distribution allocation schemes are sorted from small to large to obtain a second sorting result, wherein the second sorting result has a second weight; based on the first weight and the second weight, in combination with the first sorting result and the second sorting result, the several power distribution allocation schemes are weightedly summed by sequence number to obtain a number of sequence number summation results; the power distribution allocation scheme with the minimum value of the several sequence number summation results is obtained, and is set as the user-side power distribution scheme.

[0019] This application also provides a smart distribution network optimization dispatching system, including:

[0020] A load prediction module, which is used to traverse the user side list to perform load prediction in a preset time zone and generate a user predicted load list, wherein the user predicted load list has an access voltage level label list and an access substation label list; a user predicted load list grouping module, which is used to group the user predicted load list according to the access voltage level label list to generate a voltage-dividing predicted load; a voltage-dividing power generation prediction module, which is used to traverse the access substation label list to perform voltage-dividing power generation prediction in a preset time zone and generate a voltage-dividing predicted power generation list; a transmission loss assessment module, which is used to The module is used to evaluate the transmission loss based on the access substation label list and the user-side list, and generate a voltage-divided transmission loss ratio list; the voltage-divided power generation carbon emissions prediction module, the voltage-divided power generation carbon emissions prediction module is used to traverse the access substation label list to predict the voltage-divided power generation carbon emissions, and generate a voltage-divided predicted carbon emissions list; the distribution optimization module, the distribution optimization module is used to optimize the voltage-divided predicted power generation list and the voltage-divided predicted load based on the voltage-divided transmission loss ratio list and the voltage-divided predicted carbon emissions list, and generate a user-side distribution plan; the intelligent distribution module, the intelligent distribution module is used to perform intelligent distribution according to the user-side distribution plan.

[0021] The intelligent distribution network optimization and scheduling method and system proposed in the present application first traverse the user side list to perform load forecasting in a preset time zone and generate a user forecast load list, wherein the user forecast load list has an access voltage level label list and an access substation label list, and then group the user forecast load list according to the access voltage level label list to generate a voltage-sharing forecast load, and then traverse the access substation label list to perform voltage-sharing power generation forecasting in a preset time zone to generate a voltage-sharing forecast power generation list, and then perform transmission loss assessment based on the access substation label list and the user side list to generate a voltage-sharing transmission loss ratio list, and then traverse the access substation label list to perform voltage-sharing power generation carbon emissions forecasting to generate a voltage-sharing forecast carbon emissions list, and then based on the voltage-sharing transmission loss ratio list and the voltage-sharing forecast carbon emissions list, perform power distribution optimization on the voltage-sharing forecast power generation list and the voltage-sharing forecast load, generate a user side power distribution plan, and finally perform intelligent power distribution according to the user side power distribution plan, thereby achieving the technical effect of improving the level of refined management of the distribution network through voltage-sharing consideration and distribution optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0023] Figure 1 A flow chart of a smart distribution network optimization scheduling method provided in an embodiment of the present application.

[0024] Figure 2 A schematic diagram of the structure of the intelligent distribution network optimization and dispatching system provided in an embodiment of the present application.

[0025] Explanation of the reference numerals: load prediction module 10, user predicted load list grouping module 20, split-voltage power generation prediction module 30, transmission loss assessment module 40, split-voltage power generation carbon emission prediction module 50, distribution optimization module 60, intelligent distribution module 70. DETAILED DESCRIPTION

[0026] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0027] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0028] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0029] The present application embodiment provides a smart distribution network optimization scheduling method, such as Figure 1 As shown, the method includes:

[0030] Step S100, traverse the user side list to perform load forecasting for a preset time zone, and generate a user forecast load list, wherein the user forecast load list has an access voltage level label list and an access substation label list. Specifically, the user side refers to the power consumption end, that is, the power user, and the user side is the source of power demand and load; the user side list is a list containing basic information of all users. Collect the user's electricity consumption data from the power metering system, historical database or real-time monitoring system on the user side, including but not limited to historical electricity consumption, electricity consumption time, electricity consumption mode (such as household electricity consumption, commercial electricity consumption, industrial electricity consumption, etc.) and external factors affecting the load (such as weather, holidays, etc.), and at the same time, obtain the voltage level of the user's access to the power grid and the information of the access substation.

[0031] According to actual demand (for example, according to the law of change of power load), a day is divided into multiple preset time zones, such as peak hours, off-peak hours, and valley hours. According to the collected historical data and external factors, the load forecasting model is trained, wherein the load forecasting model can be based on time series (such as ARIMA, exponential smoothing, etc.) or machine learning (such as neural network, support vector machine, etc.), and is used to predict the power demand in the preset time zone. Different prediction models or model parameters can be used for different types of users (such as households, businesses, industries, etc.). The trained load forecasting model is applied to predict the load for each user in each preset time zone, and the prediction results can include the expected power consumption and power load curve of each time zone. The predicted load results of all users are sorted into a user predicted load list, and the access voltage level label and access substation label are added to each predicted load for subsequent grouping and optimization. By predicting the power demand of each user in the preset time zone, basic data is provided for subsequent voltage division prediction, power generation prediction and distribution optimization.

[0032] In a possible implementation, the user side list is traversed to perform load forecasting in a preset time zone, and a user forecast load list is generated, wherein the user forecast load list has an access voltage level label list and an access substation label list, and step S100 further includes step S110, extracting the first user basic information according to the user side list, wherein the first user basic information includes the first electricity industry, the first access capacity, the first commissioning time, the first user scale, the first access voltage level, and the first access substation. Specifically, each user record in the user side list is accessed one by one, and for the currently traversed user (referred to as the first user), its basic information (basic data describing the user's electricity consumption characteristics) is extracted from the user record, including the first electricity industry (the type of industry to which the user belongs, such as industry, commerce, residence, etc.), the first access capacity (the capacity size of the user's access to the power grid), the first commissioning time (the duration of using electricity in the preset time zone), the first user scale (the user's electricity scale or electricity consumption), the first access voltage level (the voltage level of the user's access to the power grid, such as high voltage, medium voltage, low voltage, etc.), and the first access substation (the name or number of the substation accessed by the user). Step S120, perform load forecasting according to the first electricity industry, the first access capacity, the first commissioning time, and the first user scale, and generate the first user's predicted load. Specifically, according to the first user's electricity industry, access capacity, commissioning time, and user scale, collect relevant historical load data, industry electricity consumption trends, seasonal changes, and other information, use load forecasting models (such as time series analysis, machine learning models, etc.), and combine the collected data to forecast the first user's future load and generate the first user's predicted load. Step S130, add the first user's predicted load to the user's predicted load list, add the first access voltage level to the access voltage level label list, and add the first access substation to the access substation label list. Specifically, add the generated first user's predicted load to the user's predicted load list (a list containing all user's predicted loads), and at the same time, add the first access voltage level to the access voltage level label list (a list used to identify the access voltage level corresponding to each user's predicted load), and add the first access substation to the access substation label list (a list used to identify the substations to which each user's predicted load is connected). This implementation method comprehensively considers various factors that affect load forecasting (electricity consumption industry, access capacity, commissioning time, user scale), and achieves the technical effect of improving the accuracy of load forecasting.

[0033] In a possible implementation, load forecasting is performed according to the first electricity industry, the first access capacity, the first commissioning time, and the first user scale to generate a first user forecast load, and step S120 further includes step S121, setting the first electricity industry as a first fixed constraint. Specifically, the first electricity industry is used as an invariant condition in the prediction model, that is, all subsequent analysis and prediction are based on this specific electricity industry. Step S122, based on the access capacity deviation threshold, the commissioning time deviation threshold, and the user scale deviation threshold, configure the first fuzzy constraint for the first access capacity, the first commissioning time, and the first user scale. Specifically, according to historical data or expert experience, a reasonable deviation range of access capacity, commissioning time, and user scale is set, that is, a range of allowed fluctuations. The above deviation range is used as a fuzzy constraint condition, allowing a certain flexibility in these parameters during prediction to cover similar situations more widely. Step S123, historical backtracking is performed according to the first fixed constraint condition and the first fuzzy constraint condition to obtain a data set of electricity consumption records of users in the same cluster, wherein the data set of electricity consumption records of users in the same cluster represents user load record data that meets the first fixed constraint condition and the first fuzzy constraint condition. Specifically, in the historical database, according to the set fixed and fuzzy constraints, the user load records that meet the conditions are screened out, and the screened load records are organized into a data set, which reflects the electricity consumption behavior of user groups similar to the current prediction object. Step S124, the mode fitting is performed on the data set of electricity consumption records of users in the same cluster to generate the predicted load of the first user. Specifically, in the data set of electricity consumption records of users in the same cluster, the value with the highest frequency of electricity consumption (i.e., the mode) is found, and the mode value is used as the prediction result, that is, it is considered that the value represents the user's possible future electricity consumption under the current conditions. This implementation method introduces fuzzy constraints to give the model a certain flexibility in parameters, and can cover similar situations more widely, thereby achieving the technical effect of improving the generalization ability of the model.

[0034] Step S200, according to the access voltage level label list, the user predicted load list is grouped to generate a voltage-divided predicted load. Specifically, the access voltage level label corresponding to each predicted load is extracted from the user predicted load list, and the access voltage level label identifies the voltage level used when the user accesses the power grid, such as 10kV, 35kV, 110kV, etc. According to different access voltage levels, a corresponding grouping structure is created in the memory or database, and each group corresponds to a specific voltage level. Traverse the user predicted load list, and assign each predicted load to the corresponding group according to its access voltage level label. All predicted loads with the same voltage level label are classified into the same group.

[0035] For each group, calculate the sum of all predicted loads in the group to obtain the voltage-divided predicted load at the voltage level. Arrange the voltage-divided predicted loads of all groups into a list or data structure, in which each element contains the voltage level and the corresponding voltage-divided predicted load value. By grouping the user predicted loads according to the access voltage level and calculating the voltage-divided predicted load at each voltage level, basic data is provided for subsequent power distribution optimization.

[0036] Step S300, traverse the access substation tag list to perform pressure-divided power generation prediction in preset time zones, and generate a pressure-divided predicted power generation list. Specifically, collect historical power generation data, power generation equipment status, weather forecast, fuel supply and other related information of each access substation. According to the type of access substation (such as thermal power generation, hydropower generation, wind power generation, photovoltaic power generation, etc.) and available data, select a suitable power generation prediction model. These models can be based on statistics (such as time series analysis, regression analysis), physics (such as meteorological model-driven power generation prediction) or machine learning (such as neural networks, random forests, etc.). Use historical power generation data and other relevant factors as input to train the selected power generation prediction model, and evaluate the prediction performance of the model through methods such as cross-validation or holdout method to ensure that the model can accurately predict future power generation. For each access substation, extract the corresponding data from the collected information according to its label, apply the trained power generation prediction model, predict the power generation of each access substation in the preset time zone, and organize the predicted power generation of each access substation into a list or data structure according to the preset time zone. The list contains the identification of the access substation, the predicted power generation of each preset time zone, and other relevant information (such as prediction confidence, power generation type, etc.). By predicting the power generation of each access substation in the preset time zone, it is used to provide a basis for subsequent distribution optimization and intelligent distribution.

[0037] In a possible implementation, the access substation tag list is traversed to perform a prediction of the voltage-divided power generation in a preset time zone, and a voltage-divided predicted power generation list is generated. Step S300 further includes step S310, extracting basic information of the first access substation according to the access substation tag list, wherein the first access substation basic information (a data set describing basic characteristics of the substation) includes a first installed capacity, a first power source type, a first access voltage level, a first commissioning year, a first unit capacity, a first number of units, and a preset time zone step. Specifically, the access substation tag list is traversed, and each substation is identified one by one. For each substation in the list (i.e., the first access substation), its basic information is extracted from the database, including but not limited to: the first installed capacity (the total installed capacity of the substation), the first power type (such as thermal power generation, hydropower generation, wind power generation, etc.), the first access voltage level (the voltage level of the substation accessing the power grid), the first commissioning year (the year when the substation starts to operate), the first unit capacity (the capacity of each unit in the substation), the first number of units (the number of units in the substation), and the preset time zone step (the time step used for prediction, such as every hour, every day, etc.). Step S320, the first power type and the first access voltage level are used as the second fixed constraint conditions. Specifically, the power type and the access voltage level are used as fixed constraints in the prediction model, that is, all subsequent analysis and prediction are based on these two specific conditions. Step S330, based on the installed capacity deviation threshold, the commissioning year deviation threshold, the unit capacity deviation threshold, the unit number deviation threshold and the time zone step deviation threshold, the second fuzzy constraint condition is configured in combination with the first installed capacity, the first commissioning year, the first unit capacity, the first unit number and the preset time zone step. Specifically, according to historical data or expert experience, a reasonable deviation range is set for the installed capacity, commissioning year, unit capacity, unit number and time zone step, and these deviation ranges are used as fuzzy constraints, allowing these parameters to have a certain fluctuation range during prediction to cover more similar situations.

[0038] Step S340, perform historical backtracking according to the second fixed constraint and the second fuzzy constraint to obtain a data set of power generation records of the same cluster substation. Specifically, in the historical database, according to the set fixed and fuzzy constraints, filter out the power generation records of the substations that meet the conditions, and organize the filtered power generation records into a data set, which reflects the power generation behavior of the substations similar to the current prediction object. Step S350, perform mode fitting on the power generation record data set of the same cluster substations to generate the predicted power generation of the first access substation. Specifically, in the power generation record data set of the same cluster substations, find the value with the highest frequency of power generation (i.e., the mode), and use the mode value as the prediction result, that is, it is considered that the value represents the possible future power generation of the substation under the current conditions. Step S360, group the predicted power generation of the first access substation according to the first access voltage level, and add it to the voltage-dividing predicted power generation list. Specifically, according to the access voltage level of the substation, the predicted power generation is grouped, and the grouped power generation is added to the voltage-dividing predicted power generation list for subsequent analysis and use. This implementation method accurately characterizes the characteristics of the prediction object by integrating multiple factors (such as power source type, access voltage level, installed capacity, etc.) and their deviation range. The introduction of fuzzy constraints makes the model flexible in parameters and can cover similar situations more widely. By obtaining a data set of power generation records of substations in the same cluster through historical backtracking, the prediction results are supported by reliable historical data, achieving the technical effect of improving the accuracy and credibility of power generation prediction.

[0039] Step S400, based on the access substation tag list and the user side list, the transmission loss is evaluated to generate a voltage-dividing transmission loss ratio list. Specifically, the power transmission path information between each user in the user side list and the access substation is collected, including the specifications, length, material and other influencing factors (such as terrain, weather, etc.) of the transmission line; the operation data of the access substation is collected, such as transformer efficiency, switch equipment loss, etc., which are used to calculate the transmission loss on the substation side. Among them, the transmission loss refers to the loss of electric energy caused by factors such as resistance and inductance during the power transmission process. According to the collected data, a suitable transmission loss calculation model is selected, which can be based on physical principles (such as an ohm loss model considering parameters such as resistance and inductance), or an empirical model based on statistical data. For each power transmission path, the selected transmission loss model is applied to calculate the transmission loss from the access substation to the user side, including the transmission loss of each link in the path (such as lines, transformers, switches, etc.).

[0040] For each access substation, the transmission losses of all its users are summarized to obtain the total transmission loss of the substation. The total transmission loss of each substation is compared with the predicted power generation of the substation (from step S300), and the voltage-dividing transmission loss ratio is calculated. This ratio reflects the percentage of transmission loss to power generation at a given voltage level, reflecting the level of transmission efficiency. The voltage-dividing transmission loss ratios of all access substations are sorted into a list or data structure, in which each element contains the identification of the access substation, the corresponding voltage level, and the voltage-dividing transmission loss ratio. By evaluating the transmission losses of different access substations and user sides in the smart distribution network, and generating a voltage-dividing transmission loss ratio list, a basis is provided for subsequent distribution optimization.

[0041] In a possible implementation, based on the access substation tag list and the user side list, the transmission loss assessment is performed to generate a voltage-dividing transmission loss ratio list, and step S400 further includes step S410, extracting the first access substation according to the access substation tag list. Specifically, access and read the list storing the access substation tags, and select (or extract) any access substation from the list as the object currently being processed, that is, the first access substation. Step S420, extracting the first user side according to the user side list, wherein the first access substation belongs to the first user side access substation tag. Specifically, access the user side list, and by comparing the user side access substation tag, find the user side associated with the extracted first access substation in the user side list. Once a matching user side is found, it is extracted as the object currently being processed, that is, the first user side. Step S430, obtain the transmission line model list and the transmission line length list from the first access substation to the first user side. Specifically, according to the information of the first access substation and the first user side, the detailed information of the transmission line between the two is queried, and the model (parameters describing the electrical and physical characteristics of the transmission line, such as conductor type, cross-sectional area, insulation layer type, etc.) and length (actual length of the transmission line from the access substation to the user side) of the transmission line are collected for calculating the transmission loss. Step S440, according to the access voltage tag, traverse the transmission line model list and the transmission line length list to predict the transmission loss, obtain the first voltage-dividing transmission loss ratio, and add it to the voltage-dividing transmission loss ratio list. Specifically, according to the access voltage tag, the voltage level of the transmission line is determined, and the model and length of the transmission line, as well as the voltage level, are used to calculate the electric energy loss in the transmission process through a predetermined algorithm or formula, and the calculated transmission loss is compared with the total transmission power or voltage to obtain the voltage-dividing transmission loss ratio, and the obtained voltage-dividing transmission loss ratio is added to the voltage-dividing transmission loss ratio list for subsequent analysis and use. This implementation method achieves the technical effect of ensuring the accuracy and comprehensiveness of transmission loss assessment by predicting transmission losses based on the type and length of transmission lines.

[0042] In a possible implementation, according to the access voltage tag, the transmission line model list and the transmission line length list are traversed to predict the transmission loss, and the first voltage-divided transmission loss ratio is obtained. Step S440 further includes step S441, collecting the transmission line model data set, the transmission line length data set, the transmission voltage data set and the transmission loss ratio identification data set, and configuring the transmission loss ratio prediction network. Specifically, the data of transmission lines of different models are collected, including the conductor material, cross-sectional area, resistivity, etc., the actual length of the transmission line (the transmission loss is proportional to the distance) data is collected, the voltage value during the transmission process is collected, and the transmission loss under different voltages is different. The transmission loss ratio data is collected for training the prediction model. Using the collected data set, a machine learning or deep learning model is constructed to predict the transmission loss ratio. This model can be a neural network that receives the transmission line model, length and transmission voltage as input and outputs the predicted transmission loss ratio. Step S442: According to the transmission loss ratio prediction network, according to the access voltage label, the transmission line model list and the transmission line length list are traversed to perform transmission loss prediction, and the first voltage-divided initial transmission loss ratio sequence is obtained. Specifically, according to the access voltage label (i.e., the voltage level of the current transmission system), the transmission loss ratio prediction network traverses the transmission line model list and the transmission line length list, and for each combination of model and length, the transmission loss is predicted according to the current voltage to generate an initial transmission loss ratio sequence, and each value in the sequence corresponds to a predicted loss ratio under a combination of model and length. Step S443: Fit the first voltage-divided initial transmission loss ratio sequence to generate the first voltage-divided transmission loss ratio. Specifically, since the transmission system includes multiple transmission sections, each section has a loss ratio, it is necessary to fit these initial transmission loss ratios to simulate the total loss of the entire transmission system. The fitting process includes combining the loss ratios of each section in a certain way (such as multiplication or weighted summation) according to the cumulative effect of the loss to obtain the total loss ratio of the entire system. After fitting, the total transmission loss ratio of the entire transmission system at the first voltage division (i.e., access voltage) is finally generated. This value reflects the overall efficiency loss of the transmission system under given voltage, line model, and length conditions. This implementation method fits the initial transmission loss ratio sequence of the first voltage division, takes into account the cumulative effect of losses in the transmission process, accurately simulates the total loss of the transmission system, and achieves the technical effect of improving the accuracy of transmission loss prediction.

[0043] Step S500, traverse the access substation tag list to predict the carbon emissions of the partial pressure power generation, and generate a partial pressure predicted carbon emissions list. Specifically, carbon emissions refer to the emissions of greenhouse gases such as carbon dioxide generated during the power generation process, which is an indicator to measure the environmental impact of power generation methods. Collect the power generation type information of each access substation, such as thermal power generation, hydropower generation, wind power generation, photovoltaic power generation, etc., and collect the unit power generation carbon emission factor (carbon emissions generated by unit power generation) of each power generation type from environmental protection departments or research institutions. The unit power generation carbon emission factor reflects the environmental impact of different power generation methods. According to the power generation type and available data, select a suitable carbon emission prediction model, which can be a simple calculation model based on the unit power generation carbon emission factor, or a complex model that integrates more factors (such as a model that integrates power generation equipment efficiency, fuel quality, combustion efficiency, etc.). For each access substation, extract the corresponding data from the collected data information according to its tag, apply the selected carbon emission prediction model, and combine the power generation type, power generation prediction (from step S300) and unit power generation carbon emission factor of the substation to calculate the partial pressure power generation carbon emissions of the substation. The carbon emissions of the partial pressure power generation of each connected substation are sorted into a list or data structure according to the preset time zone. The list contains the identification of the connected substation, the predicted power generation in each time zone, the corresponding carbon emissions, and other relevant information (such as power generation type, carbon emission factor, etc.). By predicting the carbon emissions of the partial pressure power generation of each connected substation, it is used for subsequent power distribution optimization and intelligent power distribution to achieve low-carbon power dispatching and promote the green and low-carbon development of the smart distribution network.

[0044] Step S600, based on the voltage-divided transmission loss ratio list and the voltage-divided predicted carbon emission list, the voltage-divided predicted power generation list and the voltage-divided predicted load are optimized for distribution, and a user-side distribution plan is generated. Specifically, the voltage-divided predicted power generation list, the voltage-divided predicted load, the voltage-divided transmission loss ratio list and the voltage-divided predicted carbon emission list are used as input data, and the main optimization objectives are defined according to the actual situation of the distribution network and the scheduling requirements, including minimizing transmission losses, minimizing carbon emissions, etc. According to the defined optimization objectives, an optimization algorithm is selected, which can be a classical mathematical programming method (such as linear programming, nonlinear programming, integer programming, etc.), or a heuristic algorithm (such as genetic algorithm, particle swarm optimization algorithm, simulated annealing algorithm, etc.) or a hybrid algorithm. The selected optimization algorithm is applied to solve the constructed optimization model, and the values ​​of the decision variables are continuously adjusted through iterative calculations to find a solution that satisfies the constraints and optimizes the objective function. The optimal solution obtained by the optimization calculation is converted into a user-side distribution plan, which includes the power supply plan of each substation to users of different voltage levels, and is used to achieve economic, efficient and green operation of the distribution network. The user-side power distribution plan is output to the intelligent power distribution system for reference and execution in actual operation.

[0045] In a possible implementation, based on the voltage-divided transmission loss ratio list and the voltage-divided predicted carbon emission list, the voltage-divided predicted power generation list and the voltage-divided predicted load are optimized for distribution, and a user-side distribution plan is generated. Step S600 further includes step S610, with the voltage-divided predicted power generation list, the voltage-divided predicted load and the voltage-divided transmission loss ratio list as constraints, random distribution of distribution is performed to obtain several distribution allocation plans. Specifically, a random allocation algorithm is used to generate multiple possible distribution allocation plans under the conditions of satisfying the power generation forecast, load forecast and transmission loss ratio constraints. In other words, the random allocation algorithm parameters are set, such as the number of allocations, the allocation range, etc., and each voltage level or area is traversed. According to the power generation forecast and load forecast, the power generation is randomly allocated to each user or load point to ensure that each allocation meets the transmission loss ratio limit, that is, considering the energy loss in the transmission process, and the above process is repeated to generate multiple distribution allocation plans. Step S620, transmission loss statistics are performed according to the several distribution allocation plans to obtain several transmission loss amounts. Specifically, for each power distribution allocation scheme, according to the power grid topology and the transmission loss ratio model (which can be combined with the voltage-dividing transmission loss ratio list), the transmission loss from the access substation to the user end is calculated, and all transmission losses are summarized to obtain the total transmission loss of each power distribution allocation scheme. Step S630: Based on the several transmission loss amounts, the several power distribution allocation schemes are sorted from small to large to obtain a first sorting result, wherein the first sorting result has a first weight. Specifically, the transmission loss amounts of all power distribution allocation schemes are sorted from small to large, and the sorting results are assigned a first weight to indicate the importance of power transmission efficiency. Step S640: Based on the voltage-dividing predicted carbon emission list, the several total carbon emissions of the several power distribution allocation schemes are counted. Specifically, the voltage-dividing predicted carbon emission list is used in combination with the power distribution allocation scheme to calculate the overall carbon emissions of each power distribution allocation scheme. Step S650: Based on the several total carbon emissions, the several power distribution allocation schemes are sorted from small to large to obtain a second sorting result, wherein the second sorting result has a second weight. Specifically, the total carbon emissions of all power distribution schemes are sorted from small to large, and a second weight is assigned to the sorting result to indicate the importance of environmental protection benefits. Step S660: According to the first weight and the second weight, in combination with the first sorting result and the second sorting result, the plurality of power distribution schemes are weightedly summed by serial number to obtain a plurality of serial number summation results. Specifically, according to the first weight and the second weight, the transmission loss sorting number and the carbon emission sorting number of each power distribution scheme are weightedly summed, and the power distribution scheme is comprehensively evaluated by comprehensively considering the transmission efficiency and environmental protection benefits. Step S670: The power distribution scheme with the minimum value of the plurality of serial number summation results is obtained, and is set as the user-side power distribution scheme.Specifically, find the distribution scheme with the smallest sum of the serial numbers, which achieves the optimal balance between transmission efficiency and environmental benefits, and set it as the user-side distribution scheme. This implementation method provides quantitative indicators for evaluating the efficiency and environmental protection of each distribution scheme by counting the total transmission losses and carbon emissions. By summing the weighted sum of the serial numbers, the two key indicators are combined to ensure that the selected scheme is better in multiple dimensions, achieving the technical effect of realizing refined management of power distribution and ensuring that the user-side distribution scheme achieves the optimal balance between transmission efficiency and environmental benefits.

[0046] Step S700, intelligent power distribution is performed according to the user-side power distribution plan. Specifically, the user-side power distribution plan is parsed to determine the specific information such as the amount of electricity allocated by each access substation to each user side and the power supply time. The data format of the user-side power distribution plan is converted into a format that can be recognized by the intelligent distribution system, and connected to the interface of the intelligent distribution system. The intelligent distribution system sends dispatch instructions to each access substation and distribution equipment, including power generation adjustment, load distribution, transmission path selection, etc. During the power distribution process, the operating status of the power grid is monitored in real time, including parameters such as voltage, current, and power factor. According to the monitoring results, the user-side power distribution plan is adjusted as necessary to cope with emergencies or load changes. Through the above steps, the user-side power distribution plan is converted into actual power supply to ensure the safe, stable, and efficient operation of the power grid and meet the power needs of users. The embodiment of the present application adopts technical means such as respectively performing load forecasting and power generation forecasting in preset time zones, grouping user predicted loads according to voltage levels to form voltage-divided predicted loads, predicting carbon emissions from voltage-divided power generation, evaluating voltage-divided transmission losses, comprehensively considering voltage-divided transmission loss ratios and voltage-divided carbon emissions, and optimizing distribution of voltage-divided predicted power generation and voltage-divided predicted loads, thereby achieving the technical effect of improving the level of refined management of distribution networks through voltage-divided considerations and distribution optimization.

[0047] In the above, refer to Figure 1 The smart distribution network optimization dispatching method according to the embodiment of the present invention is described in detail. Figure 2 A smart distribution network optimization and dispatching system according to an embodiment of the present invention is described.

[0048] The intelligent distribution network optimization and dispatching system according to the embodiment of the present invention is used to solve the technical problem that the existing distribution dispatching lacks distribution optimization according to the voltage level and the actual situation of the substation, resulting in insufficient refinement of distribution control, and achieves the technical effect of improving the refinement management level of the distribution network through voltage division consideration and distribution optimization. The intelligent distribution network optimization and dispatching system includes: a load prediction module 10, a user prediction load list grouping module 20, a voltage division power generation prediction module 30, a transmission loss assessment module 40, a voltage division power generation carbon emission prediction module 50, a distribution optimization module 60, and an intelligent distribution module 70.

[0049] The load prediction module 10 is used to traverse the user side list to perform load prediction in a preset time zone and generate a user predicted load list, wherein the user predicted load list has an access voltage level label list and an access substation label list; the user predicted load list grouping module 20 is used to group the user predicted load list according to the access voltage level label list to generate a voltage-dividing predicted load; the voltage-dividing power generation prediction module 30 is used to traverse the access substation label list to perform voltage-dividing power generation prediction in a preset time zone and generate a voltage-dividing predicted power generation list; the transmission loss assessment module 40 is used to The access substation label list and the user-side list are used to evaluate the transmission loss and generate a voltage-dividing transmission loss ratio list; the voltage-dividing power generation carbon emissions prediction module 50 is used to traverse the access substation label list to predict the voltage-dividing power generation carbon emissions and generate a voltage-dividing predicted carbon emissions list; the distribution optimization module 60 is used to optimize the voltage-dividing predicted power generation list and the voltage-dividing predicted load based on the voltage-dividing transmission loss ratio list and the voltage-dividing predicted carbon emissions list to generate a user-side distribution plan; the intelligent distribution module 70 is used to perform intelligent distribution according to the user-side distribution plan.

[0050] The specific configuration of the load prediction module 10 will be described in detail below. As described above, the user side list is traversed to perform load prediction for a preset time zone, and a user predicted load list is generated, wherein the user predicted load list has an access voltage level label list and an access substation label list, and the load prediction module 10 may further include: a first user basic information extraction unit is used to extract the first user basic information according to the user side list, wherein the first user basic information includes the first electricity industry, the first access capacity, the first commissioning time, the first user scale, the first access voltage level, and the first access substation; the load prediction unit is used to perform load prediction according to the first electricity industry, the first access capacity, the first commissioning time, and the first user scale, and generate the first user predicted load; the list adding unit is used to add the first user predicted load into the user predicted load list, add the first access voltage level into the access voltage level label list, and add the first access substation into the access substation label list.

[0051] Among them, load forecasting is performed according to the first electricity consumption industry, the first access capacity, the first commissioning time, and the first user scale to generate the first user predicted load. The load forecasting unit may further include: a constraint configuration subunit is used to set the first electricity consumption industry as a first fixed constraint, and configure the first fuzzy constraint for the first access capacity, the first commissioning time, and the first user scale based on the access capacity deviation threshold, the commissioning time deviation threshold, and the user scale deviation threshold; a historical backtracking subunit is used to perform historical backtracking according to the first fixed constraint and the first fuzzy constraint to obtain a data set of electricity consumption records of users in the same cluster, wherein the data set of electricity consumption records of users in the same cluster represents user load record data that meets the first fixed constraint and the first fuzzy constraint; a mode fitting subunit is used to perform mode fitting on the data set of electricity consumption records of users in the same cluster to generate the first user predicted load.

[0052] The specific configuration of the pressure-sharing power generation prediction module 30 will be described in detail below. As described above, the access substation label list is traversed to perform pressure-sharing power generation prediction in a preset time zone, and a pressure-sharing predicted power generation list is generated. The pressure-sharing power generation prediction module 30 may further include: a first access substation basic information extraction unit is used to extract the first access substation basic information according to the access substation label list, wherein the first access substation basic information includes a first installed capacity, a first power source type, a first access voltage level, a first year of commissioning, a first unit capacity, a first number of units and a preset time zone step; a constraint condition configuration unit is used to use the first power source type and the first access voltage level as the second fixed constraint condition, based on the installed capacity deviation threshold, the year of commissioning deviation threshold , unit capacity deviation threshold, unit number deviation threshold and time zone step deviation threshold, and configure the second fuzzy constraint condition in combination with the first installed capacity, the first year of commissioning, the first unit capacity, the first number of units and the preset time zone step; the historical backtracking unit is used to perform historical backtracking according to the second fixed constraint condition and the second fuzzy constraint condition to obtain a data set of power generation records of the same cluster substations; the mode fitting unit is used to perform mode fitting on the data set of power generation records of the same cluster substations to generate the predicted power generation of the first access substation; the grouping unit is used to group the predicted power generation of the first access substation according to the first access voltage level, and add it into the voltage-dividing predicted power generation list.

[0053] The specific configuration of the transmission loss assessment module 40 will be described in detail below. As described above, based on the access substation label list and the user side list, the transmission loss assessment is performed to generate a voltage-dividing transmission loss ratio list. The transmission loss assessment module 40 may further include: a first access substation extraction unit is used to extract the first access substation according to the access substation label list; a first user side extraction unit is used to extract the first user side according to the user side list, wherein the first access substation belongs to the first user side access substation label; a transmission line information acquisition unit is used to obtain a transmission line model list and a transmission line length list from the first access substation to the first user side; a transmission loss prediction unit is used to traverse the transmission line model list and the transmission line length list according to the access voltage label to perform transmission loss prediction, obtain a first voltage-dividing transmission loss ratio, and add it to the voltage-dividing transmission loss ratio list.

[0054] Wherein, the transmission line model list and the transmission line length list are traversed to perform transmission loss prediction, and a first partial voltage transmission loss ratio is obtained. The transmission loss prediction unit may further include: a transmission loss ratio prediction network configuration subunit is used to collect a transmission line model data set, a transmission line length data set, a transmission voltage data set and a transmission loss ratio identification data set, and configure a transmission loss ratio prediction network; a transmission loss prediction subunit is used to traverse the transmission line model list and the transmission line length list according to the transmission loss ratio prediction network and the access voltage label to perform transmission loss prediction, and obtain a first partial voltage initial transmission loss ratio sequence; a sequence fitting subunit is used to fit the first partial voltage initial transmission loss ratio sequence to generate the first partial voltage transmission loss ratio.

[0055] The specific configuration of the power distribution optimization module 60 will be described in detail below. As described above, based on the voltage-dividing transmission loss ratio list and the voltage-dividing predicted carbon emission list, the voltage-dividing predicted power generation list and the voltage-dividing predicted load are optimized for distribution to generate a user-side distribution plan. The power distribution optimization module 60 may further include: a power distribution random allocation unit for performing power distribution random allocation with the voltage-dividing predicted power generation list, the voltage-dividing predicted load and the voltage-dividing transmission loss ratio list as constraints to obtain a number of power distribution allocation plans; a power transmission loss statistics unit for performing power transmission loss statistics based on the several power distribution allocation plans to obtain a number of power transmission loss amounts; a sorting unit for sorting the several power distribution allocation plans from small to large based on the several power transmission loss amounts to obtain a first sorting result, wherein the first The sorting result has a first weight; the total carbon emission statistics unit is used to count the total carbon emissions of the several power distribution allocation schemes based on the voltage-divided pressure predicted carbon emission list; the sorting unit is used to sort the several power distribution allocation schemes from small to large based on the several total carbon emissions, and obtain a second sorting result, wherein the second sorting result has a second weight; the sequence number weighted summation unit is used to perform sequence number weighted summation on the several power distribution allocation schemes according to the first weight and the second weight, combined with the first sorting result and the second sorting result, to obtain several sequence number summation results; the user-side power distribution scheme generation unit is used to obtain the power distribution allocation scheme with the minimum value of the several sequence number summation results, and set it as the user-side power distribution scheme.

[0056] The smart distribution network optimization and dispatching system provided in the embodiment of the present invention can execute the smart distribution network optimization and dispatching method provided in any embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method.

[0057] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0058] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A smart distribution network optimization dispatching method, characterized in that: include: Traversing the user side list to perform load forecasting in a preset time zone, and generating a user forecast load list, wherein the user forecast load list has an access voltage level label list and an access substation label list; According to the access voltage level label list, the user predicted load list is grouped to generate a voltage-divided predicted load; Traversing the access substation tag list to perform split-voltage power generation prediction in a preset time zone, and generating a split-voltage predicted power generation list; Performing a transmission loss assessment based on the access substation tag list and the user side list to generate a voltage-dividing transmission loss ratio list; Traversing the access substation tag list to predict the carbon emissions of power generation by partial pressure, and generating a partial pressure predicted carbon emissions list; Based on the partial pressure transmission loss ratio list and the partial pressure predicted carbon emission list, the partial pressure predicted power generation list and the partial pressure predicted load are optimized for power distribution to generate a user-side power distribution plan; Perform intelligent power distribution according to the user-side power distribution plan; Wherein, based on the partial pressure transmission loss ratio list and the partial pressure predicted carbon emission list, the partial pressure predicted power generation list and the partial pressure predicted load are optimized for distribution, and a user side distribution plan is generated, including: Taking the partial voltage predicted power generation list, the partial voltage predicted load and the partial voltage transmission loss ratio list as constraints, performing random distribution of power distribution to obtain several power distribution allocation schemes; Performing power transmission loss statistics according to the plurality of power distribution allocation schemes to obtain a plurality of power transmission loss amounts; Based on the plurality of power transmission loss amounts, the plurality of power distribution allocation schemes are sorted from small to large to obtain a first sorting result, wherein the first sorting result has a first weight; Based on the partial pressure predicted carbon emission list, calculating the total carbon emissions of the plurality of power distribution schemes; Based on the plurality of total carbon emissions, the plurality of power distribution allocation schemes are sorted from small to large to obtain a second sorting result, wherein the second sorting result has a second weight; According to the first weight and the second weight, in combination with the first sorting result and the second sorting result, performing weighted summation of the plurality of power distribution allocation schemes by sequence number to obtain a plurality of sequence number summation results; A power distribution scheme that obtains the minimum value of the sum of the plurality of sequence numbers is set as the user-side power distribution scheme.

2. The smart distribution network optimization dispatching method according to claim 1, characterized in that: Traverse the user side list to perform load forecasting in a preset time zone, and generate a user forecast load list, wherein the user forecast load list has an access voltage level label list and an access substation label list, including: Extracting first user basic information according to the user side list, wherein the first user basic information includes a first electricity industry, a first access capacity, a first commissioning time, a first user scale, a first access voltage level, and a first access substation; Perform load forecasting according to the first electricity consumption industry, the first access capacity, the first commissioning time, and the first user scale to generate a first user forecast load; The first user predicted load is added to the user predicted load list, the first access voltage level is added to the access voltage level label list, and the first access substation is added to the access substation label list.

3. The smart distribution network optimization dispatching method according to claim 2, characterized in that: Performing load forecasting according to the first electricity consumption industry, the first access capacity, the first commissioning time, and the first user scale to generate a first user forecast load includes: The first electricity-consuming industry is set as a first fixed constraint condition; Based on an access capacity deviation threshold, a production time deviation threshold, and a user scale deviation threshold, configuring a first fuzzy constraint condition for the first access capacity, the first production time, and the first user scale; Perform historical backtracking according to the first fixed constraint condition and the first fuzzy constraint condition to obtain a data set of electricity consumption records of users in the same cluster, wherein the data set of electricity consumption records of users in the same cluster represents user load record data that satisfies the first fixed constraint condition and the first fuzzy constraint condition; Mode fitting is performed on the electricity consumption record data set of users in the same cluster to generate the predicted load of the first user.

4. The smart distribution network optimization dispatching method according to claim 1, characterized in that: Traversing the access substation tag list to predict the voltage-divided power generation in a preset time zone, and generating a voltage-divided predicted power generation list, including: Extracting basic information of a first access substation according to the access substation tag list, wherein the basic information of the first access substation includes a first installed capacity, a first power type, a first access voltage level, a first commissioning year, a first unit capacity, a first number of units, and a preset time zone step; The first power type and the first access voltage level are used as second fixed constraint conditions; Based on the installed capacity deviation threshold, the commissioning year deviation threshold, the unit capacity deviation threshold, the unit number deviation threshold and the time zone step deviation threshold, the second fuzzy constraint condition is configured in combination with the first installed capacity, the first commissioning year, the first unit capacity, the first unit number and the preset time zone step; Perform historical backtracking according to the second fixed constraint condition and the second fuzzy constraint condition to obtain a data set of power generation records of substations in the same cluster; Performing mode fitting on the power generation record data set of the substations in the same cluster to generate predicted power generation of the first access substation; The predicted power generation of the first access substation is grouped according to the first access voltage level, and added into the voltage-divided predicted power generation list.

5. The smart distribution network optimization dispatching method according to claim 1, characterized in that: The power transmission loss is evaluated based on the access substation tag list and the user side list, and a voltage-dividing power transmission loss ratio list is generated, including: Extracting a first access substation according to the access substation tag list; Extracting a first user side according to the user side list, wherein the first access substation belongs to a first user side access substation tag; Obtain a list of transmission line models and a list of transmission line lengths from the first access substation to the first user side; According to the access voltage label, the transmission line model list and the transmission line length list are traversed to perform transmission loss prediction, and a first voltage-dividing transmission loss ratio is obtained, which is added to the voltage-dividing transmission loss ratio list.

6. The smart distribution network optimization dispatching method according to claim 5, characterized in that: According to the access voltage label, traversing the transmission line model list and the transmission line length list to perform transmission loss prediction, and obtaining a first voltage division transmission loss ratio, including: Collect the transmission line model data set, transmission line length data set, transmission voltage data set and transmission loss ratio identification data set, and configure the transmission loss ratio prediction network; According to the transmission loss ratio prediction network and the access voltage label, the transmission line model list and the transmission line length list are traversed to perform transmission loss prediction, and a first voltage division initial transmission loss ratio sequence is obtained; The first voltage-dividing initial power transmission loss ratio sequence is fitted to generate the first voltage-dividing power transmission loss ratio.

7. Intelligent distribution network optimization dispatching system, characterized in that: The system is used to implement the smart distribution network optimization dispatching method according to any one of claims 1 to 6, and the system includes: A load prediction module, which is used to traverse the user side list to perform load prediction in a preset time zone and generate a user predicted load list, wherein the user predicted load list has an access voltage level label list and an access substation label list; A user predicted load list grouping module, the user predicted load list grouping module is used to group the user predicted load list according to the access voltage level label list to generate a divided voltage predicted load; A voltage-divided power generation prediction module, which is used to traverse the access substation tag list to perform voltage-divided power generation prediction in a preset time zone and generate a voltage-divided predicted power generation list; A power transmission loss assessment module, the power transmission loss assessment module is used to perform power transmission loss assessment based on the access substation tag list and the user side list, and generate a voltage-dividing power transmission loss ratio list; A pressure-divided power generation carbon emission prediction module, which is used to traverse the access substation tag list to predict the pressure-divided power generation carbon emission and generate a pressure-divided predicted carbon emission list; A power distribution optimization module, the power distribution optimization module is used to optimize the power distribution of the partial pressure predicted power generation list and the partial pressure predicted load based on the partial pressure transmission loss ratio list and the partial pressure predicted carbon emission list, and generate a user-side power distribution plan; An intelligent power distribution module, wherein the intelligent power distribution module is used to perform intelligent power distribution according to the user-side power distribution plan.

Images