Management Method of Carbon Emission Data of Distribution Network

Abstract

The present invention relates to a method for managing carbon emission data of a distribution network, and relates to the field of distribution networks. The method comprises: using a carbon emission data prediction model to intelligently predict the total carbon emission values ​​and the total transmission power of the target distribution network within a set time interval based on various past distribution data of the target distribution network and multiple configuration contents; when the total carbon emission values ​​predicted by the intelligent prediction are greater than the set carbon emission threshold, a mounting scale reduction strategy is executed for the target distribution network within the set time interval, otherwise, a mounting scale maintenance strategy is executed. Through the present invention, a carbon emission data prediction model of a customized mechanism is built for each distribution network, and the total carbon emission values ​​and the total transmission power of the distribution network within a future time interval are predicted based on multiple basic data that are targeted and screened, and then a corresponding carbon emission management strategy is formulated for the future time interval based on the prediction results, thereby avoiding the distribution network from exceeding the carbon emission data standard within the future time interval.

Description

Technical Field

[0001] The present invention relates to the field of power distribution networks, and in particular to a method for managing carbon emission data of a power distribution network. Background Art

[0002] The distribution network refers to the power grid that receives electric energy from the transmission grid or regional power plants and distributes it locally or step by step according to voltage to various users through distribution facilities. It is composed of overhead lines, cables, towers, distribution transformers, disconnectors, reactive power compensators and some ancillary facilities. It plays an important role in distributing electric energy in the power grid. The management of carbon emission data of the distribution network is one of the important indicators of power industry management. Since demand leads to production in the power industry, the power load is the real source of carbon emissions. The management of carbon emission data of the distribution network is also related to the working status of the power load.

[0003] For example, Chinese invention patent publication CN114626687A proposes a method and system for determining carbon emissions of a source-containing distribution system, the method comprising: calculating the density of carbon flow injected into nodes of the source-containing distribution system at each moment based on basic data of the source-containing distribution system at each moment acquired within a preset time period; obtaining the total carbon flow rate of the source-containing distribution system at each moment based on the density of carbon flow injected into nodes of the source-containing distribution system at each moment and the basic data of the source-containing distribution system at each moment; obtaining the carbon emissions of the source-containing distribution system within the preset time period by integrating the total carbon flow rate of the source-containing distribution system at each moment; the invention adopts the carbon emission flow theory to calculate the carbon emissions in the source-containing distribution system, so as to obtain more accurate carbon emissions.

[0004] For example, Chinese invention patent publication CN116231633A proposes a method, device, equipment and storage medium for monitoring carbon emissions of a distribution network. The method divides the target distribution network area into multiple power supply grids based on the network topology of the target distribution network area; calculates the carbon emission factor of each power supply grid based on the power supply relationship between the power supply grid and the conducted carbon flow; obtains the electricity consumption data of each power supply grid, and calculates the carbon emissions of each power supply grid based on the electricity consumption data and the carbon emission factor; and counts the carbon emissions of each power supply grid to obtain the carbon emission information of the target distribution network area. The invention conforms to the actual electricity consumption situation and improves the calculation accuracy of carbon emissions in the regional distribution network during the electricity consumption process.

[0005] It can be seen that the above-mentioned existing technologies only involve the past statistics and real-time measurement of carbon emissions of the distribution network, and are unable to effectively predict the carbon emissions of the distribution network in future time periods, resulting in the inability to formulate targeted carbon emissions management strategies for the distribution network in future time periods, and unable to deal with the state of carbon emissions exceeding the standard in the distribution network in future time periods, thereby resulting in actual exceeding of carbon emissions in the distribution network in future time periods. Summary of the invention

[0006] In order to solve the technical problems in the prior art, the present invention provides a method for managing carbon emission data of a distribution network, builds a carbon emission data prediction model of a customized organization for each distribution network, and based on a plurality of basic data that are screened in a targeted and comprehensive manner, makes a reliable prediction of the total carbon emission values ​​and the total transmission power in the future time interval of the distribution network, and then performs corresponding carbon emission management and transmission power exceeding standard warning for the future time interval based on the prediction results, thereby providing a solution for the carbon emission management of the distribution network in the future time interval and improving the intelligence level of the distribution network management.

[0007] According to the present invention, a method for managing carbon emission data of a distribution network is provided, the method comprising:

[0008] Obtaining each portion of distribution network data corresponding to each historical time interval of the target distribution network before the set time interval, and obtaining each portion of workload data corresponding to each historical time interval of the target distribution network before the set time interval, wherein the number of each historical time interval is proportional to the routing length of the target distribution network, and the set time interval takes the current time as the starting time;

[0009] Acquire multiple configuration contents of the target power distribution network, wherein the multiple configuration contents of the target power distribution network are the routing length, the number of cables arranged in parallel, the total number of mounted loads and distribution voltage data of the target power distribution network, and the mounted loads include two types: working load and non-working load;

[0010] Performing a set number of multiple trainings on the feedforward neural network to obtain a feedforward neural network that has completed the multiple trainings, and outputting the feedforward neural network that has completed the multiple trainings as a carbon emission data prediction model, wherein the value of the set number is positively correlated with the total number of mounted loads of the target power distribution network;

[0011] The carbon emission data prediction model is used to intelligently predict the total carbon emission value and the total transmission power of the target distribution network within the set time interval based on the distribution network data corresponding to each historical time interval before the set time interval, the workload data corresponding to each historical time interval before the set time interval, and multiple configuration contents of the target distribution network, and output them as the predicted carbon emission value and the predicted transmission power respectively;

[0012] When the received predicted carbon emission value is greater than the set carbon emission threshold, a mounting scale reduction strategy is executed on the target power distribution network within a set time interval; when the received predicted carbon emission value is less than or equal to the set carbon emission threshold, a mounting scale maintenance strategy is executed on the target power distribution network within a set time interval;

[0013] Wherein, when the received predicted carbon emission value is greater than the set carbon emission threshold, executing the mounting scale reduction strategy for the target power distribution network within the set time interval includes: when the received predicted carbon emission value is greater than the set carbon emission threshold, reducing the number of workloads planned for the target power distribution network within the set time interval;

[0014] Among them, each distribution network data corresponding to each historical time interval of the target distribution network before the set time interval is obtained, and each workload data corresponding to each historical time interval of the target distribution network before the set time interval is obtained, and the number of each historical time interval is proportional to the routing length of the target distribution network, including: a single distribution network data corresponding to each time interval is the sum of the carbon emission values, the total transmission power and the active power information of the target distribution network in the time interval, and a single workload data corresponding to each time interval is the number of workloads in the target distribution network in the time interval and the working current, working time and rated power of each workload.

[0015] It can be seen that the present invention has at least the following five outstanding substantive features:

[0016] Substantive feature 1: Targeted screening of comprehensive and sufficient multiple basic data for intelligent prediction of carbon emission data of the target distribution network within a set time interval as a future time interval, wherein the multiple basic data include distribution network data corresponding to each historical time interval of the target distribution network before the set time interval, workload data corresponding to each historical time interval of the target distribution network before the set time interval, and multiple configuration contents of the target distribution network;

[0017] Substantive feature 2: Specifically, the single distribution network data corresponding to each time interval is the sum of the carbon emission values, the sum of the transmitted electricity, and the active power information of the target distribution network in the time interval; the single workload data corresponding to each time interval is the number of workloads in the target distribution network in the time interval and the working current, working time, and rated power of each workload; the multiple configuration contents of the target distribution network are the routing length, the number of cables arranged side by side, the total number of mounted loads, and the distribution voltage data of the target distribution network;

[0018] Substantive feature three: The carbon emission data prediction model with different customized structures is designed for different distribution networks to perform intelligent prediction of carbon emission data of the target distribution network within a set time interval. The carbon emission data prediction model is a feedforward neural network that has completed multiple trainings, wherein the number of trainings is positively correlated with the total number of mounted loads of the target distribution network, thereby ensuring the effectiveness and stability of the intelligent prediction results;

[0019] Substantive feature four: In each training of the feedforward neural network, the sum of the known carbon emission values ​​and the sum of the transmitted electricity in a certain historical time interval are used as the output content of the feedforward neural network, and the distribution network data corresponding to each historical time interval before the certain historical time interval of the target distribution network, the workload data corresponding to each historical time interval before the certain historical time interval of the target distribution network, and multiple configuration contents of the target distribution network are used as the input content of the feedforward neural network item by item to complete this training operation, thereby ensuring the training effect of each training operation of the feedforward neural network;

[0020] Substantive feature five: When the predicted carbon emission value obtained by intelligent prediction is greater than the set carbon emission threshold, the mounting scale reduction strategy is executed for the target distribution network within the set time interval; when the predicted carbon emission value obtained by intelligent prediction is less than or equal to the set carbon emission threshold, the mounting scale maintenance strategy is executed for the target distribution network within the set time interval, wherein the mounting scale reduction strategy is to reduce the number of workloads planned for the target distribution network within the set time interval, and when executing the specific reduction processing, the workload with the lowest work priority will be given priority to reduce the processing, thereby improving the intelligence level of carbon emission data management of the distribution network. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The embodiments of the present invention will be described below with reference to the accompanying drawings, wherein:

[0022] Figure 1 It is a technical flow chart of the method for managing carbon emission data of distribution network according to the present invention.

[0023] Figure 2 The figure is a flowchart of the steps of a method for managing carbon emission data of a distribution network according to a first embodiment of the present invention.

[0024] Figure 3 The figure is a flowchart of the steps of a method for managing carbon emission data of a distribution network according to a second embodiment of the present invention.

[0025] Figure 4 The figure is a flowchart of the steps of a method for managing carbon emission data of a distribution network according to a third embodiment of the present invention.

[0026] Figure 5 This is a flowchart of the steps of a method for managing carbon emission data of a distribution network according to a fourth embodiment of the present invention.

[0027] Figure 6 This is a flowchart of the steps of a method for managing carbon emission data of a distribution network according to a fifth embodiment of the present invention. DETAILED DESCRIPTION

[0028] like Figure 1 As shown, a technical flow chart of a method for managing carbon emission data of a distribution network according to the present invention is given.

[0029] like Figure 1 As shown, the specific technical process of the present invention is as follows:

[0030] Technical process 1: designing carbon emission data prediction models with different customized structures for different distribution networks, so as to perform intelligent prediction of carbon emission data of the corresponding distribution network within a set time interval as a future time interval;

[0031] like Figure 1 As shown, for each power distribution network, its carbon emission data is apparently in the power distribution network, but in fact, each workload that performs power distribution operations in the power distribution network is performing carbon emissions;

[0032] Specifically, the customization of the structure of the carbon emission data prediction model is mainly reflected in the following two aspects:

[0033] First, the carbon emission data prediction model is a feed-forward neural network that has completed multiple trainings, and the number of trainings is positively correlated with the total number of mounted loads on the distribution network;

[0034] like Figure 1 As shown, the carbon emission data prediction model is a three-layer structure consisting of an input layer, an output layer and a hidden layer, and the hidden layer is located between the input layer and the output layer;

[0035] Second, in each training performed on the feedforward neural network, the sum of the known carbon emission values ​​and the sum of the transmitted electricity in a certain historical time interval are used as the output content of the feedforward neural network, and the distribution network data corresponding to each historical time interval before the certain historical time interval, the workload data corresponding to each historical time interval before the certain historical time interval, and multiple configuration contents of the distribution network are used as the input content of the feedforward neural network item by item to complete this training operation, thereby ensuring the training effect of each training operation of the feedforward neural network;

[0036] In this way, through the customized design of the structure of the above carbon emission data prediction model, the effectiveness and stability of the intelligent prediction results of carbon emission data in the future time interval are guaranteed;

[0037] Technical process 2: Targeted screening of multiple basic data that are sufficient and comprehensive for the intelligent prediction of carbon emission data in the future time period to further ensure the effectiveness and stability of the intelligent prediction results;

[0038] Specifically, the multiple basic data include each copy of the distribution network data corresponding to each historical time interval before the set time interval, each copy of the workload data corresponding to each historical time interval before the set time interval, and multiple configuration contents of the distribution network;

[0039] More specifically, the multiple configuration contents of the power distribution network are the routing length, the number of cables arranged side by side, the total number of mounted loads and the distribution voltage data of the power distribution network, wherein the mounted loads include two types: working loads and non-working loads;

[0040] Technical process three: Using a carbon emission data prediction model designed with a customized structure for the target distribution network, based on multiple basic data that are fully and comprehensively selected for targeted purposes, to perform intelligent prediction of the total carbon emission values ​​and total transmission power of the target distribution network in the future time period, and output them as predicted carbon emission values ​​and predicted transmission power respectively;

[0041] Technical process 4: When the predicted carbon emission value obtained by intelligent prediction is greater than the set carbon emission threshold, a mounting scale reduction strategy is implemented for the distribution network in the future time interval; when the predicted carbon emission value obtained by intelligent prediction is less than or equal to the set carbon emission threshold, a mounting scale maintenance strategy is implemented for the distribution network in the future time interval;

[0042] For example, the load scale reduction strategy is to reduce the number of workloads planned for the power distribution network within a set time interval, and when performing the specific reduction process, the workload with the lowest work priority is preferentially reduced;

[0043] Technical process five: when the predicted transmission power obtained by intelligent prediction is greater than the upper limit of safe distribution power of the distribution network, the power over-limit warning action related to the future time interval is executed; and when the predicted transmission power obtained by intelligent prediction is less than or equal to the upper limit of safe distribution power of the distribution network, the power over-limit warning action related to the future time interval is temporarily suspended;

[0044] It can be seen that after the processing of the above five technical processes, the intelligent prediction of the total carbon emission values ​​and the total transmission power in each future time period of the distribution network is completed, and the corresponding carbon emission management strategy and power overlimit warning strategy are customized for the future time period of the distribution network based on the result data of the intelligent prediction. While ensuring that the carbon emission data in the future time period of the distribution network meets the standards, early warning is given for the phenomenon of exceeding the total transmission power in the future time period, which improves the overall intelligence level of distribution network management.

[0045] The key points of the present invention are: the design of carbon emission data prediction models with different customized structures for different distribution networks, the targeted screening of multiple basic data for intelligent prediction of carbon emission data in future time intervals, and the dynamic formulation of carbon emission management strategies and power overlimit warning strategies for future time intervals of distribution networks based on intelligent prediction result data.

[0046] The method for managing carbon emission data of a distribution network of the present invention will be specifically described below by way of an embodiment.

[0047] First embodiment

[0048] Figure 2 The figure is a flowchart of the steps of a method for managing carbon emission data of a distribution network according to a first embodiment of the present invention.

[0049] like Figure 2 As shown, the method for managing carbon emission data of the distribution network includes the following steps:

[0050] Step S11: obtaining each copy of distribution network data corresponding to each historical time interval of the target distribution network before the set time interval, and obtaining each copy of workload data corresponding to each historical time interval of the target distribution network before the set time interval, wherein the number of each historical time interval is proportional to the routing length of the target distribution network, and the set time interval takes the current time as the starting time;

[0051] For example, the number of each historical time interval is proportional to the routing length of the target power distribution network, including: the routing length of the target power distribution network is 5 kilometers, the number of each historical time interval is 10, the routing length of the target power distribution network is 8 kilometers, the number of each historical time interval is 16, and the routing length of the target power distribution network is 10 kilometers, the number of each historical time interval is 20, and so on;

[0052] Specifically, obtaining the distribution network data corresponding to each historical time interval of the target distribution network before the set time interval includes: the set time interval is a future time interval, and its starting time is the current time, for example, the current time is 6:00 p.m., the set time interval is from 6:00 p.m. to 6:15 p.m., the routing length of the target distribution network is 5 kilometers, and the number of each historical time interval is 10;

[0053] Thus, the historical time intervals before the set time interval are 5:35 pm to 6:00 pm, 5:30 pm to 5:35 pm, 5:01 pm to 5:30 pm, 5:01 pm to 5:01 pm, 5:01 pm to 5:01 pm, 4:03 pm to 5:00 pm, 4:35 pm to 4:35 pm, 4:01 pm to 4:30 pm, 4:01 pm to 4:00 pm, 4:01 pm to 4:01 pm, 3:03 pm to 4:00 pm, and 3:30 pm to 3:03 pm, i.e., 10 historical time intervals in total;

[0054] Step S12: Acquire multiple configuration contents of the target power distribution network, wherein the multiple configuration contents of the target power distribution network are the routing length, the number of cables arranged in parallel, the total number of mounted loads and distribution voltage data of the target power distribution network, and the mounted loads include two types: working load and non-working load;

[0055] For example, multiple configuration contents of a target power distribution network are obtained, wherein the multiple configuration contents of the target power distribution network are the routing length, the number of cables arranged in parallel, the total number of mounted loads, and distribution voltage data of the target power distribution network, and the mounted loads include two types: working loads and non-working loads: a mounted load that is currently powered on is a working load at the current moment, and a mounted load that is currently powered off is a non-working load at the current moment;

[0056] Step S13: performing a set number of trainings on the feedforward neural network to obtain a feedforward neural network that has completed the trainings, and outputting the feedforward neural network that has completed the trainings as a carbon emission data prediction model, wherein the value of the set number is positively correlated with the total number of mounted loads of the target power distribution network;

[0057] For example, the value of the set number is positively correlated with the total number of mounted loads of the target power distribution network, including: the total number of mounted loads of the target power distribution network is 100, the value of the set number is 50, and the feedforward neural network is trained 50 times; the total number of mounted loads of the target power distribution network is 120, the value of the set number is 55, and the feedforward neural network is trained 55 times; the total number of mounted loads of the target power distribution network is 150, the value of the set number is 60, and the feedforward neural network is trained 60 times; and the total number of mounted loads of the target power distribution network is 200, the value of the set number is 65, and the feedforward neural network is trained 65 times;

[0058] Step S14: using the carbon emission data prediction model to intelligently predict the total carbon emission value and the total transmission power of the target distribution network within the set time interval based on the distribution network data corresponding to each historical time interval before the set time interval, the workload data corresponding to each historical time interval before the set time interval, and multiple configuration contents of the target distribution network, and output them as the predicted carbon emission value and the predicted transmission power respectively;

[0059] Specifically, a numerical simulation mode may be selected to realize intelligent prediction of the total carbon emission value and the total transmission power of the target distribution network within the set time interval by using the carbon emission data prediction model based on each distribution network data corresponding to each historical time interval of the target distribution network before the set time interval, each workload data corresponding to each historical time interval of the target distribution network before the set time interval, and multiple configuration contents of the target distribution network, and use the numerical simulation mode as the data processing process for predicting the carbon emission value and predicting the transmission power output respectively;

[0060] Step S15: When the received predicted carbon emission value is greater than the set carbon emission threshold, a mounting scale reduction strategy is executed on the target power distribution network within a set time interval; when the received predicted carbon emission value is less than or equal to the set carbon emission threshold, a mounting scale maintenance strategy is executed on the target power distribution network within a set time interval;

[0061] By executing the above-mentioned load reduction strategy, it is possible to ensure that workloads with high power distribution priority levels maintain power distribution as much as possible, while preventing the total amount of carbon emissions data of the target power distribution network from exceeding the standard within the set time interval;

[0062] Wherein, when the received predicted carbon emission value is greater than the set carbon emission threshold, executing the mounting scale reduction strategy for the target power distribution network within the set time interval includes: when the received predicted carbon emission value is greater than the set carbon emission threshold, reducing the number of workloads planned for the target power distribution network within the set time interval;

[0063] Among them, each copy of distribution network data corresponding to each historical time interval of the target distribution network before the set time interval is obtained, and each copy of workload data corresponding to each historical time interval of the target distribution network before the set time interval is obtained, and the number of each historical time interval is proportional to the routing length of the target distribution network, including: a single copy of distribution network data corresponding to each time interval is the sum of carbon emission values, total transmission power and active power information of the target distribution network in the time interval, and a single copy of workload data corresponding to each time interval is the number of workloads in the target distribution network in the time interval and the working current, working time and rated power of each workload;

[0064] Among them, a set number of multiple trainings are performed on the feedforward neural network to obtain a feedforward neural network that has completed multiple trainings, and the feedforward neural network that has completed multiple trainings is output as a carbon emission data prediction model, and the value of the set number is positively correlated with the total number of mounted loads of the target power distribution network, including: in each training performed on the feedforward neural network, the sum of the known carbon emission values ​​and the sum of the transmitted electricity in a certain historical time interval are used as the output content of the feedforward neural network, and each distribution network data corresponding to each historical time interval of the target power distribution network before the certain historical time interval, each workload data corresponding to each historical time interval of the target power distribution network before the certain historical time interval, and multiple configuration contents of the target power distribution network are used as the input content of the feedforward neural network item by item to complete this training operation;

[0065] In this way, through the customized design of each training operation mentioned above, the training effect of each training operation of the feedforward neural network can be guaranteed, thereby providing guarantee for the reliability and stability of subsequent intelligent prediction results;

[0066] Wherein, when the received predicted carbon emission value is greater than the set carbon emission threshold, the number of workloads planned for the target power distribution network within the set time interval is reduced, including: when performing the reduction process, the workload with the lowest work priority is preferentially reduced;

[0067] Among them, obtaining each copy of distribution network data corresponding to each historical time interval of the target distribution network before the set time interval, and obtaining each copy of workload data corresponding to each historical time interval of the target distribution network before the set time interval, the number of each historical time interval is proportional to the routing length of the target distribution network, and also includes: the duration of each time interval in the set time interval and each historical time interval before the set time interval is equal, and the set time interval and each historical time interval before the set time interval together form a complete time segment on the time axis;

[0068] And wherein, multiple configuration contents of the target power distribution network are obtained, and the multiple configuration contents of the target power distribution network are the routing length, the number of cables arranged side by side, the total number of mounted loads and the distribution voltage data of the target power distribution network. The mounted loads include two types: working loads and non-working loads. The working loads are loads that distribute power to the target power distribution network and work through current, and the non-working loads are loads whose power distribution is cut off by the target power distribution network.

[0069] Second embodiment

[0070] Figure 3 The figure is a flowchart of the steps of a method for managing carbon emission data of a distribution network according to a second embodiment of the present invention.

[0071] like Figure 3 As shown, compared with Figure 2 , after step S15, the method further includes:

[0072] Step S16: When the received predicted transmission power is greater than the upper limit of safe power distribution power of the target power distribution network, the power over-limit warning action related to the set time interval is executed; and when the received predicted transmission power is less than or equal to the upper limit of safe power distribution power of the target power distribution network, the power over-limit warning action related to the set time interval is temporarily suspended;

[0073] For example, an optical alarm device may be selected to perform an optical warning action of power overlimit associated with a set time interval when the received predicted transmission power is greater than the upper limit of safe power distribution power of the target power distribution network;

[0074] Alternatively, an acoustic alarm device may be selected to execute an acoustic warning action for excessive power associated with a set time interval when the received predicted transmission power is greater than the upper limit of safe power distribution of the target power distribution network.

[0075] Third embodiment

[0076] Figure 4The figure is a flowchart of the steps of a method for managing carbon emission data of a distribution network according to a third embodiment of the present invention.

[0077] like Figure 4 As shown, compared with Figure 2 After step S13, the method further includes:

[0078] Step S17: completing the model storage of the carbon emission data prediction model by storing various model parameters of the carbon emission data prediction model;

[0079] For example, an MMC storage chip, a TF storage chip or a FLASH storage chip may be selected to complete the model storage of the carbon emission data prediction model by storing various model parameters of the carbon emission data prediction model;

[0080] Wherein, completing the model storage of the carbon emission data prediction model by storing various model parameters of the carbon emission data prediction model includes: allocating different physical storage addresses to various model parameters of the carbon emission data prediction model.

[0081] Fourth embodiment

[0082] Figure 5 This is a flowchart of the steps of a method for managing carbon emission data of a distribution network according to a fourth embodiment of the present invention.

[0083] like Figure 5 As shown, compared with Figure 2 , after step S15, the method further includes:

[0084] Step S18: wirelessly transmitting the load reduction strategy executed on the target power distribution network within a set time interval or the load maintenance strategy executed on the target power distribution network within a set time interval to a remote big data management node via a wireless communication network;

[0085] Alternatively, a cloud computing management node or a blockchain management node may be selected to wirelessly receive a load scale reduction strategy executed on the target power distribution network within a set time interval or a load scale maintenance strategy executed on the target power distribution network within a set time interval via a wireless communication network.

[0086] Fifth embodiment

[0087] Figure 6 This is a flowchart of the steps of a method for managing carbon emission data of a distribution network according to a fifth embodiment of the present invention.

[0088] like Figure 6 As shown, compared with Figure 2 After step S14, the method further includes:

[0089] Step S19: receiving the predicted carbon emission value and the predicted transmission power, and completing local display of the predicted carbon emission value and the predicted transmission power through an LED display array or an LCD display array;

[0090] Alternatively, a liquid crystal display screen may be selected to replace the LED display array or the LCD display array to display the predicted carbon emission value and the predicted transmission power separately locally.

[0091] Next, various embodiments of the present invention will be further described.

[0092] In each of the above embodiments, optionally, in the method for managing carbon emission data of a distribution network:

[0093] When performing the reduction processing, the workload with the lowest work priority is preferentially reduced, including: the work priority of the workload related to the food, clothing, housing and transportation of urban residents is higher than the work priority of the workload related to the entertainment of urban residents;

[0094] For example, when performing a specific reduction process, the work priority of workloads such as elevators and lighting equipment is higher than the work priority of workloads of entertainment facilities in entertainment venues;

[0095] Wherein, when the received predicted carbon emission value is less than or equal to the set carbon emission threshold, executing the mounting scale maintenance strategy for the target power distribution network within the set time interval includes: when the received predicted carbon emission value is less than or equal to the set carbon emission threshold, maintaining the number of workloads planned for the target power distribution network within the set time interval;

[0096] Among them, a set number of multiple trainings are performed on the feedforward neural network to obtain a feedforward neural network that has completed multiple trainings, and the feedforward neural network that has completed multiple trainings is output as a carbon emission data prediction model, and the value of the set number is positively correlated with the total number of mounted loads of the target distribution network, and also includes: the greater the total number of mounted loads of the target distribution network, the larger the value of the set number.

[0097] In each of the above embodiments, optionally, in the method for managing carbon emission data of a distribution network:

[0098] Acquiring each portion of distribution network data corresponding to each historical time interval of the target distribution network before the set time interval, and acquiring each portion of workload data corresponding to each historical time interval of the target distribution network before the set time interval, wherein the number of each historical time interval is proportional to the routing length of the target distribution network, further comprising: using a numerical conversion function to represent a numerical conversion relationship in which the number of each historical time interval is proportional to the routing length of the target distribution network;

[0099] Among them, the use of a numerical conversion function to express the numerical conversion relationship that the number of each historical time interval is proportional to the routing length of the target power distribution network includes: in the numerical conversion function, the routing length of the target power distribution network is the input parameter of the numerical conversion function, and the number of each historical time interval is the output parameter of the numerical conversion function.

[0100] And in each of the above embodiments, optionally, in the method for managing carbon emission data of the distribution network:

[0101] The carbon emission data prediction model is used to intelligently predict the total carbon emission value and the total transmission power of the target distribution network within the set time interval based on each distribution network data corresponding to each historical time interval of the target distribution network before the set time interval, each workload data corresponding to each historical time interval of the target distribution network before the set time interval, and multiple configuration contents of the target distribution network, and output them as the predicted carbon emission value and the predicted transmission power respectively, including: synchronously transmitting each distribution network data corresponding to each historical time interval of the target distribution network before the set time interval, each workload data corresponding to each historical time interval of the target distribution network before the set time interval, and multiple configuration contents of the target distribution network to the carbon emission data prediction model;

[0102] Specifically, the MATLAB toolbox may be selected as a numerical simulation mode to perform an intelligent prediction of the total carbon emission value and the total transmission power of the target distribution network within the set time interval using the carbon emission data prediction model based on each distribution network data corresponding to each historical time interval before the set time interval of the target distribution network, each workload data corresponding to each historical time interval before the set time interval, and multiple configuration contents of the target distribution network, and use the simulation and test of the data processing process of predicting the carbon emission value and predicting the transmission power output respectively;

[0103] The carbon emission data prediction model is used to intelligently predict the total carbon emission value and the total transmission power of the target distribution network within the set time interval based on each distribution network data corresponding to each historical time interval before the set time interval of the target distribution network, each workload data corresponding to each historical time interval before the set time interval, and multiple configuration contents of the target distribution network, and output them as the predicted carbon emission value and the predicted transmission power respectively, also including: executing the carbon emission data prediction model to obtain the total carbon emission value and the total transmission power of the target distribution network within the set time interval output by the carbon emission data prediction model.

[0104] In addition, in the method for managing carbon emission data of a distribution network according to the present invention:

[0105] Synchronously transmitting the copies of distribution network data corresponding to the respective historical time intervals of the target distribution network before the set time interval, the copies of workload data corresponding to the respective historical time intervals of the target distribution network before the set time interval, and multiple copies of configuration contents of the target distribution network to the carbon emission data prediction model, including: using a synchronization control component to complete the synchronous transmission of the copies of distribution network data corresponding to the respective historical time intervals of the target distribution network before the set time interval, the copies of workload data corresponding to the respective historical time intervals of the target distribution network before the set time interval, and multiple copies of configuration contents of the target distribution network to the carbon emission data prediction model;

[0106] Among them, synchronously transmitting each copy of distribution network data corresponding to each historical time interval of the target distribution network before the set time interval, each copy of workload data corresponding to each historical time interval of the target distribution network before the set time interval, and multiple configuration contents of the target distribution network to the carbon emission data prediction model also includes: performing numerical normalization processing on each copy of distribution network data corresponding to each historical time interval of the target distribution network before the set time interval, each copy of workload data corresponding to each historical time interval of the target distribution network before the set time interval, and multiple configuration contents of the target distribution network, and then synchronously transmitting them to the carbon emission data prediction model;

[0107] For example, performing numerical normalization processing on each copy of distribution network data corresponding to each historical time interval of the target distribution network before a set time interval, each copy of workload data corresponding to each historical time interval of the target distribution network before a set time interval, and multiple copies of configuration content of the target distribution network, and then synchronously transmitting them to the carbon emission data prediction model includes: performing octal numerical conversion processing on each copy of distribution network data corresponding to each historical time interval of the target distribution network before a set time interval, each copy of workload data corresponding to each historical time interval of the target distribution network before a set time interval, and multiple copies of configuration content of the target distribution network, and then synchronously transmitting them to the carbon emission data prediction model;

[0108] Wherein, executing the carbon emission data prediction model to obtain the sum of carbon emission values ​​and the sum of transmission power of the target distribution network within a set time interval output by the carbon emission data prediction model includes: the sum of carbon emission values ​​and the sum of transmission power of the target distribution network within a set time interval output by the carbon emission data prediction model are two values ​​represented after numerical normalization processing;

[0109] For example, the sum of carbon emission values ​​of the target distribution network within a set time interval and the sum of transmitted electricity output by the carbon emission data prediction model are two values ​​represented after numerical normalization processing, including: the sum of carbon emission values ​​of the target distribution network within a set time interval and the sum of transmitted electricity output by the carbon emission data prediction model are two values ​​represented after octal numerical conversion processing.

[0110] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0111] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device / electronic device / computer-readable storage medium / computer program product embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0112] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. A method for managing carbon emission data of a distribution network, characterized in that: The method comprises: Obtaining each portion of distribution network data corresponding to each historical time interval of the target distribution network before the set time interval, and obtaining each portion of workload data corresponding to each historical time interval of the target distribution network before the set time interval, wherein the number of each historical time interval is proportional to the routing length of the target distribution network, and the set time interval takes the current time as the starting time; Acquire multiple configuration contents of the target power distribution network, wherein the multiple configuration contents of the target power distribution network are the routing length, the number of cables arranged in parallel, the total number of mounted loads and distribution voltage data of the target power distribution network, and the mounted loads include two types: working load and non-working load; Performing a set number of multiple trainings on the feedforward neural network to obtain a feedforward neural network that has completed the multiple trainings, and outputting the feedforward neural network that has completed the multiple trainings as a carbon emission data prediction model, wherein the value of the set number is positively correlated with the total number of mounted loads of the target power distribution network; The carbon emission data prediction model is used to intelligently predict the total carbon emission value and the total transmission power of the target distribution network within the set time interval based on the distribution network data corresponding to each historical time interval before the set time interval, the workload data corresponding to each historical time interval before the set time interval, and multiple configuration contents of the target distribution network, and output them as the predicted carbon emission value and the predicted transmission power respectively; When the received predicted carbon emission value is greater than the set carbon emission threshold, a mounting scale reduction strategy is executed on the target power distribution network within a set time interval; when the received predicted carbon emission value is less than or equal to the set carbon emission threshold, a mounting scale maintenance strategy is executed on the target power distribution network within a set time interval; Wherein, when the received predicted carbon emission value is greater than the set carbon emission threshold, executing the mounting scale reduction strategy for the target power distribution network within the set time interval includes: when the received predicted carbon emission value is greater than the set carbon emission threshold, reducing the number of workloads planned for the target power distribution network within the set time interval; Among them, each copy of distribution network data corresponding to each historical time interval of the target distribution network before the set time interval is obtained, and each copy of workload data corresponding to each historical time interval of the target distribution network before the set time interval is obtained, and the number of each historical time interval is proportional to the routing length of the target distribution network, including: a single copy of distribution network data corresponding to each time interval is the sum of carbon emission values, total transmission power and active power information of the target distribution network in the time interval, and a single copy of workload data corresponding to each time interval is the number of workloads in the target distribution network in the time interval and the working current, working time and rated power of each workload; Among them, a set number of multiple trainings are performed on the feedforward neural network to obtain a feedforward neural network that has completed multiple trainings, and the feedforward neural network that has completed multiple trainings is output as a carbon emission data prediction model, and the value of the set number is positively correlated with the total number of mounted loads of the target power distribution network, including: in each training performed on the feedforward neural network, the sum of the known carbon emission values ​​and the sum of the transmitted electricity in a certain historical time interval are used as the output content of the feedforward neural network, and each distribution network data corresponding to each historical time interval of the target power distribution network before the certain historical time interval, each workload data corresponding to each historical time interval of the target power distribution network before the certain historical time interval, and multiple configuration contents of the target power distribution network are used as the input content of the feedforward neural network item by item to complete this training operation; Wherein, when the received predicted carbon emission value is greater than the set carbon emission threshold, the number of workloads planned for the target power distribution network within the set time interval is reduced, including: when performing the reduction process, the workload with the lowest work priority is preferentially reduced; When performing the reduction processing, the workload with the lowest work priority is preferentially reduced, including: the work priority of the workload related to the food, clothing, housing and transportation of urban residents is higher than the work priority of the workload related to the entertainment of urban residents; Wherein, when the received predicted carbon emission value is less than or equal to the set carbon emission threshold, executing the mounting scale maintenance strategy for the target power distribution network within the set time interval includes: when the received predicted carbon emission value is less than or equal to the set carbon emission threshold, maintaining the number of workloads planned for the target power distribution network within the set time interval; Among them, a set number of multiple trainings are performed on the feedforward neural network to obtain a feedforward neural network that has completed multiple trainings, and the feedforward neural network that has completed multiple trainings is output as a carbon emission data prediction model, and the value of the set number is positively correlated with the total number of mounted loads of the target distribution network, and also includes: the greater the total number of mounted loads of the target distribution network, the larger the value of the set number.

2. The method for managing carbon emission data of a distribution network according to claim 1, characterized in that: Obtaining each portion of distribution network data corresponding to each historical time interval of the target distribution network before the set time interval, and obtaining each portion of workload data corresponding to each historical time interval of the target distribution network before the set time interval, wherein the number of each historical time interval is proportional to the routing length of the target distribution network and further comprising: the duration of each time interval in the set time interval and each historical time interval before the set time interval is equal, and the set time interval and each historical time interval before the set time interval together form a complete time segment on the time axis; Among them, multiple configuration contents of the target power distribution network are obtained, and the multiple configuration contents of the target power distribution network are the routing length, the number of cables arranged side by side, the total number of mounted loads and the distribution voltage data of the target power distribution network. The mounted loads include two types: working loads and non-working loads. The working loads are loads that distribute power to the target power distribution network and work through current, and the non-working loads are loads whose power distribution is cut off by the target power distribution network.

3. The method for managing carbon emission data of a distribution network according to claim 2, characterized in that: When the received predicted carbon emission value is greater than the set carbon emission threshold, a mounting scale reduction strategy is executed on the target power distribution network within a set time interval; when the received predicted carbon emission value is less than or equal to the set carbon emission threshold, a mounting scale maintenance strategy is executed on the target power distribution network within a set time interval, the method further includes: When the received predicted transmission power is greater than the upper limit of the safe distribution power of the target distribution network, the power over-limit warning action related to the set time interval is executed; and when the received predicted transmission power is less than or equal to the upper limit of the safe distribution power of the target distribution network, the power over-limit warning action related to the set time interval is temporarily suspended.

4. The method for managing carbon emission data of a distribution network according to claim 2, characterized in that: After performing a set number of multiple trainings on the feedforward neural network to obtain a feedforward neural network that has completed the multiple trainings, and outputting the feedforward neural network that has completed the multiple trainings as a carbon emission data prediction model, and the value of the set number is positively correlated with the total number of mounted loads of the target power distribution network, the method further includes: The model storage of the carbon emission data prediction model is completed by storing various model parameters of the carbon emission data prediction model; Wherein, completing the model storage of the carbon emission data prediction model by storing various model parameters of the carbon emission data prediction model includes: allocating different physical storage addresses to various model parameters of the carbon emission data prediction model.

5. The method for managing carbon emission data of a distribution network according to claim 2, characterized in that: When the received predicted carbon emission value is greater than the set carbon emission threshold, a mounting scale reduction strategy is executed on the target power distribution network within a set time interval; when the received predicted carbon emission value is less than or equal to the set carbon emission threshold, a mounting scale maintenance strategy is executed on the target power distribution network within a set time interval, the method further includes: The mounting scale reduction strategy executed on the target power distribution network within a set time interval or the mounting scale maintenance strategy executed on the target power distribution network within a set time interval is wirelessly transmitted to a remote big data management node via a wireless communication network.

6. The method for managing carbon emission data of a distribution network according to claim 2, characterized in that: After adopting the carbon emission data prediction model to intelligently predict the total carbon emission value and the total transmission power of the target distribution network within the set time interval based on each distribution network data corresponding to each historical time interval of the target distribution network before the set time interval, each workload data corresponding to each historical time interval of the target distribution network before the set time interval, and multiple configuration contents of the target distribution network, and outputting them as the predicted carbon emission value and the predicted transmission power respectively, the method further includes: The predicted carbon emission value and the predicted transmission power are received, and the predicted carbon emission value and the predicted transmission power are displayed locally and separately through an LED display array or an LCD display array.

7. The method for managing carbon emission data of a distribution network according to any one of claims 2 to 6, characterized in that: Acquiring each portion of distribution network data corresponding to each historical time interval of the target distribution network before the set time interval, and acquiring each portion of workload data corresponding to each historical time interval of the target distribution network before the set time interval, wherein the number of each historical time interval is proportional to the routing length of the target distribution network, further comprising: using a numerical conversion function to represent a numerical conversion relationship in which the number of each historical time interval is proportional to the routing length of the target distribution network; Among them, the use of a numerical conversion function to express the numerical conversion relationship that the number of each historical time interval is proportional to the routing length of the target power distribution network includes: in the numerical conversion function, the routing length of the target power distribution network is the input parameter of the numerical conversion function, and the number of each historical time interval is the output parameter of the numerical conversion function.

8. The method for managing carbon emission data of a distribution network according to any one of claims 2 to 6, characterized in that: The carbon emission data prediction model is used to intelligently predict the total carbon emission value and the total transmission power of the target distribution network within the set time interval based on each distribution network data corresponding to each historical time interval of the target distribution network before the set time interval, each workload data corresponding to each historical time interval of the target distribution network before the set time interval, and multiple configuration contents of the target distribution network, and output them as the predicted carbon emission value and the predicted transmission power respectively, including: synchronously transmitting each distribution network data corresponding to each historical time interval of the target distribution network before the set time interval, each workload data corresponding to each historical time interval of the target distribution network before the set time interval, and multiple configuration contents of the target distribution network to the carbon emission data prediction model; The carbon emission data prediction model is used to intelligently predict the total carbon emission value and the total transmission power of the target distribution network within the set time interval based on each distribution network data corresponding to each historical time interval before the set time interval of the target distribution network, each workload data corresponding to each historical time interval before the set time interval, and multiple configuration contents of the target distribution network, and output them as the predicted carbon emission value and the predicted transmission power respectively, also including: executing the carbon emission data prediction model to obtain the total carbon emission value and the total transmission power of the target distribution network within the set time interval output by the carbon emission data prediction model.

Images