CN116796906A - Electric power distribution network investment prediction analysis system and method based on data fusion - Google Patents
Electric power distribution network investment prediction analysis system and method based on data fusion Download PDFInfo
- Publication number
- CN116796906A CN116796906A CN202310825363.8A CN202310825363A CN116796906A CN 116796906 A CN116796906 A CN 116796906A CN 202310825363 A CN202310825363 A CN 202310825363A CN 116796906 A CN116796906 A CN 116796906A
- Authority
- CN
- China
- Prior art keywords
- distribution network
- power distribution
- investment
- equipment
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000009826 distribution Methods 0.000 title claims abstract description 354
- 238000000034 method Methods 0.000 title claims abstract description 36
- 238000004458 analytical method Methods 0.000 title claims abstract description 35
- 230000004927 fusion Effects 0.000 title claims abstract description 23
- 238000011156 evaluation Methods 0.000 claims abstract description 44
- 238000013075 data extraction Methods 0.000 claims abstract description 28
- 238000005457 optimization Methods 0.000 claims abstract description 20
- 230000008439 repair process Effects 0.000 claims description 137
- 238000000605 extraction Methods 0.000 claims description 53
- 238000010276 construction Methods 0.000 claims description 36
- 238000009825 accumulation Methods 0.000 claims description 27
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000007621 cluster analysis Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 17
- 238000012549 training Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 8
- 238000007726 management method Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- 238000012795 verification Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 239000000203 mixture Substances 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000009472 formulation Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000009960 carding Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000004138 cluster model Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000011234 economic evaluation Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000002407 reforming Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses an electric power distribution network investment prediction analysis system and method based on data fusion, belonging to the field of intelligent power grids, wherein the method comprises the following steps: acquiring power distribution network feedback data of a target area, inputting the feedback data into a feedback data extraction module, and generating a first configuration constraint; collecting operation information of the power equipment, analyzing the residual life of the power equipment, and generating a second configuration constraint; acquiring basic configuration information and expected information of a power distribution network, and generating a plurality of power distribution network investment schemes; and acquiring an investment scheme evaluation index set, and carrying out double-channel optimization on a plurality of power distribution network investment schemes according to the first configuration constraint and the second configuration constraint and the investment scheme evaluation index set to acquire an optimal power distribution network investment scheme as a power distribution network investment prediction analysis result. The method solves the technical problems of low accuracy and reliability of the investment prediction result of the power distribution network in the prior art, and achieves the technical effect of improving the accuracy and reliability of the investment prediction of the power distribution network based on data fusion.
Description
Technical Field
The application relates to the field of smart grids, in particular to a system and a method for predicting and analyzing investment of an electric power distribution network based on data fusion.
Background
With the deep promotion of the market reform of the electric power industry and the continuous expansion of the new energy access scale, the power distribution network is taken as an important component of an electric power system, and the investment scale and the investment accuracy become the main parts of the construction of the power distribution network.
At present, a method based on historical power distribution network fault statistics is often adopted for power distribution network investment prediction analysis, the type of faults and the number of faults which possibly occur in a period of time in the future are predicted by analyzing historical fault data, and power distribution network investment planning is conducted accordingly. However, such methods only consider historical fault data, and do not fully and comprehensively consider the operation state, life curve and latest maintenance information of the power equipment, so that it is difficult to accurately judge the actual operation state and future maintenance requirements of the power equipment.
Disclosure of Invention
The application provides a system and a method for predicting and analyzing investment of an electric power distribution network based on data fusion, and aims to solve the technical problems of low accuracy and reliability of a power distribution network investment prediction result in the prior art.
In view of the above problems, the application provides a system and a method for predicting and analyzing investment of an electric power distribution network based on data fusion.
In a first aspect of the disclosure, an electric power distribution network investment prediction analysis system based on data fusion is provided, the system comprising: the power grid feedback data module is used for acquiring power distribution network feedback data of the target area in a historical time window, wherein the power distribution network feedback data comprise equipment repair information and user complaint information; the first configuration constraint module is used for inputting the equipment repairing information and the user complaint information into the feedback data extraction module and generating a first configuration constraint according to the extracted data; the second configuration constraint module is used for collecting the operation information of the power equipment in the target area, analyzing the residual life of the power equipment by using the damage accumulation model and generating a second configuration constraint; the investment scheme generation module is used for acquiring the basic configuration information of the power distribution network and the expected information of the power distribution network in the target area in real time and generating a plurality of power distribution network investment schemes; the double-channel optimizing module is used for acquiring an investment scheme evaluation index set, and carrying out double-channel optimizing according to the first configuration constraint, the second configuration constraint, the investment scheme evaluation index set and the multiple distribution network investment schemes to acquire an optimal distribution network investment scheme; and the prediction analysis result module is used for taking the optimal distribution network investment scheme as a distribution network investment prediction analysis result.
In another aspect of the disclosure, a method for predicting and analyzing investment of an electric power distribution network based on data fusion is provided, and the method comprises the following steps: acquiring power distribution network feedback data of a target area in a historical time window, wherein the power distribution network feedback data comprises equipment repair information and user complaint information; inputting the equipment repairing information and the user complaint information into a feedback data extraction module, and generating a first configuration constraint according to the extracted data; collecting operation information of the power equipment in the target area, and analyzing the residual life of the power equipment by using the damage accumulation model to generate a second configuration constraint; acquiring basic configuration information and expected information of a power distribution network of a target area in real time, and generating a plurality of power distribution network investment schemes; acquiring an investment scheme evaluation index set, and performing double-channel optimization according to the first configuration constraint, the second configuration constraint, the investment scheme evaluation index set and a plurality of power distribution network investment schemes to acquire an optimal power distribution network investment scheme; and taking the optimal power distribution network investment scheme as a power distribution network investment prediction analysis result.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
Because the power distribution network feedback data of the target area in the historical time window is obtained, equipment repair information and user complaint information are input into a feedback data extraction module, and a first configuration constraint is generated; collecting operation information of the power equipment in the target area, analyzing the residual life of the power equipment by using the damage accumulation model, and generating a second configuration constraint; acquiring basic configuration information and expected information of a power distribution network in a target area, and generating a plurality of power distribution network investment schemes; acquiring an investment scheme evaluation index set, and carrying out double-channel optimization on a plurality of power distribution network investment schemes according to a first configuration constraint, a second configuration constraint and the investment scheme evaluation index set to acquire an optimal power distribution network investment scheme; and the optimal power distribution network investment scheme is used as a technical scheme of a power distribution network investment prediction analysis result, so that the technical problem of low accuracy and reliability of the power distribution network investment prediction result in the prior art is solved, and the technical effect of improving the accuracy and reliability of the power distribution network investment prediction based on data fusion is achieved.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
Fig. 1 is a schematic diagram of a possible flow of an electric power distribution network investment prediction analysis method based on data fusion according to an embodiment of the present application;
fig. 2 is a schematic flow chart of a possible construction time index generation in the method for predicting and analyzing investment of an electric power distribution network based on data fusion according to an embodiment of the present application;
fig. 3 is a schematic flow chart of a possible process for obtaining a first distribution network investment score in a method for predicting and analyzing investment of an electric distribution network based on data fusion according to an embodiment of the present application;
fig. 4 is a schematic diagram of a possible structure of an electric power distribution network investment prediction analysis system based on data fusion according to an embodiment of the present application.
Reference numerals illustrate: the system comprises a power grid feedback data module 11, a first configuration constraint module 12, a second configuration constraint module 13, an investment scheme generation module 14, a two-channel optimizing module 15 and a prediction analysis result module 16.
Detailed Description
The technical scheme provided by the application has the following overall thought:
the embodiment of the application provides an electric power distribution network investment prediction analysis system and method based on data fusion. Firstly, feedback data of a power distribution network of a target area in a historical time window, including equipment repair information and user complaint information, are acquired, and are input into a feedback data extraction module to generate a first configuration constraint. Meanwhile, operation information of the power equipment in the target area is collected, and the damage accumulation model is utilized to analyze the residual life of the power equipment, so that a second configuration constraint is generated. And then, acquiring basic configuration information and expected information of the power distribution network in the target area, and generating a plurality of power distribution network investment schemes. And finally, acquiring an investment scheme evaluation index set, and carrying out double-channel optimization on a plurality of power distribution network investment schemes according to the first configuration constraint, the second configuration constraint and the investment scheme evaluation index set to acquire an optimal power distribution network investment scheme.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
Example 1
As shown in fig. 1, the embodiment of the application provides a method for predicting and analyzing investment of an electric power distribution network based on data fusion, which comprises the following steps:
step S100: acquiring power distribution network feedback data of a target area in a historical time window, wherein the power distribution network feedback data comprises equipment repair information and user complaint information;
specifically, the power distribution network feedback data refers to various information feedback generated in the operation process of the power distribution network, and is used for reflecting the operation condition of the power distribution network, including equipment repair information and user complaint information. The equipment repair information refers to repair information generated when the power distribution equipment fails or is abnormal in the operation process, and comprises equipment failure types, occurrence time, a processing scheme and the like; the equipment repair information is collected and obtained through the equipment repair information management system and is used for evaluating the reliability of the power distribution network equipment. The user complaint information assigns complaint information generated by a power grid user in the process of using the power service, wherein the complaint information comprises a user name, a user address, complaint items, complaint time and the like; user complaint information is collected and obtained through a user service management system and is used for evaluating satisfaction of power distribution services.
By acquiring the feedback data of the power distribution network in the historical time window of the target area, the running condition of the power distribution network in the area can be comprehensively known, the establishment of an investment scheme is facilitated to be more practical, and the accuracy of the investment of the power distribution network is improved.
Step S200: inputting the equipment repairing information and the user complaint information into a feedback data extraction module, and generating a first configuration constraint according to the extracted data;
specifically, the feedback data extraction module is a module for analyzing and processing equipment repair information and user complaint information, and performs differential selection and dimension reduction on the feedback data to obtain data related to power distribution network investment as a first configuration constraint. The first configuration constraint refers to a constraint used to constrain and guide the formulation of the investment plan for the distribution network.
Firstly, cleaning data of equipment repair information and user complaint information, deleting invalid and repeated data, and keeping the accuracy and consistency of the data; then, selecting the attribute related to the investment of the power distribution network, such as equipment repair type, repair address, user complaint reason and the like, as the characteristic attribute, and constructing an input data set of a feedback data extraction module; then, setting parameters of a feedback data extraction module, such as a support degree and a confidence degree threshold, wherein the support degree threshold is used for filtering out infrequently occurring data, and the confidence degree threshold is used for evaluating the association strength between frequent data; the input data set is input into a feedback data extraction module, and frequent data and association rules thereof are detected by using association rule analysis and other data mining technologies, such as { power supply line faults } → { power supply line enhancement }, and other rules. And then judging the importance and rationality of the association rule, and selecting the rule with the largest investment relevance with the power distribution network to form a first configuration constraint.
By carrying out differential selection on equipment repair information and user complaint information, dimension reduction of the feedback data to the first configuration constraint is realized, important references are provided for follow-up power distribution network investment scheme optimization, and accuracy of investment decisions is facilitated.
Step S300: collecting operation information of the power equipment in the target area, and analyzing the residual life of the power equipment by using the damage accumulation model to generate a second configuration constraint;
specifically, the operation information of the power equipment refers to information generated in the operation process of various power equipment such as transformers, circuit breakers, power supply lines and the like of a power grid, such as operation parameters, load data, operation time and the like, and the operation condition and loss condition of the equipment are represented. The damage accumulation model calculates the current loss degree and the residual life of the equipment through the accumulated running time and the parameters of the equipment and the life parameter. The second configuration constraint refers to residual life data of the power equipment, which is obtained based on an analysis result of the damage accumulation model, and limits indexes or principles to be followed by the investment scheme of the power distribution network in equipment type selection and replacement, so that the investment scheme is ensured to select the power equipment with enough residual life, and the requirement of long-term reliable operation of the power distribution network is met.
Firstly, selecting power equipment related to investment of a power distribution network, such as a transformer, a circuit breaker, a power supply line and the like, wherein the service life and replacement of the equipment can directly influence the operation of the power distribution network; secondly, a data acquisition system is deployed to acquire information such as operation parameters, load data, accumulated operation time and the like of the selected equipment in real time; then, acquiring manufacturing information and expected use parameters of the equipment, such as expected service life, standard operation parameter range and the like, as basic data input by a model; then, selecting a Miner model and an IEC model as damage accumulation models, and estimating the current loss degree and the residual life based on historical use and manufacturing parameters of the equipment; next, the collected operation information and device manufacturing information are input into a damage accumulation model, and the degree of loss and the remaining life of each device are calculated as second configuration constraints.
And the second configuration constraint is obtained by collecting the operation information of the power equipment and analyzing the residual life condition of the equipment by using the damage accumulation model, so that the residual effective degree of each equipment in the power distribution network investment scheme is ensured, and the long-term reliability and stability of the power distribution network are improved.
Step S400: acquiring basic configuration information and expected information of a power distribution network of a target area in real time, and generating a plurality of power distribution network investment schemes;
Specifically, the basic configuration information of the distribution network refers to basic composition and configuration of an existing distribution network in a target area, and includes detailed information such as specific number, model number, parameters and the like of substations, distribution equipment, power supply lines and the like in the area, which serve as basic conditions and preconditions for generating an investment scheme of the distribution network. The expected information of the power distribution network refers to expected requirements of a target area on power supply capacity and service quality of the power distribution network in a certain time, such as power supply quantity, power supply reliability index, power supply efficiency and the like to be achieved, and design targets and standards are provided for generating a power distribution network investment scheme. The distribution network investment scheme is a distribution network upgrading and reforming scheme which is provided for meeting the basic configuration information and the expected information of the regional distribution network.
Firstly, acquiring the existing basic configuration information of the power distribution network in a target area, such as detailed information of the capacity and the number of substations, the types and the number of power distribution equipment, the length and the specification of a power supply line and the like, and the latest configuration information of the power distribution network. And secondly, predicting the power supply demand of the target area within 3-5 years in the future by adopting a power supply load prediction technology of the power distribution network, and taking the prediction result as the power supply quantity requirement in the expected information of the power distribution network. Then, based on the basic configuration information and the expected information of the power distribution network, various power distribution network investment schemes are proposed to meet power supply requirements, such as a newly built transformer station scheme, an extended power supply line scheme, a power distribution equipment updating scheme and the like.
The method comprises the steps of obtaining detailed information and future development expectations of an existing power distribution network in a target area, forming basic configuration information and expected information of the power distribution network, generating various power distribution network investment schemes based on the two aspects of information, and providing options and bases for subsequent scheme selection and decision analysis.
Step S500: acquiring an investment scheme evaluation index set, and performing double-channel optimization according to the first configuration constraint, the second configuration constraint, the investment scheme evaluation index set and a plurality of power distribution network investment schemes to acquire an optimal power distribution network investment scheme;
specifically, the investment scheme evaluation index set is an evaluation index for evaluating and comparing the merits of various power distribution network investment schemes, including an operation cost index, an operation economy index and a construction time index, and the indexes provide criteria for selecting an optimal investment scheme. The double-channel optimizing refers to that in the process of selecting an optimal power distribution network investment scheme, two factors of improving the power supply reliability and the power supply efficiency of a power distribution network system and improving the user satisfaction are considered at the same time, so that the optimization in two directions of technology and user satisfaction is realized.
Firstly, from the aspects of management and decision-making of the investment schemes of the power distribution network, main attributes of an evaluation scheme, such as economic performance, power supply reliability, construction time and the like, are determined; determining quantitative or qualitative evaluation indexes for each attribute; and (3) weighting each index, determining the relative importance degree of the index in overall evaluation, and further confirming the evaluation index set of the investment scheme of the power distribution network. Then, two large channels in the optimization program are determined, wherein one channel is a power distribution network engineering technical index, and the other channel is user satisfaction. Then, constructing a multi-attribute decision model in the engineering technical channel, taking the first configuration constraint and the second configuration constraint as constraint conditions, taking the technical economic evaluation index as attributes, and calculating the scores of all schemes on the attributes to obtain the technical sequence of the schemes; and evaluating the improving effect of each scheme on the power supply and the service quality of the user in the user satisfaction channel to obtain the user satisfaction ranking of the schemes. And then comparing the evaluation results of the two channels, and finding out an investment scheme which is better in performance on both channels as an optimal power distribution network investment scheme.
By acquiring evaluation indexes of the investment schemes of the power distribution network and carrying out double-channel optimization on multiple schemes based on related constraint conditions and indexes, the selection of the optimal investment schemes on two levels of power distribution network engineering technology and user satisfaction is realized, the optimal investment schemes of the power distribution network can reach the optimal balance on two aspects of technology and user satisfaction, and the accuracy and reliability of the investment prediction of the power distribution network are improved.
Step S600: and taking the optimal power distribution network investment scheme as a power distribution network investment prediction analysis result.
Specifically, the optimal power distribution network investment scheme is to achieve optimal balance in two aspects of technical indexes and user satisfaction, and can meet the power distribution network construction requirement and the user power use requirement to the greatest extent under the condition of limited investment. Firstly, according to an optimal power distribution network investment scheme, the technical design of a refinement scheme is adopted, such as determining the new or updated specific equipment model and parameters, the specific routing route of a power line, a special standard and the like; secondly, compiling investment estimation and benefit analysis reports of the scheme, including all investment contents and investment amount predictions implemented by the scheme and technical and economic benefit analysis achieved after implementation; then, an implementation schedule of the scheme and an implementation scheme, which schedule implementation contents of the scheme according to time sequence, are established, wherein the implementation scheme is a technical detail and a management key point in the implementation process. And then, predicting and analyzing the running condition of the power distribution network after the implementation of the scheme, including aspects of power supply reliability, operation cost, user satisfaction and the like. The method can verify the effect of the optimal power distribution network investment scheme and provide reference for power distribution network operation after scheme implementation. And then, various resources required by the implementation of the carding scheme, such as equipment purchasing list, construction contract list, personnel and expense budget required by project operation and the like, form a final power distribution network investment prediction analysis report.
The optimal power distribution network investment scheme selected through technical analysis is output as the final result of the method, references are provided for power distribution network investment decision and project implementation, the purpose of power distribution network investment prediction analysis is achieved, and the technical effect of improving the accuracy and reliability of power distribution network investment prediction based on data fusion is achieved.
Further, the embodiment of the application further comprises:
step S210: acquiring a sample equipment repair information set and a sample user complaint information set of a target area;
step S220: performing cluster analysis on the sample equipment repair information set by using an equipment repair type to obtain P pieces of equipment repair cluster information sets, wherein P is the type of equipment repair;
step S230: calculating interval time nodes based on the P equipment repair cluster information sets to obtain a first extraction coefficient and a first background extraction coefficient;
step S240: repairing and extracting branches according to equipment constructing a feedback data extraction module;
step S250: constructing complaint extraction branches of a feedback data extraction module according to the sample user complaint information set;
step S260: respectively inputting the equipment repairing information and the user complaint information into a feedback data extraction module for information extraction;
Step S270: and setting the information extraction result satisfied by the power distribution network investment scheme as a first configuration constraint.
Specifically, the sample equipment repair information set refers to a representative equipment repair information sample selected in the target area, and reflects the main type and characteristics of equipment repair in the area. The sample user complaint information set refers to a representative user complaint information sample selected in a target area, and reflects main complaints and satisfaction of users on regional power distribution service. And consulting an equipment report and repair management system and a user complaint management system of the target area in the last 3-5 years to obtain a sample equipment report and repair record and a sample user complaint record.
And determining the classification of equipment repair, such as overload, short circuit, fire, shutdown and the like, reading each repair record in the sample equipment repair information set, analyzing the repair content and reasons of the repair record, and judging which equipment repair type the record belongs to. And further analyzing the report record of the report type of each device, extracting the information such as the name, the report part, the report specific reason and the like of the report device, and forming the characteristic information of the report type of the device for clustering calculation. And constructing a device repair type clustering model by using k-means clustering, inputting characteristic information of each device repair type by the model, and outputting the characteristic information as a clustering type to which the device repair record belongs. And setting the number P of the clustering categories according to the stability of the equipment report type and the calculated amount of the model, wherein the P is the number of the equipment report type, and is preferably set to 3-8 clustering categories. And distributing the sample equipment repair records to P cluster categories according to the calculation result of the cluster model, wherein each cluster category comprises repair records of a certain equipment repair type, and obtaining P equipment repair cluster information sets.
And analyzing the time distribution rule of the report records in the report cluster information set of each device, calculating the average interval time T of the report of the type of device, and predicting the possible occurrence times of the report of the type of device in a certain time window in the future of the target area according to the historical time window length and the average interval time T. The future time window is divided into N sections, each section has a time length of T, and the N sections form interval time nodes of the equipment repair type. Then, each report record in the cluster information set is analyzed, and the importance of the record in all report records of the report type of the equipment to which the record belongs is calculated. And calculating a first extraction coefficient according to the importance of all repair records in the cluster information set, and judging whether the information belongs to the key information. And calculating a first background extraction coefficient according to the repair records with lower importance, wherein the first background extraction coefficient represents the duty ratio of the secondary information in the whole information and is used for filtering the secondary information.
Then, constructing equipment repair extraction branches of a feedback data extraction module according to the P pieces of equipment repair cluster information sets, wherein the equipment repair extraction branches are used for extracting key information related to power distribution network investment from a large amount of equipment repair information; and constructing complaint extraction branches of a feedback data extraction module according to the sample user complaint information set, wherein the complaint extraction branches are used for extracting key information related to power distribution network investment from a large amount of user complaint information. And then, the actually acquired equipment repairing information and the user complaint information are respectively input into an equipment repairing extraction branch and a complaint extraction branch of the feedback data extraction module to extract information. And setting the key information generated by the extraction result as a first configuration constraint which is satisfied by the power distribution network investment scheme.
The method comprises the steps of obtaining sample equipment repair information and user complaint information, constructing two branches of a feedback data extraction module, inputting the obtained actual equipment repair information and user complaint information into the branches for processing, extracting key information related to power distribution network investment, forming a first configuration constraint on an investment scheme, and guiding the formulation of the scheme.
Further, the embodiment of the application further comprises:
step S231: randomly selecting a device repair type corresponding to one cluster from the P device repair cluster information sets without returning to the P device repair cluster information sets as a first device repair type, and acquiring the first device repair cluster information set based on the first device repair type;
step S232: calculating interval time nodes based on the first equipment repair cluster information set to obtain a first maximum interval time node and a first minimum interval time node;
step S233: the equipment report repair type corresponding to one cluster is selected randomly from the P equipment report repair cluster information sets again and is not replaced again to serve as a second equipment report repair type, and a second maximum interval time node and a second minimum interval time node are obtained;
step S234: the equipment report repair type corresponding to one cluster is selected randomly from the P equipment report repair cluster information sets again and is not replaced, and the P maximum interval time node and the P minimum interval time node are obtained;
Step S235: obtaining a maximum interval time node set according to the first maximum interval time node, the second maximum interval time node and the P maximum interval time node, and obtaining a minimum interval time node set according to the first minimum interval time node, the second minimum interval time node and the P minimum interval time node;
step S236: a first extraction coefficient and a first background extraction coefficient are obtained based on the maximum interval time node set and the minimum interval time node set.
Specifically, one equipment repair type is randomly selected from the P equipment repair cluster information sets, a corresponding first equipment repair cluster information set is obtained, and after one repair type is selected, the repair type is deleted from the P equipment repair cluster information sets. And then, analyzing all the report records in the report and repair cluster information set of the first equipment, and counting the time point of each report and repair record to obtain a report and repair time sequence. And searching a first maximum interval time node and a first minimum interval time node between two latest repair time points in the repair time sequence. And then randomly selecting one equipment repair type from the P equipment repair cluster information sets again to obtain a second maximum interval time node and a second minimum interval time node of the equipment repair cluster information sets corresponding to the equipment repair type. And repeatedly and randomly selecting P equipment repair types to obtain P maximum interval time nodes and P minimum interval time nodes. Forming a maximum interval time node set according to the selected maximum interval time node of each equipment repair type; and forming a minimum interval time node set according to the minimum interval time nodes.
And then, calculating the deviation between each time node in the maximum and minimum interval time node sets and the average time interval to obtain Δtmax and Δtmin. Next, a first extraction coefficient α, α=Δtmax+ε, ε is determined as a preset parameter, for example, 30% of Δtmax, and time deviation corresponding information exceeding α is extracted as key information. The first background extraction coefficient β, β=α - Δtmin is determined, and the time deviation correspondence information between α and β is extracted as the secondary information. Alpha and beta are respectively used as the FAST network of the SLOWFAST network and the information extraction threshold value of the SLOW network, wherein the FAST network extracts key information exceeding alpha; the SLOW network extracts secondary information between alpha and beta.
The time interval nodes of the types are obtained by randomly selecting the equipment repair type, the first extraction coefficient and the first background extraction coefficient are obtained based on the concentration condition of the time interval nodes, and a basic rule is provided for the key information extraction of the equipment repair information so as to more accurately realize the dimension reduction and extraction of the information.
Further, the embodiment of the application further comprises:
step S310: extracting service life information from the operation information of the power equipment in the target area to obtain operation duration information of a plurality of pieces of equipment;
Step S320: inputting the operation duration information of the plurality of devices into the damage accumulation model to calculate the residual life, and obtaining the residual life of the plurality of devices;
step S330: setting a plurality of power equipment in a power distribution network investment scheme to have a service life less than the remaining service life of the plurality of equipment as the second configuration constraint;
wherein, the damage accumulation model is:
wherein F is ileft For the remaining life, t, of the ith power device i For the device operation duration of the ith power device, T i For the operation estimated time length of the ith power equipment, T 0 And i is the number of the power equipment in the target area and is equal to or more than 1 for the operation life of the ith power equipment.
Specifically, equipment operation time length information is extracted from historical power equipment operation information in a target area, and operation time length data of a plurality of pieces of equipment are obtained. The plurality of equipment operation duration information refers to historical operation time data of a plurality of electric equipment in a target area, reflects the service condition and the loss condition of the equipment, and provides input for calculating the residual life of the equipment by using the damage accumulation model.
And inputting the operation time length information of the plurality of devices into the damage accumulation model, and calculating to obtain the residual life of the plurality of devices. The plurality of device remaining lives refers to a remaining life predicted by a plurality of power devices in the target area based on the historical operating data. The calculation of the remaining life depends on a damage accumulation model, which is a statistical model for estimating the remaining life of the electrical equipment, and the model calculates the remaining life of the equipment by using a damage accumulation function according to the operation duration and the design working life of the equipment. The preferred damage accumulation model is: Wherein F is ileft For the remaining life, t, of the ith power device i For the device operation duration of the ith power device, T i For the operation estimated time length of the ith power equipment, T 0 And i is the number of the power equipment in the target area and is equal to or more than 1 for the operation life of the ith power equipment. Firstly, determining the types and the quantity of the power equipment in a target area, such as substation equipment, power lines and the like, and obtaining an equipment type list and quantity i; consult the list of device types to obtain the normal service life T of each type of device 0 Obtaining and counting the current service life T of each device from the inquiry of the production parameters of the device i The method comprises the steps of carrying out a first treatment on the surface of the Referring to the operation information of each device in the target area, and counting to obtain the historical operation time t of each device i The method comprises the steps of carrying out a first treatment on the surface of the Life T of equipment i And an operation time t i Inputting the damage accumulation model, and calculating to obtain the residual life F of the ith equipment ileft . Then, the equipment with the design service life of the power equipment which is related in the power distribution network investment scheme and is smaller than the residual service life of the corresponding equipment is included into the second configuration constraint, and when the power distribution network investment scheme is manufactured, the scheme needs to meet the second configuration constraint, so that the opposite equipment is causedIs ready for reasonable evaluation of formation.
The method comprises the steps of calculating the residual service life of equipment by obtaining the operation time length data of the power equipment in a target area and adopting a damage accumulation model, defining a second configuration constraint of a power distribution network investment scheme according to a comparison result of the equipment service life and the residual service life, providing equipment updating requirement judgment for making the investment scheme, and improving the accuracy and reliability of the scheme.
Further, as shown in fig. 2, the embodiment of the present application further includes:
step S510: constructing an investment scheme evaluation index set, wherein the investment scheme evaluation index set comprises an operation cost index, an operation economy index and a construction time index;
step S520: generating an operation cost index according to the equipment type, the equipment number and the length of a paved line;
step S530: generating an operation economical index according to the distribution efficiency and the load of the distribution network;
step S540: and generating a construction time index according to the line laying time, the equipment purchasing time and the equipment adding time.
Specifically, an investment scheme evaluation index set is constructed and used for evaluating the technical and economic effects of the investment scheme of the power distribution network. The investment scheme evaluation index set comprises an operation cost index, an operation economy index and a construction time index. The operation cost index reflects the operation cost of the power distribution network after the implementation of the investment scheme, including labor cost, maintenance cost, energy consumption cost and the like; the operation economy index reflects the technical economy effect of the power distribution network after the investment scheme is implemented, such as power distribution efficiency, power distribution network load rate and the like; the construction time index reflects the engineering quantity and implementation difficulty of the investment scheme, and comprises equipment purchasing period, line laying period, equipment installation period and the like.
Referring to the unit cost information of the equipment and the circuit to obtain unit cost data of the equipment and the circuit; the total cost of each type of equipment and line in the scheme is calculated based on the type and number of equipment involved in the investment scheme, and the length of the line. And referring to service life data of related equipment and circuits, calculating the updating times of each equipment and circuit and the total updating cost in the service life of the scheme. The total cost of the equipment and the circuit is divided by the service life, and the annual operation cost of each equipment and each circuit is obtained. The annual operation cost of each device and each line is added, and the annual operation cost of the power distribution network after the implementation of the investment scheme is obtained is defined as an operation cost index.
Technical parameters of the distribution network after the implementation of the investment scheme, such as parameters of distribution efficiency, maximum/minimum load, load rate and the like, are obtained; consulting industry standards to determine reasonable intervals or typical values of power distribution efficiency and load rate; and calculating the distribution efficiency and the average load rate of the distribution network after the investment scheme is implemented. Comparing the calculated result with a standard value to generate two indexes of distribution efficiency improvement quantity and load balancing condition; the distribution efficiency improvement amount and the load balancing condition index form an operation economy index.
Consulting the relevant standards of engineering cost and progress management, and obtaining the standard construction period of equipment purchasing, line laying, equipment installation and other works; estimating the actual construction period of each work according to the working content and the construction conditions of the investment scheme; and adding the estimated construction periods of all the works to obtain the total construction time of the investment scheme, and defining the total construction time as a construction time index.
The operation cost, the operation economy and the engineering quantity of the investment scheme after the implementation are predicted through the technical content of the investment scheme, and an index set for evaluating the investment scheme is generated, so that a basis is provided for feasibility analysis and scheme comparison of the investment scheme.
Further, the embodiment of the application further comprises:
step S551: constraining the plurality of distribution network investment schemes according to the first configuration constraint and the second configuration constraint to obtain a distribution network investment scheme set;
step S552: randomly selecting a power distribution network investment scheme from the power distribution network investment scheme set to serve as a first power distribution network investment scheme and serve as a historical optimal first-aid repair scheme;
step S553: analyzing and acquiring a first power distribution network investment score of the first power distribution network investment scheme based on double-channel optimizing, wherein the double-channel optimizing comprises the steps of improving the power distribution network operation quality and the user satisfaction of a target area;
Step S554: the first power distribution network investment scheme is adjusted in a plurality of adjustment modes, a first neighborhood is constructed, the first neighborhood comprises a plurality of adjustment power distribution network investment schemes, the adjustment power distribution network investment schemes are included in the power distribution network investment scheme set, and the adjustment modes comprise adjustment power distribution network investment equipment and paving lines;
step S555: analyzing and acquiring a plurality of adjustment power distribution network investment scores of the adjustment power distribution network investment schemes, and acquiring the maximum value of the adjustment power distribution network investment scores as a second power distribution network investment score;
step S556: taking the adjusted distribution network investment scheme corresponding to the second distribution network investment score as a second distribution network investment scheme, judging whether the second distribution network investment score is larger than the first distribution network investment score, if so, taking the second distribution network investment scheme as a historical optimal solution, and adding a preset adjustment mode for obtaining the second distribution network investment scheme into a tabu table, wherein the tabu table comprises a tabu iteration number, and if not, taking the first distribution network investment scheme as the historical optimal solution;
Step S557: continuing to construct a second neighborhood of the second power distribution network investment scheme, and performing iterative optimization;
step S558: and when the preset iteration times are reached, stopping optimizing, and outputting the historical optimal solution to obtain the optimal power distribution network investment scheme.
Specifically, each power distribution network investment scheme is checked, whether the first configuration constraint is met or not is judged, the scheme which is not met is directly removed, whether the second configuration constraint is met or not is judged according to the scheme which is met, the scheme which is not met is removed, and the scheme which is met is stored in a power distribution network investment scheme set.
Then, a scheme is randomly selected from the power distribution network investment scheme set to serve as a first power distribution network investment scheme and a historical optimal scheme. Then, two targets of double-channel optimizing are determined, and the two targets are respectively used for improving the running quality of the power distribution network in the target area and improving the user satisfaction; determining and evaluating technical indexes of a first power distribution network investment scheme, including power distribution efficiency, system static stability, power supply reliability and the like; determining economic indexes for evaluating user satisfaction, including average user power failure time, power quality and the like; according to parameters of equipment and lines designed by the first power distribution network investment scheme, calculating technical indexes and economic indexes by adopting a power distribution network simulation calculation or approximate calculation method, obtaining the running quality of the power distribution network and the satisfaction degree of users, defining the operation quality and the satisfaction degree as a first power distribution network investment score, wherein the score is between 0 and 100 minutes, and the higher the score is, the better the scheme effect is indicated.
The investment scheme of the first power distribution network is adjusted in a plurality of adjustment modes, a first neighborhood is constructed, for example, key equipment in the scheme is replaced on the premise that configuration constraint is met, equipment of different manufacturers and different types but equivalent in performance is selected, and a new scheme with the same technical scheme but different equipment is obtained; on the premise of meeting configuration constraint, increasing or reducing the number of certain key equipment to obtain a new scheme with slightly different technical contents; on the premise of meeting configuration constraint, changing the trend or length of the line, and selecting different line planning schemes. And analyzing each adjustment scheme in the first neighborhood, obtaining adjustment power distribution network investment scores of the adjustment schemes, and obtaining the maximum value as a second power distribution network investment score.
And taking the adjustment scheme corresponding to the investment score of the second power distribution network as the investment scheme of the second power distribution network. And judging whether the investment score of the second power distribution network is larger than that of the first power distribution network. When the power distribution network investment scheme is larger than the historical optimal scheme, the second power distribution network investment scheme is used as the historical optimal scheme; otherwise, the first power distribution network investment scheme is still the historical optimal scheme, and the adjustment mode for obtaining the second power distribution network investment scheme is added into a tabu table to identify the scheme adjustment mode which is tried but has poor effect in the iterative optimization process and is used for guiding the subsequent scheme adjustment and avoiding repeated attempts. Meanwhile, the tabu list comprises iteration times, and when the number of schemes added into the tabu list exceeds the iteration times, iteration is stopped.
And then, another distribution network investment scheme is selected from the distribution network investment scheme set to serve as a second distribution network investment scheme, scheme adjustment is carried out, a second neighborhood is constructed to find the optimal distribution network investment scheme, and when the preset iteration times are reached, the iterative optimization is stopped, so that the optimal distribution network investment scheme is obtained.
By adopting constraint condition screening and iterative optimizing methods, a scheme set with technical and economic effects meeting constraints is selected from a plurality of schemes, the schemes in the scheme set are adjusted, a plurality of adjustment schemes are obtained, scheme optimizing is carried out, an optimal solution of an investment scheme is obtained, and accuracy and reliability of investment prediction of the power distribution network are further improved.
Further, as shown in fig. 3, the embodiment of the present application further includes:
step S541: acquiring a plurality of historical power distribution network investment schemes of a target area, and grading the plurality of historical power distribution network investment schemes according to an investment scheme evaluation index set to acquire a plurality of historical power distribution network investment scores;
step S542: taking the historical power distribution network investment schemes and the historical power distribution network investment scores as construction data, and constructing an investment score model;
step S543: and inputting the first power distribution network investment scheme into the investment scoring model to obtain the first power distribution network investment score.
Specifically, a plurality of power distribution network investment schemes historically implemented in a target area are collected, each scheme is scored according to an investment scheme evaluation index set, a plurality of historical power distribution network investment scores are obtained, and the degree of each scheme achieving an evaluation target is reflected.
The investment scoring model is a model constructed to predict the scoring of the investment plan of the distribution network. Firstly, taking a plurality of obtained historical power distribution network investment schemes and corresponding historical power distribution network investment scores as training samples; secondly, selecting a neural network as a machine learning model; then, carrying out feature extraction and pretreatment on the scheme content, extracting feature indexes capable of representing technical effects of the scheme, and forming an input vector of the scheme; then, dividing a training sample set, a verification sample set and a test sample set, wherein the proportion of the training sample set, the verification sample set and the test sample set is 70%, 15% and 15%, the training sample is used for model training, the verification sample is used for super-parameter adjustment, and the test sample is used for model effect inspection; then, selecting the structure of the neural network, including the number of input layers, hidden layers, nodes, output layer nodes and the like; meanwhile, setting parameters of the neural network, including learning rate, training round number, loss function and the like; then, inputting a training sample set, training a neural network model, judging the generalization capability of the network by the effect on a verification set, and optimizing the super-parameters, wherein when the loss of the verification set is not reduced any more, the model starts to be over fitted, and the training is stopped; and evaluating the generalization performance of the model by using the test set, and further obtaining an investment scoring model meeting the requirements. And then, inputting the technical content of the first power distribution network investment scheme into an investment scoring model, and predicting the score of the first power distribution network investment scheme by using the investment scoring model to obtain a first power distribution network investment score.
By collecting historical cases, constructing a model for evaluating the effect of the investment scheme of the power distribution network, learning the mapping rule between scheme content and scores from a large amount of historical data, providing targets and directions for adjusting and optimizing the investment scheme, and improving the accuracy and reliability of investment prediction of the power distribution network
In summary, the method for predicting and analyzing the investment of the power distribution network based on the data fusion provided by the embodiment of the application has the following technical effects:
acquiring power distribution network feedback data of a target area in a historical time window, wherein the power distribution network feedback data comprises equipment repair information and user complaint information, and providing a data base for generating a first configuration constraint; inputting equipment repairing information and user complaint information into a feedback data extraction module, and generating a first configuration constraint according to the extracted data, wherein the first configuration constraint is used for effectively constraining a power distribution network investment scheme, so that the practicability of the power distribution network investment scheme is improved; collecting operation information of the power equipment in the target area, analyzing the residual life of the power equipment by using the damage accumulation model, and generating a second configuration constraint for effectively constraining the investment scheme of the power distribution network so as to ensure that the investment scheme meets the actual condition of the power equipment; acquiring basic configuration information and expected information of a power distribution network in a target area in real time, generating a plurality of power distribution network investment schemes, realizing comprehensive consideration of the schemes, and providing a global solution space for subsequent optimization; acquiring an investment scheme evaluation index set, and performing double-channel optimization according to the first configuration constraint, the second configuration constraint, the investment scheme evaluation index set and the multiple power distribution network investment schemes to acquire an optimal power distribution network investment scheme, so as to acquire a high-quality global optimal solution; and taking the optimal power distribution network investment scheme as a power distribution network investment prediction analysis result, and achieving the technical effect of improving the accuracy and reliability of power distribution network investment prediction based on data fusion.
Example two
Based on the same inventive concept as the power distribution network investment prediction analysis method based on data fusion in the foregoing embodiment, as shown in fig. 4, an embodiment of the present application provides a power distribution network investment prediction analysis system based on data fusion, where the system includes:
the power grid feedback data module 11 is used for acquiring power distribution network feedback data of a target area in a historical time window, wherein the power distribution network feedback data comprises equipment repair information and user complaint information;
a first configuration constraint module 12, configured to input the equipment repair information and the user complaint information into a feedback data extraction module, and generate a first configuration constraint according to the extracted data;
the second configuration constraint module 13 is used for collecting operation information of the power equipment in the target area, analyzing the residual life of the power equipment by using the damage accumulation model, and generating a second configuration constraint;
an investment plan generation module 14, configured to acquire, in real time, basic configuration information of the distribution network and expected information of the distribution network in the target area, and generate a plurality of distribution network investment plans;
The dual-channel optimizing module 15 is used for acquiring an investment scheme evaluation index set, and performing dual-channel optimizing according to the first configuration constraint, the second configuration constraint, the investment scheme evaluation index set and the multiple power distribution network investment schemes to acquire an optimal power distribution network investment scheme;
and a prediction analysis result module 16, wherein the prediction analysis result module is used for taking the optimal power distribution network investment scheme as a power distribution network investment prediction analysis result.
Further, the embodiment of the application further comprises:
the information set acquisition module is used for acquiring a sample equipment repair information set and a sample user complaint information set of the target area;
the report repair cluster information module is used for carrying out cluster analysis on the sample equipment report repair information set by using equipment report repair types to obtain P pieces of equipment report repair cluster information sets, wherein P is the type of equipment report repair;
the extraction coefficient acquisition module is used for calculating interval time nodes based on the P equipment repair cluster information sets to obtain a first extraction coefficient and a first background extraction coefficient;
the report repair extraction branch construction module is used for repairing the extraction branch according to the equipment for constructing the feedback data extraction module;
The complaint extraction branch module is used for constructing a complaint extraction branch of the feedback data extraction module according to the sample user complaint information set;
the information extraction module is used for respectively inputting the equipment repairing information and the user complaint information into the feedback data extraction module for information extraction;
the first configuration constraint setting module is used for setting the power distribution network investment scheme meeting information extraction result as a first configuration constraint.
Further, the embodiment of the application further comprises:
the first equipment repair type module is used for randomly selecting an equipment repair type corresponding to one cluster from the P equipment repair cluster information sets as a first equipment repair type, and acquiring a first equipment repair cluster information set based on the first equipment repair type;
the interval time node module calculates interval time nodes based on the first equipment report and repair cluster information set, and obtains a first maximum interval time node and a first minimum interval time node;
the second equipment repair type module does not replace the equipment repair type corresponding to one cluster from the P equipment repair cluster information sets again to be randomly selected as a second equipment repair type, and a second maximum interval time node and a second minimum interval time node are obtained;
The P-th equipment repair type module is used for randomly selecting an equipment repair type corresponding to one cluster from the P-th equipment repair cluster information set again without returning the P-th equipment repair type module to be used as the P-th equipment repair type, and obtaining a P-th maximum interval time node and a P-th minimum interval time node;
the time node set module is used for obtaining a maximum interval time node set according to the first maximum interval time node, the second maximum interval time node and the P maximum interval time node, and obtaining a minimum interval time node set according to the first minimum interval time node, the second minimum interval time node and the P minimum interval time node;
the first extraction coefficient acquisition module acquires a first extraction coefficient and a first background extraction coefficient based on the maximum interval time node set and the minimum interval time node set.
Further, the embodiment of the application further comprises:
the equipment operation time length module is used for extracting service life information from the power equipment operation information in the target area to obtain a plurality of pieces of equipment operation time length information;
The residual life calculation module is used for inputting the operation duration information of the plurality of devices into the damage accumulation model to calculate the residual life and obtain the residual life of the plurality of devices;
the second configuration constraint setting module is used for setting the working life of the plurality of electric power equipment in the power distribution network investment scheme to be smaller than the residual life of the plurality of equipment as the second configuration constraint;
wherein, the damage accumulation model is:
wherein F is ileft For the remaining life, t, of the ith power device i For the device operation duration of the ith power device, T i For the operation estimated time length of the ith power equipment, T 0 And i is the number of the power equipment in the target area and is equal to or more than 1 for the operation life of the ith power equipment.
Further, the embodiment of the application further comprises:
the evaluation index construction module is used for constructing an investment scheme evaluation index set, wherein the investment scheme evaluation index set comprises an operation cost index, an operation economy index and a construction time index;
the running cost index module is used for generating a running cost index according to the equipment type, the equipment number and the length of a paved line;
The operation economy index module is used for generating operation economy indexes according to the distribution efficiency and the load of the power distribution network;
the construction time index module is used for generating a construction time index according to the line laying time, the equipment purchasing time and the equipment adding time.
Further, the embodiment of the application further comprises:
the investment scheme constraint module is used for constraining the plurality of power distribution network investment schemes according to the first configuration constraint and the second configuration constraint to obtain a power distribution network investment scheme set;
the investment scheme selection module is used for randomly selecting a power distribution network investment scheme from the power distribution network investment scheme set, and taking the power distribution network investment scheme as a first power distribution network investment scheme and a historical optimal first-aid repair scheme;
the first distribution network investment scoring module is used for analyzing and acquiring a first distribution network investment score of the first distribution network investment scheme based on double-channel optimization, wherein the double-channel optimization comprises the step of improving the distribution network operation quality and the user satisfaction of a target area;
The first neighborhood construction module is used for adjusting the first power distribution network investment scheme by adopting a plurality of adjustment modes to construct a first neighborhood, wherein the first neighborhood comprises a plurality of adjustment power distribution network investment schemes, the plurality of adjustment power distribution network investment schemes are included in the power distribution network investment scheme set, and the plurality of adjustment modes comprise adjustment power distribution network investment equipment and laying lines;
the first distribution network investment scoring module is used for analyzing and acquiring a plurality of adjustment distribution network investment scores of the adjustment distribution network investment schemes and acquiring the maximum value of the adjustment distribution network investment scores as a second distribution network investment score;
the investment scheme judging module is used for taking the adjusted power distribution network investment scheme corresponding to the second power distribution network investment score as a second power distribution network investment scheme, judging whether the second power distribution network investment score is larger than the first power distribution network investment score, if so, taking the second power distribution network investment scheme as a historical optimal solution, adding a preset adjustment mode for obtaining the second power distribution network investment scheme into a tabu table, wherein the tabu table comprises a tabu iteration number, and if not, taking the first power distribution network investment scheme as the historical optimal solution;
The second neighborhood construction module is used for continuously constructing a second neighborhood of the second power distribution network investment scheme and performing iterative optimization;
and the optimal scheme acquisition module is used for stopping optimizing when the preset iteration times are reached, outputting a historical optimal solution and obtaining the optimal distribution network investment scheme.
Further, the embodiment of the application further comprises:
the historical investment scoring module is used for acquiring a plurality of historical power distribution network investment schemes of the target area, scoring the plurality of historical power distribution network investment schemes according to an investment scheme evaluation index set and acquiring a plurality of historical power distribution network investment scores;
the investment score model construction module is used for taking the historical power distribution network investment schemes and the historical power distribution network investment scores as construction data to construct an investment score model;
and the investment score acquisition module is used for inputting the first power distribution network investment scheme into the investment score model to acquire the first power distribution network investment score.
Any of the steps of the methods described above may be stored as computer instructions or programs in a non-limiting computer memory and may be called by a non-limiting computer processor to identify any method for implementing an embodiment of the present application, without unnecessary limitations.
Further, the first or second element may not only represent a sequential relationship, but may also represent a particular concept, and/or may be selected individually or in whole among a plurality of elements. It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the scope of the application. Thus, the present application is intended to include such modifications and alterations insofar as they come within the scope of the application or the equivalents thereof.
Claims (8)
1. An electric power distribution network investment prediction analysis system based on data fusion, which is characterized by comprising:
the power grid feedback data module is used for acquiring power distribution network feedback data of a target area in a historical time window, wherein the power distribution network feedback data comprise equipment repair information and user complaint information;
the first configuration constraint module is used for inputting the equipment repairing information and the user complaint information into the feedback data extraction module and generating a first configuration constraint according to the extracted data;
the second configuration constraint module is used for collecting the operation information of the power equipment in the target area, analyzing the residual life of the power equipment by using the damage accumulation model and generating a second configuration constraint;
The investment scheme generation module is used for acquiring basic configuration information of the power distribution network and expected information of the power distribution network in the target area in real time to generate a plurality of power distribution network investment schemes;
the double-channel optimizing module is used for acquiring an investment scheme evaluation index set, and carrying out double-channel optimizing according to the first configuration constraint, the second configuration constraint, the investment scheme evaluation index set and the multiple power distribution network investment schemes to acquire an optimal power distribution network investment scheme;
and the prediction analysis result module is used for taking the optimal power distribution network investment scheme as a power distribution network investment prediction analysis result.
2. The system of claim 1, wherein the device repair information and the user complaint information are input to a feedback data extraction module and a first configuration constraint is generated from the extracted data, the system comprising:
the information set acquisition module is used for acquiring a sample equipment repair information set and a sample user complaint information set of the target area;
the report repair cluster information module is used for carrying out cluster analysis on the sample equipment report repair information set by using equipment report repair types to obtain P pieces of equipment report repair cluster information sets, wherein P is the type of equipment report repair;
The extraction coefficient acquisition module is used for calculating interval time nodes based on the P equipment repair cluster information sets to obtain a first extraction coefficient and a first background extraction coefficient;
the report repair extraction branch construction module is used for repairing the extraction branch according to the equipment for constructing the feedback data extraction module;
the complaint extraction branch module is used for constructing a complaint extraction branch of the feedback data extraction module according to the sample user complaint information set;
the information extraction module is used for respectively inputting the equipment repairing information and the user complaint information into the feedback data extraction module for information extraction;
the first configuration constraint setting module is used for setting the power distribution network investment scheme meeting information extraction result as a first configuration constraint.
3. The system of claim 2, wherein the interval time node is calculated based on the P device repair cluster information sets to obtain a first extraction coefficient and a first background extraction coefficient, the system comprising:
the first equipment repair type module is used for randomly selecting an equipment repair type corresponding to one cluster from the P equipment repair cluster information sets as a first equipment repair type, and acquiring a first equipment repair cluster information set based on the first equipment repair type;
The interval time node module calculates interval time nodes based on the first equipment report and repair cluster information set, and obtains a first maximum interval time node and a first minimum interval time node;
the second equipment repair type module does not replace the equipment repair type corresponding to one cluster from the P equipment repair cluster information sets again to be randomly selected as a second equipment repair type, and a second maximum interval time node and a second minimum interval time node are obtained;
the P-th equipment repair type module is used for randomly selecting an equipment repair type corresponding to one cluster from the P-th equipment repair cluster information set again without returning the P-th equipment repair type module to be used as the P-th equipment repair type, and obtaining a P-th maximum interval time node and a P-th minimum interval time node;
the time node set module is used for obtaining a maximum interval time node set according to the first maximum interval time node, the second maximum interval time node and the P maximum interval time node, and obtaining a minimum interval time node set according to the first minimum interval time node, the second minimum interval time node and the P minimum interval time node;
The first extraction coefficient acquisition module acquires a first extraction coefficient and a first background extraction coefficient based on the maximum interval time node set and the minimum interval time node set.
4. The system of claim 1, wherein the system comprises:
the equipment operation time length module is used for extracting service life information from the power equipment operation information in the target area to obtain a plurality of pieces of equipment operation time length information;
the residual life calculation module is used for inputting the operation duration information of the plurality of devices into the damage accumulation model to calculate the residual life and obtain the residual life of the plurality of devices;
the second configuration constraint setting module is used for setting the working life of the plurality of electric power equipment in the power distribution network investment scheme to be smaller than the residual life of the plurality of equipment as the second configuration constraint;
wherein, the damage accumulation model is:
wherein F is ileft For the remaining life, t, of the ith power device i For the device operation duration of the ith power device, T i For the operation estimated time length of the ith power equipment, T 0 And i is the number of the power equipment in the target area and is equal to or more than 1 for the operation life of the ith power equipment.
5. The system of claim 1, wherein the system comprises:
the evaluation index construction module is used for constructing an investment scheme evaluation index set, wherein the investment scheme evaluation index set comprises an operation cost index, an operation economy index and a construction time index;
the running cost index module is used for generating a running cost index according to the equipment type, the equipment number and the length of a paved line;
the operation economy index module is used for generating operation economy indexes according to the distribution efficiency and the load of the power distribution network;
the construction time index module is used for generating a construction time index according to the line laying time, the equipment purchasing time and the equipment adding time.
6. The system of claim 1, wherein the system comprises:
the investment scheme constraint module is used for constraining the plurality of power distribution network investment schemes according to the first configuration constraint and the second configuration constraint to obtain a power distribution network investment scheme set;
The investment scheme selection module is used for randomly selecting a power distribution network investment scheme from the power distribution network investment scheme set, and taking the power distribution network investment scheme as a first power distribution network investment scheme and a historical optimal first-aid repair scheme;
the first distribution network investment scoring module is used for analyzing and acquiring a first distribution network investment score of the first distribution network investment scheme based on double-channel optimization, wherein the double-channel optimization comprises the step of improving the distribution network operation quality and the user satisfaction of a target area;
the first neighborhood construction module is used for adjusting the first power distribution network investment scheme by adopting a plurality of adjustment modes to construct a first neighborhood, wherein the first neighborhood comprises a plurality of adjustment power distribution network investment schemes, the plurality of adjustment power distribution network investment schemes are included in the power distribution network investment scheme set, and the plurality of adjustment modes comprise adjustment power distribution network investment equipment and laying lines;
the first distribution network investment scoring module is used for analyzing and acquiring a plurality of adjustment distribution network investment scores of the adjustment distribution network investment schemes and acquiring the maximum value of the adjustment distribution network investment scores as a second distribution network investment score;
The investment scheme judging module is used for taking the adjusted power distribution network investment scheme corresponding to the second power distribution network investment score as a second power distribution network investment scheme, judging whether the second power distribution network investment score is larger than the first power distribution network investment score, if so, taking the second power distribution network investment scheme as a historical optimal solution, adding a preset adjustment mode for obtaining the second power distribution network investment scheme into a tabu table, wherein the tabu table comprises a tabu iteration number, and if not, taking the first power distribution network investment scheme as the historical optimal solution;
the second neighborhood construction module is used for continuously constructing a second neighborhood of the second power distribution network investment scheme and performing iterative optimization;
and the optimal scheme acquisition module is used for stopping optimizing when the preset iteration times are reached, outputting a historical optimal solution and obtaining the optimal distribution network investment scheme.
7. The system of claim 6, wherein the system comprises:
the historical investment scoring module is used for acquiring a plurality of historical power distribution network investment schemes of the target area, scoring the plurality of historical power distribution network investment schemes according to an investment scheme evaluation index set and acquiring a plurality of historical power distribution network investment scores;
The investment score model construction module is used for taking the historical power distribution network investment schemes and the historical power distribution network investment scores as construction data to construct an investment score model;
and the investment score acquisition module is used for inputting the first power distribution network investment scheme into the investment score model to acquire the first power distribution network investment score.
8. The utility model provides a power distribution network investment prediction analysis method based on data fusion, which is characterized in that the method comprises the following steps:
acquiring power distribution network feedback data of a target area in a historical time window, wherein the power distribution network feedback data comprises equipment repair information and user complaint information;
inputting the equipment repairing information and the user complaint information into a feedback data extraction module, and generating a first configuration constraint according to the extracted data;
collecting operation information of the power equipment in the target area, and analyzing the residual life of the power equipment by using the damage accumulation model to generate a second configuration constraint;
acquiring basic configuration information and expected information of a power distribution network of a target area in real time, and generating a plurality of power distribution network investment schemes;
Acquiring an investment scheme evaluation index set, and performing double-channel optimization according to the first configuration constraint, the second configuration constraint, the investment scheme evaluation index set and a plurality of power distribution network investment schemes to acquire an optimal power distribution network investment scheme;
and taking the optimal power distribution network investment scheme as a power distribution network investment prediction analysis result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310825363.8A CN116796906A (en) | 2023-07-06 | 2023-07-06 | Electric power distribution network investment prediction analysis system and method based on data fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310825363.8A CN116796906A (en) | 2023-07-06 | 2023-07-06 | Electric power distribution network investment prediction analysis system and method based on data fusion |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116796906A true CN116796906A (en) | 2023-09-22 |
Family
ID=88036670
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310825363.8A Pending CN116796906A (en) | 2023-07-06 | 2023-07-06 | Electric power distribution network investment prediction analysis system and method based on data fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116796906A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116976531A (en) * | 2023-09-25 | 2023-10-31 | 华夏天信智能物联股份有限公司 | Integrated management method and system for underground electric control equipment |
-
2023
- 2023-07-06 CN CN202310825363.8A patent/CN116796906A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116976531A (en) * | 2023-09-25 | 2023-10-31 | 华夏天信智能物联股份有限公司 | Integrated management method and system for underground electric control equipment |
| CN116976531B (en) * | 2023-09-25 | 2024-02-20 | 华夏天信智能物联股份有限公司 | Integrated management method and system for underground electric control equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | Development of low voltage network templates—Part I: Substation clustering and classification | |
| CN110705873B (en) | Power distribution network running state portrait analysis method | |
| CN111382897A (en) | Transformer area low-voltage trip prediction method and device, computer equipment and storage medium | |
| CN108364187A (en) | A kind of power failure sensitive users based on power failure sensitivity characteristic determine method and system | |
| CN116865258B (en) | Hierarchical distributed power supply intelligent power grid construction method | |
| CN113723844B (en) | Low-voltage station theoretical line loss calculation method based on ensemble learning | |
| CN116796906A (en) | Electric power distribution network investment prediction analysis system and method based on data fusion | |
| KR20220150739A (en) | Forecasting method and system of distributed energy resource for distribution planning | |
| CN110826228A (en) | Regional power grid operation quality limit evaluation method | |
| CN117610214B (en) | Intelligent power distribution network wiring planning method based on dynamic geographic features | |
| CN114065634A (en) | Data-driven power quality monitoring and stationing optimization method and device | |
| CN114091213A (en) | Power communication network planning scheme evaluation system | |
| Böttcher et al. | Investigating Systemic Extrapolation of Distribution Grid Investment Costs | |
| Gerossier et al. | A novel method for decomposing electricity feeder load into elementary profiles from customer information | |
| CN113505951A (en) | Distribution network planning overall process evaluation management system | |
| CN112508254A (en) | Method for determining investment prediction data of transformer substation engineering project | |
| CN108123436B (en) | Voltage out-of-limit prediction model based on principal component analysis and multiple regression algorithm | |
| Xu et al. | Evaluation of fault level of sensitive equipment caused by voltage sag via data mining | |
| CN111144628A (en) | Distributed energy supply type cooling, heating and power load prediction model system and method | |
| CN115409264A (en) | Power distribution network emergency repair stagnation point position optimization method based on feeder line fault prediction | |
| Zhang et al. | Data-driven feature description of heat wave effect on distribution system | |
| Alarcon-Rodriguez et al. | Multi-objective planning of distributed energy resources with probabilistic constraints | |
| Gianluigi et al. | The innovative FlexPlan methodology to reap the benefits of including storage and load flexibility in grid planning: methodology and regional study cases | |
| Li et al. | Probabilistic load forecasting of adaptive multiple polynomial regression considering temperature scenario and dummy variables | |
| CN117557009B (en) | Power efficiency monitoring method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |