CN113537614A - Construction method, system, equipment and medium of power grid engineering cost prediction model - Google Patents
Construction method, system, equipment and medium of power grid engineering cost prediction model Download PDFInfo
- Publication number
- CN113537614A CN113537614A CN202110857750.0A CN202110857750A CN113537614A CN 113537614 A CN113537614 A CN 113537614A CN 202110857750 A CN202110857750 A CN 202110857750A CN 113537614 A CN113537614 A CN 113537614A
- Authority
- CN
- China
- Prior art keywords
- power grid
- prediction model
- project
- engineering
- training
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 63
- 238000012549 training Methods 0.000 claims abstract description 113
- 238000000034 method Methods 0.000 claims abstract description 31
- 238000005457 optimization Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 230000008569 process Effects 0.000 description 7
- 238000004590 computer program Methods 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 4
- 210000002569 neuron Anatomy 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000007786 learning performance Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0206—Price or cost determination based on market factors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Tourism & Hospitality (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Operations Research (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Evolutionary Biology (AREA)
- Biomedical Technology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Educational Administration (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Public Health (AREA)
Abstract
The invention discloses a construction method, a system, equipment and a medium of a power grid engineering cost prediction model, wherein the construction method comprises the following steps: acquiring historical data of construction cost of different project types in a power grid project, and dividing the historical data into a plurality of stage project training sets; selecting at least one target training set corresponding to a preset prediction requirement from the plurality of stages of project training sets and combining the target training sets to obtain a combined training set; and training the initial prediction model by using the combined training set to obtain a target power grid engineering cost prediction model. According to the method, the training data are split and combined, so that the model obtained by training is more in line with the power grid engineering cost prediction requirement, and the prediction result is more accurate.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a method, a system, equipment and a medium for constructing a power grid engineering cost prediction model.
Background
With the increase of power demand and the development of power grid technology, the construction cost and the construction scale of the current power grid project are continuously increased, and all levels of power grid companies face huge capital pressure, so how to reasonably and effectively predict the construction cost of the power grid project under the condition of ensuring to meet the reliability requirement, and further realize the accurate control of the construction cost is an important problem to be solved by the current power grid companies.
Because multi-dimensional information and huge data volume are often involved in the power grid engineering construction process, in the existing power grid engineering construction cost prediction model construction process, the model is usually directly trained by using the whole power grid engineering cost data, the influence of the data type on the model prediction accuracy is not considered, a more accurate prediction result is difficult to obtain, and the training time is easily longer by directly using a large amount of training data to train the model.
Disclosure of Invention
Aiming at the technical problems, the invention provides a construction method, a system, equipment and a medium of a power grid engineering cost prediction model, which enable the model obtained by training to better meet the power grid engineering cost prediction requirement and enable the prediction result to be more accurate by splitting and combining training data.
In a first aspect, the present invention provides a method for constructing a power grid engineering cost prediction model, including:
acquiring historical data of construction cost of each project type in a power grid project, and dividing the historical data into a plurality of stage project training sets; the engineering types comprise power transformation engineering, overhead engineering and cable engineering;
selecting at least one target training set corresponding to a preset prediction requirement from the plurality of stages of project training sets and combining the target training sets to obtain a combined training set;
and training the initial prediction model by using the combined training set to obtain a target power grid engineering cost prediction model.
Optionally, the construction stage of each project type in the power grid project includes a capital construction stage, an operation stage and a scrapping stage.
Optionally, the history data further includes: the construction time and the construction area of each project type in the power grid project; the construction area comprises provincial level engineering, city level engineering and village level engineering.
Optionally, the dividing the historical data into a plurality of stage project training sets specifically includes: dividing the historical data into M stage project training sets according to the construction stages and construction areas of the project types in the power grid project; m is a natural number greater than zero.
Optionally, the initial prediction model is trained by using the combined training set to obtain a target power grid engineering cost prediction model, which specifically includes: for any training sample in the combined training set, obtaining an output result of the initial prediction model based on the training sample; and adjusting the parameters and/or the structure of the initial prediction model according to the output result until the prediction accuracy of the output result reaches a preset requirement, and determining the current initial prediction model as a target power grid engineering cost prediction model.
Optionally, the initial prediction model specifically includes: the multi-layer optimization core multi-item learning machine comprises K hidden layers, and K is a natural number larger than zero.
As a further improvement of the first aspect, the historical data may be divided into a plurality of engineering project training sets according to different engineering types of the power grid engineering; and respectively training the initial prediction model by using the engineering project training sets corresponding to different engineering types to obtain a corresponding target power grid engineering cost prediction model.
In a second aspect, the present invention provides a system for constructing a power grid engineering cost prediction model, including:
the data dividing unit is used for acquiring historical data of construction cost of each project type in the power grid project and dividing the historical data into a plurality of stage project training sets; the engineering types comprise power transformation engineering, overhead engineering and cable engineering;
the data combination unit is used for selecting at least one target training set corresponding to a preset prediction requirement from the plurality of stage project training sets and combining the target training sets to obtain a combined training set;
and the model training unit is used for training the initial prediction model by utilizing the combined training set to obtain a target power grid engineering cost prediction model.
In a third aspect, the present invention provides a data processing apparatus, comprising a processor, coupled with a memory, where the memory stores a program, and the program is executed by the processor, so that the data processing apparatus executes the method for constructing a power grid project cost prediction model according to the first aspect.
In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method for constructing the power grid engineering cost prediction model according to the first aspect.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, the historical data of the construction cost of the power grid project is split and combined, and the corresponding combined training set is determined according to different prediction requirements, so that the model obtained by training is more in line with the prediction requirements of the construction cost of the power grid project, and the prediction result is more accurate.
Drawings
In order to more clearly illustrate the technical solution of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for constructing a power grid project cost prediction model according to an embodiment of the present invention.
Fig. 2 is a structural block diagram of a system for constructing a power grid project cost prediction model according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be understood that the step numbers used herein are for convenience of description only and are not used as limitations on the order in which the steps are performed.
It is to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the specification of the present invention and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
The terms "comprises" and "comprising" indicate the presence of the described features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
The term "and/or" refers to and includes any and all possible combinations of one or more of the associated listed items.
As shown in fig. 1, in a first aspect, an embodiment of the present invention provides a method for constructing a power grid engineering cost prediction model, including the following steps:
s11: acquiring historical data of construction cost of each project type in a power grid project, and dividing the historical data into a plurality of stage project training sets; the engineering types include power transformation engineering, overhead engineering and cable engineering.
Specifically, the historical data can be divided into N engineering project training sets according to the engineering types of the power grid engineering, and meanwhile, the historical data can be divided into M stage project training sets according to the construction stages and the construction positions of different engineering types in the power grid engineering; n, M are all natural numbers greater than zero.
It should be noted that, in this embodiment, the construction phase of each project type in the power grid project includes a capital construction phase, an operation phase, and a scrapping phase.
Specifically, the historical data further comprises construction time and construction areas of each project type in the power grid project; the construction area comprises provincial level engineering, city level engineering and village level engineering.
Specifically, the construction time of the grid project cost data is divided by the construction year, for example, 2010 cable projects from city a to city B.
The data volume of the power grid engineering cost data is large generally, when an existing power grid engineering cost prediction model is built, the whole data is usually trained uniformly, data of different engineering types and different construction stages are not subjected to dimension division, and the accuracy of the prediction model obtained through extensive training is limited.
According to the method, the power grid engineering cost data are subjected to multi-dimensional division according to different types, and then model training is respectively carried out on the divided data according to the prediction requirements, so that the prediction result of the obtained prediction model is more accurate.
S12: and selecting at least one target training set corresponding to a preset prediction requirement from the plurality of stage project training sets and combining to obtain a combined training set.
Specifically, a corresponding relationship between the prediction requirement and a plurality of stage project training sets is preset, and different stage data corresponding to the prediction requirement are extracted from the M stage project training sets according to the corresponding relationship and combined, for example: the training data sets of the C city-D city capital construction stage in 2011, the C city-D city scrapping stage in 2012 and the E city-F city running stage in 2013 are combined.
Considering that the technology is updated faster, the construction time span of the combined data set can be set to be no more than 5 years; meanwhile, considering that the difference of data between engineering data of different levels is large, the construction areas of the combined data sets need to be in the same level so as to ensure the accuracy of the prediction result, for example, a provincial engineering training data set cannot be combined with a municipal engineering training data set and a village engineering training data set.
S13: and training the initial prediction model by using the combined training set to obtain a target power grid engineering cost prediction model.
And for any training sample in the combined training set, obtaining an output result of the initial prediction model based on the training sample, adjusting the parameters and/or the structure of the initial prediction model according to the output result until the prediction accuracy of the output result reaches a preset requirement, and determining the current initial prediction model as a target power grid engineering cost prediction model.
Specifically, the combined training set is further divided into a sub-training set and a sub-testing set, the output result of the initial prediction model based on each training sample in the sub-training set is obtained, and the parameters and/or the structure of the initial prediction model are adjusted according to the output result until the prediction accuracy of the output result reaches the preset requirement; at this time, the trained current initial prediction model is tested by using a sub-test set: and (3) calculating error values of the output result of the model test and the label results in the sub-test set in an iterative manner, if the error values are larger than or equal to a preset threshold value, further adjusting parameters and/or structures of the initial prediction model according to the output result until the error values are smaller than the preset threshold value, and determining the current initial prediction model as the target power grid engineering cost prediction model.
Specifically, the initial prediction model can be set as a multi-layer optimization kernel learning machine. An Optimized Extreme Learning Machine (O-ELM) is a feedforward neural network, and the Learning performance of the network can be improved by optimizing and selecting input variables of the Extreme Learning Machine, configuration and bias parameters of hidden layer nodes, regularization coefficients and the like; the Kernel Extreme Learning Machine (KELM) adopts Kernel functions to represent unknown implicit layer nonlinear feature mapping, and calculates the output weight of the network by a regularized least square method without setting the number of nodes of the network implicit layer.
In one embodiment, after obtaining the combined training set, an initial prediction model is first set: the number K of layers of the model hidden layer and the number of neurons of the first K-1 layers of hidden layers are configured, and the number of neurons of the last layer does not need to be set.
And after the initial prediction model setting is completed, inputting the sub-training sets in the combined training set into the constructed multilayer optimized kernel limit learning machine for training, optimizing the weight parameters of the front K-1 hidden layer based on the training samples in the sub-training sets according to the limit learning machine-self-coding principle, and optimizing the kernel parameters and the regularization coefficients of the K hidden layer according to the genetic algorithm, thereby completing the training of the parameters of each hidden layer and obtaining the trained multilayer optimized kernel limit learning machine.
Wherein, the optimization process comprises:
1) based on training samples, calculating an input weight matrix of the current hidden layer according to an extreme learning machine-self-encoding principle, and solving the input weight matrix to obtain the output weight of the current hidden layer.
Specifically, the multi-layer optimization kernel limit learning machine generates input weights and hidden layer offsets of orthogonal random encoder input layers based on an extreme learning machine-self-encoding principle, solves output weights of a decoder, and stores the output weights as the input of the next layer of the multi-layer optimization kernel limit learning machine.
2) And taking the transpose of the output weight of the current hidden layer as the input of the next hidden layer, calculating the input weight matrix of the next hidden layer by the next hidden layer based on the transpose of the output weight of the current hidden layer, solving the input weight matrix of the next hidden layer to obtain the output weight of the next hidden layer until the input weight and the output weight of the hidden layer of the K-1 th layer are obtained through calculation.
3) And optimizing the kernel parameters and the regularization coefficients by the K-th hidden layer according to a genetic algorithm, thereby completing the training of the parameters of each hidden layer and obtaining the trained multilayer optimized kernel limit learning machine, wherein the kernel parameters are important parameters of the kernel function.
4) And testing the trained multilayer optimized kernel limit learning machine by using the subtest set, iteratively calculating error values of output results of the model and label results in the subtest set, if the error values are greater than or equal to a preset threshold value, increasing the number of neurons of a front K-1 hidden layer of the multilayer optimized kernel limit learning machine to obtain a new multilayer optimized kernel limit learning machine, and determining the current multilayer optimized kernel limit learning machine as a target power grid engineering cost prediction model until the error values are smaller than the preset threshold value.
In some embodiments, the time period of the prediction model may be further set, for example, the time period is set to 5 years, at this time, the power grid construction cost data from (T-5) year to T year is used for model training, and the obtained power grid construction cost prediction model is used for predicting the power grid construction cost result of T +1 year, so as to improve the prediction accuracy.
In another embodiment, the initial prediction models are trained respectively by using engineering project training sets corresponding to different engineering types of the power grid engineering to obtain corresponding target power grid engineering cost prediction models.
It can be understood that the initial prediction model can also be trained by using stage project training sets corresponding to different construction information of the power grid project, so as to obtain a corresponding target power grid engineering cost prediction model.
In order to further improve the accuracy of model prediction, another embodiment of the present invention provides an average prediction method for optimizing and adjusting a prediction model, which includes the following specific steps:
1) according to the prediction requirements, data extraction and combination are carried out on a plurality of stage project training sets of power grid engineering construction stages (a capital construction stage, an operation stage and a scrapping stage), an initial prediction model is trained by utilizing the combined training data set, a target power grid engineering cost prediction model is obtained, and then data to be detected are input into the target power grid engineering cost prediction model to obtain a first prediction value;
2) respectively and independently training initial prediction models by using stage project training sets corresponding to three construction stages (a capital construction stage, an operation stage and a scrapping stage) of the power grid project to obtain power grid project cost prediction models corresponding to the three construction stages, respectively inputting data to be tested into the three power grid project cost prediction models to obtain three prediction results, summing the prediction results, averaging the prediction results to obtain a second prediction value;
3) and summing the first predicted value and the second predicted value to obtain an average value, and obtaining a final power grid engineering cost predicted value of the data to be tested.
It should be noted that, in consideration of the relevance among multiple dimensions of the power grid engineering cost data, before model training, feature dimensionality reduction can be performed on the data, the data structure is simplified, the data volume is reduced, the accuracy of the prediction result is ensured to be high, and meanwhile, the training process of the model is faster.
In a second aspect, referring to fig. 2, another embodiment of the present invention provides a system for constructing a power grid project cost prediction model, including a data partitioning unit 101, a data combining unit 102, and a model training unit 103.
The data dividing unit 101 is used for acquiring historical data of construction cost of each project type in a power grid project and dividing the historical data into a plurality of stage project training sets; the engineering types include power transformation engineering, overhead engineering and cable engineering.
The data combining unit 102 is configured to select at least one target training set corresponding to a preset prediction requirement from the plurality of stage project training sets and combine the target training sets to obtain a combined training set.
The model training unit 103 is configured to train the initial prediction model by using the combined training set to obtain a target power grid engineering cost prediction model.
Because the information interaction, execution process and other contents between the units in the system are based on the same concept as the method embodiment of the present invention, specific contents can be referred to the description in the method embodiment of the present invention, and are not described herein again.
In a third aspect, the present invention provides a data processing apparatus, comprising a processor, coupled with a memory, where the memory stores a program, and the program is executed by the processor, so that the data processing apparatus executes the method for constructing a power grid project cost prediction model according to the first aspect.
In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the method for constructing the power grid engineering cost prediction model according to the first aspect.
It will be understood by those skilled in the art that all or part of the processes of the methods of the above embodiments may be implemented by a computer program, which may be stored in a computer-readable storage medium, and may include the processes of the embodiments of the methods when executed. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention.
Claims (10)
1. A construction method of a power grid engineering cost prediction model is characterized by comprising the following steps:
acquiring historical data of construction cost of each project type in a power grid project, and dividing the historical data into a plurality of stage project training sets; the engineering types comprise power transformation engineering, overhead engineering and cable engineering;
selecting at least one target training set corresponding to a preset prediction requirement from the plurality of stages of project training sets and combining the target training sets to obtain a combined training set;
and training the initial prediction model by using the combined training set to obtain a target power grid engineering cost prediction model.
2. The method of constructing a power grid construction cost prediction model according to claim 1,
the construction stage of each project type in the power grid project comprises a capital construction stage, an operation stage and a scrapping stage.
3. The method of constructing a power grid construction cost prediction model according to claim 2, wherein the historical data further comprises:
the construction time and the construction area of each project type in the power grid project; the construction area comprises provincial level engineering, city level engineering and village level engineering.
4. The method for constructing the power grid project cost prediction model according to claim 3, wherein the historical data is divided into a plurality of stage project training sets, specifically:
dividing the historical data into M stage project training sets according to the construction stages and construction areas of the project types in the power grid project; m is a natural number greater than zero.
5. The method for constructing a power grid project cost prediction model according to claim 1, wherein the training of the initial prediction model by using the combined training set to obtain the target power grid project cost prediction model comprises:
for any training sample in the combined training set, obtaining an output result of the initial prediction model based on the training sample;
adjusting parameters and/or structures of the initial prediction model according to the output result until the prediction accuracy of the output result reaches a preset requirement;
and determining the current initial prediction model as a target power grid engineering cost prediction model.
6. The method for constructing the power grid project cost prediction model according to claim 1, wherein the initial prediction model is specifically:
the multi-layer optimization core multi-item learning machine comprises K hidden layers, and K is a natural number larger than zero.
7. The method for constructing a power grid project cost prediction model according to claim 1, further comprising:
dividing the historical data into a plurality of engineering project training sets according to different engineering types of the power grid engineering;
and respectively training the initial prediction model by using the engineering project training sets corresponding to different engineering types to obtain a corresponding target power grid engineering cost prediction model.
8. A construction system of a power grid engineering cost prediction model is characterized by comprising the following steps:
the data dividing unit is used for acquiring historical data of construction cost of different project types in the power grid project and dividing the historical data into a plurality of stage project training sets; the engineering types comprise power transformation engineering, overhead engineering and cable engineering;
the data combination unit is used for selecting at least one target training set corresponding to a preset prediction requirement from the plurality of stage project training sets and combining the target training sets to obtain a combined training set;
and the model training unit is used for training the initial prediction model by utilizing the combined training set to obtain a target power grid engineering cost prediction model.
9. A data processing apparatus, characterized by comprising:
a processor coupled to a memory, the memory storing a program that is executable by the processor to cause the data processing apparatus to perform a method of constructing a power grid construction cost prediction model according to any of claims 1 to 7.
10. A computer storage medium storing computer instructions for executing the method of constructing a power grid construction cost prediction model according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110857750.0A CN113537614A (en) | 2021-07-28 | 2021-07-28 | Construction method, system, equipment and medium of power grid engineering cost prediction model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110857750.0A CN113537614A (en) | 2021-07-28 | 2021-07-28 | Construction method, system, equipment and medium of power grid engineering cost prediction model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113537614A true CN113537614A (en) | 2021-10-22 |
Family
ID=78121230
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110857750.0A Pending CN113537614A (en) | 2021-07-28 | 2021-07-28 | Construction method, system, equipment and medium of power grid engineering cost prediction model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113537614A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114037538A (en) * | 2021-11-15 | 2022-02-11 | 国网湖北省电力有限公司经济技术研究院 | Power grid infrastructure project investment balance control method and system |
| CN114493477A (en) * | 2021-12-13 | 2022-05-13 | 南通科达建材科技股份有限公司 | BIM-based multi-dimensional statistical method and system for building cost |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111506575A (en) * | 2020-03-26 | 2020-08-07 | 第四范式（北京）技术有限公司 | Method, device and system for training branch point traffic prediction model |
| CN111582325A (en) * | 2020-04-20 | 2020-08-25 | 华南理工大学 | Multi-order feature combination method based on automatic feature coding |
| CN111784061A (en) * | 2020-07-07 | 2020-10-16 | 广东电网有限责任公司 | Training method, device and equipment for power grid engineering cost prediction model |
| CN112132639A (en) * | 2020-10-23 | 2020-12-25 | 中国科学院计算技术研究所 | Dynamic pricing method of data set based on machine learning |
| CN112766536A (en) * | 2021-03-16 | 2021-05-07 | 交通运输部路网监测与应急处置中心 | Model training method, device and terminal for calculating road engineering labor unit price |
-
2021
- 2021-07-28 CN CN202110857750.0A patent/CN113537614A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111506575A (en) * | 2020-03-26 | 2020-08-07 | 第四范式（北京）技术有限公司 | Method, device and system for training branch point traffic prediction model |
| CN111582325A (en) * | 2020-04-20 | 2020-08-25 | 华南理工大学 | Multi-order feature combination method based on automatic feature coding |
| CN111784061A (en) * | 2020-07-07 | 2020-10-16 | 广东电网有限责任公司 | Training method, device and equipment for power grid engineering cost prediction model |
| CN112132639A (en) * | 2020-10-23 | 2020-12-25 | 中国科学院计算技术研究所 | Dynamic pricing method of data set based on machine learning |
| CN112766536A (en) * | 2021-03-16 | 2021-05-07 | 交通运输部路网监测与应急处置中心 | Model training method, device and terminal for calculating road engineering labor unit price |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114037538A (en) * | 2021-11-15 | 2022-02-11 | 国网湖北省电力有限公司经济技术研究院 | Power grid infrastructure project investment balance control method and system |
| CN114037538B (en) * | 2021-11-15 | 2023-11-03 | 国网湖北省电力有限公司经济技术研究院 | Method and system for controlling investment balance of power grid infrastructure project |
| CN114493477A (en) * | 2021-12-13 | 2022-05-13 | 南通科达建材科技股份有限公司 | BIM-based multi-dimensional statistical method and system for building cost |
| CN114493477B (en) * | 2021-12-13 | 2023-11-21 | 南通科达建材科技股份有限公司 | Building cost multidimensional statistics method and system based on BIM |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109214708B (en) | Electric power system risk assessment method based on cross entropy theory optimization support vector machine | |
| CN113537614A (en) | Construction method, system, equipment and medium of power grid engineering cost prediction model | |
| US20210090552A1 (en) | Learning apparatus, speech recognition rank estimating apparatus, methods thereof, and program | |
| CN114609994B (en) | Fault diagnosis method and device based on multi-granularity regularized rebalancing increment learning | |
| CN111881023A (en) | Software aging prediction method and device based on multi-model comparison | |
| CN114490065A (en) | Load prediction method, device and equipment | |
| CN115481549A (en) | Cylindrical linear motor multi-objective optimization method, equipment and storage medium | |
| CN112734106A (en) | Method and device for predicting energy load | |
| CN111783242A (en) | RVM-KF-based rolling bearing residual life prediction method and device | |
| CN111832693A (en) | Neural network layer operation and model training method, device and equipment | |
| CN116627773B (en) | Abnormality analysis method and system of production and marketing difference statistics platform system | |
| Saadawi et al. | DEVS execution acceleration with machine learning | |
| US11003823B2 (en) | Re-design of analog circuits | |
| CN114819107B (en) | Mixed data assimilation method based on deep learning | |
| CN116054144A (en) | Distribution network reconstruction method, system and storage medium for distributed photovoltaic access | |
| CN113822441B (en) | Decision model training method, device, terminal equipment and storage medium | |
| CN114510469A (en) | Method, device, equipment and medium for identifying bad data of power system | |
| CN111913462B (en) | Chemical fault monitoring method based on generalized multiple independent element analysis model | |
| CN114021465A (en) | Electric power system robust state estimation method and system based on deep learning | |
| EP3663992A1 (en) | Learning-finished model integration method, device, program, ic chip, and system | |
| WO2019209571A1 (en) | Proactive data modeling | |
| US20230169240A1 (en) | Computing device and method generating optimal input data | |
| Xin et al. | Surrogate model assisted multi-objective differential evolution algorithm for performance optimization at software architecture level | |
| CN113962146A (en) | Multi-fidelity proxy model modeling method based on canonical correlation analysis | |
| US20240028872A1 (en) | Estimation apparatus, learning apparatus, methods and programs for the same |
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 |