CN114066018A - Power distribution station construction material demand prediction method based on support vector - Google Patents
Power distribution station construction material demand prediction method based on support vector Download PDFInfo
- Publication number
- CN114066018A CN114066018A CN202111252699.7A CN202111252699A CN114066018A CN 114066018 A CN114066018 A CN 114066018A CN 202111252699 A CN202111252699 A CN 202111252699A CN 114066018 A CN114066018 A CN 114066018A
- Authority
- CN
- China
- Prior art keywords
- power distribution
- data set
- distribution station
- attribute parameters
- construction
- 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 204
- 239000004035 construction material Substances 0.000 title claims abstract description 83
- 238000000034 method Methods 0.000 title claims abstract description 66
- 239000013598 vector Substances 0.000 title claims abstract description 46
- 239000000463 material Substances 0.000 claims abstract description 96
- 238000010276 construction Methods 0.000 claims abstract description 60
- 238000012545 processing Methods 0.000 claims abstract description 43
- 230000009467 reduction Effects 0.000 claims abstract description 35
- 230000008569 process Effects 0.000 claims abstract description 30
- 238000010606 normalization Methods 0.000 claims abstract description 19
- 238000005457 optimization Methods 0.000 claims abstract description 13
- 238000003860 storage Methods 0.000 claims description 17
- 238000004458 analytical method Methods 0.000 claims description 13
- 230000006870 function Effects 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 11
- 238000013507 mapping Methods 0.000 claims description 7
- 230000003993 interaction Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 4
- 238000007689 inspection Methods 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 12
- 238000004422 calculation algorithm Methods 0.000 abstract description 7
- 238000010801 machine learning Methods 0.000 abstract description 5
- 238000012360 testing method Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000011156 evaluation Methods 0.000 description 4
- 238000003058 natural language processing Methods 0.000 description 4
- 238000012706 support-vector machine Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000013277 forecasting method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 239000004566 building material Substances 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
- 238000012800 visualization 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
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- 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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/10—Noise analysis or noise optimisation
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Educational Administration (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a power distribution station construction material demand prediction method based on support vectors, which is characterized by obtaining power distribution attribute parameters of a historical construction power distribution station and material consumption corresponding to the power distribution attribute parameters; denoising the power distribution attribute parameters and the material consumption, and removing irrelevant features to obtain a denoising data set; carrying out normalization processing on the noise reduction data set to obtain a standardized data set; performing parameter optimization processing on the standardized data set by adopting a support vector regression model to obtain a power distribution station construction material demand prediction model; the predicted value of the corresponding project material demand to be tested is determined according to the power distribution station construction material demand prediction model and the project power distribution attribute parameters to be tested, the phenomenon that the traditional machine learning algorithm is easy to cause overfitting and influences the power distribution station construction material demand prediction effect is reduced, the construction materials can be effectively utilized and managed, and the power distribution station construction process is guaranteed to be smooth.
Description
Technical Field
The application relates to the field of power grid material demand prediction, in particular to a power distribution station construction material demand prediction method and system based on support vectors and a storage medium.
Background
In the conventional power distribution station construction process, the demand of the power distribution station construction materials is often estimated in a manpower statistic evaluation mode, a huge amount of manpower and material resources are needed to collect data in the early stage of construction and gather the data, and the material storage is ensured to meet the material demand in the power distribution station construction process, so that the power distribution station is completed according to a plan, but the manpower statistic efficiency is low, and the construction materials cannot be effectively utilized and managed.
The conventional method for predicting the material demand of the construction of the power distribution station through a traditional regression algorithm according to historical construction data of the past year and according to preset attribute parameters of items to be tested is adopted, but the traditional machine learning algorithm considers that the prediction is correct only when the predicted regression value is completely matched with a specific numerical value, so that overfitting is easily caused, and the prediction effect of the material demand of the construction of the power distribution station is influenced.
Disclosure of Invention
The present application is directed to solving, at least to some extent, one of the technical problems in the related art. Therefore, the application provides a method and a system for forecasting the construction material demand of a power distribution station based on a support vector, and a storage medium.
In a first aspect, an embodiment of the present application provides a method for predicting demand for construction materials of a distribution station based on support vectors, including:
acquiring power distribution attribute parameters of a historical construction power distribution station and material consumption corresponding to the power distribution attribute parameters;
denoising the power distribution attribute parameters and the material consumption, and removing irrelevant features to obtain a denoising data set;
carrying out normalization processing on the noise reduction data set to obtain a standardized data set;
performing parameter optimization processing on the standardized data set by adopting a support vector regression model to obtain a power distribution station construction material demand prediction model;
acquiring a power distribution attribute parameter of a project to be detected;
determining a predicted value corresponding to the material demand of the project to be tested according to the power distribution station construction material demand prediction model and the power distribution attribute parameters of the project to be tested;
and performing inverse normalization processing on the predicted value to obtain the material usage amount of the corresponding item to be detected.
The power distribution station construction material demand prediction method based on the support vector has the following beneficial effects: in the transformer substation construction process, carry out data preprocessing to historical power distribution station construction data and obtain the power distribution station construction data set, according to the data set, adopt the mode of seeking the optimum through the parameter among the support vector regression model to obtain the power distribution station construction goods and materials demand prediction model, confirm to correspond the project goods and materials use amount that awaits measuring, it causes the overfitting easily to reduce traditional machine learning algorithm, influences the condition emergence of power distribution station construction goods and materials demand prediction effect, can effectively utilize and manage the construction goods and materials, the guarantee power distribution station construction process is smooth.
Optionally, in an embodiment of the present application, the performing parameter optimization processing on the standardized data set by using a support vector regression model to obtain a power distribution station construction material demand prediction model includes:
mapping the normalized data set to a feature space using a kernel function;
determining a hyperplane in the feature space, wherein the hyperplane is a plane with the minimum distance among all data in the standardized data set;
and obtaining a power distribution station construction material demand prediction model according to the hyperplane.
Optionally, in an embodiment of the present application, the normalizing the noise reduction data set to obtain a normalized data set includes:
performing K value clustering analysis on the noise reduction data set to obtain the noise reduction data set from which repeated data are removed;
and carrying out normalization processing on the noise reduction data set after the repeated data are removed to obtain a standardized data set.
Optionally, in an embodiment of the present application, after determining a predicted value of the material demand of the item to be tested according to the power distribution station construction material demand prediction model and the power distribution attribute parameter of the item to be tested, the method further includes:
carrying out judgment and inspection processing on the material demand prediction model to obtain a judgment coefficient;
and under the condition that the judgment coefficient does not reach the threshold value, determining the predicted value of the material demand of the corresponding item to be tested according to the construction material demand prediction model of the power distribution station and the power distribution attribute parameters of the item to be tested.
Optionally, in an embodiment of the present application, the obtaining of the power distribution attribute parameter of the historical construction power distribution station and the material consumption amount corresponding to the power distribution attribute parameter includes:
and extracting the power distribution attribute parameters of the historical construction power distribution station and the material consumption corresponding to the power distribution attribute parameters in the historical data report.
Optionally, in an embodiment of the present application, the denoising processing performed on the power distribution attribute parameters and the material consumption to obtain a denoising data set after removing irrelevant features includes:
and carrying out noise reduction treatment on the power distribution attribute parameters and the material consumption by using a correlation coefficient analysis method, and removing irrelevant features to obtain a noise reduction data set, wherein the correlation coefficient analysis method comprises analysis by using covariance and a covariance matrix.
Optionally, in an embodiment of the present application, the normalizing the noise reduction data set to obtain a normalized data set further includes:
and processing the noise reduction data set according to a preset weight vector, wherein the weight vector is obtained by an analytic hierarchy process.
In a second aspect, an embodiment of the present application provides a system for predicting demand of materials for construction of a power distribution station, including:
the data preprocessing module is used for acquiring distribution attribute parameters of a historical construction power distribution station and material consumption corresponding to the distribution attribute parameters, denoising the distribution attribute parameters and the material consumption, removing irrelevant features to obtain a denoising data set, and normalizing the denoising data set to obtain a standardized data set;
the demand forecasting model building module is used for performing parameter optimization processing on the standardized data set by adopting a support vector regression model to obtain a power distribution station construction material demand forecasting model;
and the data interaction module is used for determining a predicted value corresponding to the material demand of the item to be tested according to the power distribution station construction material demand prediction model and the power distribution attribute parameters of the item to be tested, and performing inverse normalization processing on the predicted value to obtain the material usage amount of the corresponding item to be tested.
The power distribution station construction material demand prediction system of the embodiment of the application at least has the following beneficial effects: in the transformer substation construction process, the power distribution station construction material demand prediction system is used, the data preprocessing module carries out data preprocessing on historical power distribution station construction data to obtain a power distribution station construction data set, the demand prediction model construction module obtains a power distribution station construction material demand prediction model in a support vector regression model in a parameter optimization mode according to the data set, a user determines the use amount of corresponding to-be-detected project materials through the data interaction module, the accuracy of a power distribution station construction material demand prediction result is improved, the construction materials are effectively utilized and managed, and the smoothness of the power distribution station construction process is guaranteed.
In a third aspect, an embodiment of the present application provides a system for predicting demand for construction materials of a distribution substation, including: memory, processor and computer program stored on the memory and executable on the processor, the processor implementing the demand prediction method as claimed in any one of claims 1 to 7 when executing the computer program.
In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions for causing a computer to perform the demand forecasting method according to any one of claims 1 to 7.
Drawings
The accompanying drawings are included to provide a further understanding of the claimed subject matter and are incorporated in and constitute a part of this specification, illustrate embodiments of the subject matter and together with the description serve to explain the principles of the subject matter and not to limit the subject matter.
Fig. 1 is a flowchart of a method for forecasting demand of construction materials of a distribution substation based on support vectors according to an embodiment of the present application;
fig. 2 is a flowchart of a method for forecasting demand of construction materials of a distribution substation based on support vectors according to an embodiment of the present application;
fig. 3 is a flowchart of a method for forecasting demand of construction materials of a distribution substation based on support vectors according to an embodiment of the present application;
fig. 4 is a flowchart of a method for forecasting demand of construction materials of a distribution substation based on support vectors according to an embodiment of the present application;
fig. 5 is a block diagram of a power distribution station construction material demand prediction system according to another embodiment of the present disclosure.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
It should be noted that although functional block divisions are provided in the system drawings and logical orders are shown in the flowcharts, in some cases, the steps shown and described may be performed in different orders than the block divisions in the systems or in the flowcharts. The terms first, second and the like in the description and in the claims, and the drawings described above, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
In the conventional power distribution station construction process, the demand of the power distribution station construction materials is often estimated in a manpower statistic evaluation mode, a huge amount of manpower and material resources are needed to collect data in the early stage of construction and gather the data, and the material storage is ensured to meet the material demand in the power distribution station construction process, so that the power distribution station is completed according to a plan, but the manpower statistic efficiency is low, and the construction materials cannot be effectively utilized and managed.
The conventional method for predicting the material demand of the construction of the power distribution station through a traditional regression algorithm according to historical construction data of the past year and according to preset attribute parameters of items to be tested is adopted, but the traditional machine learning algorithm considers that the prediction is correct only when the predicted regression value is completely matched with a specific numerical value, so that overfitting is easily caused, and the prediction effect of the material demand of the construction of the power distribution station is influenced.
Based on the above, the application provides a distribution station construction material demand prediction method, a distribution station construction material demand prediction system and a storage medium based on support vectors, in the transformer substation construction process, data preprocessing is performed on historical distribution station construction data to obtain a distribution station construction data set, according to the data set, a distribution station construction material demand prediction model is obtained in a support vector regression model in a parameter optimization mode, the use amount of materials of corresponding to-be-detected items is determined, the situations that a traditional machine learning algorithm is easy to cause overfitting, the distribution station construction material demand prediction effect is influenced are reduced, construction materials can be effectively utilized and managed, and the smooth construction process of the distribution station is guaranteed.
The embodiments of the present application will be further explained with reference to the drawings.
Referring to fig. 1, fig. 1 is a flowchart illustrating a method for forecasting demand for construction materials of a distribution substation based on support vectors according to an embodiment of the present application, where the forecasting method includes, but is not limited to, step S110, step S120, step S130, step S140, step S150, step S160, and step S170.
Step S110: and acquiring the power distribution attribute parameters of the historical construction power distribution station and the material consumption corresponding to the power distribution attribute parameters.
In some embodiments, the power distribution attribute parameters of the historical construction power distribution station and the material consumption corresponding to the power distribution attribute parameters are obtained, and the power distribution attribute parameters of the historical construction power distribution station may be peripheral building layout information, voltage level, estimated completion period, estimated amount, human resource period, building scale, weather condition, and the like. The preset attributes can be one or more of the preset attributes, the material consumption is actual data corresponding to the power distribution attribute parameters, wherein it is conceivable that the power distribution attribute parameters are changed by technicians in related fields according to actual conditions, the power distribution attribute parameters in the process of historical building of the power distribution station are recorded through manpower or sensing equipment, and the sensing equipment comprises any sensing equipment which can be accessed, such as a thermosensitive element, a photosensitive element, a gas sensitive element, a force sensitive element, a magnetic sensitive element, a humidity sensitive element, a sound sensitive element, a radiation sensitive element, a color sensitive element and a taste sensitive element. Technical personnel in the relevant field can select corresponding sensing equipment according to actual conditions, and more sensing equipment is accessed to form more sensor combinations, so that the material consumption corresponding to the set power distribution attribute parameters is obtained through statistics.
Step S120: and denoising the power distribution attribute parameters and the material consumption, and removing irrelevant features to obtain a denoising data set.
In some embodiments, the obtained power distribution attribute parameters and material consumption inevitably include useless or practically unrelated data, the data is noise data for reducing the prediction accuracy of the generated model, and in order to remove the noise data, data denoising processing is performed, and irrelevant features are removed from the power distribution attribute parameters and the material consumption to obtain a denoising data set, so that a regression model with better accuracy can be obtained, and a better prediction effect is achieved.
In some embodiments, the power distribution attribute parameters and the material consumption are subjected to noise reduction treatment in a mode of one or more combinations of binning, clustering, regression adaptation, computer and manual checking; for example: the data are sequenced, and noise data with large difference are removed by utilizing the data neighbor smooth sequence value, or noise reduction processing is carried out on the power distribution attribute parameters and the material consumption in a manual screening and counting mode.
It is conceivable that even if the power distribution attribute parameters and the material consumption amount are not subjected to the noise reduction processing, the subsequent operations can be performed by directly using the power distribution attribute parameters and the material consumption amount as the noise reduction data set.
Step S130: and carrying out normalization processing on the noise reduction data set to obtain a standardized data set.
In some embodiments, normalization processing is performed, namely a dimensional expression is transformed into a dimensionless expression, in the process of performing normalization processing on the noise reduction data set to obtain a normalized data set, firstly the dimensional expression such as voltage, power and the like in the noise reduction data set is converted into a scalar, then data scaling is performed on the converted scalar to obtain the normalized data set, data processing is facilitated, data are mapped into a range of 0-1 for processing, and subsequent operation is more convenient and faster.
It is conceivable that the normalization process is suitable for a stable data set without extreme maximum and minimum values, so that the noise reduction data set obtained by performing the noise reduction process on the original data set is suitable for the normalization process, and the effect of accelerating the optimization process is achieved
Step S140: and performing parameter optimization processing on the standardized data set by adopting a support vector regression model to obtain a power distribution station construction material demand prediction model.
In some embodiments, by performing a parameter optimization process on a normalized data set using a support vector regression model, it is contemplated that when performing regression prediction, a given training sample is used
D＝{(x1，y1)，(x2，y2)，……，(xn，yn),yi∈R}
In the conventional regression model, f (x) is output to enable the f (x) to be as close to y as possible, f (x) can be understood as a generated model, and when f (x) is judged to be completely the same as y, the regression model is determined to be normal in prediction, so that a large amount of data is strictly required to train the regression model with good prediction effect, and the prediction consumption of material consumption in the actual construction process is influenced; in the support vector regression model, there may be an epsilon deviation between f (x) and y, and if and only if the absolute value of the difference between f (x) and y is greater than epsilon, the loss is calculated, which is equivalent to constructing a region ranging from-epsilon to + epsilon with f (x) as the center, and the training sample falls into this region, it is considered to be predicted correctly, thereby reducing the occurrence of the over-fitting phenomenon, improving the utilization rate of the data amount and the test sample set, and it is worth noting that the relaxation degrees at the two sides of the region may be different.
In some embodiments, the process of obtaining the forecasting model of the demand of the construction materials of the power distribution station comprises the following steps:
the demand forecasting model for building materials of the power distribution station comprises the following steps: f (x) ═ ωτx+b
The parameter solving process of the distribution station construction material demand prediction model f (x) can be expressed as the following problem:
g is a loss function for calculating the loss of the power distribution station construction material demand prediction model;
finally, solving, and building a material demand prediction model for the power distribution station:
wherein, yiIs the regression value of the ith sample, yi＝f(xi),xiCorresponding to the standardized data set, f (x) corresponding to the generated forecasting model of the material demand of the power distribution station construction, yiAnd correspondingly outputting the prediction result.
In the process of actually processing the historical data of the transformer substation, the selected parameters are necessarily multivariate, so that the dimension reduction processing can be performed before the process of supporting the vector regression model, and the subsequent data processing is facilitated.
Step S150: and acquiring the power distribution attribute parameters of the item to be tested.
In some embodiments, the power distribution attribute parameter of the item to be tested is input as an input value, the power distribution attribute parameter of the item to be tested may be peripheral building layout information, voltage level, expected completion period, budget amount, human resource period, building size, weather condition, etc., and the preset attribute may be one or more of them.
Conceivably, the method for acquiring the power distribution attribute parameters of the item to be tested includes acquiring through computer and manual check, and acquiring through various types of accessed sensing equipment.
Step S160: and determining a predicted value corresponding to the material demand of the project to be tested according to the construction material demand prediction model of the power distribution station and the power distribution attribute parameters of the project to be tested.
In some embodiments, after the predicted value corresponding to the project material demand to be tested is determined according to the power distribution station construction material demand prediction model and the project power distribution attribute parameters to be tested, visual display can be performed, including generation of a data chart, so that a power station construction material demand prediction result can be better represented.
In some embodiments, after a prediction value corresponding to the project material demand to be tested is determined according to a power distribution station construction material demand prediction model and the project power distribution attribute parameters to be tested, the project power distribution attribute parameters to be tested and the project material demand corresponding to the project material demand to be tested are stored in a mapping table of a computer storage device, data are updated, the effective data occupation ratio of a data set is optimized, and the prediction effect of the regression model generated again is better and more accurate.
Step S170: and performing inverse normalization processing on the predicted value to obtain the material usage amount of the corresponding item to be detected.
In some embodiments, after the predicted value corresponding to the project material demand to be tested is determined according to the power distribution station construction material demand prediction model and the project power distribution attribute parameter to be tested, the predicted value corresponding to the project material demand to be tested is normalized data, and the predicted effect can be better displayed by the data obtained by performing inverse normalization on the normalized data. It is conceivable that the material usage amount of the corresponding item to be tested may also be obtained through the mapping relationship table in the computer storage device.
Another embodiment of the present application further provides a prediction method, as shown in fig. 2, fig. 2 is a schematic diagram of another embodiment of the refinement procedure of step S140 in fig. 1, including but not limited to:
step S210: the normalized data set is mapped to a feature space using a kernel function.
In some embodiments, it is found in the mapping process that when the variable increases, the dimension mapped to the high-dimensional space grows exponentially, is not easy to calculate, and needs to be processed by using the kernel function degree to the standardized data set. The kernel function is used for converting the features from low dimension to high dimension, the kernel function is calculated on the low dimension, the actual classification effect is shown on the high dimension, the effect of avoiding complex calculation on the high dimension is achieved, and the same result is obtained.
In some embodiments, the kernel functions used include polynomial kernel functions, gaussian kernel functions, and linear kernel functions.
Step S220: a hyperplane is determined in the feature space, the hyperplane being the plane of minimum distance for all data in the normalized data set.
Step S230: and obtaining a power distribution station construction material demand prediction model according to the hyperplane.
In some embodiments, the obtained power distribution station construction material demand prediction model is a support vector regression model, which is an application of an SVM (support vector machine) to a regression problem; the SVM is a two-class classification model, so that the learning strategy of the power distribution station construction material demand prediction model is interval maximization, and when the practical construction problem of a transformer substation is solved, multidimensional characteristic space standardized data set mapping data cannot be directly classified by using a two-dimensional processing mode, so that the SVM is providedThe latitude of the hyperplane is only one dimension lower than that of the data to be processed, so that classification is finished; meanwhile, it is conceivable that support vector regression is to find a hyperplane so that the distance from all data to the hyperplane is the minimum, and therefore after dividing the hyperplane, the hyperplane can be expressed as: f (x) ═ ωτAnd x + b, obtaining a power distribution station construction material demand prediction model according to the calculation formula in the step S140, and no longer repeated.
Another embodiment of the present application further provides a prediction method, as shown in fig. 3, fig. 3 is a schematic diagram of another embodiment of the refinement procedure of step S130 in fig. 1, including but not limited to:
step S310: and performing K value clustering analysis on the noise reduction data set to obtain the noise reduction data set after repeated data are removed.
Step S320: and carrying out normalization processing on the noise reduction data set after the repeated data are removed to obtain a standardized data set.
In some embodiments, it is conceivable to perform K-value clustering analysis on the normalized data set, determine a clustering center according to the euclidean distance, optimize data, reduce the amount of data calculation, and improve the generation speed and the prediction accuracy of the prediction model.
Another embodiment of the application further provides a prediction method, wherein the material demand prediction model is subjected to judgment coefficient inspection, and if the judgment coefficient does not reach a threshold value, the step of determining the prediction value of the material demand of the corresponding item to be tested according to the material demand prediction model built in the power distribution station and the power distribution attribute parameters of the item to be tested is carried out again.
It is conceivable that the determination coefficient is a regression model evaluation index, and the model prediction accuracy is evaluated by comparing the regression model evaluation index with a threshold value; and if the model prediction accuracy is lower than the threshold value, iteration is carried out, and the operation of generating the model is repeated to improve the accuracy of the model prediction accuracy.
In some embodiments, denoising the power distribution attribute parameters and the material consumption, and removing the extraneous features to obtain a denoising data set, including: and (3) carrying out noise reduction treatment on the distribution attribute parameters and the material consumption by using a correlation coefficient analysis method, and removing irrelevant features to obtain a noise reduction data set, wherein the correlation coefficient analysis method comprises analysis by using covariance and a covariance matrix.
Another embodiment of the present application further provides a prediction method, as shown in fig. 4, including but not limited to:
step S410: and carrying out judgment and inspection processing on the material demand prediction model to obtain a judgment coefficient.
Step S420: and under the condition that the judgment coefficient does not reach the threshold value, determining the predicted value of the material demand of the corresponding item to be tested according to the construction material demand prediction model of the power distribution station and the power distribution attribute parameters of the item to be tested.
In some embodiments, a decision coefficient test is performed, the decision coefficient being a correlation coefficient R, the threshold comprising a first threshold and a second threshold, the correlation coefficient R test being for detecting a degree of fit of a regression of the sample to an observed value of the sample, and the calculation formula being: the square of the correlation coefficient is the regression square sum/total dispersion square sum 1-the remaining square sum/total dispersion square sum; for the judgment coefficient, although the curve fitting degree is higher as the value is closer to 1, the overfitting phenomenon occurs when the judgment coefficient is continuously closer to 1, so that the judgment coefficient is between the first threshold value and the second threshold value, and the predicted value corresponding to the material demand of the item to be measured is considered to be accurate.
In some embodiments, the step of performing the judgment coefficient test occurs after the step of performing parameter optimization processing on the standardized data set by using a support vector regression model to obtain a power distribution station construction material demand prediction model, the step of performing the judgment coefficient test on the material demand prediction model again if the judgment coefficient does not reach a threshold value, and the step of determining the predicted value of the corresponding to-be-tested item material demand according to the power distribution station construction material demand prediction model and the to-be-tested item power distribution attribute parameters according to the judgment coefficient and the threshold value.
In some embodiments, the obtaining of the power distribution attribute parameters and the material consumption corresponding to the power distribution attribute parameters of the power distribution station for historical construction includes obtaining the power distribution attribute parameters and the material consumption corresponding to the power distribution attribute parameters of the power distribution station for historical construction in a direct input mode; and extracting power distribution attribute parameters of the historical construction power distribution station and material consumption corresponding to the power distribution attribute parameters in the historical data report in a natural language processing mode, wherein the preset attribute parameters and the material consumption have a mapping relation.
Conceivably, the power distribution attribute parameters and the material consumption corresponding to the power distribution attribute parameters in the data report related to the construction of the transformer substation are extracted through natural language processing, wherein the natural language processing process comprises the steps of removing stop words, segmenting words, replacing synonyms, vectorizing corpus, calculating cosine similarity and the like; the natural language processing is adopted to save the labor consumption, expand the original data set and improve the prediction precision of the transformer substation material demand prediction model.
In some embodiments, normalizing the noise reduction data set to obtain a normalized data set, further comprises processing the noise reduction data set according to a preset weight vector, the weight vector being obtained by an analytic hierarchy process; it is conceivable to enlarge the influence of the effective data by presetting the weight vector, and improve the reliability of the data set.
Referring to fig. 5, another embodiment of the present application further provides a demand forecasting system for construction materials of a distribution substation, including:
the data preprocessing module 510 is configured to obtain power distribution attribute parameters of the historical construction power distribution station and material consumption corresponding to the power distribution attribute parameters, and preprocess the power distribution attribute parameters and the material consumption corresponding to the power distribution attribute parameters to obtain preprocessed data;
the demand prediction model construction module 520 is used for constructing a distribution station construction material demand prediction model according to the preprocessed data, and the distribution station construction material demand prediction model comprises a support vector regression model;
and the data interaction module 530 is used for performing inverse normalization processing on the predicted value according to the power distribution station construction material demand prediction model and the to-be-tested project power distribution attribute parameters to obtain the corresponding to-be-tested project material usage amount.
The power distribution station construction material demand prediction system of the embodiment of the application at least has the following beneficial effects: in the transformer substation construction process, the power distribution station construction material demand prediction system is used, the data preprocessing module 510 carries out data preprocessing on historical power distribution station construction data to obtain a power distribution station construction data set, the demand prediction model construction module 520 obtains a power distribution station construction material demand prediction model in a support vector regression model in a parameter optimizing mode according to the data set, a user determines the use amount of corresponding to-be-detected project materials through the data interaction module 530, the accuracy of a power distribution station construction material demand prediction result is improved, the construction materials are effectively utilized and managed, and the power distribution station construction process is guaranteed to be smooth.
In some embodiments, the data interaction module 530 includes a visualization operation terminal, which is used to control the data preprocessing module 510 to perform data preprocessing, and visually display the usage amount of the corresponding item to be tested, obtained by the demand prediction model construction module 520, where the visual display includes generating a data chart and generating a three-dimensional mode, so that a user can more clearly know the demand of the power distribution station construction materials, the construction materials are more effectively utilized and managed, and the smooth construction process of the power distribution station is ensured.
An embodiment of the present application further provides a substation construction material demand prediction system, which may be used to perform the prediction method in any of the above embodiments.
The above-described embodiments of the apparatus are merely illustrative, wherein the units illustrated as separate components may or may not be physically separate, i.e. may be located in one place, or may also be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
Further, an embodiment of the present application also provides a computer-readable storage medium storing computer-executable instructions for execution by one or more control processors for performing the prediction method as in any of the above embodiments.
One of ordinary skill in the art will appreciate that all or some of the steps, systems, and methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can accessed by a computer. In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as known to those skilled in the art.
While the preferred embodiments of the present invention have been described, the present invention is not limited to the above embodiments, and those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention, and such equivalent modifications or substitutions are included in the scope of the present invention defined by the claims.
Claims (10)
1. A power distribution station construction material demand prediction method based on support vectors is characterized by comprising the following steps:
acquiring power distribution attribute parameters of a historical construction power distribution station and material consumption corresponding to the power distribution attribute parameters;
denoising the power distribution attribute parameters and the material consumption, and removing irrelevant features to obtain a denoising data set;
carrying out normalization processing on the noise reduction data set to obtain a standardized data set;
performing parameter optimization processing on the standardized data set by adopting a support vector regression model to obtain a power distribution station construction material demand prediction model;
acquiring a power distribution attribute parameter of a project to be detected;
determining a predicted value corresponding to the material demand of the project to be tested according to the power distribution station construction material demand prediction model and the power distribution attribute parameters of the project to be tested;
and performing inverse normalization processing on the predicted value to obtain the material usage amount of the corresponding item to be detected.
2. The method for forecasting the demand of the construction materials of the power distribution station based on the support vector of claim 1, wherein the step of performing parameter optimization processing on the standardized data set by using a support vector regression model to obtain the forecasting model of the demand of the construction materials of the power distribution station comprises the following steps:
mapping the normalized data set to a feature space using a kernel function;
determining a hyperplane in the feature space, wherein the hyperplane is a plane with the minimum distance among all data in the standardized data set;
and obtaining a power distribution station construction material demand prediction model according to the hyperplane.
3. The method for forecasting the demand of construction materials of the power distribution station based on the support vector according to claim 1, wherein the normalizing the noise reduction data set to obtain a normalized data set comprises:
performing K value clustering analysis on the noise reduction data set to obtain the noise reduction data set from which repeated data are removed;
and carrying out normalization processing on the noise reduction data set after the repeated data are removed to obtain a standardized data set.
4. The method for forecasting the material demand of the power distribution station construction based on the support vector of claim 1, wherein after determining the forecast value of the material demand of the corresponding item to be tested according to the forecast model of the material demand of the power distribution station construction and the distribution attribute parameters of the item to be tested, the method further comprises:
carrying out judgment and inspection processing on the material demand prediction model to obtain a judgment coefficient;
and under the condition that the judgment coefficient does not reach the threshold value, determining the predicted value of the material demand of the corresponding item to be tested according to the construction material demand prediction model of the power distribution station and the power distribution attribute parameters of the item to be tested.
5. The method for forecasting the demand of the power distribution station construction materials based on the support vector of claim 1, wherein the obtaining of the power distribution attribute parameters of the historical construction power distribution station and the material consumption corresponding to the power distribution attribute parameters comprises:
and extracting the power distribution attribute parameters of the historical construction power distribution station and the material consumption corresponding to the power distribution attribute parameters in the historical data report.
6. The method for forecasting the demand of the support vector-based substation construction materials according to claim 1, wherein the denoising processing is performed on the distribution attribute parameters and the material consumption, and a denoising data set is obtained after irrelevant features are removed, including:
and carrying out noise reduction treatment on the power distribution attribute parameters and the material consumption by using a correlation coefficient analysis method, and removing irrelevant features to obtain a noise reduction data set, wherein the correlation coefficient analysis method comprises analysis by using covariance and a covariance matrix.
7. The method for forecasting the demand of construction materials of power distribution stations based on support vectors according to claim 1, wherein the normalization processing of the noise reduction data set is performed to obtain a normalized data set, and further comprising:
and processing the noise reduction data set according to a preset weight vector, wherein the weight vector is obtained by an analytic hierarchy process.
8. A power distribution station construction material demand prediction system, characterized by comprising:
the data preprocessing module is used for acquiring distribution attribute parameters of a historical construction power distribution station and material consumption corresponding to the distribution attribute parameters, denoising the distribution attribute parameters and the material consumption, removing irrelevant features to obtain a denoising data set, and normalizing the denoising data set to obtain a standardized data set;
the demand forecasting model building module is used for performing parameter optimization processing on the standardized data set by adopting a support vector regression model to obtain a power distribution station construction material demand forecasting model;
and the data interaction module is used for determining a predicted value corresponding to the material demand of the item to be tested according to the power distribution station construction material demand prediction model and the power distribution attribute parameters of the item to be tested, and performing inverse normalization processing on the predicted value to obtain the material usage amount of the corresponding item to be tested.
9. A power distribution station construction material demand prediction system comprises: memory, processor and computer program stored on the memory and executable on the processor, characterized in that the processor implements the demand prediction method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium having stored thereon computer-executable instructions for causing a computer to perform the demand prediction method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111252699.7A CN114066018A (en) | 2021-10-27 | 2021-10-27 | Power distribution station construction material demand prediction method based on support vector |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111252699.7A CN114066018A (en) | 2021-10-27 | 2021-10-27 | Power distribution station construction material demand prediction method based on support vector |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114066018A true CN114066018A (en) | 2022-02-18 |
Family
ID=80235762
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111252699.7A Pending CN114066018A (en) | 2021-10-27 | 2021-10-27 | Power distribution station construction material demand prediction method based on support vector |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114066018A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116502771A (en) * | 2023-06-21 | 2023-07-28 | 国网浙江省电力有限公司宁波供电公司 | Power distribution method and system based on electric power material prediction |
-
2021
- 2021-10-27 CN CN202111252699.7A patent/CN114066018A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116502771A (en) * | 2023-06-21 | 2023-07-28 | 国网浙江省电力有限公司宁波供电公司 | Power distribution method and system based on electric power material prediction |
| CN116502771B (en) * | 2023-06-21 | 2023-12-01 | 国网浙江省电力有限公司宁波供电公司 | Power distribution method and system based on electric power material prediction |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8756175B1 (en) | Robust and fast model fitting by adaptive sampling | |
| US20120084251A1 (en) | Probabilistic data mining model comparison | |
| CN105354595A (en) | Robust visual image classification method and system | |
| CN105786711A (en) | Data analysis method and device | |
| CN109543693A (en) | Weak labeling data noise reduction method based on regularization label propagation | |
| Zaidan et al. | Predicting atmospheric particle formation days by Bayesian classification of the time series features | |
| CN111144109B (en) | Text similarity determination method and device | |
| CN113988044B (en) | Method for judging error question reason type | |
| CN116383727A (en) | Method, system, equipment and medium for identifying coarse errors in power plant system measurement | |
| CN110310012B (en) | Data analysis method, device, equipment and computer readable storage medium | |
| CN114066018A (en) | Power distribution station construction material demand prediction method based on support vector | |
| CN111461923A (en) | Electricity stealing monitoring system and method based on deep convolutional neural network | |
| Zeybek | Inlier point preservation in outlier points removed from the ALS point cloud | |
| CN113762151A (en) | Fault data processing method and system and fault prediction method | |
| CN116109907B (en) | Target detection method, target detection device, electronic equipment and storage medium | |
| CN111598580A (en) | XGboost algorithm-based block chain product detection method, system and device | |
| CN117272145A (en) | Health state evaluation method and device of switch machine and electronic equipment | |
| CN110458581B (en) | Method and device for identifying business turnover abnormality of commercial tenant | |
| CN116451081A (en) | Data drift detection method, device, terminal and storage medium | |
| CN113177603B (en) | Training method of classification model, video classification method and related equipment | |
| CN112418313B (en) | Big data online noise filtering system and method | |
| CN115081515A (en) | Energy efficiency evaluation model construction method and device, terminal and storage medium | |
| CN105719098A (en) | Detection method and system for enterprise profit sensitivity schemes | |
| CN111913940B (en) | Temperature membership tag prediction method and device, electronic equipment and storage medium | |
| CN115392662A (en) | Quality identification grading management system and method based on image data |
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 |