CN112801418A - Power grid defect material prediction method - Google Patents

Power grid defect material prediction method Download PDF

Info

Publication number
CN112801418A
CN112801418A CN202110281744.5A CN202110281744A CN112801418A CN 112801418 A CN112801418 A CN 112801418A CN 202110281744 A CN202110281744 A CN 202110281744A CN 112801418 A CN112801418 A CN 112801418A
Authority
CN
China
Prior art keywords
model
power grid
prediction
base model
defect material
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.)
Granted
Application number
CN202110281744.5A
Other languages
Chinese (zh)
Other versions
CN112801418B (en
Inventor
俞虹
代洲
程文美
唐诚旋
蒋群群
陈珏伊
张秀
徐一蝶
王钧泽
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guizhou Power Grid Co Ltd
Original Assignee
Guizhou Power Grid Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guizhou Power Grid Co Ltd filed Critical Guizhou Power Grid Co Ltd
Priority to CN202110281744.5A priority Critical patent/CN112801418B/en
Publication of CN112801418A publication Critical patent/CN112801418A/en
Application granted granted Critical
Publication of CN112801418B publication Critical patent/CN112801418B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06F18/243—Classification techniques relating to the number of classes
    • G06F18/24323—Tree-organised classifiers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of 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
    • 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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Business, Economics & Management (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Strategic Management (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Molecular Biology (AREA)
  • Biomedical Technology (AREA)
  • Human Resources & Organizations (AREA)
  • Computing Systems (AREA)
  • Biophysics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Marketing (AREA)
  • Evolutionary Biology (AREA)
  • General Business, Economics & Management (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Tourism & Hospitality (AREA)
  • Development Economics (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • Primary Health Care (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a power grid defect material prediction method which comprises the steps of starting a plurality of threads based on the core number of a central processing unit, and performing parallel training on each base model by utilizing each thread; predicting the power grid defect materials by using the trained basic models respectively to obtain corresponding prediction results; taking the reciprocal of the root mean square error of the base model as the weight of the base model; performing weighted fusion on the weight of the base model and the prediction result to complete power grid defect material prediction; according to the invention, the speed of training the base model is increased and the prediction speed is increased in a multi-thread mode; meanwhile, the accuracy of prediction is improved by weighting and fusing multiple models.

Description

Power grid defect material prediction method
Technical Field
The invention relates to the technical field of performance optimization and material demand prediction, in particular to a power grid defect material prediction method.
Background
The stable and healthy operation of the power grid system is very important for people to live; however, the grid system is too large and the plant may not always operate perfectly. Extreme weather, emergency, equipment aging, etc. can cause grid faults.
For equipment materials of a power grid, three types are mainly used: daily equipment materials, emergency equipment materials and major disaster defect materials. The invention mainly aims at emergency equipment materials. When equipment fails, warehouses at all places need to be prepared for replacement to ensure the normal operation of the power grid; however, the warehouse in each place needs to purchase the amount of each type of material, so that the material is not lacked, and the material is not excessively stored, which becomes a problem worthy of research.
At present, most researches on the prediction of defective equipment focus on improving the prediction accuracy of a certain type of materials, but in a power grid system, different regions and different material data are distributed very differently, and the data distribution is not very regular. Therefore, to accurately predict the defective materials of the power grid hierarchy, multiple models need to be fused. The traditional fusion method is average weighted fusion, or Stacking fusion. However, both methods have some own defects, and the average weighted fusion method is too simple and has a problem in precision. The Stacking fusion method is relatively complicated, depends on the second stage fusion model, and is required to be higher in accuracy.
Meanwhile, when the models are fused, the traditional method is to train the models in series and then select and fuse the models, but the efficiency is not high; when the amount of data increases, the efficiency decreases by continuing the serial prediction and fusion.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. In this section, as well as in the abstract and the title of the invention of this application, simplifications or omissions may be made to avoid obscuring the purpose of the section, the abstract and the title, and such simplifications or omissions are not intended to limit the scope of the invention.
The present invention has been made in view of the above-mentioned conventional problems.
Therefore, the invention provides a power grid defect material prediction method, which can solve the problem of poor material prediction effect of emergency equipment.
In order to solve the technical problems, the invention provides the following technical scheme: starting a plurality of threads based on the core number of a central processing unit, and performing parallel training on each base model by using each thread; predicting the power grid defect materials by using the trained basic models respectively to obtain corresponding prediction results; taking the reciprocal of the root mean square error of the base model as the weight of the base model; and performing weighted fusion on the prediction result based on the weight of the base model to complete power grid defect material prediction.
As an optimal scheme of the power grid defect material prediction method, the method comprises the following steps: starting the plurality of threads comprises defining an implementation class of a Runnable interface and rewriting a run method of the Runnable interface; creating an instance of a Runnable implementation class; calling a parameter structure of the Thread class, transferring the instance as a parameter, and creating an object of the Thread class; the start method of the Thread class object is called.
As an optimal scheme of the power grid defect material prediction method, the method comprises the following steps: the base model comprises a ridge regression model, a lasso regression model, an elastic network regression model, a gradient lifting tree, an extreme gradient lifting model and a negative feedback neural network model.
As an optimal scheme of the power grid defect material prediction method, the method comprises the following steps: the parallel training of the base model comprises the steps of solving an optimization target according to a target formula to finish the training of the base model; the target formula is as follows:
Figure BDA0002978944590000021
wherein ,nsamplesIs the number of samples, w is the weight coefficient of the vector in each dimension of the sample, X is the sample data, y is the amount of material defect, alpha, beta are regular coefficients, | | w | | electrically non-visible1、||w||2Respectively, a first order norm and a second order norm of the coefficient.
As an optimal scheme of the power grid defect material prediction method, the method comprises the following steps: the prediction result comprises that the power grid defect materials are predicted by using the base model to respectively obtain predicted values
Figure BDA0002978944590000022
The predicted value
Figure BDA0002978944590000023
Comprises the following steps:
Figure BDA0002978944590000024
wherein ,
Figure BDA0002978944590000025
the predicted values of the power grid defect materials of the ridge regression model, the lasso regression model and the elastic network regression model are obtained, x is input feature data of the power grid materials, theta is a weight parameter vector, and T is a transposition symbol.
As an optimal scheme of the power grid defect material prediction method, the method comprises the following steps: the predicted value
Figure BDA0002978944590000026
Comprises the steps of (a) preparing a mixture of a plurality of raw materials,
Figure BDA0002978944590000031
wherein ,
Figure BDA0002978944590000032
a predicted value of defect material, f, for the gradient lifting tree and the extreme gradient lifting modelkThe kth classification regression tree, K the number of classification regression trees, and Γ the space of the classification regression trees.
As an optimal scheme of the power grid defect material prediction method, the method comprises the following steps: the predicted value
Figure BDA0002978944590000033
Comprises the steps of (a) preparing a mixture of a plurality of raw materials,
Figure BDA0002978944590000034
wherein ,
Figure BDA0002978944590000035
defect material prediction for negative feedback neural network model, w1Is a parameter of the first layer, σ is an activation function, w2Is a weight parameter of the second layer.
As an optimal scheme of the power grid defect material prediction method, the method comprises the following steps: the fitted base model is filtered out according to a threshold of the root mean square error.
The invention has the beneficial effects that: according to the invention, the speed of training the base model is increased and the prediction speed is increased in a multi-thread mode; meanwhile, the accuracy of prediction is improved by weighting and fusing multiple models.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced 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 to obtain other drawings based on these drawings without inventive exercise. Wherein:
fig. 1 is a schematic flow chart of a power grid defective material prediction method according to a first embodiment of the present invention;
fig. 2 is a schematic diagram of time distribution of power grid defective materials of a power grid defective material prediction method according to a first embodiment of the present invention;
fig. 3 is a schematic diagram illustrating comparison of prediction accuracy of a power grid defect material prediction method according to a second embodiment of the present invention;
fig. 4 is a schematic diagram of comparing parallel time and serial time of a power grid defect material prediction method according to a second embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, specific embodiments accompanied with figures are described in detail below, and it is apparent that the described embodiments are a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present invention, shall fall within the protection scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those specifically described and will be readily apparent to those of ordinary skill in the art without departing from the spirit of the present invention, and therefore the present invention is not limited to the specific embodiments disclosed below.
Furthermore, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
The present invention will be described in detail with reference to the drawings, wherein the cross-sectional views illustrating the structure of the device are not enlarged partially in general scale for convenience of illustration, and the drawings are only exemplary and should not be construed as limiting the scope of the present invention. In addition, the three-dimensional dimensions of length, width and depth should be included in the actual fabrication.
Meanwhile, in the description of the present invention, it should be noted that the terms "upper, lower, inner and outer" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation and operate, and thus, cannot be construed as limiting the present invention. Furthermore, the terms first, second, or third are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected and connected" in the present invention are to be understood broadly, unless otherwise explicitly specified or limited, for example: can be fixedly connected, detachably connected or integrally connected; they may be mechanically, electrically, or directly connected, or indirectly connected through intervening media, or may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Example 1
Referring to fig. 1 to 2, a first embodiment of the present invention provides a method for predicting defective materials of a power grid, including:
s1: and starting a plurality of threads based on the core number of the central processing unit, and performing parallel training on each base model by using each thread.
The steps of starting a plurality of threads are as follows:
(1) defining an implementation class of a Runnable interface and rewriting a run () method of the Runnable interface;
(2) creating an instance of a Runnable implementation class;
(3) calling a parameter structure of the Thread class, transferring the instance as a parameter, and creating an object of the Thread class;
(4) the start () method of the Thread class object is called.
It should be noted that the Runnable interface is a thread auxiliary class, and only one run () method is defined, and the start () method can make the thread start executing; the java virtual machine may call the run () method of the thread.
An example procedure for starting multiple threads is as follows:
Figure BDA0002978944590000051
further, each base model is trained in parallel by each thread, wherein the base models comprise a ridge regression model, a lasso regression model, an elastic network regression model, a gradient lifting tree, an extreme gradient lifting model and a negative feedback neural network model.
Specifically, the optimization target is solved according to a target formula, and training of a base model is completed;
the target formula is as follows:
Figure BDA0002978944590000061
wherein ,nsamplesIs the number of samples, w is the weight coefficient of the vector in each dimension of the sample, X is the sample data, y is the amount of material defect, alpha, beta are regular coefficients, | | w | | electrically non-visible1、||w||2Respectively, a first order norm and a second order norm of the coefficient.
Preferably, the present embodiment improves the speed of training the base model and the prediction speed by using multiple threads.
S2: and predicting the power grid defect materials by using the trained basic models respectively to obtain corresponding prediction results.
Predicting the power grid defect materials by using the basic model to respectively obtain predicted values
Figure BDA0002978944590000062
The power grid defect materials comprise a hardware fitting body, a stay wire body, a concrete pole, a porcelain insulator, a CPU plug-in unit, an overhead conductor, a switching contactor, a charging module, a composite insulator and the like, and the distribution conditions are shown in figure 2.
Prediction value
Figure BDA0002978944590000063
Comprises the following steps:
Figure BDA0002978944590000064
wherein ,
Figure BDA0002978944590000065
the power grid defect material prediction value (unit is a piece, and the value is a positive real number) of a ridge regression model, a lasso regression model and an elastic network regression model, x is input characteristic data (commissioning date, manufacturer, defect occurrence date, weather of.
Prediction value
Figure BDA0002978944590000066
In order to realize the purpose,
Figure BDA0002978944590000067
wherein ,
Figure BDA0002978944590000068
a predicted value of defect material, f, for the gradient lifting tree and the extreme gradient lifting modelkThe kth classification regression tree, K the number of classification regression trees, and Γ the space of the classification regression trees.
Prediction value
Figure BDA0002978944590000069
In order to realize the purpose,
Figure BDA00029789445900000610
wherein ,
Figure BDA00029789445900000611
defect material prediction for negative feedback neural network model, w1Is a parameter of the first layer, σ is an activation function, w2Is a weight parameter of the second layer.
S3: and taking the reciprocal of the root mean square error of the base model as the weight of the base model, and filtering the fitted base model according to the threshold value of the root mean square error.
It should be noted that the Root Mean Square Error (RMSE) is a typical indicator of the regression model, and is used to indicate how much error the model will generate in the prediction, and the calculation formula is as follows:
Figure BDA0002978944590000071
wherein n is the number of samples, yiIn the form of an actual value of the value,
Figure BDA0002978944590000072
is a predicted value.
The threshold for root mean square error was set to 0.01.
S4: and performing weighted fusion on the prediction result based on the weight of the base model to complete the power grid defect material prediction.
In the embodiment, weighted summation is carried out based on the reciprocal of RMSE, and the fitted model is filtered according to the threshold value (0.001) of RMSE, so that the prediction precision is further improved; meanwhile, the multithreading method is utilized, the core of the CPU is utilized to the maximum extent, and the computing speed is improved.
Example 2
In order to verify and explain the technical effects adopted in the method, the embodiment selects the traditional technical scheme and adopts the method to perform comparison test, and compares the test results by means of scientific demonstration to verify the real effect of the method.
The first traditional technical scheme is as follows: adopting a single model to predict the defective materials, such as only using a base learner to predict the defective materials; in consideration of the actual situation of the problem, the aim is to realize accurate prediction of various defective materials in each district and county, and then a single model cannot realize the aim; because the meteorological data of each region have differences, the damage degree and the space-time distribution of different materials also have differences.
The second traditional technical scheme is as follows: because of the problems existing in the first conventional technical scheme, improvement is needed, and the most common method is to perform multi-model fusion to improve the prediction precision; taking the model mentioned above as a base learner, and then fusing the results of the base learner; the most common fusion methods are average weighted fusion and Stacking fusion; the disadvantage of the average weighted fusion is that the fusion is too simple and rough, while the disadvantage of the Stacking fusion is relatively complex, the precision depends on the fusion model of the second stage, and the fusion is performed serially.
In order to verify that the method has simplicity, high prediction accuracy and high prediction speed compared with the traditional technical scheme, the single model prediction method in the traditional technical scheme I is compared with the average weighting fusion method and the Stacking method in the traditional scheme II; and (4) performing prediction evaluation by using real power grid defect material data and combining meteorological data.
The method utilizes real power grid defect material data, combines meteorological data and utilizes Python to write codes so as to compare and analyze the three schemes; during prediction, each kind of data of each county (Wudang, cloud rock, Xiiwen, Nanming, Shuanglong, North city, river, Kaiyang, beacon, Huishi, Qingzhen, Baiyun, Huaxi, Jinyang and Longli) is subjected to prediction, and then the mean square error RMSE of real data and a prediction result is calculated.
The results are shown in FIGS. 3 and 4; FIG. 3 is a summary RMSE comparison of the prediction results for each county after applying the RMSE-based weighted fusion method, showing that the prediction accuracy of the method is higher than that of the average weighted fusion method and the Stacking method; FIG. 4 is a comparison of performance, and it can be seen that the present method predicts by using multiple threads much faster than single thread training (single model prediction) and the results of the prediction; under the existing data condition, the single-thread method needs 97s, but the method only needs 90 s; and it is anticipated that the more models, the higher the acceleration achieved by the multi-threaded approach; the more cores of the CPU, the better acceleration ratio can be obtained; the larger the data volume is, the more obvious the advantages of multithreading can be reflected.
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.

Claims (8)

1. A power grid defect material prediction method is characterized by comprising the following steps: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
starting a plurality of threads based on the core number of the central processing unit, and performing parallel training on each base model by using each thread;
predicting the power grid defect materials by using the trained basic models respectively to obtain corresponding prediction results;
taking the reciprocal of the root mean square error of the base model as the weight of the base model;
and performing weighted fusion on the prediction result based on the weight of the base model to complete power grid defect material prediction.
2. The grid defect material prediction method of claim 1, wherein: the opening of the plurality of threads includes,
defining an implementation class of the Runnable interface and rewriting a run method of the Runnable interface;
creating an instance of a Runnable implementation class;
calling a parameter structure of the Thread class, transferring the instance as a parameter, and creating an object of the Thread class;
the start method of the Thread class object is called.
3. A grid defect material prediction method as claimed in claim 2, characterized in that: the base model may include a base model that includes,
ridge regression model, lasso regression model, elastic network regression model, gradient lifting tree, extreme gradient lifting model, and negative feedback neural network model.
4. A grid defect material prediction method as claimed in claim 1 or 3, characterized by: the parallel training of the base model includes,
solving the optimization target according to a target formula to complete the training of the base model;
the target formula is as follows:
Figure FDA0002978944580000011
wherein ,nsamplesIs the number of samples, w is the weight coefficient of the vector in each dimension of the sample, X is the sample data, y is the amount of material defect, alpha, beta are regular coefficients, | | w | | electrically non-visible1、||w||2Respectively, a first order norm and a second order norm of the coefficient.
5. The optimized model-parallel defect material prediction method of claim 4, wherein: the result of the prediction may include,
predicting the power grid defect materials by using the base model to respectively obtain predicted values
Figure FDA0002978944580000012
The predicted value
Figure FDA0002978944580000021
Comprises the following steps:
Figure FDA0002978944580000022
wherein ,
Figure FDA0002978944580000023
the predicted values of the power grid defect materials of the ridge regression model, the lasso regression model and the elastic network regression model are obtained, x is input feature data of the power grid materials, theta is a weight parameter vector, and T is a transposition symbol.
6. The optimized model-parallel defect material prediction method of claim 5, wherein: the predicted value
Figure FDA0002978944580000024
Comprises the steps of (a) preparing a mixture of a plurality of raw materials,
Figure FDA0002978944580000025
wherein ,
Figure FDA0002978944580000026
a predicted value of defect material, f, for the gradient lifting tree and the extreme gradient lifting modelkThe kth classification regression tree, K the number of classification regression trees, and Γ the space of the classification regression trees.
7. The optimized model-parallel defect material prediction method of claim 4 or 5, wherein: the predicted value
Figure FDA0002978944580000027
Comprises the steps of (a) preparing a mixture of a plurality of raw materials,
Figure FDA0002978944580000028
wherein ,
Figure FDA0002978944580000029
defect material prediction for negative feedback neural network model, w1Is a parameter of the first layer, σ is an activation function, w2Is a weight parameter of the second layer.
8. The grid defect material prediction method of claim 1, wherein: also comprises the following steps of (1) preparing,
the fitted base model is filtered out according to a threshold of the root mean square error.
CN202110281744.5A 2021-03-16 2021-03-16 Method for predicting defective materials of power grid Active CN112801418B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110281744.5A CN112801418B (en) 2021-03-16 2021-03-16 Method for predicting defective materials of power grid

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110281744.5A CN112801418B (en) 2021-03-16 2021-03-16 Method for predicting defective materials of power grid

Publications (2)

Publication Number Publication Date
CN112801418A true CN112801418A (en) 2021-05-14
CN112801418B CN112801418B (en) 2023-10-10

Family

ID=75816976

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110281744.5A Active CN112801418B (en) 2021-03-16 2021-03-16 Method for predicting defective materials of power grid

Country Status (1)

Country Link
CN (1) CN112801418B (en)

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111639815A (en) * 2020-06-02 2020-09-08 贵州电网有限责任公司 Method and system for predicting power grid defect materials through multi-model fusion
CN112365077A (en) * 2020-11-20 2021-02-12 贵州电网有限责任公司 Construction method of intelligent storage scheduling system for power grid defective materials
CN112488404A (en) * 2020-12-07 2021-03-12 广西电网有限责任公司电力科学研究院 Multithreading efficient prediction method and system for large-scale power load of power distribution network

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111639815A (en) * 2020-06-02 2020-09-08 贵州电网有限责任公司 Method and system for predicting power grid defect materials through multi-model fusion
CN112365077A (en) * 2020-11-20 2021-02-12 贵州电网有限责任公司 Construction method of intelligent storage scheduling system for power grid defective materials
CN112488404A (en) * 2020-12-07 2021-03-12 广西电网有限责任公司电力科学研究院 Multithreading efficient prediction method and system for large-scale power load of power distribution network

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
刘佳颖: "基于模型融合的空气质量预测研究", 《中国优秀硕士学位论文全文数据库 工程科技I辑》 *
陈艳平 徐受蓉: "《Java语言程序设计实用教程 第2版》", 31 January 2019 *

Also Published As

Publication number Publication date
CN112801418B (en) 2023-10-10

Similar Documents

Publication Publication Date Title
CN109687458B (en) Grid planning method considering regional distribution network risk bearing capacity difference
CN110705873B (en) Power distribution network running state portrait analysis method
Mamadou et al. Definition of a state-of-energy indicator (SoE) for electrochemical storage devices: application for energetic availability forecasting
CN106295911B (en) A kind of grid branch parameter evaluation method based on chromatographic assays
CN108764684A (en) Intelligent box substation health state evaluation method based on Fuzzy AHP
CN108733928B (en) SCD file virtual circuit automatic checking method based on intermediate model file
CN105471647B (en) A kind of power communication network fault positioning method
CN109143074A (en) A kind of power battery model parameter identification method and system
CN110927581A (en) Multi-level index evaluation method for operating state of energy storage equipment based on entropy weight method
CN108132441A (en) The range of operation of energy-storage battery module state-of-charge determines method and device
CN116561573A (en) Training set circulation splitting training method for voltage stability evaluation
CN110824375A (en) Method for calculating actual capacity of retired storage battery
CN112686404B (en) Power distribution network fault first-aid repair-based collaborative optimization method
CN116894165B (en) Cable aging state assessment method based on data analysis
CN112684294B (en) Distribution network fault rush-repair positioning method based on dynamic influence of environment
CN112801418A (en) Power grid defect material prediction method
CN107563641B (en) Disaster-resistant multi-scene differentiation planning method for power distribution network considering disaster preference
CN113283492A (en) Photovoltaic output scene generation method and scene generation device based on Catboost algorithm
CN113269351A (en) Feature selection method for power grid equipment fault probability prediction
CN113516280A (en) Optimization method for power grid equipment fault probability prediction based on big data
CN115311509A (en) Power system transient stability evaluation method and system based on imaging data driving
CN111553040B (en) Power grid topology analysis high-performance computing method and device based on GPU acceleration
CN114170291A (en) Power equipment inspection method
CN113466630A (en) RSSPN model-based power distribution network fault reason classification method
Angadi et al. An ensemble based data mining model for contingency analysis of power system under STLO

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
GR01 Patent grant
GR01 Patent grant