CN111458769B - Method and system for predicting environmental meteorological data of power transmission line - Google Patents

Method and system for predicting environmental meteorological data of power transmission line Download PDF

Info

Publication number
CN111458769B
CN111458769B CN202010453119.XA CN202010453119A CN111458769B CN 111458769 B CN111458769 B CN 111458769B CN 202010453119 A CN202010453119 A CN 202010453119A CN 111458769 B CN111458769 B CN 111458769B
Authority
CN
China
Prior art keywords
data
meteorological
model
transmission line
training
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010453119.XA
Other languages
Chinese (zh)
Other versions
CN111458769A (en
Inventor
路通
岳圣凯
袁明磊
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.)
Nanjing University
Original Assignee
Nanjing University
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 Nanjing University filed Critical Nanjing University
Priority to CN202010453119.XA priority Critical patent/CN111458769B/en
Publication of CN111458769A publication Critical patent/CN111458769A/en
Application granted granted Critical
Publication of CN111458769B publication Critical patent/CN111458769B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01W—METEOROLOGY
    • G01W1/00—Meteorology
    • G01W1/10—Devices for predicting weather conditions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—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
    • 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
    • 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
    • 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
    • G06Q50/10—Services
    • G06Q50/26—Government or public services

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Economics (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • Tourism & Hospitality (AREA)
  • Data Mining & Analysis (AREA)
  • Strategic Management (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Marketing (AREA)
  • General Engineering & Computer Science (AREA)
  • General Business, Economics & Management (AREA)
  • Environmental & Geological Engineering (AREA)
  • Primary Health Care (AREA)
  • Mathematical Physics (AREA)
  • Development Economics (AREA)
  • Molecular Biology (AREA)
  • Biomedical Technology (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Water Supply & Treatment (AREA)
  • Ecology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Atmospheric Sciences (AREA)
  • Biodiversity & Conservation Biology (AREA)
  • Educational Administration (AREA)
  • Environmental Sciences (AREA)
  • Public Health (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Game Theory and Decision Science (AREA)

Abstract

The invention discloses a method and a system for predicting environmental meteorological data of a power transmission line, which relate to the technical field of meteorological model prediction and solve the technical problems of poor anti-dryness capability and easy data interference of the traditional meteorological prediction method. The final prediction model obtained by the method has strong anti-drying capacity, is not easily interfered by abnormal data, and has more accurate prediction data compared with the existing model.

Description

Method and system for predicting environmental meteorological data of power transmission line
Technical Field
The disclosure relates to the technical field of meteorological prediction models, in particular to a method and a system for power transmission line environmental meteorological data prediction.
Background
With global warming and circulation abnormality, extreme weather appears more frequently, and ice disasters in the south of China cause large-area tower collapse, tower damage, broken lines, insulator falling and other faults of a power grid in recent years, so that large-area long-time power failure is caused, normal production and life are seriously affected, and heavy power grid repair burden is brought. The weather prediction plays an important role in various fields of power planning, disaster prevention and reduction, real-time monitoring and the like of a power system, for example, the output power of a photovoltaic power generation system depends on the solar radiation quantity received by a photovoltaic panel to a great extent, the solar radiation quantity is directly related to various weather factors, and the prediction of the photovoltaic output power cannot leave the prediction of the weather. In a power system containing wind power generation, wind power fluctuation caused by random variation of wind speed is directly related to the stability and control problems of the power system. Therefore, in order to predict such disaster problems in advance and deploy preventive measures in time, it is necessary to predict weather conditions in the future accurately and in time.
The traditional techniques for weather prediction are mainly performed by satellite cloud maps, statistics or dynamic-statistical methods. With the rapid development of artificial intelligence technology in recent years, many researches for weather prediction based on artificial intelligence related technology appear, and the intelligent degree, the accuracy and the like are improved to a certain extent. However, due to the complexity and difficulty of the meteorological prediction problem, especially the meteorological prediction of the power transmission line environment, which has a high requirement on accuracy, once misjudgment is made, the application scene of normal production safety of society may be affected, and the current related method still has the problems of low prediction accuracy, poor anti-interference capability and the like, and cannot accurately predict the meteorological conditions at the future time.
Disclosure of Invention
The invention provides a method and a system for forecasting meteorological data of the environment of a power transmission line, and the technical purpose is to ensure that the meteorological data forecasting method has strong anti-dryness capability and is not easily interfered by abnormal data.
The technical purpose of the present disclosure is achieved by the following technical solutions:
a method for power transmission line environmental meteorological data prediction comprises the following steps:
s1: acquiring environmental meteorological data of the power transmission line and weather forecast data at corresponding time to form a data set D;
s2: dividing the D into a training set D1 and a testing set D2;
s3: putting the training set D1 into a TCN model for training to obtain a meteorological prediction model, wherein the TCN model is a time domain convolution network combined with a weighting channel;
s4: putting a test set D2 into the meteorological prediction model for testing, adjusting the hyper-parameter theta of the meteorological prediction model according to the test effect, and repeating the step S3 until the meteorological prediction model converges or reaches the maximum iteration times to obtain a final prediction model;
s5: and inputting the data set D into the final prediction model to predict the meteorological information of the power transmission line.
Further, the data set D includes: temperature at a height of 2 meters above ground, relative humidity at a height of 2 meters above ground, wind speed at a height of 10 meters above ground, and corresponding weather forecast data.
Further, the step S3 includes:
s31: dividing data in the training set D1 into 1, 2.. and n groups, wherein n is a positive integer greater than 1, and the value range of the data group contained in each group is [32,64,128 ];
s32: for the 1 st set of meteorological data sequence x in the training set D11＝[x11,x21,...,xn1]Extracting the characteristics to obtain a characteristic matrix F1＝[F11,F21,...,Fn1]；
S33: the feature matrix F1Inputting the full connection layer L (.) of the TCN model for training, and outputting a predicted value
Figure BDA0002508291190000031
m is a positive integer;
s34: calculating the said
Figure BDA0002508291190000032
Mean square error MSE (1) with actual meteorological data;
s35: optimizing the hyper-parameter Θ using a small batch gradient descent method MBGD in combination with the MSE (1);
s36: reading the data of group 2, inputting the data into the TCN model after the optimization of the hyper-parameter Θ, and repeating the steps S31 to S36 until mse (n) gradually converges or the maximum number of iterations is reached.
Further, the feature matrix
Figure BDA0002508291190000033
Figure BDA0002508291190000034
Figure BDA0002508291190000035
Wherein x isnIs the meteorological data sequence [ x ] of the nth group1n,x2n,...,xnn]，
Figure BDA0002508291190000036
Vectors, w, representing the composition of hidden variables of the i-th layerkRepresenting a channel weighting parameter, k being the number of channels, and Residual (.) being a Residual block in the TCN model.
Further, the feature matrix Fn＝[F1n,F2n,...,Fnn]Inputting the predicted vector into the full connection layer L (), and outputting the predicted vector consisting of m predicted values
Figure BDA0002508291190000037
Then
Figure BDA0002508291190000038
Figure BDA0002508291190000039
Wherein, YiRepresenting the real value of the meteorological data, and m represents the number of predicted values output by the full connection layer.
A system for power transmission line environmental meteorological data prediction, comprising:
the data acquisition module is used for acquiring environmental meteorological data of the power transmission line and weather forecast data at corresponding time to form a data set D;
a random division module dividing the D into a training set D1 and a test set D2;
the model training module is used for putting the training set D1 into a TCN model for training to obtain a meteorological prediction model, wherein the TCN model is a time domain convolution network combined with a weighting channel;
the model testing module is used for inputting a testing set D2 into the meteorological prediction model for testing, adjusting the hyper-parameter theta of the meteorological prediction model according to a testing effect, and repeating model training until the meteorological prediction model converges or reaches the maximum iteration times to obtain a final prediction model;
and the prediction module is used for inputting the data set D into the final prediction model to predict the meteorological information of the power transmission line.
Further, the data set D includes: temperature at a height of 2 meters above ground, relative humidity at a height of 2 meters above ground, wind speed at a height of 10 meters above ground, and corresponding weather forecast data.
Further, the model training module comprises:
a grouping unit, which is used for dividing the data in the training set D1 into 1,2, and n groups, wherein n is a positive integer greater than 1, and the value range of the data group contained in each group is [32,64,128 ];
a feature extraction unit for the 1 st group of meteorological data sequences x in the training set D11＝[x11,x21,...,xn1]Extracting the characteristics to obtain a characteristic matrix F1＝[F11,F21,...,Fn1]；
A training unit for transforming the feature matrix F1Inputting the full connection layer L (.) of the TCN model for training, and outputting a predicted value
Figure BDA0002508291190000041
m is a positive integer;
a calculation unit calculating the
Figure BDA0002508291190000042
Mean square error MSE (1) with actual meteorological data;
and the optimization unit is used for optimizing the hyper-parameter theta by using a small batch gradient descent method MBGD in combination with the MSE (1).
Further, the feature matrix
Figure BDA0002508291190000051
Figure BDA0002508291190000052
Figure BDA0002508291190000053
Wherein x isnIs the meteorological data sequence [ x ] of the nth group1n,x2n,...,xnn]，
Figure BDA0002508291190000054
Vectors, w, representing the composition of hidden variables of the i-th layerkRepresenting a channel weighting parameter, k being the number of channels, and Residual (.) being a Residual block in the TCN model.
Further, the feature matrix Fn＝[F1n,F2n,...,Fnn]Inputting the predicted vector into the full connection layer L (), and outputting the predicted vector consisting of m predicted values
Figure BDA0002508291190000055
Then
Figure BDA0002508291190000056
Figure BDA0002508291190000057
Wherein, YiRepresenting the real value of the meteorological data, and m represents the number of predicted values output by the full connection layer.
The beneficial effect of this disclosure lies in: the method and the system for predicting the environmental meteorological data of the power transmission line acquire the environmental meteorological data of the power transmission line and the weather forecast data of corresponding time, divide the data into a training set and a test set, put the training set into a TCN model combined with a weighting channel for training to obtain a meteorological prediction model, test the meteorological prediction model by using the test set, adjust the hyper-parameter theta of the meteorological prediction model, and repeat model training until the meteorological prediction model converges or reaches the maximum iteration number to obtain a final prediction model. The final prediction model obtained by the method has strong anti-drying capacity, is not easily interfered by abnormal data, and has more accurate prediction data compared with the existing model.
Drawings
FIG. 1 is a flow chart of the disclosed method;
FIG. 2 is a schematic diagram of a channel weighting method;
fig. 3 is a system framework diagram of the present disclosure.
Detailed Description
The technical scheme of the disclosure will be described in detail with reference to the accompanying drawings.
A sensor is arranged near the power transmission line to acquire meteorological data of the surrounding environment of the power transmission line, and the actual meteorological data are recorded according to weather forecast data, so that the sensor can acquire the meteorological data in real time. The period and content of the acquisition data set D are for example:
acquisition period of data set D: one hour;
acquisition content of data set D: including at least the temperature at a height of 2 meters above the ground, the relative humidity at a height of 2 meters above the ground, the wind speed at a height of 10 meters above the ground, and corresponding weather forecast data.
Then establishing a one-to-one correspondence relationship between the collected meteorological data and the corresponding weather forecast data according to time, arranging the sorted meteorological data and the corresponding weather forecast data according to a time sequence, finally counting the number of time sequence entries, and dividing the data set D into a training set D1 and a testing set D2 according to a ratio of 9: 1.
The TCN model with channel weighting and its full connection layer are used to fit the current n sets of historical meteorological data and the corresponding weather forecast data to obtain m sets of predicted values of future meteorological data as the power transmission line environment meteorological prediction model output by the TCN model, as shown in the flowchart of the method of the present disclosure shown in fig. 1.
FIG. 2 is a schematic diagram of a channel weighting method according to the present disclosure, as shown in FIG. 2, a feature matrix
Figure BDA0002508291190000071
Figure BDA0002508291190000072
Figure BDA0002508291190000073
Wherein x isnIs the meteorological data sequence [ x ] of the nth group1n,x2n,...,xnn]The vector is formed by splicing the collected data and the weather forecast data;
Figure BDA0002508291190000074
the vector which represents the component of the hidden variable of the ith layer, namely the output of the residual block of the ith layer; w is akRepresenting channel weighting parameters, l, K and K are all hyperparameters, l is taken
Figure BDA0002508291190000079
K may be [8,16,32,64,128,256 ]](ii) a Residual (.) is a Residual block in the TCN model.
The feature matrix Fn＝[F1n,F2n,...,Fnn]Inputting the prediction vector into a full connection layer L (), and outputting the prediction vector consisting of m prediction values
Figure BDA0002508291190000075
Then
Figure BDA0002508291190000076
Figure BDA0002508291190000077
Wherein, YiRepresenting the true value of the meteorological data, m representing the number of predicted values output by the fully-connected layer, MSE (n) being
Figure BDA0002508291190000078
Mean square error with actual meteorological data. The hyper-parameters Θ (Θ representing in the present application all the hyper-parameters of the TCN model) are optimized using the small batch gradient descent method MBGD in combination with the mse (n) until the mse (n) converges gradually or reaches a maximum number of iterations, preferably the mse (n) is less than 1 or reaches a maximum number of iterations 500.
After a meteorological prediction model is obtained, the environmental meteorological data of the power transmission line are tested on a test set D2, the effect of the model is detected, and the hyper-parameters are adjusted according to the effect of the model, such as: learning rate lr, momentum factor mu, input sequence length n, predicted sequence length m, channel weighting parameter wkNumber of channels k, etc. And jumping to step S3 to retrain until the meteorological prediction model obtains satisfactory effect on the test set, and obtaining the final prediction model.
Prediction of future meteorological data, for example:
inputting: predicting meteorological data of three time sequences before a time point;
and (3) outputting: x month and x day at 0 point, humidity of 0.4, temperature of-1.8 deg.C, wind speed of 0.4m/s,
x month and x day at 2 points, humidity 0.6, temperature-2.4 deg.C, wind speed 5.1m/s,
x month and x day at 4 points, humidity of 0.4, temperature of-2.5 deg.C, wind speed of 3.2m/s, etc.
Fig. 3 is a schematic diagram of the system of the present disclosure, and specific system components are not described again. The method and the system for predicting the meteorological data of the environment of the power transmission line provided by the invention have many methods and ways for implementing the technical scheme, the above description is only a preferred embodiment of the invention, and it should be noted that, for those skilled in the art, a plurality of improvements and modifications can be made without departing from the principle of the invention, and these improvements and modifications should also be regarded as the protection scope of the invention. All the components not specified in the present embodiment can be realized by the prior art.

Claims (6)

1. A method for predicting environmental meteorological data of a power transmission line is characterized by comprising the following steps:
s1: acquiring environmental meteorological data of the power transmission line and weather forecast data at corresponding time to form a data set D;
s2: dividing the D into a training set D1 and a testing set D2;
s3: putting the training set D1 into a TCN model for training to obtain a meteorological prediction model, wherein the TCN model is a time domain convolution network combined with a weighting channel;
s4: putting a test set D2 into the meteorological prediction model for testing, adjusting the hyper-parameter theta of the meteorological prediction model according to the test effect, and repeating the step S3 until the meteorological prediction model converges or reaches the maximum iteration times to obtain a final prediction model;
s5: inputting the data set D into the final prediction model to predict meteorological information of the power transmission line;
wherein the step S3 includes:
s31: dividing data in the training set D1 into 1, 2.. and n groups, wherein n is a positive integer greater than 1, and the value range of the data group contained in each group is [32,64,128 ];
s32: for the 1 st set of meteorological data sequence x in the training set D11＝[x11,x21,...,xn1]Extracting the characteristics to obtain a characteristic matrix F1＝[F11,F21,...,Fn1]；
S33: the feature matrix F1Inputting the full connection layer L (.) of the TCN model for training, and outputting a predicted value
Figure FDA0002985923190000011
m is a positive integer;
s34: calculating the said
Figure FDA0002985923190000012
Mean square error MSE (1) with actual meteorological data;
s35: optimizing the hyper-parameter Θ using a small batch gradient descent method MBGD in combination with the MSE (1);
s36: reading the data of the group 2, inputting the data into the TCN model after the hyper-parameter theta optimization, and repeating the steps S31 to S36 until MSE (n) gradually converges or the maximum iteration number is reached;
and a feature matrix
Figure FDA0002985923190000013
Figure FDA0002985923190000014
Figure FDA0002985923190000015
Wherein x isnIs the meteorological data sequence [ x ] of the nth group1n,x2n,...,xnn]，
Figure FDA0002985923190000016
Vectors, w, representing the composition of hidden variables of the i-th layerkRepresenting a channel weighting parameter, k being the number of channels, and Residual (.) being a Residual block in the TCN model.
2. The method for prediction of meteorological data for an electric transmission line environment of claim 1, wherein the data set D comprises: temperature at a height of 2 meters above ground, relative humidity at a height of 2 meters above ground, wind speed at a height of 10 meters above ground, and corresponding weather forecast data.
3. The method for forecasting meteorological data of the environment of the power transmission line according to claim 2, wherein the feature matrix F isn＝[F1n,F2n,...,Fnn]Inputting the predicted vector into the full connection layer L (), and outputting the predicted vector consisting of m predicted values
Figure FDA0002985923190000021
Then
Figure FDA0002985923190000022
Figure FDA0002985923190000023
Wherein, YiRepresenting the real value of the meteorological data, and m represents the number of predicted values output by the full connection layer.
4. A system for power transmission line environmental meteorological data prediction, comprising:
the data acquisition module is used for acquiring environmental meteorological data of the power transmission line and weather forecast data at corresponding time to form a data set D;
a random division module dividing the D into a training set D1 and a test set D2;
the model training module is used for putting the training set D1 into a TCN model for training to obtain a meteorological prediction model, wherein the TCN model is a time domain convolution network combined with a weighting channel;
the model testing module is used for inputting a testing set D2 into the meteorological prediction model for testing, adjusting the hyper-parameter theta of the meteorological prediction model according to a testing effect, and repeating model training until the meteorological prediction model converges or reaches the maximum iteration times to obtain a final prediction model;
the prediction module is used for inputting the data set D into the final prediction model to predict the meteorological information of the power transmission line;
wherein the model training module comprises:
a grouping unit, which is used for dividing the data in the training set D1 into 1,2, and n groups, wherein n is a positive integer greater than 1, and the value range of the data group contained in each group is [32,64,128 ];
feature extraction sheetMeta, for the 1 st set of meteorological data sequences x in the training set D11＝[x11,x21,...,xn1]Extracting the characteristics to obtain a characteristic matrix F1＝[F11,F21,...,Fn1]；
A training unit for transforming the feature matrix F1Inputting the full connection layer L (.) of the TCN model for training, and outputting a predicted value
Figure FDA0002985923190000024
m is a positive integer;
a calculation unit calculating the
Figure FDA0002985923190000025
Mean square error MSE (1) with actual meteorological data;
the optimization unit is used for optimizing the hyper-parameter theta by using a small batch gradient descent method MBGD in combination with the MSE (1);
and a feature matrix
Figure FDA0002985923190000026
Figure FDA0002985923190000031
Figure FDA0002985923190000032
Wherein x isnIs the meteorological data sequence [ x ] of the nth group1n,x2n,...,xnn]，
Figure FDA0002985923190000033
Vectors, w, representing the composition of hidden variables of the i-th layerkRepresenting a channel weighting parameter, k being the number of channels, and Residual (.) being a Residual block in the TCN model.
5. The system for prediction of meteorological data for an electric transmission line environment of claim 4, wherein the data set D comprises: temperature at a height of 2 meters above ground, relative humidity at a height of 2 meters above ground, wind speed at a height of 10 meters above ground, and corresponding weather forecast data.
6. The system for forecasting meteorological data for an electric transmission line environment of claim 5, wherein the feature matrix Fn＝[F1n,F2n,...,Fnn]Inputting the predicted vector into the full connection layer L (), and outputting the predicted vector consisting of m predicted values
Figure FDA0002985923190000034
Then
Figure FDA0002985923190000035
Figure FDA0002985923190000036
Wherein, YiRepresenting the real value of the meteorological data, and m represents the number of predicted values output by the full connection layer.
CN202010453119.XA 2020-05-26 2020-05-26 Method and system for predicting environmental meteorological data of power transmission line Active CN111458769B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010453119.XA CN111458769B (en) 2020-05-26 2020-05-26 Method and system for predicting environmental meteorological data of power transmission line

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010453119.XA CN111458769B (en) 2020-05-26 2020-05-26 Method and system for predicting environmental meteorological data of power transmission line

Publications (2)

Publication Number Publication Date
CN111458769A CN111458769A (en) 2020-07-28
CN111458769B true CN111458769B (en) 2021-05-28

Family

ID=71682874

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010453119.XA Active CN111458769B (en) 2020-05-26 2020-05-26 Method and system for predicting environmental meteorological data of power transmission line

Country Status (1)

Country Link
CN (1) CN111458769B (en)

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112363251A (en) * 2020-10-26 2021-02-12 上海眼控科技股份有限公司 Weather prediction model generation method, weather prediction method and device
CN112561199B (en) * 2020-12-23 2024-06-21 北京百度网讯科技有限公司 Weather parameter prediction model training method, weather parameter prediction method and device
CN113222019B (en) * 2021-05-13 2024-05-28 中国南方电网有限责任公司超高压输电公司检修试验中心 Meteorological forecast data processing method, device and equipment for transmission line tower
CN113642234A (en) * 2021-08-09 2021-11-12 贵州电网有限责任公司 Power grid icing prediction method based on multi-source characteristic time convolution deep learning
CN114066057A (en) * 2021-11-16 2022-02-18 五凌电力有限公司 Meteorological data prediction method, apparatus, device, storage medium and program product

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110110930A (en) * 2019-05-08 2019-08-09 西南交通大学 A kind of Recognition with Recurrent Neural Network Short-Term Load Forecasting Method improving whale algorithm

Family Cites Families (29)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH01200473A (en) * 1988-02-04 1989-08-11 Tokyo Electric Co Ltd Transmission and reception device for pos system
JPH0573530A (en) * 1991-09-17 1993-03-26 Toshiba Corp Method and device for inflow prediction
WO2009116105A2 (en) * 2008-03-21 2009-09-24 Gianfranco Antonini A traffic assignment method for multimodal transportation networks
CA2772023A1 (en) * 2009-08-18 2011-02-24 Ben Gurion University Of The Negev Research And Development Authority System and method for analyzing imaging data
IN2014DN05828A (en) * 2012-02-20 2015-05-15 Toshiba Kk
US20140372038A1 (en) * 2013-04-04 2014-12-18 Sky Motion Research, Ulc Method for generating and displaying a nowcast in selectable time increments
CN103616734B (en) * 2013-12-11 2015-11-18 山东大学 Synchronous real time meteorological data is measured and wind speed and direction prognoses system and method on a large scale
CN104361414B (en) * 2014-11-24 2020-01-07 武汉大学 Power transmission line icing prediction method based on correlation vector machine
CN105787270B (en) * 2016-02-25 2018-06-08 国网山东省电力公司电力科学研究院 A kind of transmission line of electricity Multiple Time Scales load capacity dynamic prediction method
AU2017273520B2 (en) * 2016-05-31 2020-04-09 Accuweather, Inc. Method and system for predicting the impact of forecasted weather, environmental and/or geologic conditions
CN106157177A (en) * 2016-07-29 2016-11-23 国网电力科学研究院武汉南瑞有限责任公司 A kind of transmission line of electricity snowfall wide area monitoring and pre-alarming method based on miniradar
US10183677B2 (en) * 2016-09-20 2019-01-22 Ford Global Technologies, Llc Ice and snow detection systems and methods
CN107203810A (en) * 2017-05-22 2017-09-26 河海大学 A kind of precipitation Forecasting Methodology based on depth network
US20190114546A1 (en) * 2017-10-12 2019-04-18 Nvidia Corporation Refining labeling of time-associated data
EP3480822A1 (en) * 2017-11-01 2019-05-08 Icon Clinical Research Limited A prediction modelling system for clinical trials
CN108508505B (en) * 2018-02-05 2020-12-15 南京云思创智信息科技有限公司 Heavy rainfall and thunderstorm forecasting method and system based on multi-scale convolutional neural network
CN108761461B (en) * 2018-05-29 2022-02-18 南京信息工程大学 Rainfall forecasting method based on weather radar echo time sequence image
CN109190578B (en) * 2018-09-13 2019-10-18 合肥工业大学 The sign language video interpretation method merged based on convolution network with Recognition with Recurrent Neural Network
CN109447260B (en) * 2018-10-08 2022-11-18 中国人民解放军空军研究院战场环境研究所 Local numerical weather forecast product correction method based on deep learning
CN109492823B (en) * 2018-11-26 2021-04-30 南京大学 Method for predicting icing thickness of power transmission line
US10573312B1 (en) * 2018-12-04 2020-02-25 Sorenson Ip Holdings, Llc Transcription generation from multiple speech recognition systems
CN110188397B (en) * 2019-05-06 2022-07-19 南瑞集团有限公司 Model and method for predicting icing of overhead transmission line
CN110334589B (en) * 2019-05-23 2021-05-14 中国地质大学（武汉） High-time-sequence 3D neural network action identification method based on hole convolution
CN110442860A (en) * 2019-07-05 2019-11-12 大连大学 Name entity recognition method based on time convolutional network
CN110221360A (en) * 2019-07-25 2019-09-10 广东电网有限责任公司 A kind of power circuit thunderstorm method for early warning and system
CN110728411B (en) * 2019-10-18 2022-04-12 河海大学 High-low altitude area combined rainfall prediction method based on convolutional neural network
CN110889535B (en) * 2019-10-28 2022-07-12 国网江西省电力有限公司电力科学研究院 Multi-point wind speed prediction method in wind power plant based on convolution cyclic neural network
CN110837137A (en) * 2019-11-07 2020-02-25 刘健华 Typhoon prediction alarm method
CN111126680A (en) * 2019-12-11 2020-05-08 浙江大学 Road section traffic flow prediction method based on time convolution neural network

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110110930A (en) * 2019-05-08 2019-08-09 西南交通大学 A kind of Recognition with Recurrent Neural Network Short-Term Load Forecasting Method improving whale algorithm

Also Published As

Publication number Publication date
CN111458769A (en) 2020-07-28

Similar Documents

Publication Publication Date Title
CN111458769B (en) Method and system for predicting environmental meteorological data of power transmission line
CN109934423B (en) Photovoltaic power station power prediction method and system based on grid-connected inverter operation data
CN102945508B (en) Model correction based wind power forecasting method
CN110570122B (en) Offshore wind power plant reliability assessment method considering wind speed seasonal characteristics and current collection system element faults
CN113496311A (en) Photovoltaic power station generated power prediction method and system
CN109978242A (en) The photovoltaic power generation cluster power forecasting method and device of scale are risen based on statistics
CN111695736B (en) Photovoltaic power generation short-term power prediction method based on multi-model fusion
CN106570593A (en) Photovoltaic power station output data repairing method based on weather information
CN104598715B (en) A kind of region wind-powered electricity generation power predicating method based on Climatological forecasting wind speed
CN111311027A (en) Wind speed prediction method for power transmission line
CN112925825A (en) Multi-meteorological-factor prediction method for power transmission line
WO2021063461A1 (en) Method for planning a layout of a renewable energy site
CN114021830A (en) Multi-time-range wind speed prediction method based on CNN-LSTM
CN113379142A (en) Short-term wind power prediction method based on wind speed correction and fusion model
CN108694479A (en) Consider the distribution network reliability prediction technique that weather influences time between overhaul
CN112801332A (en) Short-term wind speed prediction method based on gray level co-occurrence matrix
CN115730524A (en) Machine learning-based numerical simulation virtual anemometry error correction method
CN117763353A (en) Offshore wind turbine model training method suitable for digital twin system
CN103632314B (en) Wind energy turbine set generalized node feature modeling method based on probability statistics
CN118312576A (en) Prediction method and system for high-temperature heat wave-drought composite disaster and electronic equipment
CN113984198A (en) Short wave radiation prediction method and system based on convolutional neural network
Cheggaga et al. A neural network solution for extrapolation of wind speeds at heights ranging for improving the estimation of wind producible
CN116842839A (en) Power distribution facility rain and waterlogging submerged power outage risk prediction method and related device
CN110059972B (en) Daily solar radiation resource assessment method based on functional deep belief network
CN115912334A (en) Method for establishing prediction model of output guarantee rate of wind power plant and prediction method

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