CN111488896A - Distribution line time-varying fault probability calculation method based on multi-source data mining - Google Patents

Distribution line time-varying fault probability calculation method based on multi-source data mining Download PDF

Info

Publication number
CN111488896A
CN111488896A CN201910080205.8A CN201910080205A CN111488896A CN 111488896 A CN111488896 A CN 111488896A CN 201910080205 A CN201910080205 A CN 201910080205A CN 111488896 A CN111488896 A CN 111488896A
Authority
CN
China
Prior art keywords
fault
data
distribution line
historical
rate
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
CN201910080205.8A
Other languages
Chinese (zh)
Other versions
CN111488896B (en
Inventor
韩新阳
张钧
王东
宋金根
苏峰
靳晓凌
吴国威
张全
杨军
田鑫
张岩
代贤忠
王大玮
张玥
张沛
周建其
谢桦
柴玉凤
王旭斌
陈昊
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.)
State Grid Zhejiang Electric Power Co Ltd
State Grid Energy Research Institute Co Ltd
Original Assignee
State Grid Zhejiang Electric Power Co Ltd
State Grid Energy Research Institute 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 State Grid Zhejiang Electric Power Co Ltd, State Grid Energy Research Institute Co Ltd filed Critical State Grid Zhejiang Electric Power Co Ltd
Priority to CN201910080205.8A priority Critical patent/CN111488896B/en
Publication of CN111488896A publication Critical patent/CN111488896A/en
Application granted granted Critical
Publication of CN111488896B publication Critical patent/CN111488896B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • 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)
  • Data Mining & Analysis (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a distribution line time-varying fault probability calculation method based on multi-source data mining, which comprises the following steps of: determining historical fault data of the power distribution network, historical meteorological data and the geographical position of a transformer substation to which each feeder line belongs; screening out data of faults caused by severe weather as a training sample set; respectively counting the fault rate and the repair rate of the distribution line in normal weather and severe weather; constructing an SVM meteorological classifier according to the training sample set and an SVM method; modeling by using a Fock-Planck equation; and determining the time-varying fault probability of the distribution line obtained by current meteorological calculation. The method and the system fully consider the influence of severe meteorological factors on the fault of the distribution line based on the reliability statistical data and the historical meteorological data stored in the power distribution network informatization system, realize automatic and accurate calculation and analysis of the fault probability of the distribution line, and can effectively and accurately calculate the time-varying fault probability of the distribution line.

Description

Distribution line time-varying fault probability calculation method based on multi-source data mining
Technical Field
The invention relates to the technical field of power system analysis, in particular to a method for calculating distribution line time-varying fault probability based on multi-source data mining.
Background
Along with the development of a power distribution network, the grid structure is increasingly complex, the permeability of renewable energy sources in the power distribution network is continuously improved, distribution line faults caused by risk sources of different types all bring a lot of challenges to the operation of the power distribution network, and risk assessment becomes an indispensable link for the operation of the power distribution network.
The accurate calculation of the distribution line fault probability is the basis of operation risk assessment, and the methods for calculating the distribution line fault probability in the prior art are mainly divided into an element outage steady-state probability method, a random fuzzy variable modeling method, a manual scoring method and a fuzzy expert system method. The component outage steady-state probability method represents the failure probability of the distribution line by the steady-state probability in the markov process, and fails to characterize the time-varying characteristics of the distribution line failure during operation. In the power distribution network operation risk assessment, time-varying values reflecting different operation condition conditions are adopted to represent fault probability; the existing method adopts a random fuzzy variable modeling method and combines expert experience to calculate the time-varying fault probability of different lines.
However, the random fuzzy variable modeling, the manual scoring method and the fuzzy reasoning method have strong subjectivity, and may bring certain errors to the calculation of the distribution line fault probability. In addition, researchers also respectively provide a time-varying fault probability calculation method for the distribution line based on different types of risk sources. But distribution lines can receive multiple risk sources to act simultaneously in operation, for example, bad weather such as lightning stroke, strong wind, distribution lines self factors such as ageing and defect. It is not comprehensive to consider only a single source of risk in the above studies.
In view of this, it is urgently needed to provide a distribution line operation risk time-varying fault probability calculation method which truly reflects the time-varying fault probability of a distribution line under different operation conditions based on multi-source data such as external weather and line self-state, and to provide a reference for a scheduling operator to evaluate the system operation risk.
Disclosure of Invention
In order to solve the technical problems, the technical scheme adopted by the invention is to provide a distribution line time-varying fault probability calculation method based on multi-source data mining, which comprises the following steps:
s1, determining historical fault data of the power distribution network, historical meteorological data and the geographical position of a transformer substation to which each feeder line belongs according to the collected power grid data;
s2, screening out data of faults caused by severe weather according to historical fault data, and finding out corresponding weather data in the historical weather data to be used as a training sample set;
s3, respectively counting the fault rate and the repair rate of the distribution line in normal weather and the fault rate and the repair rate in severe weather;
s4, constructing an SVM meteorological classifier according to the training sample set and the SVM method;
s5, modeling the distribution line state transition process in the step S3 by using a Fock-Planck equation;
s6, determining the current weather, and determining the fault rate and the repair rate in the current operation state according to the step S4;
s7, substituting the fault rate and the repair rate determined in the step S6 into a Fock-Planck equation, and calculating to obtain the time-varying fault probability of the distribution line;
wherein, historical meteorological data includes: daily average temperature, daily maximum/low temperature, daily average wind speed, daily cumulative precipitation, daily cumulative lightning stroke; and screening out data of severe weather due to thunderstorm, strong wind and ice coating from historical fault data.
In the above method, the step S2 includes:
the distribution line operation training sample set is as follows:
S＝{(xi，yi)，xi∈Rn，yi∈{0，1}}
in the formula, XiRepresenting the ith n-dimensional input directionVolume, including meteorological data of temperature, wind speed, precipitation, lightning strike, humidity;
yithe distribution line is classified according to whether the current distribution line running state has a fault or not; y isi0 indicates that no fault occurs in the distribution line in the current-day operating state, and yi1 means that the number of times of the line failure is greater than 0 on the day, and means that the line failure occurs.
In the above method, the step S3 includes:
by the classification statistics of the data with the fault and the data without the fault in step S2, the state transition rate λ in the fault-prone environment can be obtained separately01As shown in the following formula:
Figure BDA0001960142930000031
in the formula, NLjiIndicating i-th fault, T, occurring on j-th lineLIndicating the duration of the operating condition;
repair rate mu01The following formula:
Figure BDA0001960142930000032
in the formula, RLjiDenotes the ith repair, D, of the jth lineLIndicating the duration of the operating condition.
In the above method, the step S4 includes:
constructing a classification plane equation as follows:
f(x)＝＜ω·x＞+b
wherein ω is (ω)1,ω1...ωn) Is a weight vector, x ═ x1,x2...xm)T(ii) a b is a threshold value, training errors are used as constraint conditions, and relaxation variables are introduced, so that the optimization problem of the maximum separation surface of the two types of samples can be represented as follows:
Figure BDA0001960142930000041
s.t. yi[＜ω·x＞+b]≥1-ξi
Figure BDA0001960142930000042
0≤αi≤C,ξi≥0,i＝1,2...,l
where C > 0 is a penalty factor, with a larger value indicating a greater penalty for an exceeded data point.
In the method, the distribution line state transition process in step S5 is modeled as follows:
Figure BDA0001960142930000043
P′(t)＝P(t)Q
in the formula, P0Probability of feeder being in normal operation, P1Is the probability that the feeder is in the fault state.
The invention provides a distribution line operation risk time-varying fault probability calculation method based on multi-source data mining, which is based on reliability statistical data and historical meteorological data stored in a power distribution network informatization system, fully considers the influence of severe meteorological factors on the distribution line fault, realizes automatic and accurate calculation and analysis of the distribution line fault probability, and can effectively and accurately calculate the distribution line time-varying fault probability. The method avoids errors caused by judgment of a dispatcher according to self experience, can objectively reflect the fault probability of the distribution line in different meteorological environments, and realizes accurate judgment and analysis of the operation risk of the distribution network.
Drawings
FIG. 1 is a flow chart provided by the present invention;
FIG. 2 is a schematic diagram illustrating a calculation process of a distribution line operation risk time-varying fault probability provided by the present invention;
figure 3 is a schematic diagram of a two-state cycle process framework for fault-repair of a distribution line according to the present invention.
Detailed Description
The invention is described in detail below with reference to specific embodiments and the accompanying drawings.
As shown in fig. 1-2, the invention provides a distribution line operation risk time-varying fault probability calculation method based on multi-source data mining, which comprises the following steps:
s1, determining historical fault data, historical meteorological data, historical load data and the geographical position of the transformer substation to which each feeder line belongs according to the collected power grid data;
the historical meteorological data includes: daily average temperature, daily maximum/low temperature, daily average wind speed, daily cumulative precipitation, daily cumulative lightning stroke, daily average solar radiation, daily average air pressure, daily specific humidity, daily relative humidity, and the like. And screening out data of faults caused by severe weather such as thunderstorm, strong wind, ice coating and the like from the historical fault data, and finding out corresponding weather data from the historical weather data to be used as a training sample.
S2, screening out data of faults caused by severe weather according to the historical fault data, and finding out corresponding weather data in the historical weather data to be used as a training sample set.
The distribution line training sample set is represented by:
S＝{(xi,yi)，xi∈Rn,yi∈{0,1}} (1)
in the formula, xiAnd representing the ith n-dimensional input vector, including meteorological data such as temperature, wind speed, precipitation, lightning stroke, humidity and the like. y isiThe distribution line is classified according to whether the current distribution line running state has a fault or not; label yi0 indicates that no fault occurs in the distribution line in the current-day operating state, and the label yi1 means that the number of times of the line failure is greater than 0 on the day, and means that the line failure occurs.
And S3, respectively counting the fault rate and the repair rate of the distribution line in normal weather and the fault rate and the repair rate in severe weather. As shown in FIG. 3, the fault-repair two-state cycle of distribution lines, whether in normal or inclement weather, is described, where λ01The fault rate of the distribution line from a normal operation state to a fault state under the action of two types of risk sources is a value which changes along with time and the operation condition of the distribution line; mu.s01The repair rate of the distribution line from the fault state to the normal operation state is shown.
By performing the classification statistics on the data with the fault and the data without the fault in step S2, the fault rate λ in the fault-prone environment can be obtained separately01As shown in the following formula:
Figure BDA0001960142930000051
in the formula, NLjiIndicating i-th fault, T, occurring on j-th lineLIndicating the duration of the operating condition.
Repair rate mu01The following formula:
Figure BDA0001960142930000061
in the formula, RLjiDenotes the ith repair, D, of the jth lineLIndicating the duration of the operating condition.
S4, constructing an SVM weather classifier according to the training sample set and an SVM (Support Vector Machine) method, wherein the SVM weather classifier comprises the following steps:
constructing a classification plane equation as follows:
f(x)＝＜ω·x＞+b (4)
wherein ω is (ω)1,ω1...ωn) Is a weight vector, x ═ x1,x2...xm)TB is a threshold value, the training error is taken as a constraint condition, and a relaxation variable ξ is introducediThe optimization problem that maximizes the separation plane for both types of samples can be expressed as:
Figure BDA0001960142930000062
where C > 0 is a penalty factor, with a larger value indicating a greater penalty for an exceeded data point.
And (3) solving the following quadratic programming problem with linear inequality constraint by adopting a Lagrange multiplier method according to the problem, namely the quadratic programming problem with linear inequality constraint in conversion:
Figure BDA0001960142930000063
in the formula (I), the compound is shown in the specification,
Figure BDA0001960142930000064
is a lagrange multiplier.
The optimization problem can be solved by adopting a Lagrange multiplier method; by introducing a kernel function k (x, x)i) The objective function becomes:
Figure BDA0001960142930000071
in the formula, αi,αjMore than or equal to 0(i, j ═ 1, 2.., l) is lagrange multiplier, xiFor the ith sample, xjIs the j-th sample, and i is 1, 2.
Of all the kernel functions, the radial basis function has a good effect on handling the non-linearity problem, and if fewer parameters are to be determined than the polynomial kernel function, the radial basis function K (x)iAnd x) is of the formula:
Figure BDA0001960142930000072
in the selection of parameters of the SVM, a grid search method is adopted in the embodiment to train the values m and n for C and σ, and a group of parameters with the highest prediction accuracy is selected as parameters of a kernel function in the SVM model according to a model training result.
S5, modeling the distribution line state transition process in the step S3 by using a Fock-Planck equation, which is specifically shown as the following formula:
Figure BDA0001960142930000073
P′(t)＝P(t)Q (9)
in the formula, P0Probability of feeder being in normal operation, P1Is the probability that the feeder is in the fault state.
S6, determining the current weather, and determining the fault rate lambda under the current operation state according to the step S401And the repair rate mu01。
S7, determining the fault rate lambda determined in the step S601And the repair rate mu01And substituting the value into a Fock-Planck equation, and calculating to obtain the time-varying fault probability P of the distribution line.
The invention provides a distribution line operation risk time-varying fault probability calculation method based on multi-source data mining, which is based on reliability statistical data and historical meteorological data stored in a power distribution network informatization system, fully considers the influence of severe meteorological factors on the distribution line fault, realizes automatic and accurate calculation and analysis of the distribution line fault probability, and can effectively and accurately calculate the distribution line time-varying fault probability. The method avoids errors caused by judgment of a dispatcher according to self experience, can objectively reflect the fault probability of the distribution line in different meteorological environments, and realizes accurate judgment and analysis of the operation risk of the distribution network.
The present embodiment will be described below by way of specific examples
In the case, 828 total power accident statistical data of 120 feeders in a certain area in south, namely monthly power accident statistical data from 1 month 2014 to 2015 month 7 are collected. The fault feature variable is selected according to the fault feature variable selection method proposed in the above embodiment, the obtained optimal fault feature variable is shown in table 1, and the evaluation value of the optimal fault feature subset is 0.722.
TABLE 1 optimal Fault feature variables
Type (B) Fault signature variable
Feeder fault characteristics Transformer substation to which fault occurrence time and feeder line belong
External influencing factor Maximum daily temperature, minimum daily temperature, average daily humidity, and average daily wind speed
Self-influencing factor Line length
Factor of influence of operation Line load
By adopting the time-varying fault probability calculation method provided by the embodiment, the time-varying fault probability of all the distribution lines under severe weather can be calculated. The time-varying fault probability and the loss load risk value of the partial distribution line are shown in the table 2 and the table 3.
TABLE 2 probability of time-varying faults for partial lines
Figure BDA0001960142930000081
Figure BDA0001960142930000091
TABLE 3 loss of load risk values for partial lines
Figure BDA0001960142930000092
The present invention is not limited to the above-mentioned preferred embodiments, and any structural changes made under the teaching of the present invention shall fall within the protection scope of the present invention, which has the same or similar technical solutions as the present invention.

Claims (5)

1. A distribution line time-varying fault probability calculation method based on multi-source data mining is characterized by comprising the following steps:
s1, determining historical fault data of the power distribution network, historical meteorological data and the geographical position of a transformer substation to which each feeder line belongs according to the collected power grid data;
s2, screening out data of faults caused by severe weather according to historical fault data, and finding out corresponding weather data in the historical weather data to be used as a training sample set;
s3, respectively counting the fault rate and the repair rate of the distribution line in normal weather and the fault rate and the repair rate in severe weather;
s4, constructing an SVM meteorological classifier according to the training sample set and the SVM method;
s5, modeling the distribution line state transition process in the step S3 by using a Fock-Planck equation;
s6, determining the current weather, and determining the fault rate and the repair rate in the current operation state according to the step S4;
s7, substituting the fault rate and the repair rate determined in the step S6 into a Fock-Planck equation, and calculating to obtain the time-varying fault probability of the distribution line;
wherein, historical meteorological data includes: daily average temperature, daily maximum/low temperature, daily average wind speed, daily cumulative precipitation, daily cumulative lightning stroke; and screening out data of severe weather due to thunderstorm, strong wind and ice coating from historical fault data.
2. The computing method according to claim 1, wherein the step S2 includes:
the distribution line operation training sample set is as follows:
S＝{(xi，yi)，xi∈Rn，yi∈{0，1}}
in the formula, xiRepresenting the ith n-dimensional input vector, including meteorological data of temperature, wind speed, precipitation, lightning stroke and humidity;
yithe distribution line is classified according to whether the current distribution line running state has a fault or not; y isi0 indicates that no fault occurs in the distribution line in the current-day operating state, and yi1 means that the number of times of the line failure is greater than 0 on the day, and means that the line failure occurs.
3. The computing method according to claim 2, wherein the step S3 includes:
by the classification statistics of the data with the fault and the data without the fault in step S2, the state transition rate λ in the fault-prone environment can be obtained separately01As shown in the following formula:
Figure FDA0001960142920000021
in the formula, NLjiIndicating i-th fault, T, occurring on j-th lineLIndicating the duration of the operating condition;
repair rate mu01The following formula:
Figure FDA0001960142920000022
in the formula, RLjiDenotes the ith repair, D, of the jth lineLIndicating the duration of the operating condition.
4. The computing method according to claim 3, wherein the step S4 includes:
constructing a classification plane equation as follows:
y＝<ω·x>+b
wherein ω is (ω)1，ω1...ωn) Is a weight vector, x ═ x1，x2...xm)T(ii) a b is a threshold value, and takes a training error as a constraint condition and introducesThe optimization problem of relaxing the variable ξ so that the separation plane is the largest for both types of samples can be expressed as:
Figure FDA0001960142920000031
s.t.yi[<ω·x>+b]≥1-ξi
Figure FDA0001960142920000032
0≤αi≤C，ξi≥0，i＝1，2...，l
where C > 0 is a penalty factor, with a larger value indicating a greater penalty for an exceeded data point.
5. The method of claim 1 wherein the distribution line state transition process of step S5 is modeled as follows:
Figure FDA0001960142920000033
P′(t)＝P(t)Q
in the formula, P0Probability of feeder being in normal operation, P1Is the probability that the feeder is in the fault state.
CN201910080205.8A 2019-01-28 2019-01-28 Distribution line time-varying fault probability calculation method based on multi-source data mining Active CN111488896B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910080205.8A CN111488896B (en) 2019-01-28 2019-01-28 Distribution line time-varying fault probability calculation method based on multi-source data mining

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910080205.8A CN111488896B (en) 2019-01-28 2019-01-28 Distribution line time-varying fault probability calculation method based on multi-source data mining

Publications (2)

Publication Number Publication Date
CN111488896A true CN111488896A (en) 2020-08-04
CN111488896B CN111488896B (en) 2023-08-11

Family

ID=71795890

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910080205.8A Active CN111488896B (en) 2019-01-28 2019-01-28 Distribution line time-varying fault probability calculation method based on multi-source data mining

Country Status (1)

Country Link
CN (1) CN111488896B (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112749904A (en) * 2021-01-14 2021-05-04 国网湖南省电力有限公司 Power distribution network fault risk early warning method and system based on deep learning
CN112785138A (en) * 2021-01-18 2021-05-11 内蒙古电力（集团）有限责任公司呼和浩特供电局 Method for carrying out three-span line monitoring analysis early warning based on numerical weather
CN113052224A (en) * 2021-03-19 2021-06-29 国网河南省电力公司电力科学研究院 Interactive fusion method and system for power and meteorological multi-source data
CN113469457A (en) * 2021-07-22 2021-10-01 中国电力科学研究院有限公司 Power transmission line fault probability prediction method fused with attention mechanism
CN113553547A (en) * 2021-07-15 2021-10-26 广西电网有限责任公司电力科学研究院 Overhead line time-varying fault probability calculation system and method
CN114638169A (en) * 2022-03-29 2022-06-17 国网能源研究院有限公司 Method and device for calculating time-varying fault probability of transformer and computer readable storage medium
CN116187583A (en) * 2023-04-17 2023-05-30 国网黑龙江省电力有限公司齐齐哈尔供电公司 Power distribution network big data fault prediction method

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140297235A1 (en) * 2013-01-31 2014-10-02 Betazi, Llc Production analysis and/or forecasting methods, apparatus, and systems
WO2016033883A1 (en) * 2014-09-04 2016-03-10 国家电网公司 Power transmission line gallop risk early-warning method based on adaboost
CN107516170A (en) * 2017-08-30 2017-12-26 东北大学 A kind of difference self-healing control method based on probability of equipment failure and power networks risk

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140297235A1 (en) * 2013-01-31 2014-10-02 Betazi, Llc Production analysis and/or forecasting methods, apparatus, and systems
WO2016033883A1 (en) * 2014-09-04 2016-03-10 国家电网公司 Power transmission line gallop risk early-warning method based on adaboost
CN107516170A (en) * 2017-08-30 2017-12-26 东北大学 A kind of difference self-healing control method based on probability of equipment failure and power networks risk

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
段涛;罗毅;施琳;朱益华;陈建军;李鹏;: "计及气象因素的输电线路故障概率的实时评估模型" *
黄景德;郝学良;: "基于模糊积分的潜隐性故障状态转移过程分析" *

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112749904A (en) * 2021-01-14 2021-05-04 国网湖南省电力有限公司 Power distribution network fault risk early warning method and system based on deep learning
CN112749904B (en) * 2021-01-14 2023-06-27 国网湖南省电力有限公司 Power distribution network fault risk early warning method and system based on deep learning
CN112785138A (en) * 2021-01-18 2021-05-11 内蒙古电力（集团）有限责任公司呼和浩特供电局 Method for carrying out three-span line monitoring analysis early warning based on numerical weather
CN113052224A (en) * 2021-03-19 2021-06-29 国网河南省电力公司电力科学研究院 Interactive fusion method and system for power and meteorological multi-source data
CN113052224B (en) * 2021-03-19 2022-07-22 国网河南省电力公司电力科学研究院 Interactive fusion method and system for power and meteorological multi-source data
CN113553547A (en) * 2021-07-15 2021-10-26 广西电网有限责任公司电力科学研究院 Overhead line time-varying fault probability calculation system and method
CN113469457A (en) * 2021-07-22 2021-10-01 中国电力科学研究院有限公司 Power transmission line fault probability prediction method fused with attention mechanism
CN113469457B (en) * 2021-07-22 2024-04-19 中国电力科学研究院有限公司 Power transmission line fault probability prediction method integrating attention mechanism
CN114638169A (en) * 2022-03-29 2022-06-17 国网能源研究院有限公司 Method and device for calculating time-varying fault probability of transformer and computer readable storage medium
CN114638169B (en) * 2022-03-29 2024-06-07 国网能源研究院有限公司 Transformer time-varying fault probability calculation method, device and computer readable storage medium
CN116187583A (en) * 2023-04-17 2023-05-30 国网黑龙江省电力有限公司齐齐哈尔供电公司 Power distribution network big data fault prediction method
CN116187583B (en) * 2023-04-17 2023-11-03 国网黑龙江省电力有限公司齐齐哈尔供电公司 Power distribution network big data fault prediction method

Also Published As

Publication number Publication date
CN111488896B (en) 2023-08-11

Similar Documents

Publication Publication Date Title
CN111488896B (en) Distribution line time-varying fault probability calculation method based on multi-source data mining
WO2021213192A1 (en) Load prediction method and load prediction system employing general distribution
CN111695736B (en) Photovoltaic power generation short-term power prediction method based on multi-model fusion
CN102478584B (en) Wind power station wind speed prediction method based on wavelet analysis and system thereof
CN113496311A (en) Photovoltaic power station generated power prediction method and system
CN103473621A (en) Wind power station short-term power prediction method
WO2011101189A2 (en) Energy generating system and control thereof
CN105069521A (en) Photovoltaic power plant output power prediction method based on weighted FCM clustering algorithm
CN111626473A (en) Two-stage photovoltaic power prediction method considering error correction
CN114386753A (en) Equipment risk comprehensive analysis early warning method based on main transformer load condition
CN110365053A (en) Short-term wind power forecast method based on delay optimisation strategy
Chen et al. Research on wind power prediction method based on convolutional neural network and genetic algorithm
CN112183877A (en) Photovoltaic power station fault intelligent diagnosis method based on transfer learning
CN115829145A (en) Photovoltaic power generation capacity prediction system and method
CN115859099A (en) Sample generation method and device, electronic equipment and storage medium
CN108960522A (en) A kind of photovoltaic power generation quantity prediction analysis method
CN117669960A (en) New energy power prediction method based on multivariable meteorological factors
CN115169659A (en) Ultra-short-term roof photovoltaic power prediction method and system based on multiple classifiers
CN113991711A (en) Capacity configuration method for energy storage system of photovoltaic power station
CN113610285A (en) Power prediction method for distributed wind power
CN117200223A (en) Day-ahead power load prediction method and device
KR20190071174A (en) Method and system for short-term wind speed prediction based on pressure data
CN107909096A (en) A kind of fault of converter early warning criterion implementation method based on two points of K mean clusters
CN110309978B (en) Neural network photovoltaic power prediction model and method based on secondary dynamic adjustment
CN111815051A (en) GRNN photovoltaic power generation prediction method considering weather influence factors

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