CN116167609A - Power system risk assessment method based on neural network model - Google Patents

Power system risk assessment method based on neural network model Download PDF

Info

Publication number
CN116167609A
CN116167609A CN202211095913.7A CN202211095913A CN116167609A CN 116167609 A CN116167609 A CN 116167609A CN 202211095913 A CN202211095913 A CN 202211095913A CN 116167609 A CN116167609 A CN 116167609A
Authority
CN
China
Prior art keywords
power system
neural network
network model
fault
severity
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202211095913.7A
Other languages
Chinese (zh)
Inventor
龙云
张少凡
刘璐豪
梁雪青
卢有飞
赵宏伟
吴任博
陈明辉
刘超
王历晔
刘俊
刘晓明
赵誉
彭鑫
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.)
Guangzhou Power Supply Bureau of Guangdong Power Grid Co Ltd
Original Assignee
Guangzhou Power Supply Bureau of Guangdong 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 Guangzhou Power Supply Bureau of Guangdong Power Grid Co Ltd filed Critical Guangzhou Power Supply Bureau of Guangdong Power Grid Co Ltd
Priority to CN202211095913.7A priority Critical patent/CN116167609A/en
Publication of CN116167609A publication Critical patent/CN116167609A/en
Pending legal-status Critical Current

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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • 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
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • 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

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

Abstract

The invention discloses a power system risk assessment method based on a neural network model, which comprises the following steps: s1, acquiring historical meteorological data and historical operation data of a power system, acquiring fault probabilities of different meteorological conditions according to the historical meteorological data and the historical operation data, and forming a vulnerable curve; s2, constructing a neural network model, and training the model by utilizing historical meteorological data and historical operation data according to a vulnerable curve formed by the fault probability to obtain a trained model; s3, inputting real-time meteorological data and real-time operation data into a model, and outputting various topological structure sets and fault probabilities under various topological structures by the model; s4, calculating line power flow under various topological structures, obtaining risk indexes of fault severity according to the line power flow, and calculating the fault severity under various topological structures; s5, acquiring a comprehensive risk index according to the fault probability and the fault severity under various topological structures, and evaluating the risk of the power system through the comprehensive risk index.

Description

Power system risk assessment method based on neural network model
Technical Field
The invention relates to the technical field of power, in particular to a power system risk assessment method based on a neural network model.
Background
The evaluation of the conventional power system is mainly aimed at the stability of the power system, i.e. the ability of the power system to maintain stability after a fault. In particular deterministic faults, such as the "N-1" criterion, i.e. the ability of the power system to stabilize after all elements have failed independently in sequence is evaluated. As the scale of the power system is enlarged and the structure is complex, the uncertainty of the power system is more and more obvious, and the following aspects are mainly shown: grid connection of renewable energy sources such as solar energy, light energy and the like increases uncertainty of a power generation side of a power system; the expansion of the load scale and the complexity of the type increase the uncertainty of the load side of the power system, such as an electric automobile and the like, which are not only the load of the power system, but also can play a role in regulating and controlling the charge and discharge of the power system; the increasingly worse external environment of extreme weather, etc., increases the uncertainty of the power system failure. In summary, the conventional deterministic evaluation method cannot meet the fault characteristic requirements of the modern power system. The probability of occurrence of the power system faults is gradually considered in the power system evaluation, and the probability of occurrence of the power system faults is evaluated by introducing the reliability evaluation. With the occurrence of power failure of large power systems at home and abroad, expert students find that the reliability cannot accurately evaluate the faults.
The power system, particularly the overhead transmission line, is exposed to the external environment, and the frequent occurrence of extreme weather directly threatens the safety and stability of the power system. Extreme weather events are events that occur over a period of time, are less frequent, and have a severe impact on economic and social energy. Aiming at extreme meteorological events with small probability and serious consequences, the risk assessment method can comprehensively assess the influence and the damage degree of the extreme meteorological events on the power system. Firstly, because the frequency of occurrence of extreme weather events is limited, the probability index of faults cannot be obtained based on statistics of a large amount of historical fault data, and the probability of faults is obtained through simulation of the surrounding environment of a power system and mass scene simulation by a better research method, namely modeling simulation. Secondly, indexes for measuring the fault result comprise a plurality of indexes such as the number of broken lines, the number of inverted towers, the occurrence times of short-circuit faults, social and economic losses and the like. Extreme weather events are increasingly a significant factor in threatening the safe and stable operation of power systems. The existing method evaluates the influence of the extreme event on the power system, and can not rapidly and accurately analyze the risk condition.
Disclosure of Invention
The invention aims to solve the problem that the risk of a power system cannot be rapidly and accurately estimated in the prior art, and provides a power system risk estimation method based on a neural network model, which predicts the fault probability of the power system under various topological structures and remarkably improves the operation intelligence and safety of the power system.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
a power system risk assessment method based on a neural network model comprises the following steps:
s1, acquiring historical meteorological data and historical operation data of a power system, acquiring fault probabilities of different meteorological conditions according to the historical meteorological data and the historical operation data of the power system, and forming a vulnerable curve;
s2, constructing a neural network model, and training the neural network model by utilizing a vulnerable curve formed by the fault probability and combining historical meteorological data and historical operation data to obtain a trained neural network model;
s3, inputting real-time meteorological data and real-time operation data of the power system into a neural network model, and outputting various topological structure sets and fault probabilities of the power system under various topological structures by the neural network model;
s4, calculating line power flow of the power system under various topological structures, obtaining risk indexes of fault severity of the power system according to the line power flow, and calculating the fault severity of the power system under various topological structures;
s5, acquiring a comprehensive risk index of the power system according to the fault probability and the fault severity of the power system under various topological structures, and evaluating the operation risk of the power system through the comprehensive risk index.
Preferably, the probability of failure of different meteorological conditions is represented by a vulnerable curve, which is calculated by the following formula:
Figure BDA0003838628810000021
wherein P(s) is the probability that the power system is in or exceeds a damage state under dangerous stress s;
Figure BDA0003838628810000022
is the average engineering stress when the dangerous stress s reaches the damage state threshold; beta is the standard deviation of the natural logarithm of engineering stress when the dangerous stress s reaches the damage state threshold value; Φ is a standard normal cumulative distribution function.
Preferably, the neural network model adopts a Bayesian neural network, the neural network model comprises an input layer, a hidden layer and an output layer, and the neural network model has the structure as follows:
l 0 ＝x
l i ＝s i (W i *l i-1 +b i )
y＝l n
wherein x is an input, l 0 For input layer, l i-1 Is the i-1 layer hidden layer, l i Is the i-th hidden layer, W i Weights of hidden layers for the ith layer, b i For the deviation of the i-th hidden layer, l n And y is output for the output layer.
Preferably, the parameter θ= (W, b) of the bayesian neural network obeys a random probability distribution p (θ), W is the weight of the hidden layer, b is the deviation of the hidden layer, and p (θ) is the probability distribution function of the parameter θ.
Preferably, since the parameter θ= (W, b) obeys a random probability distribution p (θ), different output values of the same input value and probabilities of the different output values can be obtained through the bayesian neural network.
Preferably, the risk indicator measuring the severity of a fault in the power system includes a severity of line overload and a severity of voltage out-of-limit.
Preferably, the calculation formula of the voltage out-of-limit severity is:
Figure BDA0003838628810000031
in the method, in the process of the invention,
Figure BDA0003838628810000032
is the voltage out-of-limit of the power system node i under the j-th topological structure at the moment tSeverity of (I)>
Figure BDA0003838628810000033
The voltage of the power system node i under the j-th topological structure at the moment t.
Preferably, the calculation formula of the overload severity of the line is:
Figure BDA0003838628810000034
in the method, in the process of the invention,
Figure BDA0003838628810000035
for the line overload severity of the power system line l under the j-th topological structure at the moment t, < ->
Figure BDA0003838628810000036
And the load factor of the power system circuit l under the j-th topological structure at the moment t.
Preferably, the severity of the fault of the power system under various topologies is:
Figure BDA0003838628810000037
in the formula Sev (V) j,t ,ρ j,t ) For the fault severity of the power system under the j-th topological structure at the moment of t, V j,t For the voltage of the power system under the j-th topological structure at the moment t, ρ j,t For the line load rate alpha of the power system under the j-th topological structure at the moment t i As a weight factor of node i, beta l Is the weighting factor for line l.
Preferably, the calculation formula of the comprehensive risk index is:
Figure BDA0003838628810000038
wherein, risk is the comprehensive Risk index of the power system, J is the total number of topological structures under certain meteorological conditions,
Figure BDA0003838628810000039
the fault probability of the power system under the j-th topological structure.
Compared with the prior art, the method and the device have the advantages that the fault probability data of the power elements under different meteorological conditions are obtained according to the historical meteorological data and the historical operation data of the power system, the neural network model is constructed, the fault probability of the power system under various topological structures is predicted through the neural network model, the risk condition under various topological conditions can be rapidly calculated according to the fault probability and the fault severity of the power system under different topological structures, and the operation intelligence and the operation safety of the power system are remarkably improved.
Drawings
Fig. 1 is a flowchart of a power system risk assessment method based on a neural network model.
Fig. 2 is a schematic diagram of a bayesian neural network.
FIG. 3 is a schematic diagram of the wind speed condition of the affected line.
Fig. 4 is a graph of fault probabilities for a power system under various topologies.
Fig. 5 is a comprehensive risk schematic diagram of the power system.
Detailed Description
The power system risk assessment method based on the neural network model is further described below with reference to the accompanying drawings and specific embodiments.
Referring to fig. 1, the invention discloses a power system risk assessment method based on a neural network model, which comprises the following steps:
s1, acquiring historical meteorological data and historical operation data of a power system, acquiring fault probabilities of different meteorological conditions according to the historical meteorological data and the historical operation data of the power system, and forming a vulnerable curve.
S2, constructing a neural network model, and training the neural network model by utilizing a vulnerable curve formed by the fault probability and combining historical meteorological data and historical operation data to obtain a trained neural network model.
S3, inputting real-time meteorological data and real-time operation data of the power system into a neural network model, and outputting various topological structure sets and fault probabilities of the power system under various topological structures by the neural network model.
S4, calculating line power flow of the power system under various topological structures, obtaining risk indexes of fault severity of the power system according to the line power flow, and calculating the fault severity of the power system under various topological structures.
S5, acquiring a comprehensive risk index of the power system according to the fault probability and the fault severity of the power system under various topological structures, and evaluating the operation risk of the power system through the comprehensive risk index.
Specifically, in step S1, fault probability data of the power element under different meteorological conditions is obtained according to historical meteorological data and historical operation data of the power system. The historical meteorological data and the historical operation data of the power system comprise information such as network topological structures, active and reactive power output of a generator, active and reactive power demand of a load, node voltage of each bus, load rate of each power transmission line, current wind speed, predicted wind speed data and the like. Preprocessing historical meteorological data and historical operation data to obtain fault probability data of the power system under different meteorological conditions, and forming a vulnerable curve. The vulnerable curve is a quantitative index for the influence of meteorological conditions on the failure rate of elements in the running process of the power system.
The fault probability of different meteorological conditions is represented by a vulnerable curve, and the calculation formula is as follows:
Figure BDA0003838628810000041
wherein P(s) is the probability that the power system is in or exceeds a damage state under dangerous stress s;
Figure BDA0003838628810000042
is the average engineering stress when the dangerous stress s reaches the damage state threshold; beta is the natural logarithm of engineering stress when dangerous stress s reaches the threshold value of damage stateStandard deviation; Φ is a standard normal cumulative distribution function.
In step S2, the neural network model adopts a bayesian neural network, and the neural network model includes an input layer, a hidden layer and an output layer, and has a structure as follows:
l 0 ＝x
l i ＝s i (W i *l i-1 +b i )
y＝l n
wherein x is an input, l 0 For input layer, l i-1 Is the i-1 layer hidden layer, l i Is the i-th hidden layer, W i Weights of hidden layers for the ith layer, b i For the deviation of the i-th hidden layer, l n And y is output for the output layer.
Referring to fig. 2, a parameter θ= (W, b) of the bayesian neural network obeys a random probability distribution p (θ), W is a weight of a hidden layer, b is a deviation of the hidden layer, and p (θ) is a probability distribution function of the parameter θ. Since the parameter θ= (W, b) obeys the random probability distribution p (θ), different output values of the same input value and probabilities of the different output values can be obtained through the bayesian neural network. To calculate the probability of different output values, a large number of calculations (e.g., monte carlo sampling) can be performed on the same input value, and the different output values and their corresponding frequencies are counted.
The invention forms a vulnerable curve by utilizing fault probability data of a power system under different meteorological conditions, sets priori distribution on a parameter theta= (W, b) of a Bayesian neural network by utilizing the vulnerable curve, and then carries out parameter updating by utilizing historical meteorological data and historical operation data based on Bayesian variational reasoning to train a neural network model. Inputting real-time meteorological data and real-time operation data of the power system into a trained neural network model, and outputting various topological structure sets and fault probability of the power system under various topological structures by the neural network model
Figure BDA0003838628810000051
In step S4, the line flow of the power system under various topologies is calculated by using the power system simulation software BPA. Risk indicators measuring the severity of a fault in a power system include line overload severity and voltage out-of-limit severity. And calculating the line overload severity and the voltage out-of-limit severity of the power system based on the line load flow calculation result of the circuit system, wherein the fault severity of the power system under various topological structures is the weighted summation of the line overload severity and the voltage out-of-limit severity.
The calculation formula of the voltage out-of-limit severity is:
Figure BDA0003838628810000052
in the method, in the process of the invention,
Figure BDA0003838628810000053
for the voltage out-of-limit severity of the power system node i under the j-th topological structure at time t,/>
Figure BDA0003838628810000054
The voltage of the power system node i under the j-th topological structure at the moment t. />
The calculation formula of the overload severity of the line is:
Figure BDA0003838628810000055
in the method, in the process of the invention,
Figure BDA0003838628810000056
for the line overload severity of the power system line l under the j-th topological structure at the moment t, < ->
Figure BDA0003838628810000057
And the load factor of the power system circuit l under the j-th topological structure at the moment t.
The severity of the fault of the power system under various topologies is:
Figure BDA0003838628810000061
in the formula Sev (V) j,t ,ρ j,t ) For the fault severity of the power system under the j-th topological structure at the moment of t, V j,t For the voltage of the power system under the j-th topological structure at the moment t, ρ j,t For the line load rate alpha of the power system under the j-th topological structure at the moment t i As a weight factor of node i, beta l Is the weighting factor for line l.
In step S5, the comprehensive risk indicator is the sum of products of failure probability and failure severity of the power system under various topological structures, and the calculation formula of the comprehensive risk indicator is:
Figure BDA0003838628810000062
wherein, risk is the comprehensive Risk index of the power system, J is the total number of topological structures under certain meteorological conditions,
Figure BDA0003838628810000063
the fault probability of the power system under the j-th topological structure.
According to the power system Risk assessment method based on the neural network model, the operation Risk of the power system is assessed through the comprehensive Risk index Risk.
The method is adopted for testing, and an IEEE-118 standard test calculation example is used for selecting a certain hurricane scene, wherein three affected lines are sequentially line 3-5, line 3-12 and line 2-12. To facilitate description of the system topology, the states of the affected lines are described by a state vector of "100", where "1" indicates line disconnection and "0" indicates normal operation of the line, and the three state quantities represent lines 3-5, 3-12, and 2-12, respectively.
According to the neural network model, risk assessment is carried out on the power system 24 hours a whole day affected by hurricane, a real-time monitoring view of the wind speed of an affected line is shown in fig. 3, the fault probability of the power system under various topological structures is shown in fig. 4, and the comprehensive risk situation of the power system is shown in fig. 5. It can be seen that at higher wind speeds, the affected line failure probability (i.e. the failure probability) is greater and the risk value is greater at this time (a probability of 0 in fig. 4 indicates that the line has broken). The result shows that the method can quickly and accurately evaluate the fault probability risk of the power system under the extreme weather condition.
In summary, the invention obtains the fault probability data of the power element under different meteorological conditions according to the historical meteorological data and the historical operation data of the power system, constructs the neural network model, predicts the fault probability of the power system under various topological structures through the neural network model, can rapidly calculate the risk condition under various topological conditions according to the fault probability and the fault severity of the power system under different topological structures, and remarkably improves the operation intelligence and the operation safety of the power system.
The foregoing description is directed to the preferred embodiments of the present invention, but the embodiments are not intended to limit the scope of the invention, and all equivalent changes or modifications made under the technical spirit of the present invention should be construed to fall within the scope of the present invention.

Claims (10)

1. The power system risk assessment method based on the neural network model is characterized by comprising the following steps of:
s1, acquiring historical meteorological data and historical operation data of a power system, acquiring fault probabilities of different meteorological conditions according to the historical meteorological data and the historical operation data of the power system, and forming a vulnerable curve;
s2, constructing a neural network model, and training the neural network model by utilizing a vulnerable curve formed by the fault probability and combining historical meteorological data and historical operation data to obtain a trained neural network model;
s3, inputting real-time meteorological data and real-time operation data of the power system into a neural network model, and outputting various topological structure sets and fault probabilities of the power system under various topological structures by the neural network model;
s4, calculating line power flow of the power system under various topological structures, obtaining risk indexes of fault severity of the power system according to the line power flow, and calculating the fault severity of the power system under various topological structures;
s5, acquiring a comprehensive risk index of the power system according to the fault probability and the fault severity of the power system under various topological structures, and evaluating the operation risk of the power system through the comprehensive risk index.
2. The power system risk assessment method based on the neural network model according to claim 1, wherein the fault probability of different meteorological conditions is represented by a vulnerable curve, and the calculation formula is:
Figure FDA0003838628800000011
wherein P(s) is the probability that the power system is in or exceeds a damage state under dangerous stress s;
Figure FDA0003838628800000012
is the average engineering stress when the dangerous stress s reaches the damage state threshold; beta is the standard deviation of the natural logarithm of engineering stress when the dangerous stress s reaches the damage state threshold value; Φ is a standard normal cumulative distribution function.
3. The power system risk assessment method based on the neural network model according to claim 1, wherein the neural network model adopts a bayesian neural network, the neural network model comprises an input layer, a hidden layer and an output layer, and the neural network model has the structure that:
l 0 ＝x
l i ＝s i (W i *l i-1 +b i )
y＝l n
wherein x is an input, l 0 For input layer, l i-1 Is the i-1 layer hidden layer, l i Is the i-th hidden layer, W i Weights of hidden layers for the ith layer, b i For the deviation of the i-th hidden layer, l n And y is output for the output layer.
4. A power system risk assessment method based on a neural network model according to claim 3, wherein the parameter θ= (W, b) of the bayesian neural network obeys a random probability distribution p (θ), W being the weight of the hidden layer, b being the deviation of the hidden layer, p (θ) being the probability distribution function of the parameter θ.
5. The power system risk assessment method based on the neural network model according to claim 4, wherein since the parameter θ= (W, b) obeys a random probability distribution p (θ), different output values of the same input value and probabilities of different output values can be obtained through the bayesian neural network.
6. The power system risk assessment method based on the neural network model of claim 1, wherein the risk indicators measuring the severity of the fault of the power system include the severity of line overload and the severity of voltage out-of-limit.
7. The power system risk assessment method based on the neural network model of claim 6, wherein the calculation formula of the severity of the voltage out-of-limit is:
Figure FDA0003838628800000021
in the method, in the process of the invention,
Figure FDA0003838628800000022
for the voltage out-of-limit severity of the power system node i under the j-th topological structure at time t,/>
Figure FDA0003838628800000023
The voltage of the power system node i under the j-th topological structure at the moment t.
8. The power system risk assessment method based on the neural network model of claim 7, wherein the calculation formula of the line overload severity is:
Figure FDA0003838628800000024
in the method, in the process of the invention,
Figure FDA0003838628800000025
for the line overload severity of the power system line l under the j-th topological structure at the moment t, < ->
Figure FDA0003838628800000026
And the load factor of the power system circuit l under the j-th topological structure at the moment t.
9. The power system risk assessment method based on the neural network model according to claim 8, wherein the severity of the fault of the power system under various topologies is:
Figure FDA0003838628800000027
in the formula Sev (V) j,t ,ρ j,t ) For the fault severity of the power system under the j-th topological structure at the moment of t, V j,t For the voltage of the power system under the j-th topological structure at the moment t, ρ j,t For the line load rate alpha of the power system under the j-th topological structure at the moment t i As a weight factor of node i, beta l Is the weighting factor for line l.
10. The power system risk assessment method based on the neural network model according to claim 9, wherein the calculation formula of the comprehensive risk index is:
Figure FDA0003838628800000028
wherein, risk is the comprehensive Risk index of the power system, J is the total number of topological structures under certain meteorological conditions,
Figure FDA0003838628800000029
the fault probability of the power system under the j-th topological structure. />
CN202211095913.7A 2022-09-08 2022-09-08 Power system risk assessment method based on neural network model Pending CN116167609A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211095913.7A CN116167609A (en) 2022-09-08 2022-09-08 Power system risk assessment method based on neural network model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211095913.7A CN116167609A (en) 2022-09-08 2022-09-08 Power system risk assessment method based on neural network model

Publications (1)

Publication Number Publication Date
CN116167609A true CN116167609A (en) 2023-05-26

Family

ID=86418870

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211095913.7A Pending CN116167609A (en) 2022-09-08 2022-09-08 Power system risk assessment method based on neural network model

Country Status (1)

Country Link
CN (1) CN116167609A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116565861A (en) * 2023-07-10 2023-08-08 广东电网有限责任公司江门供电局 Power distribution network reliability assessment method, system, equipment and medium
CN117811842A (en) * 2024-02-29 2024-04-02 南京邮电大学 Power grid security risk assessment method based on privacy calculation

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116565861A (en) * 2023-07-10 2023-08-08 广东电网有限责任公司江门供电局 Power distribution network reliability assessment method, system, equipment and medium
CN116565861B (en) * 2023-07-10 2023-10-03 广东电网有限责任公司江门供电局 Power distribution network reliability assessment method, system, equipment and medium
CN117811842A (en) * 2024-02-29 2024-04-02 南京邮电大学 Power grid security risk assessment method based on privacy calculation
CN117811842B (en) * 2024-02-29 2024-05-14 南京邮电大学 Power grid security risk assessment method based on privacy calculation

Similar Documents

Publication Publication Date Title
CN116167609A (en) Power system risk assessment method based on neural network model
CN108921410B (en) Method for constructing and improving elastic resilience index of power distribution network
CN107292478B (en) Method for acquiring influence situation of disaster on power distribution network
CN108512226B (en) Method for evaluating resilience of power system under disaster
CN103279808B (en) Circuit on power system state transition probability prediction analysis method under vile weather
CN103679282B (en) The Forecasting Methodology of wind power climbing
CN105205571A (en) Risk-considered urban power network operation security assessment method
CN113569411B (en) Disaster weather-oriented power grid operation risk situation awareness method
CN111507509A (en) Risk assessment method for extreme events of power system
CN115034510A (en) Power grid safety risk overall process closed-loop management and control optimization method and device suitable for typhoon scene
Wang et al. Data-driven prediction method for characteristics of voltage sag based on fuzzy time series
CN113609637B (en) Multi-disaster power distribution network elasticity assessment method considering fault linkage
CN114117730A (en) Elasticity evaluation method for power distribution network under typhoon disaster
CN112613676A (en) High-resolution power grid elasticity evaluation method
CN112632748A (en) Power system stability risk optimization method, system and storage medium
CN115859627A (en) Dynamic simulation model, screening method, equipment and medium for cascading failure of power system
CN116014790A (en) Elasticity evaluation method for power distribution network containing distributed energy sources
CN115775107A (en) Power grid information physical system risk assessment method considering cascading failure
CN116167477A (en) Power system risk assessment method considering meteorological condition influence
Xu et al. Blackout risk assessment of cascading outages considering wind power uncertainty
Chen et al. Risk assessment for power system static security based on fuzzy modeling of weather conditions
CN112182952A (en) Multi-objective optimization scheduling method for improving elasticity of power system
Wei et al. Resilience Assessment Using Simulation System of Distribution Network under Extreme Weather
Hu et al. Resilience-constrained economic dispatch for cascading failures prevention
CN117175548B (en) Sequential fault emergency control method based on random power flow

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
CB03 Change of inventor or designer information

Inventor after: Zhang Shaofan

Inventor after: Liu Jun

Inventor after: Liu Xiaoming

Inventor after: Zhao Yu

Inventor after: Peng Xin

Inventor after: Liu Luhao

Inventor after: Liang Xueqing

Inventor after: Lu Youfei

Inventor after: Zhao Hongwei

Inventor after: Wu Renbo

Inventor after: Chen Minghui

Inventor after: Liu Chao

Inventor after: Wang Liye

Inventor before: Long Yun

Inventor before: Wang Liye

Inventor before: Liu Jun

Inventor before: Liu Xiaoming

Inventor before: Zhao Yu

Inventor before: Peng Xin

Inventor before: Zhang Shaofan

Inventor before: Liu Luhao

Inventor before: Liang Xueqing

Inventor before: Lu Youfei

Inventor before: Zhao Hongwei

Inventor before: Wu Renbo

Inventor before: Chen Minghui

Inventor before: Liu Chao

CB03 Change of inventor or designer information