CN116452005A - Risk assessment method, device, equipment and storage medium for electric power system - Google Patents
Risk assessment method, device, equipment and storage medium for electric power system Download PDFInfo
- Publication number
- CN116452005A CN116452005A CN202310590864.2A CN202310590864A CN116452005A CN 116452005 A CN116452005 A CN 116452005A CN 202310590864 A CN202310590864 A CN 202310590864A CN 116452005 A CN116452005 A CN 116452005A
- Authority
- CN
- China
- Prior art keywords
- data
- value
- variables
- historical data
- power
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012502 risk assessment Methods 0.000 title claims abstract description 78
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000005070 sampling Methods 0.000 claims abstract description 67
- 230000009467 reduction Effects 0.000 claims abstract description 53
- 238000004364 calculation method Methods 0.000 claims abstract description 37
- 238000011156 evaluation Methods 0.000 claims abstract description 14
- 230000006870 function Effects 0.000 claims description 35
- 238000004590 computer program Methods 0.000 claims description 21
- 238000007781 pre-processing Methods 0.000 claims description 20
- 238000012545 processing Methods 0.000 claims description 19
- 230000001419 dependent effect Effects 0.000 claims description 17
- 238000005315 distribution function Methods 0.000 claims description 16
- 238000010248 power generation Methods 0.000 claims description 11
- 238000006243 chemical reaction Methods 0.000 claims description 10
- 238000009827 uniform distribution Methods 0.000 claims description 9
- 238000000342 Monte Carlo simulation Methods 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 7
- 238000007476 Maximum Likelihood Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 5
- 238000002347 injection Methods 0.000 description 6
- 239000007924 injection Substances 0.000 description 6
- 238000009826 distribution Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
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
- 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
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- 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)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Water Supply & Treatment (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Primary Health Care (AREA)
- Probability & Statistics with Applications (AREA)
- Public Health (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
According to the risk assessment method, the risk assessment device, the risk assessment equipment and the risk assessment storage medium for the electric power system, the multiple types of historical data of the electric power system are obtained, and the multiple types of historical data are converted into uniformly distributed historical sequences; calculating and based on the maximum mutual information values of any two first variables in the uniformly distributed history sequence, obtaining information coefficients of any two first variables, and determining the maximum information coefficients; constructing a Bayesian network model based on the maximum information coefficient, obtaining a plurality of evenly distributed discrete samples based on the Bayesian network model, and carrying out data reduction on each evenly distributed discrete sample to obtain original historical data corresponding to each evenly distributed discrete sample; sampling the system state of the original historical data, calculating the accumulated risk value corresponding to each system state, and integrating the accumulated risk values corresponding to all the system states to obtain a risk evaluation value of the power system; compared with the prior art, the technical scheme of the invention can improve the speed and accuracy of risk assessment calculation.
Description
Technical Field
The invention relates to the technical field of digital power grids and artificial intelligence, in particular to a risk assessment method, a risk assessment device, risk assessment equipment and a risk assessment storage medium for a power system.
Background
With the exhaustion of fossil energy and the gradual deterioration of environmental climate, energy transformation has to be accelerated, renewable new energy represented by wind energy and solar energy is connected with a power grid in large quantity, and the power generation of the renewable energy has randomness and uncertainty naturally, so that the operation uncertainty of a power system is further enlarged, and once the power system has serious faults, huge impact and loss are generated on economy and society.
The scale and complexity of the power system are increased sharply, the difficulty of power grid risk assessment is increased, the traditional power system risk assessment method mainly adopts a probability statistical method and a simulation method based on a physical model, wherein the probability statistical method is usually based on historical data, a mathematical model is established by utilizing a probability theory and a statistical principle to predict future risks, however, the method has the defects that complex dependency relations among various historical variables are difficult to describe accurately, and new challenges caused by large-scale access of new energy cannot be dealt with; the simulation method based on the physical model needs to establish an accurate physical model of the power system, the uncertainty of model parameters and model structures is large, and the complexity and the calculation cost of the model are high.
For this reason, in order to evaluate the risk of the power system more accurately, it is currently necessary to develop a new method and technology for providing scientific support for safe and stable operation and sustainable development of the power system.
Disclosure of Invention
The invention aims to solve the technical problems that: provided are a risk assessment method, a risk assessment device, risk assessment equipment and risk assessment storage medium for an electric power system, and the speed and accuracy of risk assessment calculation are improved.
In order to solve the above technical problems, the present invention provides a risk assessment method for an electric power system, including:
acquiring multiple types of historical data of a power system, and performing data preprocessing on each type of historical data so as to convert the multiple types of historical data into a uniformly distributed historical sequence;
calculating the maximum mutual information value of any two first variables in the uniform distribution history sequence, obtaining information coefficients of the any two first variables based on the maximum mutual information value, and determining the maximum information coefficient based on the information coefficients;
constructing a Bayesian network model based on the maximum information coefficient;
based on the Bayesian network model, obtaining a plurality of evenly distributed discrete samples, and carrying out data reduction on each evenly distributed discrete sample to obtain original historical data corresponding to each evenly distributed discrete sample;
And sampling the system state of the original historical data, calculating the accumulated risk value corresponding to each system state, and integrating the accumulated risk values corresponding to all the system states to obtain a risk evaluation value of the power system.
In one possible implementation manner, the data preprocessing is performed on each type of history data so as to convert the multiple types of history data into a uniformly distributed history sequence, which specifically includes:
calculating an edge probability density estimation value of each type of historical data based on the kernel density estimation;
integrating the edge probability density estimation value to obtain an edge distribution function of each type of historical data, and calculating an inverse function of the edge distribution function;
and calculating first variables corresponding to each type of historical data based on the inverse function, integrating all the first variables, and generating a uniformly distributed historical sequence.
In one possible implementation manner, based on the kernel density estimation, calculating an edge probability density estimation value of each type of historical data based on the kernel density estimation, wherein the calculation manner of the edge probability density estimation value is as follows:
wherein f x (α i ) Alpha is the estimated value of the probability density of the edge ij As historical data alpha i Is the jth data point of (2); n is the data amount; h is the bandwidth; k is a kernel function, and is taken as a normal distribution function.
In one possible implementation manner, calculating the maximum mutual information value of any two first variables in the uniformly distributed history sequence, and obtaining the information coefficient of any two first variables based on the maximum mutual information value specifically includes:
selecting any two first variables in the uniformly distributed history sequence, generating a first grid, and dividing the first grid in an X-axis and Y-axis manner to obtain grid division number;
based on the grid division number, setting a plurality of division modes, and calculating maximum mutual information values corresponding to any two first variables in each division mode;
and carrying out normalization processing on the maximum mutual information value to obtain a normalized mutual information value, and selecting the maximum value in the normalized mutual information value to obtain information coefficients of any two first variables.
In one possible implementation manner, based on the maximum information coefficient, a bayesian network model is constructed, which specifically includes:
taking all first variables in the uniformly distributed history sequence as network nodes, taking two first variables corresponding to the maximum information coefficient as edges, and randomly generating a plurality of Bayesian network structures;
based on the scoring search function, calculating a search score corresponding to each Bayesian network structure, and selecting a Bayesian network structure corresponding to the highest value of the search score as an optimal Bayesian network structure;
Based on a maximum likelihood estimation method, calculating network parameters of the optimal Bayesian network structure, and constructing a Bayesian network model based on the optimal Bayesian network structure and the network parameters.
In one possible implementation manner, performing data reduction on each uniformly distributed discrete sample to obtain original historical data corresponding to each uniformly distributed discrete sample, which specifically includes:
based on a random number generator, generating random numbers corresponding to each evenly distributed discrete sample, and inputting the random numbers into a preset data conversion formula so as to convert the random numbers into original historical data, wherein the preset data conversion formula is as follows:
in the method, in the process of the invention,the w uniform distribution obtained for the ns th samplingRandom number corresponding to scattered sample,/->Original historical data corresponding to the w uniformly distributed discrete samples obtained for the ns th sampling, +.>As an inverse function.
In one possible implementation manner, system state sampling is performed on the original historical data, and an accumulated risk value corresponding to each system state is calculated, which specifically includes:
establishing a power grid risk assessment index system, wherein the power grid risk assessment index system comprises an expected annual blackout electric quantity value and an insufficient electric power probability;
Classifying each original history data into independent variables and dependent variables;
when the original historical data is classified into independent variables, sampling the system state of the independent variables based on non-sequential Monte Carlo simulation to obtain first state sampling data;
when the power generation total capacity of the power system is determined to not meet the load, and the condition of power flow out-of-limit and node voltage out-of-limit occurs in the power system, carrying out load reduction processing on the first state sampling data based on a preset load removal strategy to obtain a first load reduction amount corresponding to each system state;
calculating a first year power failure electric quantity expected value and a first power shortage probability based on the first state sampling data and the first load reduction amount, and obtaining a first accumulated risk value corresponding to each system state based on the first year power failure electric quantity expected value and the first power shortage probability;
when the original historical data are classified into dependent variables, performing system state sampling on the dependent variables based on the optimal Bayesian network structure to obtain second state sampling data;
when the power generation total capacity of the power system is determined to not meet the load, and the condition of power flow out-of-limit and node voltage out-of-limit occurs in the power system, carrying out load reduction processing on the second state sampling data based on a preset load removal strategy to obtain a second load reduction amount corresponding to each system state;
And calculating expected values of power failure electric quantity in the second year and second power shortage probability based on the second state sampling data and the second load reduction amount, and obtaining a second accumulated risk value corresponding to each system state based on the expected values of power failure electric quantity in the second year and the second power shortage probability.
The invention also provides a risk assessment device of the power system, which comprises: the system comprises a data preprocessing module, a data calculation module, a model construction module, a data reduction module and a risk evaluation value calculation module;
the data preprocessing module is used for acquiring multiple types of historical data of the power system, and performing data preprocessing on each type of historical data so as to convert the multiple types of historical data into a uniformly distributed historical sequence;
the data calculation module is used for calculating the maximum mutual information value of any two first variables in the uniform distribution history sequence, obtaining information coefficients of the any two first variables based on the maximum mutual information value, and determining the maximum information coefficient based on the information coefficients;
the model construction module is used for constructing a Bayesian network model based on the maximum information coefficient;
The data reduction module is used for obtaining a plurality of evenly distributed discrete samples based on the Bayesian network model, and carrying out data reduction on each evenly distributed discrete sample to obtain original historical data corresponding to each evenly distributed discrete sample;
and the risk evaluation value calculation module is used for sampling the system state of the original historical data, calculating the accumulated risk value corresponding to each system state, and integrating the accumulated risk values corresponding to all the system states to obtain a risk evaluation value of the power system.
In one possible implementation manner, the data preprocessing module is configured to perform data preprocessing on each type of history data, so as to convert the multiple types of history data into a uniformly distributed history sequence, and specifically includes:
calculating an edge probability density estimation value of each type of historical data based on the kernel density estimation;
integrating the edge probability density estimation value to obtain an edge distribution function of each type of historical data, and calculating an inverse function of the edge distribution function;
and calculating first variables corresponding to each type of historical data based on the inverse function, integrating all the first variables, and generating a uniformly distributed historical sequence.
In one possible implementation manner, the data preprocessing module is configured to calculate an edge probability density estimation value of each type of historical data based on the kernel density estimation, where the calculation manner of the edge probability density estimation value is as follows:
wherein f x (α i ) Alpha is the estimated value of the probability density of the edge ij As historical data alpha i Is the jth data point of (2); n is the data amount; h is the bandwidth; k is a kernel function, and is taken as a normal distribution function.
In one possible implementation manner, the data calculation module is configured to calculate a maximum mutual information value of any two first variables in the uniformly distributed history sequence, and obtain information coefficients of any two first variables based on the maximum mutual information value, and specifically includes:
selecting any two first variables in the uniformly distributed history sequence, generating a first grid, and dividing the first grid in an X-axis and Y-axis manner to obtain grid division number;
based on the grid division number, setting a plurality of division modes, and calculating maximum mutual information values corresponding to any two first variables in each division mode;
and carrying out normalization processing on the maximum mutual information value to obtain a normalized mutual information value, and selecting the maximum value in the normalized mutual information value to obtain information coefficients of any two first variables.
In one possible implementation manner, the model building module is configured to build a bayesian network model based on the maximum information coefficient, and specifically includes:
taking all first variables in the uniformly distributed history sequence as network nodes, taking two first variables corresponding to the maximum information coefficient as edges, and randomly generating a plurality of Bayesian network structures;
based on the scoring search function, calculating a search score corresponding to each Bayesian network structure, and selecting a Bayesian network structure corresponding to the highest value of the search score as an optimal Bayesian network structure;
based on a maximum likelihood estimation method, calculating network parameters of the optimal Bayesian network structure, and constructing a Bayesian network model based on the optimal Bayesian network structure and the network parameters.
In one possible implementation manner, the data reduction module is configured to perform data reduction on each evenly-distributed discrete sample to obtain original historical data corresponding to each evenly-distributed discrete sample, and specifically includes:
based on a random number generator, generating random numbers corresponding to each evenly distributed discrete sample, and inputting the random numbers into a preset data conversion formula so as to convert the random numbers into original historical data, wherein the preset data conversion formula is as follows:
In the method, in the process of the invention,random numbers corresponding to the w uniformly distributed discrete samples obtained for the ns th sampling, ++>Original historical data corresponding to the w uniformly distributed discrete samples obtained for the ns th sampling, +.>As an inverse function.
In one possible implementation manner, the risk assessment value calculating module is configured to sample the system state of the original historical data, and calculate an accumulated risk value corresponding to each system state, and specifically includes:
establishing a power grid risk assessment index system, wherein the power grid risk assessment index system comprises an expected annual blackout electric quantity value and an insufficient electric power probability;
classifying each original history data into independent variables and dependent variables;
when the original historical data is classified into independent variables, sampling the system state of the independent variables based on non-sequential Monte Carlo simulation to obtain first state sampling data;
when the power generation total capacity of the power system is determined to not meet the load, and the condition of power flow out-of-limit and node voltage out-of-limit occurs in the power system, carrying out load reduction processing on the first state sampling data based on a preset load removal strategy to obtain a first load reduction amount corresponding to each system state;
Calculating a first year power failure electric quantity expected value and a first power shortage probability based on the first state sampling data and the first load reduction amount, and obtaining a first accumulated risk value corresponding to each system state based on the first year power failure electric quantity expected value and the first power shortage probability;
when the original historical data are classified into dependent variables, performing system state sampling on the dependent variables based on the optimal Bayesian network structure to obtain second state sampling data;
when the power generation total capacity of the power system is determined to not meet the load, and the condition of power flow out-of-limit and node voltage out-of-limit occurs in the power system, carrying out load reduction processing on the second state sampling data based on a preset load removal strategy to obtain a second load reduction amount corresponding to each system state;
and calculating expected values of power failure electric quantity in the second year and second power shortage probability based on the second state sampling data and the second load reduction amount, and obtaining a second accumulated risk value corresponding to each system state based on the expected values of power failure electric quantity in the second year and the second power shortage probability.
The invention also provides a terminal device comprising a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the risk assessment method of the power system according to any one of the above when executing the computer program.
The invention also provides a computer readable storage medium, which comprises a stored computer program, wherein the computer program is used for controlling equipment where the computer readable storage medium is located to execute the risk assessment method of the electric power system according to any one of the above.
Compared with the prior art, the risk assessment method, the risk assessment device, the risk assessment equipment and the storage medium of the power system have the following beneficial effects:
converting the multi-type historical data into a uniformly distributed historical sequence by acquiring the multi-type historical data of the power system; calculating the maximum mutual information value of any two first variables in the uniformly distributed history sequence, obtaining and determining the maximum information coefficient based on the information coefficient of any two first variables on the basis of the maximum mutual information value; constructing a Bayesian network model based on the maximum information coefficient; based on a Bayesian network model, obtaining a plurality of evenly distributed discrete samples, and carrying out data reduction on each evenly distributed discrete sample to obtain original historical data corresponding to each evenly distributed discrete sample; sampling the system state of the original historical data, calculating the accumulated risk value corresponding to each system state, and integrating the accumulated risk values corresponding to all the system states to obtain a risk evaluation value of the power system; compared with the prior art, the technical scheme of the invention can improve the speed and accuracy of risk assessment calculation.
Drawings
FIG. 1 is a schematic flow chart of an embodiment of a risk assessment method for an electric power system according to the present invention;
fig. 2 is a schematic structural diagram of an embodiment of a risk assessment apparatus for an electric power system according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Embodiment 1, referring to fig. 1, fig. 1 is a schematic flow chart of an embodiment of a risk assessment method for an electric power system according to the present invention, as shown in fig. 1, the method includes steps 101 to 105, specifically as follows:
step 101: and acquiring multiple types of historical data of the power system, and performing data preprocessing on each type of historical data so as to convert the multiple types of historical data into a uniformly distributed historical sequence.
In one embodiment, the plurality of types of historical data include, but are not limited to, wind and light output data, numerical weather forecast data, wherein the numerical weather forecast data includes wind speed, wind direction, temperature and humidity.
In an embodiment, a history sequence is generated for each type of history data acquired, wherein the history sequence may be a history sequence with any probability distribution, and thus each type of history data needs to be converted into a uniformly distributed sequence.
In one embodiment, an edge probability density estimate is calculated for each type of historical data based on the kernel density estimate.
Specifically, the calculation mode of the edge probability density estimation value is as follows:
wherein f x (α i ) Alpha is the estimated value of the probability density of the edge ij For the i-th type of history data alpha i Is the jth data point of (2); n is the data amount; h is the bandwidth; k is a kernel function, and is taken as a normal distribution function.
In one embodiment, the edge probability density estimation value is integrated to obtain an edge distribution function of each type of history data, and an inverse function of the edge distribution function is calculated.
Specifically, the edge probability density estimation value is subjected to integral processing based on an integral calculation formula, wherein the integral calculation formula is as follows:
wherein F is x (α i ) As an edge distribution function, f x (α i ) Is an edge probability density estimate.
In an embodiment, based on the inverse function, a first variable corresponding to each type of history data is calculated, where a calculation formula of the first variable is as follows:
Wherein beta is 1 For class 1 historical data alpha 1 Corresponding first variable, beta w For the w-th type history data alpha w A corresponding first variable is provided for the first time,as an inverse function.
In one embodiment, after each type of history data is converted into first variables, all the first variables are integrated to generate a uniformly distributed history sequence.
Step 102: and calculating the maximum mutual information value of any two first variables in the uniform distribution history sequence, obtaining the information coefficient of the any two first variables based on the maximum mutual information value, and determining the maximum information coefficient based on the information coefficient.
In an embodiment, any two first variables in the uniformly distributed history sequence are selected, discretization processing is performed on the any two first variables, a first grid is generated, and X-axis and Y-axis division is performed on the first grid to obtain grid division number; based on the grid division number, a plurality of division modes are set, and the maximum mutual information value corresponding to any two first variables in each division mode is calculated.
Specifically, generating a first grid for each two first variables in the uniformly distributed history sequence, dividing the first grid into X and Y grids by an X axis and a Y axis to obtain grid division numbers, fixing the grid division numbers, generating a plurality of division modes by changing division positions, and calculating the maximum mutual information value IX of each division method; y, wherein the maximum mutual information value I [ X ]; the calculation formula of Y is as follows:
Wherein, p (X), p (Y) is the independent probability of any two selected first variables, and is the ratio of the data quantity and the total data quantity in a certain grid; p (X, Y) is the joint probability between any two first variables, is the ratio of the data quantity falling in a certain grid to the total data quantity, and X, Y refer to any grid in the first grids respectively.
In an embodiment, the maximum mutual information value is normalized to obtain a normalized mutual information value, and the maximum value in the normalized mutual information value is selected to obtain information coefficients of any two first variables.
Specifically, normalization processing is performed on the maximum mutual information value obtained by changing the dividing position, and the maximum value of the normalized mutual information under different grid division is selected as an information coefficient MIC value, and the expression is:
where x, y is the number of divisions divided in two directions, and B is a variable, and is generally set to 0.6 th power of the data amount.
In an embodiment, any two first variables in the uniform distribution history sequence are obtained to obtain a first variable matching pair, all the first variable matching pairs in the uniform distribution history sequence are obtained, information coefficients corresponding to all the first variable matching pairs are calculated, the maximum value of the information coefficients is selected from all the information coefficients, and the maximum information coefficient is ensured.
Step 103: and constructing a Bayesian network model based on the maximum information coefficient.
In an embodiment, all the first variables in the uniformly distributed history sequence are taken as network nodes, and two first variables corresponding to the maximum information coefficient are taken as edges, so that a plurality of bayesian network structures are randomly generated.
In an embodiment, the segmentation level of each first variable is determined based on the corresponding grid division condition when the maximum mutual information value is obtained, and the segmentation level of each first variable is used as an input sample set of the bayesian network.
In an embodiment, based on the scoring search function, a search score corresponding to each bayesian network structure is calculated, and a bayesian network structure corresponding to the highest value of the search score is selected as an optimal bayesian network structure.
Specifically, after a plurality of Bayesian network structures are randomly generated, searching the network structure with the highest score as an optimal structure by taking a scoring search function as a basis; wherein the scoring search function calculation expression is:
wherein n is the number of network nodes; q i Is node x i The number of parent node value combinations; r is (r) i Is node x i The number of values of (2); m is m ijk For concentrating node x for a sample i For the kth value, the father node is the sample number of the jth value combination; m is m ij Is m ijk At k E [1, r i ]Inner sum.
In an embodiment, the network parameters of the optimal bayesian network structure are calculated based on a maximum likelihood estimation method.
Specifically, the network parameter calculation expression calculated by using the maximum likelihood estimation method is:
wherein D is a sample set; θ is a parameter; l (θ|D) is a likelihood function of θ; θ * To obtain a value of θ when L (θ|d) is maximized.
In an embodiment, a bayesian network model is constructed based on the optimal bayesian network structure and the network parameters, so that the statistical dependency among various types of historical data is mapped by using the estimation of the bayesian network.
Step 104: based on the Bayesian network model, a plurality of evenly distributed discrete samples are obtained, and data reduction is carried out on each evenly distributed discrete sample to obtain original historical data corresponding to each evenly distributed discrete sample.
In an embodiment, according to an optimal bayesian network model structure and a conditional probability distribution of a bayesian network model, parent nodes and child nodes of each network node in the bayesian network model are obtained, step-by-step sampling is performed from the parent nodes to the child nodes, and a plurality of evenly distributed discrete samples are obtained, wherein the plurality of evenly distributed discrete samples are as follows:
Wherein ns is the ns th sampling, L ns For a plurality of evenly distributed discrete samples at the ns-th samplingAnd (5) collecting books.
In an embodiment, based on a random number generator, a random number corresponding to each uniformly distributed discrete sample is generated, and the random number is input into a preset data conversion formula, so that the random number is converted into original historical data, wherein the preset data conversion formula is as follows:
in the method, in the process of the invention,random numbers corresponding to the w uniformly distributed discrete samples obtained for the ns th sampling, ++>Original historical data corresponding to the w uniformly distributed discrete samples obtained for the ns th sampling, +.>As an inverse function.
Specifically, a random number generator is used for generating a random number for each evenly distributed discrete sample obtained by sampling to obtainAnd converts it into the original history data having the same distribution as the history sequence
Step 105: and sampling the system state of the original historical data, calculating the accumulated risk value corresponding to each system state, and integrating the accumulated risk values corresponding to all the system states to obtain a risk evaluation value of the power system.
In one embodiment, a grid risk assessment indicator system is established, wherein the grid risk assessment indicator system comprises expected annual blackout power and insufficient power probability.
Specifically, for annual blackout power expectancy EENS:
wherein n(s) is the number of occurrences of the system state s; NS is the total number of samples; c (C) i (s) is the amount of load reduction (MW) at system state s in the ith sample.
Specifically, for expected annual blackout power P LOLP ：
In an embodiment, before the power grid risk assessment index system is established, basic parameter data of the power system is obtained, and the simulation times NS are set, wherein the basic parameter data comprise a power grid topological structure, and the power grid topological structure comprises generator data and line data.
In one embodiment, each raw history data is classified into independent and dependent variables; preferably, the independent variables are such as conventional generators, random failure of the line is stopped; dependent variables such as photovoltaic output and illumination intensity, fan output and wind speed; subjective judgment can be performed on each original historical data according to the selected variables.
In one embodiment, when the original historical data is classified as an independent variable, the independent variable is subjected to system state sampling based on non-sequential Monte Carlo simulation to obtain first state sampling data.
In an embodiment, when it is determined that the total power generation capacity of the power system does not meet the load, and when the power flow out-of-limit and node voltage out-of-limit conditions occur in the power system, load reduction processing is performed on the first state sampling data based on a preset load removal strategy, so as to obtain a first load reduction amount corresponding to each system state.
In one embodiment, based on system alternating current power flow calculation, judging whether power flow out-of-limit and node voltage out-of-limit conditions occur in the power system; specifically, for a power system including n nodes, the flow equation in the polar coordinate form is as follows:
wherein n is the number of system nodes; p (P) i And Q i The injection active power and the injection reactive power of the node i are sequentially; v (V) i And delta i The amplitude and phase angle of the voltage of the node i are sequentially; delta ij ＝δ i ―δ j ，G ij And B ij The real and imaginary parts of the admittances in the node admittance matrix are in turn.
In an embodiment, the preset load shedding strategy is an optimal load shedding model based on communication, wherein an objective function of the optimal load shedding model is a minimum total load shedding amount.
Specifically, for the objective function, the following is shown:
min∑ i∈ND C i 。
specifically, the constraint condition of the objective function is as follows:
wherein C is i Is the load shedding size at node i; p (P) i And Q i The injection active power and the injection reactive power of the node i are sequentially; v and delta are node voltage amplitude vector and phase angle vector in turn; v (V) i An element of V; PD (potential difference) device i And QDs i The active power and the reactive power of the load at the node i are sequentially; and->The lower limit and the upper limit of the injection active power and the injection reactive power of the node i are sequentially set; t (T) k Is the flow on branch k; />Is the limit delivery capacity on branch k; />And->The lower limit and the upper limit of the voltage amplitude of the node i are sequentially set; ND, NG, L and N are in turn the set of load nodes, supply nodes, all branches and all nodes in the system.
In an embodiment, based on the first state sampling data and the first load reduction amount, a first expected annual power outage amount and a first power shortage probability are calculated, and based on the first expected annual power outage amount and the first power shortage probability, a first accumulated risk value corresponding to each system state is obtained.
Specifically, based on first state sampling data, obtaining first occurrence times of each system state s in the first state sampling data, setting the total number of the first state sampling data as a first total number of samples, substituting the first occurrence times, the first total number and the first load reduction amount into a annual power outage electric quantity expected value calculation formula to obtain a first annual power outage electric quantity expected value, substituting the first occurrence times and the first total number into a power shortage probability calculation formula to obtain a first power shortage probability, and integrating the first annual power outage electric quantity expected value and the first power shortage probability to obtain a first accumulated risk value corresponding to each system state.
In an embodiment, when the original historical data is classified as an dependent variable, performing state sampling on the dependent variable based on the optimal bayesian network structure to obtain second state sampling data.
In an embodiment, when it is determined that the total power generation capacity of the power system does not meet the load and the power flow out-of-limit and node voltage out-of-limit conditions occur in the power system, load reduction processing is performed on the second state sampling data based on a preset load removal strategy, so as to obtain a second load reduction amount corresponding to each system state.
In an embodiment, based on the second state sampling data and the second load reduction amount, a second expected value of power outage in the second year and a second power shortage probability are calculated, and based on the second expected value of power outage in the second year and the second power shortage probability, a second accumulated risk value corresponding to each dependent variable is obtained.
Specifically, based on second state sampling data, obtaining second occurrence times of each system state s in the first state sampling data, setting the total number of the second state sampling data as a second total number of samples, substituting the second occurrence times, the second total number and the second load reduction amount into an annual power outage expected value calculation formula to obtain a second annual power outage expected value, substituting the second occurrence times and the second total number into a power shortage probability calculation formula to obtain a second power shortage probability, and integrating the second annual power outage expected value and the second power shortage probability to obtain a second accumulated risk value corresponding to each system state.
In summary, according to the risk assessment method for the power system provided by the invention, each historical data is preprocessed, so that a historical sequence possibly with any probability distribution is transformed into a sequence with uniform distribution; different dividing modes are executed to calculate the maximum mutual information value between any two first variables, and then the maximum information coefficient between any two first variables, namely the maximum information coefficient between each historical data, is obtained; based on the maximum information coefficient, constructing a Bayesian network model to realize modeling of the relationship among a plurality of first variables; restoring uniformly distributed discrete samples obtained by Bayesian network sampling to original historical data; performing risk analysis on each system state in the original historical data by adopting non-sequential Monte Carlo simulation to obtain an accumulated risk index; compared with the prior art, the method has the advantages that the condition dependency relationship among the historical data is described through the maximum information coefficient and the Bayesian network, the complex dependency relationship among the variables in the power system can be accurately described, meanwhile, the high efficiency and the flexibility of the non-sequential Monte Carlo simulation are utilized, the speed and the accuracy of risk assessment calculation can be greatly improved, the research and the development of the method have important significance in the power system risk assessment field, and scientific support can be provided for safe and stable operation and sustainable development of the power system.
Embodiment 2, referring to fig. 2, fig. 2 is a schematic structural diagram of an embodiment of a risk assessment apparatus for an electric power system according to the present invention, as shown in fig. 2, the apparatus includes a data preprocessing module 201, a data calculation module 202, a model building module 203, a data restoration module 204, and a risk assessment value calculation module 205, which are specifically as follows:
the data preprocessing module 201 is configured to obtain multiple types of history data of the power system, and perform data preprocessing on each type of history data, so as to convert the multiple types of history data into a uniformly distributed history sequence.
The data calculation module 202 is configured to calculate a maximum mutual information value of any two first variables in the uniformly distributed history sequence, obtain information coefficients of the any two first variables based on the maximum mutual information value, and determine a maximum information coefficient based on the information coefficients.
The model construction module 203 is configured to construct a bayesian network model based on the maximum information coefficient.
The data reduction module 204 is configured to obtain a plurality of uniformly distributed discrete samples based on the bayesian network model, and perform data reduction on each uniformly distributed discrete sample to obtain original historical data corresponding to each uniformly distributed discrete sample.
The risk evaluation value calculation module 205 is configured to sample the system state of the original historical data, calculate an accumulated risk value corresponding to each system state, and integrate the accumulated risk values corresponding to all the system states to obtain a risk evaluation value of the power system.
In an embodiment, the data preprocessing module 201 is configured to perform data preprocessing on each type of history data, so as to convert the multiple types of history data into a uniformly distributed history sequence, and specifically includes: calculating an edge probability density estimation value of each type of historical data based on the kernel density estimation; integrating the edge probability density estimation value to obtain an edge distribution function of each type of historical data, and calculating an inverse function of the edge distribution function; and calculating first variables corresponding to each type of historical data based on the inverse function, integrating all the first variables, and generating a uniformly distributed historical sequence.
In an embodiment, the data preprocessing module 201 is configured to calculate, based on the kernel density estimation, an edge probability density estimation value of each type of historical data based on the kernel density estimation, where the edge probability density estimation value is calculated as follows:
Wherein f x (α i ) Alpha is the estimated value of the probability density of the edge ij As historical data alpha i Is the jth data point of (2); n is the data amount; h is the bandwidth; k is a kernel function, and is taken as a normal distribution function.
In an embodiment, the data calculating module 202 is configured to calculate a maximum mutual information value of any two first variables in the uniformly distributed history sequence, and obtain information coefficients of any two first variables based on the maximum mutual information value, and specifically includes: selecting any two first variables in the uniformly distributed history sequence, generating a first grid, and dividing the first grid in an X-axis and Y-axis manner to obtain grid division number; based on the grid division number, setting a plurality of division modes, and calculating maximum mutual information values corresponding to any two first variables in each division mode; and carrying out normalization processing on the maximum mutual information value to obtain a normalized mutual information value, and selecting the maximum value in the normalized mutual information value to obtain information coefficients of any two first variables.
In one embodiment, the model building module 203 is configured to build a bayesian network model based on the maximum information coefficient, and specifically includes: taking all first variables in the uniformly distributed history sequence as network nodes, taking two first variables corresponding to the maximum information coefficient as edges, and randomly generating a plurality of Bayesian network structures; based on the scoring search function, calculating a search score corresponding to each Bayesian network structure, and selecting a Bayesian network structure corresponding to the highest value of the search score as an optimal Bayesian network structure; based on a maximum likelihood estimation method, calculating network parameters of the optimal Bayesian network structure, and constructing a Bayesian network model based on the optimal Bayesian network structure and the network parameters.
In an embodiment, the data reduction module 204 is configured to perform data reduction on each evenly-distributed discrete sample to obtain original historical data corresponding to each evenly-distributed discrete sample, and specifically includes: based on a random number generator, generating random numbers corresponding to each evenly distributed discrete sample, and inputting the random numbers into a preset data conversion formula so as to convert the random numbers into original historical data, wherein the preset data conversion formula is as follows:
in the method, in the process of the invention,random numbers corresponding to the w uniformly distributed discrete samples obtained for the ns th sampling, ++>Original historical data corresponding to the w uniformly distributed discrete samples obtained for the ns th sampling, +.>As an inverse function.
In an embodiment, the risk assessment value calculating module 205 is configured to sample the system state of the original historical data, and calculate an accumulated risk value corresponding to each system state, and specifically includes: and establishing a power grid risk assessment index system, wherein the power grid risk assessment index system comprises an expected annual blackout electric quantity value and an insufficient electric power probability.
In one embodiment, the risk assessment value calculation module 205 is configured to classify each of the raw history data into independent variables and dependent variables.
In one embodiment, the risk assessment value calculation module 205 is configured to sample the system state of the independent variable based on the non-sequential monte carlo simulation when the original history data is classified as the independent variable, so as to obtain first state sampling data; when the power generation total capacity of the power system is determined to not meet the load, and the condition of power flow out-of-limit and node voltage out-of-limit occurs in the power system, carrying out load reduction processing on the first state sampling data based on a preset load removal strategy to obtain a first load reduction amount corresponding to each system state; and calculating expected values of power failure electric quantity in the first year and first power shortage probability based on the first state sampling data and the first load reduction amount, and obtaining a first accumulated risk value corresponding to each system state based on the expected values of power failure electric quantity in the first year and the first power shortage probability.
In an embodiment, the risk assessment value calculation module 205 is configured to, when the original historical data is classified as an dependent variable, sample a system state of the dependent variable based on the optimal bayesian network structure, to obtain second state sampling data; when the power generation total capacity of the power system is determined to not meet the load, and the condition of power flow out-of-limit and node voltage out-of-limit occurs in the power system, carrying out load reduction processing on the second state sampling data based on a preset load removal strategy to obtain a second load reduction amount corresponding to each system state; and calculating expected values of power failure electric quantity in the second year and second power shortage probability based on the second state sampling data and the second load reduction amount, and obtaining a second accumulated risk value corresponding to each system state based on the expected values of power failure electric quantity in the second year and the second power shortage probability.
It will be clear to those skilled in the art that, for convenience and brevity of description, reference may be made to the corresponding process in the foregoing method embodiment for the specific working process of the above-described apparatus, which is not described in detail herein.
It should be noted that, the embodiment of the risk assessment device of the power system described above is merely illustrative, where the modules described as separate components may or may not be physically separated, and the components displayed as the modules may or may not be physical units, may be located in one place, or may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
On the basis of the embodiment of the risk assessment method of the electric power system, another embodiment of the present invention provides a risk assessment terminal device of the electric power system, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, where the processor executes the computer program to implement the risk assessment method of the electric power system according to any one of the embodiments of the present invention.
Illustratively, in this embodiment the computer program may be partitioned into one or more modules, which are stored in the memory and executed by the processor to perform the present invention. The one or more modules may be a series of computer program instruction segments capable of performing a specific function for describing the execution of the computer program in a risk assessment terminal device of the power system.
The risk assessment terminal equipment of the power system can be computing equipment such as a desktop computer, a notebook computer, a palm computer and a cloud server. The risk assessment terminal device of the power system may include, but is not limited to, a processor, a memory.
The processor may be a central processing unit (Central Processing Unit, CPU), other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), off-the-shelf programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. The general purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is a control center of the risk assessment terminal device of the electric power system, and connects the respective parts of the risk assessment terminal device of the entire electric power system using various interfaces and lines.
The memory may be used to store the computer program and/or module, and the processor may implement various functions of the risk assessment terminal device of the power system by running or executing the computer program and/or module stored in the memory, and invoking data stored in the memory. The memory may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function, and the like; the storage data area may store data created according to the use of the cellular phone, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart Media Card (SMC), secure Digital (SD) Card, flash Card (Flash Card), at least one disk storage device, flash memory device, or other volatile solid-state storage device.
On the basis of the embodiment of the risk assessment method of the power system, another embodiment of the present invention provides a storage medium, where the storage medium includes a stored computer program, and when the computer program runs, the device where the storage medium is controlled to execute the risk assessment method of the power system according to any embodiment of the present invention.
In this embodiment, the storage medium is a computer-readable storage medium, and the computer program includes computer program code, where the computer program code may be in a source code form, an object code form, an executable file, or some intermediate form, and so on. The computer readable medium may include: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the computer readable medium contains content that can be appropriately scaled according to the requirements of jurisdictions in which such content is subject to legislation and patent practice, such as in certain jurisdictions in which such content is subject to legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunication signals.
In summary, according to the risk assessment method, the risk assessment device, the risk assessment equipment and the risk assessment storage medium for the electric power system, the multiple types of historical data of the electric power system are obtained, and the multiple types of historical data are converted into the uniformly distributed historical sequence; calculating the maximum mutual information value of any two first variables in the uniformly distributed history sequence, obtaining and determining the maximum information coefficient based on the information coefficient of any two first variables on the basis of the maximum mutual information value; constructing a Bayesian network model based on the maximum information coefficient; based on a Bayesian network model, obtaining a plurality of evenly distributed discrete samples, and carrying out data reduction on each evenly distributed discrete sample to obtain original historical data corresponding to each evenly distributed discrete sample; sampling the system state of the original historical data, calculating the accumulated risk value corresponding to each system state, and integrating the accumulated risk values corresponding to all the system states to obtain a risk evaluation value of the power system; compared with the prior art, the technical scheme of the invention can improve the speed and accuracy of risk assessment calculation.
The foregoing is merely a preferred embodiment of the present invention, and it should be noted that modifications and substitutions can be made by those skilled in the art without departing from the technical principles of the present invention, and these modifications and substitutions should also be considered as being within the scope of the present invention.
Claims (10)
1. A risk assessment method for an electrical power system, comprising:
acquiring multiple types of historical data of a power system, and performing data preprocessing on each type of historical data so as to convert the multiple types of historical data into a uniformly distributed historical sequence;
calculating the maximum mutual information value of any two first variables in the uniform distribution history sequence, obtaining information coefficients of the any two first variables based on the maximum mutual information value, and determining the maximum information coefficient based on the information coefficients;
constructing a Bayesian network model based on the maximum information coefficient;
based on the Bayesian network model, obtaining a plurality of evenly distributed discrete samples, and carrying out data reduction on each evenly distributed discrete sample to obtain original historical data corresponding to each evenly distributed discrete sample;
and sampling the system state of the original historical data, calculating the accumulated risk value corresponding to each system state, and integrating the accumulated risk values corresponding to all the system states to obtain a risk evaluation value of the power system.
2. The method for risk assessment of a power system according to claim 1, wherein each type of history data is subjected to data preprocessing so as to convert the plurality of types of history data into a uniformly distributed history sequence, specifically comprising:
calculating an edge probability density estimation value of each type of historical data based on the kernel density estimation;
integrating the edge probability density estimation value to obtain an edge distribution function of each type of historical data, and calculating an inverse function of the edge distribution function;
and calculating first variables corresponding to each type of historical data based on the inverse function, integrating all the first variables, and generating a uniformly distributed historical sequence.
3. The risk assessment method of a power system according to claim 2, wherein an edge probability density estimation value of each type of history data is calculated based on the kernel density estimation, and based on the kernel density estimation, wherein the edge probability density estimation value is calculated as follows:
wherein f x (α i ) Alpha is the estimated value of the probability density of the edge ij As historical data alpha i Is the jth data point of (2); n is the data amount; h is the bandwidth; k is a kernel function, and is taken as a normal distribution function.
4. The risk assessment method of a power system according to claim 1, wherein calculating a maximum mutual information value of any two first variables in the uniformly distributed history sequence, and obtaining information coefficients of any two first variables based on the maximum mutual information value, specifically comprises:
Selecting any two first variables in the uniformly distributed history sequence, generating a first grid, and dividing the first grid in an X-axis and Y-axis manner to obtain grid division number;
based on the grid division number, setting a plurality of division modes, and calculating maximum mutual information values corresponding to any two first variables in each division mode;
and carrying out normalization processing on the maximum mutual information value to obtain a normalized mutual information value, and selecting the maximum value in the normalized mutual information value to obtain information coefficients of any two first variables.
5. The method for risk assessment of a power system according to claim 4, wherein constructing a bayesian network model based on the maximum information coefficient comprises:
taking all first variables in the uniformly distributed history sequence as network nodes, taking two first variables corresponding to the maximum information coefficient as edges, and randomly generating a plurality of Bayesian network structures;
based on the scoring search function, calculating a search score corresponding to each Bayesian network structure, and selecting a Bayesian network structure corresponding to the highest value of the search score as an optimal Bayesian network structure;
based on a maximum likelihood estimation method, calculating network parameters of the optimal Bayesian network structure, and constructing a Bayesian network model based on the optimal Bayesian network structure and the network parameters.
6. The risk assessment method of a power system according to claim 1, wherein the data reduction is performed on each evenly distributed discrete sample to obtain original historical data corresponding to each evenly distributed discrete sample, and the method specifically comprises:
based on a random number generator, generating random numbers corresponding to each evenly distributed discrete sample, and inputting the random numbers into a preset data conversion formula so as to convert the random numbers into original historical data, wherein the preset data conversion formula is as follows:
in the method, in the process of the invention,random numbers corresponding to the w uniformly distributed discrete samples obtained for the ns th sampling, ++>Original historical data corresponding to the w uniformly distributed discrete samples obtained for the ns th sampling, +.>As an inverse function.
7. The method for risk assessment of a power system according to claim 5, wherein the system state sampling is performed on the raw historical data, and the calculation of the accumulated risk value corresponding to each system state specifically includes:
establishing a power grid risk assessment index system, wherein the power grid risk assessment index system comprises an expected annual blackout electric quantity value and an insufficient electric power probability;
classifying each original history data into independent variables and dependent variables;
When the original historical data is classified into independent variables, sampling the system state of the independent variables based on non-sequential Monte Carlo simulation to obtain first state sampling data;
when the power generation total capacity of the power system is determined to not meet the load, and the condition of power flow out-of-limit and node voltage out-of-limit occurs in the power system, carrying out load reduction processing on the first state sampling data based on a preset load removal strategy to obtain a first load reduction amount corresponding to each system state;
calculating a first year power failure electric quantity expected value and a first power shortage probability based on the first state sampling data and the first load reduction amount, and obtaining a first accumulated risk value corresponding to each system state based on the first year power failure electric quantity expected value and the first power shortage probability;
when the original historical data are classified into dependent variables, performing system state sampling on the dependent variables based on the optimal Bayesian network structure to obtain second state sampling data;
when the power generation total capacity of the power system is determined to not meet the load, and the condition of power flow out-of-limit and node voltage out-of-limit occurs in the power system, carrying out load reduction processing on the second state sampling data based on a preset load removal strategy to obtain a second load reduction amount corresponding to each system state;
And calculating expected values of power failure electric quantity in the second year and second power shortage probability based on the second state sampling data and the second load reduction amount, and obtaining a second accumulated risk value corresponding to each system state based on the expected values of power failure electric quantity in the second year and the second power shortage probability.
8. A risk assessment apparatus for an electric power system, comprising: the system comprises a data preprocessing module, a data calculation module, a model construction module, a data reduction module and a risk evaluation value calculation module;
the data preprocessing module is used for acquiring multiple types of historical data of the power system, and performing data preprocessing on each type of historical data so as to convert the multiple types of historical data into a uniformly distributed historical sequence;
the data calculation module is used for calculating the maximum mutual information value of any two first variables in the uniform distribution history sequence, obtaining information coefficients of the any two first variables based on the maximum mutual information value, and determining the maximum information coefficient based on the information coefficients;
the model construction module is used for constructing a Bayesian network model based on the maximum information coefficient;
The data reduction module is used for obtaining a plurality of evenly distributed discrete samples based on the Bayesian network model, and carrying out data reduction on each evenly distributed discrete sample to obtain original historical data corresponding to each evenly distributed discrete sample;
and the risk evaluation value calculation module is used for sampling the system state of the original historical data, calculating the accumulated risk value corresponding to each system state, and integrating the accumulated risk values corresponding to all the system states to obtain a risk evaluation value of the power system.
9. A terminal device comprising a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, the processor implementing the risk assessment method of the power system according to any one of claims 1 to 7 when the computer program is executed.
10. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored computer program, wherein the computer program, when run, controls a device in which the computer readable storage medium is located to perform the risk assessment method of the power system according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310590864.2A CN116452005A (en) | 2023-05-24 | 2023-05-24 | Risk assessment method, device, equipment and storage medium for electric power system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310590864.2A CN116452005A (en) | 2023-05-24 | 2023-05-24 | Risk assessment method, device, equipment and storage medium for electric power system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116452005A true CN116452005A (en) | 2023-07-18 |
Family
ID=87130359
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310590864.2A Pending CN116452005A (en) | 2023-05-24 | 2023-05-24 | Risk assessment method, device, equipment and storage medium for electric power system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116452005A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118365139A (en) * | 2024-06-17 | 2024-07-19 | 国网上海市电力公司 | Risk situation awareness method, system, equipment and medium |
-
2023
- 2023-05-24 CN CN202310590864.2A patent/CN116452005A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118365139A (en) * | 2024-06-17 | 2024-07-19 | 国网上海市电力公司 | Risk situation awareness method, system, equipment and medium |
| CN118365139B (en) * | 2024-06-17 | 2024-09-13 | 国网上海市电力公司 | Risk situation awareness method, system, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | A new chaotic time series hybrid prediction method of wind power based on EEMD-SE and full-parameters continued fraction | |
| CN116452005A (en) | Risk assessment method, device, equipment and storage medium for electric power system | |
| CN115660232A (en) | Ultra-short-term prediction method, device and system for wind power | |
| CN113609699B (en) | Calculation method and system of alternating current power flow model of radial power distribution network | |
| CN118153766A (en) | Wind power output prediction method, device and medium in extreme weather scene | |
| CN114298132A (en) | Wind power prediction method and device and electronic equipment | |
| Zhang et al. | Joint forecasting of regional wind and solar power based on attention neural network | |
| CN111950752A (en) | Photovoltaic power station generating capacity prediction method, device and system and storage medium thereof | |
| Wu et al. | Uncertain flow calculations of a distribution network containing DG based on blind number theory | |
| CN108694475A (en) | Short-term time scale photovoltaic cell capable of generating power amount prediction technique based on mixed model | |
| CN111079982B (en) | Planning method, system, medium and electronic equipment for cable path of wind power plant | |
| CN115528684A (en) | Ultra-short-term load prediction method and device and electronic equipment | |
| CN115275975A (en) | Method and device for determining electric power data matching degree of optical storage charging station | |
| CN115329487A (en) | Parameter setting method for photovoltaic power generation system and terminal equipment | |
| CN114139803A (en) | Method, system, equipment and medium for predicting short-term power of wind power station | |
| CN113904338A (en) | Wind power grid-connected system and frequency characteristic probability load flow calculation method and system | |
| Cho et al. | Application of Parallel ANN-PSO to Hourly Solar PV Estimation | |
| Xu et al. | A new approach for fast reliability evaluation of composite power system considering wind farm | |
| Apostolopoulou et al. | Effects of solar and wind generation integration on feeder hosting capacity | |
| CN115829165B (en) | Distributed photovoltaic operation condition analysis method and device based on power generation performance difference | |
| CN116128130B (en) | Short-term wind energy data prediction method and device based on graphic neural network | |
| CN117154725B (en) | Water-wind-solar multi-energy complementary scheduling method, device, computer equipment and medium | |
| CN115459269A (en) | Multi-scene power distribution network reconstruction method and device | |
| CN116169681A (en) | Power grid morphology analysis method, system, electronic equipment and medium | |
| SA’ADU et al. | NONLINEAR AUTOREGRESSIVE NEURAL NETWORK FOR WIND POWER GENERATION FORECASTING |
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 |