CN112101673B - Power grid development trend prediction method and system based on hidden Markov model - Google Patents
Power grid development trend prediction method and system based on hidden Markov model Download PDFInfo
- Publication number
- CN112101673B CN112101673B CN202011000648.0A CN202011000648A CN112101673B CN 112101673 B CN112101673 B CN 112101673B CN 202011000648 A CN202011000648 A CN 202011000648A CN 112101673 B CN112101673 B CN 112101673B
- Authority
- CN
- China
- Prior art keywords
- power grid
- membership
- grid development
- target index
- trend
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000011161 development Methods 0.000 title claims abstract description 181
- 238000000034 method Methods 0.000 title claims abstract description 34
- 239000011159 matrix material Substances 0.000 claims abstract description 67
- 238000005457 optimization Methods 0.000 claims abstract description 32
- 238000012847 principal component analysis method Methods 0.000 claims abstract description 10
- 238000012549 training Methods 0.000 claims abstract description 10
- 238000012545 processing Methods 0.000 claims description 15
- 230000008859 change Effects 0.000 claims description 10
- 230000008901 benefit Effects 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 5
- 238000009434 installation Methods 0.000 claims description 4
- 238000012797 qualification Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000004134 energy conservation Methods 0.000 claims description 3
- 230000036541 health Effects 0.000 claims description 3
- 238000000513 principal component analysis Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000003745 diagnosis Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 239000005995 Aluminium silicate Substances 0.000 description 1
- 235000012211 aluminium silicate Nutrition 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011157 data evaluation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- NLYAJNPCOHFWQQ-UHFFFAOYSA-N kaolin Chemical compound O.O.O=[Al]O[Si](=O)O[Si](=O)O[Al]=O NLYAJNPCOHFWQQ-UHFFFAOYSA-N 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 230000035699 permeability Effects 0.000 description 1
- 238000011160 research Methods 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/02—Computing arrangements based on specific mathematical models using fuzzy logic
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Computational Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Pure & Applied Mathematics (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Algebra (AREA)
- Probability & Statistics with Applications (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Life Sciences & Earth Sciences (AREA)
- Automation & Control Theory (AREA)
- Biomedical Technology (AREA)
- Fuzzy Systems (AREA)
- Molecular Biology (AREA)
Abstract
The invention discloses a power grid development trend prediction method and system based on a hidden Markov model. The method comprises the following steps: calculating a target index value corresponding to the target index type by adopting a principal component analysis method; determining a power grid development dynamic trend feature vector according to the target index value; solving parameters of a membership function model according to the power grid development dynamic trend feature vector and the optimization model and generating a membership function; substituting the power grid development dynamic trend feature vector into a membership function to generate a power grid development dynamic trend membership vector; generating a membership matrix according to the membership vector of the dynamic trend of the power grid development, and clustering the membership matrix; training the hidden Markov model according to the clustered membership matrix, and predicting the power grid development trend level by adopting a Viterbi algorithm according to the trained hidden Markov model. By adopting the method and the system provided by the invention, the development trend of the power grid can be reasonably judged so as to assist in adjusting various decision guides of the development and deployment of the power grid in the future.
Description
Technical Field
The invention relates to the technical field of power grid development trend prediction, in particular to a power grid development trend prediction method and system based on a hidden Markov model.
Background
With the maturation of new technologies such as artificial intelligence and the like and the improvement of the permeability of various new energy sources, the development brings great change to the power grid. The development state of the power grid is not reflected from the national construction, enterprise development, market construction, the power grid itself, and even from various perspectives of user service. The quantitative power grid development state is a basic work for smoothly developing power grid development diagnosis research, understanding the power grid development situation, evaluating the development dynamics and realizing the basis of power grid development trend prediction.
Based on power grid development diagnosis work, few methods for predicting and early warning power grid development trend are provided. In the dynamic process of accelerating development of the power grid, the power grid development result obtained by historical data evaluation shows a little delay for future development planning of the power grid, and the requirement of power grid development guidance cannot be met. Therefore, it is necessary to establish an effective prediction method to reasonably judge the power grid development trend so as to assist in adjusting decision guidance of future power grid development and deployment.
Disclosure of Invention
The invention aims to provide a power grid development trend prediction method and a power grid development trend prediction system based on a hidden Markov model, which can reasonably judge the power grid development trend so as to assist in adjusting various decision guides of future power grid development deployment.
In order to achieve the above object, the present invention provides the following solutions:
a power grid development trend prediction method comprises the following steps:
acquiring a target index set of a power grid development trend; the target index set comprises a plurality of target index types related to the power grid development trend, and each target index type comprises a plurality of basic indexes;
carrying out standardization processing on each basic index to obtain a standardized basic index value;
calculating a target index value corresponding to each target index type by adopting a principal component analysis method according to the standardized basic index value;
determining a power grid development dynamic trend feature vector corresponding to each target index type according to the target index values;
acquiring a power grid development trend early warning grade, and determining a membership function model according to the power grid development trend early warning grade;
solving parameters of the membership function model according to the power grid development dynamic trend feature vector and the optimization model, and generating a membership function according to the solved parameters; the optimization model is constructed according to fuzzy entropy;
substituting the power grid development dynamic trend feature vector into the membership function to generate a power grid development dynamic trend membership vector;
generating a membership matrix according to the power grid development dynamic trend membership vector, and clustering the membership matrix to obtain a clustered membership matrix;
training the hidden Markov model according to the clustered membership matrix to obtain a trained hidden Markov model;
and predicting the power grid development trend level by adopting a Viterbi algorithm according to the trained hidden Markov model.
Alternatively to this, the method may comprise,
the target index type specifically comprises:
development speed and scale, development safety and quality, development efficiency and benefit, and development operation and policy;
the basic indexes of the development speed and the scale specifically comprise:
GDP speed increasing, power supply installation speed increasing, load speed increasing, variable capacitance load ratio, line load ratio, household average distribution capacity, line length and interconnection rate;
the basic indexes of the development safety and quality specifically comprise:
n-1 passing rate, potential safety hazard number, power supply reliability, equipment availability coefficient, voltage qualification rate, equipment average life, automation coverage rate, cabling rate and intelligent ammeter coverage rate;
the basic indexes of the development efficiency and the benefit specifically comprise:
line maximum load rate, average load rate, transformer substation maximum load rate, line loss rate, number of business units per capita, power transformation capacity per capita, line length per capita, renewable energy access ratio, energy conservation and emission reduction, and power grid investment ratio;
the basic indexes of the development management and policy specifically comprise:
the unit power grid asset power load, the unit power grid asset sales amount, the net profit, the asset liability rate, the income growth rate and the purchase-sale spread increment ratio.
Optionally, the normalizing process is performed on each basic index to obtain a normalized basic index value, which specifically includes:
judging which type of the basic index is to obtain a first judging result;
if the first judging result is a maximum index, the basic index is subjected to standardization processing according to the following formula:
if the first judging result is a minimum index, the base index is normalized according to the following formula:
if the first judging result is a qualified index, the basic index is subjected to standardization processing according to the following formula:
in the method, in the process of the invention,represents the normalized basic index value, +.>The basic index value before conversion is represented, xi represents a safety threshold value for a qualified index, i represents a target index type, and j represents a basic index.
Optionally, calculating, according to the normalized basic index value, a target index value corresponding to each target index type by using a principal component analysis method, including:
within the full time sequence length, selecting the standardized basic index values in the same target index type to generate a sample matrix; the full-time sequence length is the length from the beginning year to the end year, the rows of the sample matrix represent the years, and the columns of the sample matrix represent the basic indexes;
calculating a correlation coefficient of each element in the sample matrix, and generating a correlation coefficient matrix according to the correlation coefficient;
solving a plurality of characteristic values of the correlation coefficient matrix, and arranging all the characteristic values in a sequence from big to small;
calculating the variance contribution rate of each characteristic value; the variance contribution rate of the characteristic values is the ratio of the selected characteristic values to the sum of all the characteristic values;
sequentially accumulating the variance contribution rates of the feature values from the variance contribution rate corresponding to the maximum feature value according to the order of the variance contribution rates from large to small, and taking the feature value corresponding to the accumulated variance contribution rate as a main component when the accumulated value of the variance contribution rate exceeds a preset contribution rate value for the first time;
taking the sum of products of the principal component and the variance contribution rate corresponding to the principal component as a target index value;
wherein,
the sample matrix is:
wherein X is a sample matrix, t is year, and X tj A normalized basic index value representing the jth basic index of the t-th year;
the target index value is:
I i =α 1 λ 1 +α 2 λ 2 +...+α m λ m
wherein I is i A is the target index value of the ith target index type m Represents the variance contribution rate, lambda corresponding to the mth principal component m Representing the mth principal component.
Optionally, determining, according to the target index value, a feature vector of a dynamic trend of power grid development corresponding to each target index type, specifically includes:
the index change rate f is calculated according to the following formula:
f=I i (t+1)-I i (t)
calculating dynamic trend characteristics RES of power grid development according to the following formula:
wherein,
wherein I is i (t+1) represents the target index value of the t+1st year of the I-th target index type, I i (t) represents the target index value of the ith target index type in the t year, Δt represents the prediction step length, f (x) represents the line graph function of the target index value in time sequence, and g (x) represents the electricityA network development tie trend function, x represents a time variable;
generating a power grid development dynamic trend feature vector according to the index change rate and the dynamic trend feature of the power grid development;
wherein, the power grid development dynamic trend feature vector Q is as follows:
wherein RES is t Representing a dynamic trend characteristic of the grid development in the t-th year,indicating the index change rate in the t year.
Optionally, the determining the membership function model according to the early warning level of the power grid development trend specifically includes:
determining a membership function model according to the following formula:
in the formula, early warning is shown when the power grid development trend early warning level S=1, 2,3 and S=1, secondary early warning is shown when S=2, health is shown when S=3, and r is shown in the formula 1 (fet) represents the corresponding membership function when s=1, r 2 (fet) represents the corresponding membership function when s=2, r 3 (fet) represents the corresponding membership function when s=3, q= { fet 1 ,fet 2 ,...,fet t The fet represents the column vector of the characteristic vector Q of the dynamic trend of the power grid, a 1 Represent the firstA parameter, a 2 Representing a second parameter.
Optionally, the solving the parameters of the membership function model according to the feature vector of the dynamic trend of the power grid development and the optimization model, and generating the membership function according to the parameters obtained by solving specifically includes:
establishing an optimization model; the optimization model is as follows:
wherein u=1, 2,3, r 1 =r 1 (fet),r 2 =r 2 (fet),r 3 =r 3 (fet),H(r 1 ,r 2 ,r 3 ) Represents an optimization function, k represents the total number of target index types, k=4, s (r u ) Is an intermediate function;
substituting the power grid development dynamic trend feature vector into the optimization model and then performing optimization operation to obtain parameters of the membership function model;
and generating a membership function according to the parameters of the membership function model.
Optionally, the clustering of the membership matrix to obtain a clustered membership matrix specifically includes:
clustering the membership matrix according to the following formula:
wherein E represents the sum of squares, r represents the cluster type, C represents the total number of clusters, and m represents the number of clusters classified into C r The power grid development dynamic trend membership vector, C r Representing the cluster center, M represents the membership matrix.
The invention also provides a power grid development trend prediction system, which comprises:
the data acquisition module is used for acquiring a target index set of the power grid development trend; the target index set comprises a plurality of target index types related to the power grid development trend, and each target index type comprises a plurality of basic indexes;
the standardized processing module is used for carrying out standardized processing on each basic index to obtain a standardized basic index value;
the principal component analysis module is used for calculating target index values corresponding to each target index type by adopting a principal component analysis method according to the normalized basic index values;
the feature vector determining module is used for determining a power grid development dynamic trend feature vector corresponding to each target index type according to the target index values;
the membership function model building module is used for obtaining the early warning grade of the power grid development trend and determining a membership function model according to the early warning grade of the power grid development trend;
the membership function generating module is used for solving parameters of the membership function model according to the power grid development dynamic trend feature vector and the optimization model and generating a membership function according to the solved parameters; the optimization model is constructed according to fuzzy entropy;
the membership vector generation module is used for substituting the power grid development dynamic trend feature vector into the membership function to generate a power grid development dynamic trend membership vector;
the clustering module is used for generating a membership matrix according to the membership vector of the power grid development dynamic trend, and clustering the membership matrix to obtain a clustered membership matrix;
the hidden Markov model training module is used for training the hidden Markov model according to the clustered membership matrix to obtain a trained hidden Markov model;
and the power grid development trend grade prediction module is used for predicting the power grid development trend grade by adopting a Viterbi algorithm according to the trained hidden Markov model.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a power grid development trend prediction method and a power grid development trend prediction system based on a hidden Markov model, wherein a principal component analysis method is adopted to calculate target index values corresponding to each target index type; according to the target index values, determining a power grid development dynamic trend feature vector corresponding to each target index type; solving parameters of a membership function model according to the power grid development dynamic trend feature vector and the optimization model, and generating a membership function according to the solved parameters; substituting the power grid development dynamic trend feature vector into a membership function to generate a power grid development dynamic trend membership vector; generating a membership matrix according to the membership vector of the dynamic trend of the power grid development, and clustering the membership matrix to obtain a clustered membership matrix; training the hidden Markov model according to the clustered membership matrix, predicting the power grid development trend grade by adopting a Viterbi algorithm according to the trained hidden Markov model, and reasonably judging the power grid development trend to assist in adjusting various decision guides of future power grid development deployment.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a method for predicting a power grid development trend based on a hidden Markov model in an embodiment of the present invention;
fig. 2 is a block diagram of a power grid development trend prediction system based on a hidden markov model in an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. 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.
The invention aims to provide a power grid development trend prediction method and a power grid development trend prediction system based on a hidden Markov model, which can reasonably judge the power grid development trend so as to assist in adjusting various decision guides of future power grid development deployment.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
Examples
Fig. 1 is a flowchart of a power grid development trend prediction method based on a hidden markov model in an embodiment of the present invention, as shown in fig. 1, a power grid development trend prediction method based on a hidden markov model includes:
step 101: acquiring a target index set of a power grid development trend; the target index set comprises a plurality of target index types related to the power grid development trend, and each target index type comprises a plurality of basic indexes.
The target index type specifically comprises:
development speed and scale, development safety and quality, development efficiency and benefit, and development operation and policy;
basic indexes of development speed and scale specifically include:
GDP speed increasing, power supply installation speed increasing, load speed increasing, variable capacitance load ratio, line load ratio, household average distribution capacity, line length and interconnection rate;
basic indexes of developing safety and quality specifically comprise:
n-1 passing rate, potential safety hazard number, power supply reliability, equipment availability coefficient, voltage qualification rate, equipment average life, automation coverage rate, cabling rate and intelligent ammeter coverage rate;
basic indexes of development efficiency and benefit specifically include:
line maximum load rate, average load rate, transformer substation maximum load rate, line loss rate, number of business units per capita, power transformation capacity per capita, line length per capita, renewable energy access ratio, energy conservation and emission reduction, and power grid investment ratio;
basic indexes of development management and policy specifically include:
the unit power grid asset power load, the unit power grid asset sales amount, the net profit, the asset liability rate, the income growth rate and the purchase-sale spread increment ratio.
Step 102: and (3) carrying out standardization processing on each basic index to obtain a standardized basic index value.
Step 102, specifically includes:
and judging which type of index the basic index is, and obtaining a first judgment result.
{ GDP speed-up, power installation speed-up, load speed-up, average power distribution capacity, line length, interconnection rate, N-1 pass rate, power supply reliability } and the like belong to extremely large indexes; { potential safety hazard number, line loss rate, asset liability rate } and the like belong to extremely small indexes; { variable capacitance-to-load ratio, line capacitance-to-load ratio } and the like belong to the qualification index.
If the first judging result is a very large index, the basic index is standardized according to the following formula:
if the first judging result is a minimum index, the basic index is standardized according to the following formula:
if the first judging result is a qualified index, the basic index is subjected to standardization processing according to the following formula:
in the method, in the process of the invention,represents the normalized basic index value, +.>The basic index value before conversion is represented, xi represents a safety threshold value for a qualified index, i represents a target index type, and j represents a basic index.
Step 103: and calculating the target index value corresponding to each target index type by adopting a principal component analysis method according to the standardized basic index value.
Step 103, specifically includes:
within the full time sequence length, selecting the standardized basic index values in the same target index type to generate a sample matrix; the full-time sequence length is the length from the beginning year to the end year, the rows of the sample matrix represent the years, and the columns of the sample matrix represent the basic indexes;
calculating a correlation coefficient of each element in the sample matrix, and generating a correlation coefficient matrix according to the correlation coefficients;
solving a plurality of characteristic values of the correlation coefficient matrix, and arranging all the characteristic values in a sequence from big to small;
calculating the variance contribution rate of each characteristic value; the variance contribution rate of the characteristic values is the ratio of the selected characteristic values to the sum of all the characteristic values;
sequentially accumulating the variance contribution rates of the feature values from the variance contribution rate corresponding to the maximum feature value according to the order of the variance contribution rates from large to small, and taking the feature value corresponding to the accumulated variance contribution rate as a main component when the accumulated value of the variance contribution rate exceeds a preset contribution rate value for the first time;
taking the sum of products of the principal component and the variance contribution rate corresponding to the principal component as a target index value;
wherein,
the sample matrix is:
wherein X is a sample matrix, t is year, and X tj A normalized basic index value representing the jth basic index of the t-th year;
the target index value is:
I i =α 1 λ 1 +α 2 λ 2 +...+α m λ m
wherein I is i A is the target index value of the ith target index type m Represents the variance contribution rate, lambda corresponding to the mth principal component m Representing the mth principal component.
Step 104: and determining the power grid development dynamic trend feature vector corresponding to each target index type according to the target index values.
Step 104 specifically includes:
the index change rate f is calculated according to the following formula:
f=I i (t+1)-I i (t)
calculating dynamic trend characteristics RES of power grid development according to the following formula:
wherein,
wherein I is i (t+1) represents the target index value of the t+1st year of the I-th target index type, I i (t)The method comprises the steps of representing a target index value of an ith target index type in a t year, wherein deltat represents a prediction step length, f (x) represents a line graph function of the target index value on time sequence, g (x) represents a power grid development tie trend function, and x represents a time variable.
And generating a power grid development dynamic trend feature vector according to the index change rate and the dynamic trend feature of the power grid development.
The power grid development dynamic trend feature vector Q is as follows:
wherein RES is t Representing a dynamic trend characteristic of the grid development in the t-th year,indicating the index change rate in the t year.
Step 105: and acquiring the early warning grade of the power grid development trend, and determining a membership function model according to the early warning grade of the power grid development trend.
Step 105 specifically includes:
the membership function model (choice of the kaolin membership function model) is determined according to the following formula:
in the formula, early warning is shown when the power grid development trend early warning level S=1, 2,3 and S=1, secondary early warning is shown when S=2, health is shown when S=3, and r is shown in the formula 1 (fet) represents the corresponding membership function when s=1, r 2 (fet) represents the corresponding membership function when s=2, r 3 (fet) represents the corresponding membership function, X, when s=3 K ={fet 1 ,fet 2 ,...,fet T The fet represents the column vector of the characteristic vector Q of the dynamic trend of the power grid, a 1 Representing a first parameter, a 2 Representing a second parameter.
Step 106: solving parameters of a membership function model according to the power grid development dynamic trend feature vector and the optimization model, and generating a membership function according to the solved parameters; and constructing an optimization model according to the fuzzy entropy.
Step 106, specifically includes:
domain of design and discussion X K ={fet 1 ,fet 2 ,...,fet T State field r= { R } 1 ,r 2 ,r 3 Then from the Fuzzy Entropy (FEI) as a measure of ambiguity, an optimization model can be built:
establishing an optimization model; the optimization model is as follows:
wherein u=1, 2,3, r 1 =r 1 (fet),r 2 =r 2 (fet),r 3 =r 3 (fet),H(r 1 ,r 2 ,r 3 ) Represents an optimization function, k represents the total number of target index types, k=4, s (r u ) Is an intermediate function;
substituting the power grid development dynamic trend feature vector into an optimization model, and then performing optimization operation to obtain parameters of a membership function model;
and generating a membership function according to the parameters of the membership function model.
Step 107: substituting the power grid development dynamic trend feature vector into the membership function to generate a power grid development dynamic trend membership vector.
Step 108: generating a membership matrix according to the membership vector of the dynamic trend of the power grid development, and clustering the membership matrix to obtain the clustered membership matrix.
Step 108 specifically includes:
clustering the membership matrix according to the following formula:
wherein E represents the sum of squares, r represents the cluster type, C represents the total number of clusters, and m represents the number of clusters classified into C r The power grid development dynamic trend membership vector, C r And (3) representing a clustering center, wherein M represents a membership matrix, M is a 4*3 matrix, and the rows of the matrix M represent target index types.
Step 109: training the hidden Markov model according to the clustered membership matrix to obtain a trained hidden Markov model.
Step 110: and predicting the power grid development trend grade by adopting a Viterbi algorithm according to the trained hidden Markov model.
And inputting a sequence to be predicted, and calculating a power grid development trend grade sequence by using a dimension bit algorithm.
Analyzing the weak links of the power grid development by combining the trend grade discrimination results and the index values; and the development trend parameters are used for participating in power grid development diagnosis and evaluation work with different meanings, so as to assist in realizing power grid situation awareness and comprehensive power grid evaluation work.
Fig. 2 is a block diagram of a power grid development trend prediction system based on a hidden markov model in an embodiment of the present invention. As shown in fig. 2, a power grid development trend prediction system based on a hidden markov model includes:
the data acquisition module 201 is configured to acquire a target index set of a power grid development trend; the target index set comprises a plurality of target index types related to the power grid development trend, and each target index type comprises a plurality of basic indexes.
The normalization processing module 202 is configured to perform normalization processing on each base index to obtain a normalized base index value.
The principal component analysis module 203 is configured to calculate, according to the normalized basic index value, a target index value corresponding to each target index type by using a principal component analysis method.
The feature vector determining module 204 is configured to determine a power grid development dynamic trend feature vector corresponding to each target index type according to the target index values.
The membership function model building module 205 is configured to obtain a power grid development trend early warning level, and determine a membership function model according to the power grid development trend early warning level.
The membership function generating module 206 is configured to solve parameters of a membership function model according to the dynamic trend feature vector of the power grid development and the optimization model, and generate a membership function according to the solved parameters; and constructing an optimization model according to the fuzzy entropy.
The membership vector generation module 207 is configured to substitute the power grid development dynamic trend feature vector into a membership function to generate a power grid development dynamic trend membership vector.
And the clustering module 208 is configured to generate a membership matrix according to the membership vector of the dynamic trend of the power grid, and cluster the membership matrix to obtain a clustered membership matrix.
The hidden markov model training module 209 is configured to train the hidden markov model according to the clustered membership matrix to obtain a trained hidden markov model.
The power grid trend level prediction module 210 is configured to predict the power grid trend level by using a viterbi algorithm according to the trained hidden markov model.
For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The power grid development trend prediction method and system based on the hidden Markov model provided by the invention can evaluate the future development trend of the power grid based on the current basic index and model, develop power grid planning in advance for the power grid department, and provide effective support for weak links.
The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to assist in understanding the methods of the present invention and the core ideas thereof; also, it is within the scope of the present invention to be modified by those of ordinary skill in the art in light of the present teachings. In summary, the present description should not be construed as limiting the invention.
Claims (2)
1. The utility model provides a power grid development trend prediction method which is characterized by comprising the following steps:
acquiring a target index set of a power grid development trend; the target index set comprises a plurality of target index types related to the power grid development trend, and each target index type comprises a plurality of basic indexes;
carrying out standardization processing on each basic index to obtain a standardized basic index value;
calculating a target index value corresponding to each target index type by adopting a principal component analysis method according to the standardized basic index value;
determining a power grid development dynamic trend feature vector corresponding to each target index type according to the target index values;
acquiring a power grid development trend early warning grade, and determining a membership function model according to the power grid development trend early warning grade;
solving parameters of the membership function model according to the power grid development dynamic trend feature vector and the optimization model, and generating a membership function according to the solved parameters; the optimization model is constructed according to fuzzy entropy;
substituting the power grid development dynamic trend feature vector into the membership function to generate a power grid development dynamic trend membership vector;
generating a membership matrix according to the power grid development dynamic trend membership vector, and clustering the membership matrix to obtain a clustered membership matrix;
training the hidden Markov model according to the clustered membership matrix to obtain a trained hidden Markov model;
according to the trained hidden Markov model, predicting the power grid development trend level by adopting a Viterbi algorithm;
the target index type specifically comprises:
development speed and scale, development safety and quality, development efficiency and benefit, and development operation and policy;
the basic indexes of the development speed and the scale specifically comprise:
GDP speed increasing, power supply installation speed increasing, load speed increasing, variable capacitance load ratio, line load ratio, household average distribution capacity, line length and interconnection rate;
the basic indexes of the development safety and quality specifically comprise:
n-1 passing rate, potential safety hazard number, power supply reliability, equipment availability coefficient, voltage qualification rate, equipment average life, automation coverage rate, cabling rate and intelligent ammeter coverage rate;
the basic indexes of the development efficiency and the benefit specifically comprise:
line maximum load rate, average load rate, transformer substation maximum load rate, line loss rate, number of business units per capita, power transformation capacity per capita, line length per capita, renewable energy access ratio, energy conservation and emission reduction, and power grid investment ratio;
the basic indexes of the development management and policy specifically comprise:
the unit power grid asset power supply load, the unit power grid asset sales amount, the net profit, the asset liability rate, the income increasing rate and the purchase-sale price difference increment ratio;
the step of carrying out standardization processing on each basic index to obtain a standardized basic index value, which specifically comprises the following steps:
judging which type of the basic index is to obtain a first judging result;
if the first judging result is a maximum index, the basic index is subjected to standardization processing according to the following formula:
if the first judging result is a minimum index, the base index is normalized according to the following formula:
if the first judging result is a qualified index, the basic index is subjected to standardization processing according to the following formula:
in the method, in the process of the invention,represents the normalized basic index value, +.>The basic index value before conversion is represented, xi represents a safety threshold value aiming at a qualified index, i represents a target index type, and j represents a basic index;
calculating a target index value corresponding to each target index type by adopting a principal component analysis method according to the normalized basic index value, wherein the method specifically comprises the following steps:
within the full time sequence length, selecting the standardized basic index values in the same target index type to generate a sample matrix; the full-time sequence length is the length from the beginning year to the end year, the rows of the sample matrix represent the years, and the columns of the sample matrix represent the basic indexes;
calculating a correlation coefficient of each element in the sample matrix, and generating a correlation coefficient matrix according to the correlation coefficient;
solving a plurality of characteristic values of the correlation coefficient matrix, and arranging all the characteristic values in a sequence from big to small;
calculating the variance contribution rate of each characteristic value; the variance contribution rate of the characteristic values is the ratio of the selected characteristic values to the sum of all the characteristic values;
sequentially accumulating the variance contribution rates of the feature values from the variance contribution rate corresponding to the maximum feature value according to the order of the variance contribution rates from large to small, and taking the feature value corresponding to the accumulated variance contribution rate as a main component when the accumulated value of the variance contribution rate exceeds a preset contribution rate value for the first time;
taking the sum of products of the principal component and the variance contribution rate corresponding to the principal component as a target index value;
wherein,
the sample matrix is:
wherein X is a sample matrix, t is year, and X tj A normalized basic index value representing the jth basic index of the t-th year;
the target index value is:
I i =α 1 λ 1 +α 2 λ 2 +...+α m λ m
wherein I is i A is the target index value of the ith target index type m Represents the variance contribution rate, lambda corresponding to the mth principal component m Represents the mth principal component;
according to the target index value, determining a power grid development dynamic trend feature vector corresponding to each target index type, wherein the power grid development dynamic trend feature vector specifically comprises:
calculating the index change rate according to the following formula
Calculating dynamic trend characteristics RES of power grid development according to the following formula:
wherein,
wherein I is i (t+1) represents the target index value of the t+1st year of the I-th target index type, I i (t) represents a target index value of the ith target index type in the t year, Δt represents a prediction step length, f (x) represents a line graph function of the target index value on a time sequence, g (x) represents a power grid development tie trend function, and x represents a time variable;
generating a power grid development dynamic trend feature vector according to the index change rate and the dynamic trend feature of the power grid development;
wherein, the power grid development dynamic trend feature vector Q is as follows:
wherein RES is t Representing a dynamic trend characteristic of the grid development in the t-th year,index change rate indicating the t year;
the determining the membership function model according to the power grid development trend early warning level specifically comprises the following steps:
determining a membership function model according to the following formula:
in the formula, early warning is shown when the power grid development trend early warning level S=1, 2,3 and S=1, secondary early warning is shown when S=2, health is shown when S=3, and r is shown in the formula 1 (fet) represents the corresponding membership function when s=1, r 2 (fet) represents the corresponding membership function when s=2, r 3 (fet) represents the corresponding membership function when s=3, q= { fet 1 ,fet 2 ,...,fet t The fet represents the column vector of the characteristic vector Q of the dynamic trend of the power grid, a 1 Representing a first parameter, a 2 Representing a second parameter;
solving parameters of the membership function model according to the power grid development dynamic trend feature vector and the optimization model, and generating a membership function according to the solved parameters, wherein the method specifically comprises the following steps:
establishing an optimization model; the optimization model is as follows:
wherein u=1, 2,3, r 1 =r 1 (fet),r 2 =r 2 (fet),r 3 =r 3 (fet),H(r 1 ,r 2 ,r 3 ) Represents an optimization function, k represents the total number of target index types, k=4, s (r u ) Is an intermediate function;
substituting the power grid development dynamic trend feature vector into the optimization model and then performing optimization operation to obtain parameters of the membership function model;
generating a membership function according to the parameters of the membership function model;
clustering the membership matrix to obtain a clustered membership matrix, wherein the clustering method specifically comprises the following steps of:
clustering the membership matrix according to the following formula:
wherein E represents the sum of squares, r represents the cluster type, C represents the total number of clusters, and m represents the number of clusters classified into C r The power grid development dynamic trend membership vector, C r Representing the cluster center, M represents the membership matrix.
2. A power grid development trend prediction system constructed according to the power grid development trend prediction method of claim 1, comprising:
the data acquisition module is used for acquiring a target index set of the power grid development trend; the target index set comprises a plurality of target index types related to the power grid development trend, and each target index type comprises a plurality of basic indexes;
the standardized processing module is used for carrying out standardized processing on each basic index to obtain a standardized basic index value;
the principal component analysis module is used for calculating target index values corresponding to each target index type by adopting a principal component analysis method according to the normalized basic index values;
the feature vector determining module is used for determining a power grid development dynamic trend feature vector corresponding to each target index type according to the target index values;
the membership function model building module is used for obtaining the early warning grade of the power grid development trend and determining a membership function model according to the early warning grade of the power grid development trend;
the membership function generating module is used for solving parameters of the membership function model according to the power grid development dynamic trend feature vector and the optimization model and generating a membership function according to the solved parameters; the optimization model is constructed according to fuzzy entropy;
the membership vector generation module is used for substituting the power grid development dynamic trend feature vector into the membership function to generate a power grid development dynamic trend membership vector;
the clustering module is used for generating a membership matrix according to the membership vector of the power grid development dynamic trend, and clustering the membership matrix to obtain a clustered membership matrix;
the hidden Markov model training module is used for training the hidden Markov model according to the clustered membership matrix to obtain a trained hidden Markov model;
and the power grid development trend grade prediction module is used for predicting the power grid development trend grade by adopting a Viterbi algorithm according to the trained hidden Markov model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011000648.0A CN112101673B (en) | 2020-09-22 | 2020-09-22 | Power grid development trend prediction method and system based on hidden Markov model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011000648.0A CN112101673B (en) | 2020-09-22 | 2020-09-22 | Power grid development trend prediction method and system based on hidden Markov model |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112101673A CN112101673A (en) | 2020-12-18 |
CN112101673B true CN112101673B (en) | 2024-01-16 |
Family
ID=73754825
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011000648.0A Active CN112101673B (en) | 2020-09-22 | 2020-09-22 | Power grid development trend prediction method and system based on hidden Markov model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112101673B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113705874B (en) * | 2021-08-19 | 2024-03-15 | 国家电网有限公司 | New energy power grid evolution prediction method, device, computer equipment and storage medium |
CN116757337B (en) * | 2023-08-18 | 2023-11-21 | 克拉玛依市鼎泰建设(集团)有限公司 | House construction progress prediction system based on artificial intelligence |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103326903A (en) * | 2013-07-05 | 2013-09-25 | 华北电力大学 | Hidden-Markov-based Internet network delay forecasting method |
WO2013174146A1 (en) * | 2012-05-23 | 2013-11-28 | 国家电网公司 | Optimized evaluation method for wind power output power under multi-constraint condition for reducing transmission loss |
CN105976257A (en) * | 2015-12-17 | 2016-09-28 | 国家电网公司 | Power grid vulnerability evaluation method based on membership function fuzzy comprehensive evaluation method |
CN106372799A (en) * | 2016-08-31 | 2017-02-01 | 全球能源互联网研究院 | Power grid security risk prediction method |
CN106709821A (en) * | 2017-03-10 | 2017-05-24 | 东北电力大学 | Main component analysis-based power supply reliability evaluation method of medium-voltage power distribution network |
CN107274047A (en) * | 2017-04-24 | 2017-10-20 | 国网江西省电力公司赣州供电分公司 | A kind of power network method of post project evaluation based on multilevel extension assessment method |
CN108154256A (en) * | 2017-11-27 | 2018-06-12 | 国网北京市电力公司 | The determining method and device of forecasting risk value, storage medium |
CN109902265A (en) * | 2019-02-28 | 2019-06-18 | 西南石油大学 | A kind of underground method for early warning based on hidden Markov model |
CN110336768A (en) * | 2019-01-22 | 2019-10-15 | 西北大学 | A kind of Tendency Prediction method based on joint hidden Markov model and genetic algorithm |
CN111027732A (en) * | 2018-10-09 | 2020-04-17 | 中国电力科学研究院有限公司 | Method and system for generating multi-wind-farm output scene |
CN111582571A (en) * | 2020-04-30 | 2020-08-25 | 中国电力科学研究院有限公司 | Power grid operation situation sensing method and system with model driving and data driving integrated |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6602609B2 (en) * | 2015-09-04 | 2019-11-06 | パナソニック インテレクチュアル プロパティ コーポレーション オブ アメリカ | Power usage state estimation method |
CN106022645B (en) * | 2016-06-07 | 2021-02-12 | 深圳市芝电能源科技有限公司 | Non-invasive online real-time power load identification method and identification system |
US11493911B2 (en) * | 2018-12-27 | 2022-11-08 | Utopus Insights, Inc. | System and method for proactive handling of multiple faults and failure modes in an electrical network of energy assets |
-
2020
- 2020-09-22 CN CN202011000648.0A patent/CN112101673B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2013174146A1 (en) * | 2012-05-23 | 2013-11-28 | 国家电网公司 | Optimized evaluation method for wind power output power under multi-constraint condition for reducing transmission loss |
CN103326903A (en) * | 2013-07-05 | 2013-09-25 | 华北电力大学 | Hidden-Markov-based Internet network delay forecasting method |
CN105976257A (en) * | 2015-12-17 | 2016-09-28 | 国家电网公司 | Power grid vulnerability evaluation method based on membership function fuzzy comprehensive evaluation method |
CN106372799A (en) * | 2016-08-31 | 2017-02-01 | 全球能源互联网研究院 | Power grid security risk prediction method |
CN106709821A (en) * | 2017-03-10 | 2017-05-24 | 东北电力大学 | Main component analysis-based power supply reliability evaluation method of medium-voltage power distribution network |
CN107274047A (en) * | 2017-04-24 | 2017-10-20 | 国网江西省电力公司赣州供电分公司 | A kind of power network method of post project evaluation based on multilevel extension assessment method |
CN108154256A (en) * | 2017-11-27 | 2018-06-12 | 国网北京市电力公司 | The determining method and device of forecasting risk value, storage medium |
CN111027732A (en) * | 2018-10-09 | 2020-04-17 | 中国电力科学研究院有限公司 | Method and system for generating multi-wind-farm output scene |
CN110336768A (en) * | 2019-01-22 | 2019-10-15 | 西北大学 | A kind of Tendency Prediction method based on joint hidden Markov model and genetic algorithm |
CN109902265A (en) * | 2019-02-28 | 2019-06-18 | 西南石油大学 | A kind of underground method for early warning based on hidden Markov model |
CN111582571A (en) * | 2020-04-30 | 2020-08-25 | 中国电力科学研究院有限公司 | Power grid operation situation sensing method and system with model driving and data driving integrated |
Non-Patent Citations (6)
Title |
---|
Hidden Markov Models revealing the household thermal profiling from smart meter data;dataAnatoli Paul Ulmeanu 等;Energy and Buildings;第154卷;127-140 * |
Higher Automated Learning through Principal Component Analysis and Markov Models;Alan Carlin 等;Artificial Intelligence in Education;661-665 * |
Solving Ill-Conditioned State-Estimation Problems in Distribution Grids With Hidden-Markov Models of Load Dynamics;Inês L. Roça 等;IEEE Transactions on Power Systems;第35卷(第1期);1-9 * |
基于HMM模型的电力负荷预测模型研究;郑敏嘉;卢洵;程鑫;;机电工程技术(11);170-173 * |
基于隐马尔科夫和主成分分析的电网数据词典构建;秦欢 等;电力大数据;第22卷(第1期);16-21 * |
电网发展诊断的改进模糊评价模型与评级;艾欣 等;中国电力;第55卷(第5期);66-75+165 * |
Also Published As
Publication number | Publication date |
---|---|
CN112101673A (en) | 2020-12-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105117602B (en) | A kind of metering device running status method for early warning | |
CN110232203B (en) | Knowledge distillation optimization RNN short-term power failure prediction method, storage medium and equipment | |
CN112101673B (en) | Power grid development trend prediction method and system based on hidden Markov model | |
CN110490409B (en) | DNN-based low-voltage transformer area line loss rate benchmarking value setting method | |
CN105956788A (en) | Dynamic management control method for cost of power transmission and transformation project | |
CN110837915B (en) | Low-voltage load point prediction and probability prediction method for power system based on hybrid integrated deep learning | |
CN112308427A (en) | New energy consumption restriction factor evaluation method and system based on combined empowerment-grey correlation | |
CN110428270A (en) | The potential preference client recognition methods of the channel of logic-based regression algorithm | |
CN116579768B (en) | Power plant on-line instrument operation and maintenance management method and system | |
CN113780684A (en) | Intelligent building user energy consumption behavior prediction method based on LSTM neural network | |
CN113595071A (en) | Transformer area user identification and voltage influence evaluation method | |
CN112506982A (en) | Method for predicting maximum load of line and distribution transformer | |
CN116937563A (en) | Space load prediction method and system considering space-time correlation | |
CN115222160A (en) | Rail transit traction load prediction method based on measured big data | |
CN113935523A (en) | Voltage trend prediction method based on voltage change rule | |
CN115310653A (en) | Photovoltaic array residual life prediction method based on performance degradation data | |
CN115186882A (en) | Clustering-based controllable load spatial density prediction method | |
CN114118587A (en) | Electric energy quality evaluation method, system, equipment and storage medium for distributed photovoltaic | |
Shen et al. | An interval analysis scheme based on empirical error and mcmc to quantify uncertainty of wind speed | |
CN113949060A (en) | Voltage trend prediction system based on voltage change rule | |
Wang et al. | An alternative method for estimating wind-power capacity credit based on reliability evaluation using intelligent search | |
CN111797924A (en) | Three-dimensional garden portrait method and system based on clustering algorithm | |
CN117710153B (en) | Energy utilization auxiliary decision-making method and system based on multi-terminal equipment | |
CN113822473B (en) | Traction energy consumption reasonable interval prediction method based on multidimensional data | |
CN113537528B (en) | Preprocessing method and system for state monitoring data of power transmission and transformation equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |