CN112215512A - Comprehensive evaluation index weight quantification method and system considering functional characteristics of microgrid - Google Patents
Comprehensive evaluation index weight quantification method and system considering functional characteristics of microgrid Download PDFInfo
- Publication number
- CN112215512A CN112215512A CN202011138774.2A CN202011138774A CN112215512A CN 112215512 A CN112215512 A CN 112215512A CN 202011138774 A CN202011138774 A CN 202011138774A CN 112215512 A CN112215512 A CN 112215512A
- Authority
- CN
- China
- Prior art keywords
- weight
- index
- subjective
- evaluation
- objective
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 128
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000011002 quantification Methods 0.000 title claims abstract description 12
- 238000012706 support-vector machine Methods 0.000 claims abstract description 46
- 239000011159 matrix material Substances 0.000 claims description 60
- 238000010276 construction Methods 0.000 claims description 25
- 238000004364 calculation method Methods 0.000 claims description 18
- 230000007613 environmental effect Effects 0.000 claims description 18
- 230000008901 benefit Effects 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 17
- 230000002068 genetic effect Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 230000004044 response Effects 0.000 claims description 7
- 238000012549 training Methods 0.000 claims description 7
- 239000007789 gas Substances 0.000 claims description 6
- 239000005431 greenhouse gas Substances 0.000 claims description 6
- 238000012423 maintenance Methods 0.000 claims description 6
- 238000013145 classification model Methods 0.000 abstract description 3
- 238000004445 quantitative analysis Methods 0.000 abstract description 3
- 238000011160 research Methods 0.000 description 9
- 238000011161 development Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Entrepreneurship & Innovation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Molecular Biology (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Computational Linguistics (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Genetics & Genomics (AREA)
- Physiology (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
Abstract
The invention provides a comprehensive evaluation index weight quantification method and system considering functional characteristics of a micro-grid, which comprises the steps of constructing a micro-grid comprehensive evaluation system, calculating the subjective weight and the objective weight of each evaluation index, and determining the weight ratio of the subjective weight and the objective weight of a power supply guarantee type micro-grid or an economic type micro-grid by taking the optimal accuracy value as a target based on a support vector machine. The invention optimizes the subjective and objective weight ratio of an evaluation system based on a combined evaluation theory and a support vector machine classification model, can objectively carry out quantitative analysis on the importance degree of an index, and can also give consideration to the actual meaning and property of the index. Meanwhile, guidance is provided for system operation performance evaluation of various types of micro-grids in a targeted manner by combining the functional characteristics of the various types of micro-grids, and the method is suitable for evaluating a multi-target complex micro-grid system and is convenient for evaluators to carry out scientific and reasonable evaluation on the micro-grid system by integrating various factors and expected targets.
Description
Technical Field
The invention relates to the technical field of comprehensive evaluation of a microgrid, in particular to a comprehensive evaluation index weight quantification method and system considering functional characteristics of the microgrid.
Background
Under the dual pressure of environmental protection and energy exhaustion, the micro-grid has huge development potential and benefit space as an effective means for renewable energy utilization with various realization forms and different scales. As a small-sized power distribution system, the evaluation of the operational reliability, the economical efficiency and the environmental protection of a micro-grid is an important subject in the research field of the micro-grid. At present, the construction of a micro-grid project is developed in a small number of regions in the absence of a perfect micro-grid technology evaluation standard system, and the development of renewable energy sources is restricted.
The reasonable evaluation of the operation of the micro-grid system is beneficial to the scientific development and the large-scale popularization of the micro-grid application. Through active exploration and research on the evaluation of the index weight of the micro-grid, the method can provide theoretical and technical support for developing the project construction work of the micro-grid, optimizes the operation description capacity of the micro-grid, and further enhances the evaluation capacity of the operation condition of the micro-grid. The current research mainly discusses the construction of the evaluation index of the microgrid, and some weight index determination methods are mentioned, which have certain guiding significance for actual evaluation, but the evaluation index value is too subjective or too objective, and the development targets of various types of microgrid are not considered, so that further research is needed to meet the requirement of the construction of a scientific and reasonable evaluation system of the microgrid.
Document CN109784755A discloses a power grid intelligent level evaluation method based on an analytic hierarchy process, which is based on evaluation system index data, performs data standardization through a fuzzy membership function, and calculates index weight by using the analytic hierarchy process, thereby realizing intelligent evaluation of a power grid. Document CN108197746A discloses an evaluation method considering environmental protection of a microgrid, which is to construct a comprehensive objective function with optimal system economic and environmental protection indexes under the constraint of multiple operating scenes of the microgrid, so as to obtain an evaluation system model considering multiple objectives and multiple scenes. The invention adopts a single subjective or objective evaluation method to determine the index weight value, and has the problems that the subjectivity of the evaluation result is too strong or the evaluation result does not necessarily accord with the actual meaning of the target and the like.
The document ' Muyonghe, Luzong, Qiaoyin, and the like ', a comprehensive evaluation index system for grid safety and benefit based on multi-operator hierarchical analysis fuzzy evaluation, a power grid technology, 2015,39(01):23-28 ' researches a comprehensive evaluation method for considering grid safety and benefit, constructs 4-layer index systems of a target layer, a category layer, an index layer and a sub-index layer, and establishes a multi-operator hierarchical analysis fuzzy evaluation model by combining a fuzzy analytic hierarchy process. The literature ' cheng dazzling, zhang ning, wang jia ming, and the like ' comprehensive evaluation of a power transmission network planning scheme for high-proportion renewable energy grid connection, power system automation, 2019,43(03):33-42+57 ' deeply researches the current research situations of the construction, evaluation process, evaluation method and the like of a comprehensive evaluation system for power transmission network planning, and proposes a research prospect of power transmission network planning evaluation for high-proportion renewable energy grid connection. The above documents are all research on multidimensional comprehensive evaluation of system operation to realize the optimal cooperation of each index layer, but each type of microgrid or microgrid at different periods needs to meet different functional characteristics, so that a comprehensive evaluation system should be distinguished or adjusted, and further, the functional performance of each type or microgrid at each period can be scientifically evaluated and judged.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a comprehensive evaluation index weight quantification method and system considering the functional characteristics of a microgrid.
According to the comprehensive evaluation index weight quantification method for calculating the functional characteristics of the microgrid, provided by the invention, the method comprises the following steps:
the system construction step: constructing a comprehensive evaluation system of the microgrid;
and a weight calculation step: calculating subjective weight of each evaluation index by adopting a network analytic hierarchy process, and calculating objective weight of each evaluation index by adopting an entropy weight method;
determining the linear combination proportion of the subjective and objective weights: and determining the weight ratio of the subjective weight and the objective weight of the microgrid by taking the accuracy value optimal as a target based on a support vector machine.
Preferably, the system building step comprises:
a step of constructing a criterion layer: constructing a criterion layer, wherein the criterion layer comprises 3 main evaluation levels of system operation reliability, economy and environmental protection;
constructing a base layer; the method comprises the following steps of considering basic layer indexes on the basis of a criterion layer, and considering energy supply reliability, electric energy quality, source-load matching degree and demand side response indexes on a reliability layer; the cost and comprehensive benefit indexes such as construction, operation and maintenance and the like are considered in the aspect of economy; the indexes of renewable energy utilization rate, greenhouse gas emission and pollution gas emission are considered in the aspect of environmental protection.
Preferably, the network analytic hierarchy process for calculating the subjective weight of each index includes:
constructing a super matrix: according to a comprehensive evaluation system of the microgrid, on the basis of each criterion layer, carrying out indirect dominance comparison on each index in the criterion layer according to the influence of each index on the criterion layer to obtain normalized ranking weight, and constructing a judgment super matrix W;
constructing a weighting matrix: based on the indirect dominance comparison of the target layer on the influence of each criterion layer on the target layer, a weighting matrix A is obtained, and a weighting super matrix is further constructed
Calculating a limit hypermatrix and an index subjective weight matrix: pair-weighted supermatrixCalculating a limit supermatrixWhen in useThe limit at k → ∞ exists, converges and is unique, thenThe jth column of (a) is the limit relative ordering of each index to the index j, and further an index subjective weight matrix is obtained.
Preferably, the entropy weighting method for calculating the objective weight of each evaluation index comprises:
dimensionless processing steps: carrying out dimensionless processing on the decision matrix;
index entropy calculation step: calculating the metric value of each index according to the decision matrix, and standardizing the metric value to obtain entropy representing the importance of the index;
determining an objective weight of an evaluation index: and determining an objective evaluation weight value of the evaluation index according to the definition and the property of the entropy.
Preferably, the step of determining the ratio of linear combination of subjective and objective weights comprises:
and (3) performing subjective and objective weight linear combination: measuring subjective weight and objective weight by linear combination;
modeling a support vector machine: carrying out corresponding index value calculation on indexes of the sample schemes according to the combined weight, perfecting labels of the sample schemes, taking the label value as 1 if the label is a power supply guarantee type microgrid, taking the label value as a non-1 value if the label is a power supply economic type microgrid, and training a support vector machine by adopting the index values and the label values of all the sample schemes;
solving: and judging the optimal weight ratio value according to the accuracy value of the trained support vector machine, wherein the greater the accuracy value is, the more accurate the support vector machine model is represented, and optimizing and solving are carried out on the parameters of the support vector machine by adopting a genetic algorithm.
The comprehensive evaluation index weight quantification system considering the functional characteristics of the microgrid, provided by the invention, comprises the following modules:
a system construction module: constructing a comprehensive evaluation system of the microgrid;
a weight calculation module: calculating subjective weight of each evaluation index by adopting a network analytic hierarchy process, and calculating objective weight of each evaluation index by adopting an entropy weight method;
and an subjective and objective weight linear combination proportion determining module: and determining the weight ratio of the subjective weight and the objective weight of the microgrid by taking the accuracy value optimal as a target based on a support vector machine.
Preferably, the architecture module comprises:
a criterion layer construction module: constructing a criterion layer, wherein the criterion layer comprises 3 main evaluation levels of system operation reliability, economy and environmental protection;
a base layer construction module; the method comprises the following steps of considering basic layer indexes on the basis of a criterion layer, and considering energy supply reliability, electric energy quality, source-load matching degree and demand side response indexes on a reliability layer; the cost and comprehensive benefit indexes such as construction, operation and maintenance and the like are considered in the aspect of economy; the indexes of renewable energy utilization rate, greenhouse gas emission and pollution gas emission are considered in the aspect of environmental protection.
Preferably, the network analytic hierarchy process for calculating the subjective weight of each index includes:
constructing a super matrix module: according to a comprehensive evaluation system of the microgrid, on the basis of each criterion layer, carrying out indirect dominance comparison on each index in the criterion layer according to the influence of each index on the criterion layer to obtain normalized ranking weight, and constructing a judgment super matrix W;
and constructing a weighting matrix module: based on the indirect dominance comparison of the target layer on the influence of each criterion layer on the target layer, a weighting matrix A is obtained, and a weighting super matrix is further constructed
The module for calculating the limit hypermatrix and the index subjective weight matrix comprises: pair-weighted supermatrixCalculating a limit supermatrixWhen in useThe limit at k → ∞ exists, converges and is unique, thenThe jth column of (a) is the limit relative ordering of each index to the index j, and further an index subjective weight matrix is obtained.
Preferably, the objective weight calculation module for calculating each evaluation index by the entropy weight method comprises:
a dimensionless processing module: carrying out dimensionless processing on the decision matrix;
index entropy value calculation module: calculating the metric value of each index according to the decision matrix, and standardizing the metric value to obtain entropy representing the importance of the index;
an evaluation index objective weight determination module: and determining an objective evaluation weight value of the evaluation index according to the definition and the property of the entropy.
Preferably, the subjective and objective weight linear combination ratio determination module comprises:
and an subjective and objective weight linear combination module: measuring subjective weight and objective weight by linear combination;
a support vector machine modeling module: carrying out corresponding index value calculation on indexes of the sample schemes according to the combined weight, perfecting labels of the sample schemes, taking the label value as 1 if the label is a power supply guarantee type microgrid, taking the label value as a non-1 value if the label is a power supply economic type microgrid, and training a support vector machine by adopting the index values and the label values of all the sample schemes;
a solving module: and judging the optimal weight ratio value according to the accuracy value of the trained support vector machine, wherein the greater the accuracy value is, the more accurate the support vector machine model is represented, and optimizing and solving are carried out on the parameters of the support vector machine by adopting a genetic algorithm.
Compared with the prior art, the invention has the following beneficial effects:
1. the invention combines the subjective and objective evaluation methods, takes the advantages of the subjective and objective weight evaluation method into account, can objectively carry out quantitative analysis on the importance degree of the index, can also embody the actual meaning and property of the index, avoids the problems of too strong subjectivity of the evaluation result or non-conformity with the actual condition and the like, and has higher reliability.
2. The method considers the functional characteristics of various types of micro-grids, optimizes the subjective and objective weight ratio of the comprehensive evaluation indexes of the various types of micro-grids by adopting the support vector machine classification model, can describe the complex micro-grid system with multiple indexes and multiple target functions, improves the description capability of the operational functional characteristics of the micro-grid system, and has wide application range.
3. The method adopts the genetic algorithm to optimize the parameters of the support vector machine model, can improve the accuracy of the model, and simultaneously avoids the condition that the evaluation result is difficult to converge.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
fig. 1 is a comprehensive evaluation system diagram of a microgrid in the invention.
Fig. 2 is a flowchart of a method for quantizing combining weights in the present invention.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any way. It should be noted that it would be obvious to those skilled in the art that various changes and modifications can be made without departing from the spirit of the invention. All falling within the scope of the present invention.
As shown in fig. 1 and 2, the method for quantifying the weight of the comprehensive evaluation index of the microgrid provided by the invention mainly comprises four steps: constructing a comprehensive evaluation system of the microgrid; based on a combined weight theory, calculating the subjective weight of the evaluation index by adopting a network analytic hierarchy process, and calculating the objective weight of the evaluation index by adopting an entropy weight method; and determining the subjective and objective weight linear combination proportion of the power supply guarantee type and economic type micro-grid by taking the optimal accuracy value as a target based on the support vector machine, wherein the method specifically comprises the following steps:
step 1: and constructing a comprehensive evaluation system of the microgrid. The method comprises the following steps of constructing a comprehensive evaluation system of the microgrid from three levels of system operation reliability, economy and environmental protection, further screening basic indexes on the basis of each level, judging whether the basic indexes are independent or not, judging whether dependence or feedback relation exists or not, and the like, and further obtaining the comprehensive evaluation system of the microgrid.
(1) And constructing a criterion layer. The comprehensive evaluation system is divided into two layers, wherein the first layer is a criterion layer and is three main evaluation layers of system operation reliability, economy and environmental protection.
(2) And constructing a base layer. Base layer indicators are considered on a criteria layer basis. Energy supply reliability, electric energy quality, source load matching degree and demand side response index are considered in the reliability aspect, the energy supply reliability can reflect stability and reliability of system operation, the electric energy quality can reflect whether the electric energy output by the system meets the customer demand, the source load matching degree can reflect whether the supply and demand relationship between the system energy and the load is scientific and reasonable, and the demand side response reflects whether the system can timely process the demand of the client. The cost and comprehensive benefit indexes such as construction, operation and maintenance are considered on the economic aspect, the construction cost, the operation cost, the environment cost, the pollution discharge cost, the electricity purchasing cost and the like are mainly considered on the cost, and the reliability benefit, the energy-saving benefit, the loss reduction benefit, the electricity selling benefit, the subsidy benefit and the like are mainly considered on the benefit. The indexes of renewable energy utilization rate, greenhouse gas emission and pollution gas emission are considered in the aspect of environmental protection.
Step 2: and calculating the subjective weight of each evaluation index. On the basis of a comprehensive evaluation system of a microgrid, combining the judgment of an evaluation expert, calculating the subjective weight of each evaluation index by adopting a network analytic hierarchy process, measuring the influence of each basic index to construct a judgment matrix, and organically combining qualitative analysis and quantitative analysis to obtain the subjective weight of the basic index.
(1) A super matrix is constructed. According to a comprehensive evaluation system of the microgrid, on the basis of each criterion layer, indirect dominance comparison is carried out on each index in the criterion layer according to the influence of each index on the criterion layer, normalized ranking weights are obtained, and a judgment super matrix W is constructed.
(2) A weighting matrix is constructed. Based on the indirect dominance comparison of the target layer on the influence of each criterion layer on the target layer, a weighting matrix A is obtained, and a weighting super matrix is further constructed
(3) Computing limit hypermatrices and fingersAnd marking a subjective weight matrix. For super matrixCalculating a limit supermatrixWhen in useThe limit at k → ∞ exists, converges and is unique, thenThe jth column of (a) is the limit relative ordering of each index to the index j, and further an index subjective weight matrix is obtained.
And step 3: and calculating the objective weight of each evaluation index. After a comprehensive evaluation system of the microgrid is established, the uncertainty of each index is measured by adopting an entropy weight method, the entropy of each index is calculated, and then objective weight is obtained.
(1) And (5) carrying out dimensionless treatment. The evaluation indexes are m in total, and n is provided as an alternative scheme1Forming an index decision matrix X ═ Xij)n×mBecause the evaluation indexes have different dimensions and types, the decision matrix needs to be subjected to non-dimensionalization treatment, and the decision matrix obtained after the non-dimension treatment is Y (Y is equal to Y)ij)n×m。
In the formula (1), xij,yijA decision value of the ith scheme and a dimensionless processed decision value representing the index j.
(2) The entropy of each index is calculated. And calculating the metric value of each index according to the decision matrix, and normalizing the metric value to obtain the entropy representing the importance of the index.
In the formulae (2) and (3), H (y)j) A metric value representing an index j; e (y)j) Representing the entropy value of the index j.
(3) And determining the objective weight of the evaluation index. According to the definition and property of entropy, e (y)j) Determining an objective evaluation weight value theta of an evaluation index jj:
In the formula (4), θjRepresents the objective evaluation weight value of the index j.
And 4, step 4: and determining the linear combination proportion of the subjective and objective weights. After the subjective and objective weights of all indexes are obtained, the subjective and objective weight linear combination proportion of the power supply guarantee type and economic type micro-grid is determined by taking the optimal accuracy value as a target based on the support vector machine, the comprehensive index value of the sample scheme is calculated by combining the subjective and objective weights of the indexes, the label value of the sample scheme is determined according to the functional characteristics of the sample micro-grid, the support vector machine is trained by utilizing all the sample schemes, the parameters of the support vector machine are optimized by adopting a genetic algorithm, and the optimal linear proportion coefficient of the subjective and objective weights of the indexes taking the optimal accuracy value of the support vector machine as the target can be obtained by iterative optimization. Comprises the following steps.
(1) And the subjective and objective weights are linearly combined. And measuring subjective weight and objective weight comprehensively by adopting linear combination.
ωi=αw′i+(1-α)w″i (5)
In the formula (5), alpha is more than or equal to 0 and less than or equal to 1, w'iDenotes the subjective weight, w ″iRepresenting the objective weight.
(2) And (4) modeling by a support vector machine. According to the combined weight pair n1The indexes of each scheme are used for calculating corresponding index values, and then n is perfected1If the label of the scheme is a power supply guarantee type micro-grid,the label value is label 1, and if the power supply economic micro-grid is adopted, the label value is label 1. N is to be1And training the support vector machine by using the index value and the label value of each scheme.
(3) And solving the genetic algorithm based on the accuracy value. And judging the optimal alpha value according to the accuracy value of the trained support vector machine, wherein the larger the accuracy value is, the more accurate the support vector machine model is represented, and optimizing and solving are carried out on the parameters of the support vector machine by adopting a genetic algorithm.
The invention also provides a comprehensive evaluation index weight quantification system considering the functional characteristics of the microgrid, which comprises the following modules:
a system construction module: constructing a comprehensive evaluation system of the microgrid;
a weight calculation module: calculating subjective weight of each evaluation index by adopting a network analytic hierarchy process, and calculating objective weight of each evaluation index by adopting an entropy weight method;
and an subjective and objective weight linear combination proportion determining module: and respectively determining the weight ratio of the subjective weight and the objective weight of the microgrid based on the support vector machine and by taking the accuracy value optimal as a target.
Further, the architecture building module comprises:
a criterion layer construction module: constructing a criterion layer, wherein the criterion layer comprises 3 main evaluation levels of system operation reliability, economy and environmental protection;
a base layer construction module; the method comprises the following steps of considering basic layer indexes on the basis of a criterion layer, and considering energy supply reliability, electric energy quality, source-load matching degree and demand side response indexes on a reliability layer; the cost and comprehensive benefit indexes such as construction, operation and maintenance and the like are considered in the aspect of economy; the indexes of renewable energy utilization rate, greenhouse gas emission and pollution gas emission are considered in the aspect of environmental protection.
Further, the subjective weight calculation module for calculating each index by the network analytic hierarchy process comprises:
constructing a super matrix module: according to a comprehensive evaluation system of the microgrid, on the basis of each criterion layer, carrying out indirect dominance comparison on each index in the criterion layer according to the influence of each index on the criterion layer to obtain normalized ranking weight, and constructing a judgment super matrix W;
and constructing a weighting matrix module: based on the indirect dominance comparison of the target layer on the influence of each criterion layer on the target layer, a weighting matrix A is obtained, and a weighting super matrix is further constructed
The module for calculating the limit hypermatrix and the index subjective weight matrix comprises: pair-weighted supermatrixCalculating a limit supermatrixWhen in useThe limit at k → ∞ exists, converges and is unique, thenThe jth column of (a) is the limit relative ordering of each index to the index j, and further an index subjective weight matrix is obtained.
Further, the objective weight calculation module for calculating each evaluation index by the entropy weight method comprises:
a dimensionless processing module: carrying out dimensionless processing on the decision matrix;
index entropy value calculation module: calculating the metric value of each index according to the decision matrix, and standardizing the metric value to obtain entropy representing the importance of the index;
an evaluation index objective weight determination module: and determining an objective evaluation weight value of the evaluation index according to the definition and the property of the entropy.
Further, the subjective and objective weight linear combination proportion determination module comprises:
and an subjective and objective weight linear combination module: measuring subjective weight and objective weight by linear combination;
a support vector machine modeling module: carrying out corresponding index value calculation on indexes of the sample schemes according to the combined weight, perfecting labels of the sample schemes, taking the label value as 1 if the label is a power supply guarantee type microgrid, taking the label value as a non-1 value if the label is a power supply economic type microgrid, and training a support vector machine by adopting the index values and the label values of all the sample schemes;
a solving module: and judging the optimal weight ratio value according to the accuracy value of the trained support vector machine, wherein the greater the accuracy value is, the more accurate the support vector machine model is represented, and optimizing and solving are carried out on the parameters of the support vector machine by adopting a genetic algorithm.
The comprehensive evaluation index system for the micro-grid is constructed from three aspects of system operation reliability, economy and environmental protection, the ratio of subjective weight and objective weight of the evaluation system is optimized based on a combined evaluation theory and a support vector machine classification model, index subjective weight is determined by adopting a network analytic hierarchy process, objective weight is determined by an entropy weight method, and then the comprehensive evaluation index system capable of describing power supply guarantee type and power supply economy type micro-grid is obtained through support vector machine training sample data based on genetic optimization. The method can objectively and quantitatively analyze the importance degree of the index, also can give consideration to the actual meaning and the property of the index, and has higher reliability; meanwhile, the method can describe the functional characteristics of various types of micro-grids, provide guidance for system operation performance evaluation of various types of micro-grids, can evaluate a complex micro-grid system with multiple indexes and multiple target functions, and is wide in application range.
In the description of the present application, it is to be understood that the terms "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience in describing the present application and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation, and be operated, and thus, should not be construed as limiting the present application.
The foregoing description of specific embodiments of the present invention has been presented. It is to be understood that the present invention is not limited to the specific embodiments described above, and that various changes or modifications may be made by one skilled in the art within the scope of the appended claims without departing from the spirit of the invention. The embodiments and features of the embodiments of the present application may be combined with each other arbitrarily without conflict.
Claims (10)
1. A comprehensive evaluation index weight quantification method considering functional characteristics of a micro-grid is characterized by comprising the following steps:
the system construction step: constructing a comprehensive evaluation system of the microgrid;
and a weight calculation step: calculating subjective weight of each evaluation index by adopting a network analytic hierarchy process, and calculating objective weight of each evaluation index by adopting an entropy weight method;
determining the linear combination proportion of the subjective and objective weights: and determining the weight ratio of the subjective weight and the objective weight of the microgrid by taking the accuracy value optimal as a target based on a support vector machine.
2. The method for quantifying the comprehensive evaluation index weight considering the functional characteristics of the microgrid according to claim 1, characterized in that the system construction step comprises:
a step of constructing a criterion layer: constructing a criterion layer, wherein the criterion layer comprises 3 main evaluation levels of system operation reliability, economy and environmental protection;
constructing a base layer; the method comprises the following steps of considering basic layer indexes on the basis of a criterion layer, and considering energy supply reliability, electric energy quality, source-load matching degree and demand side response indexes on a reliability layer; the cost and comprehensive benefit indexes such as construction, operation and maintenance and the like are considered in the aspect of economy; the indexes of renewable energy utilization rate, greenhouse gas emission and pollution gas emission are considered in the aspect of environmental protection.
3. The method for quantifying the weights of the comprehensive evaluation indexes considering the functional characteristics of the microgrid according to claim 1, wherein the step of calculating the subjective weights of the indexes by using a network analytic hierarchy process comprises the following steps:
constructing a super matrix: according to a comprehensive evaluation system of the microgrid, on the basis of each criterion layer, carrying out indirect dominance comparison on each index in the criterion layer according to the influence of each index on the criterion layer to obtain normalized ranking weight, and constructing a judgment super matrix W;
constructing a weighting matrix: based on the indirect dominance comparison of the target layer on the influence of each criterion layer on the target layer, a weighting matrix A is obtained, and a weighting super matrix is further constructed
Calculating a limit hypermatrix and an index subjective weight matrix: pair-weighted supermatrixCalculating a limit supermatrixWhen in useThe limit at k → ∞ exists, converges and is unique, thenThe jth column of (a) is the limit relative ordering of each index to the index j, and further an index subjective weight matrix is obtained.
4. The method of claim 1, wherein the entropy weighting method for calculating the objective weight of each evaluation index comprises:
dimensionless processing steps: carrying out dimensionless processing on a decision matrix, wherein the decision matrix consists of evaluation indexes and a scheme for selection;
index entropy calculation step: calculating the metric value of each index according to the decision matrix, and standardizing the metric value to obtain entropy representing the importance of the index;
determining an objective weight of an evaluation index: and determining an objective evaluation weight value of the evaluation index according to the definition and the property of the entropy.
5. The method for quantifying the comprehensive evaluation index weight considering the functional characteristics of the microgrid according to claim 1, wherein the step of determining the linear combination proportion of the subjective and objective weights comprises the steps of:
and (3) performing subjective and objective weight linear combination: measuring subjective weight and objective weight by linear combination;
modeling a support vector machine: carrying out corresponding index value calculation on indexes of the sample schemes according to the combined weight, perfecting labels of the sample schemes, taking the label value as 1 if the label is a power supply guarantee type microgrid, taking the label value as a non-1 value if the label is a power supply economic type microgrid, and training a support vector machine by adopting the index values and the label values of all the sample schemes;
solving: and judging the optimal weight ratio value according to the accuracy value of the trained support vector machine, wherein the greater the accuracy value is, the more accurate the support vector machine model is represented, and optimizing and solving are carried out on the parameters of the support vector machine by adopting a genetic algorithm.
6. A comprehensive evaluation index weight quantification system for calculating functional characteristics of a micro-grid is characterized by comprising the following modules:
a system construction module: constructing a comprehensive evaluation system of the microgrid;
a weight calculation module: calculating subjective weight of each evaluation index by adopting a network analytic hierarchy process, and calculating objective weight of each evaluation index by adopting an entropy weight method;
and an subjective and objective weight linear combination proportion determining module: and determining the weight ratio of the subjective weight and the objective weight of the microgrid by taking the accuracy value optimal as a target based on a support vector machine.
7. The comprehensive evaluation index weight quantification system considering the functional characteristics of the microgrid as claimed in claim 6, wherein the system construction module comprises:
a criterion layer construction module: constructing a criterion layer, wherein the criterion layer comprises 3 main evaluation levels of system operation reliability, economy and environmental protection;
a base layer construction module; the method comprises the following steps of considering basic layer indexes on the basis of a criterion layer, and considering energy supply reliability, electric energy quality, source-load matching degree and demand side response indexes on a reliability layer; the cost and comprehensive benefit indexes such as construction, operation and maintenance and the like are considered in the aspect of economy; the indexes of renewable energy utilization rate, greenhouse gas emission and pollution gas emission are considered in the aspect of environmental protection.
8. The system of claim 6, wherein the subjective weighting module for calculating each index by network analytic hierarchy process comprises:
constructing a super matrix module: according to a comprehensive evaluation system of the microgrid, on the basis of each criterion layer, carrying out indirect dominance comparison on each index in the criterion layer according to the influence of each index on the criterion layer to obtain normalized ranking weight, and constructing a judgment super matrix W;
and constructing a weighting matrix module: based on the indirect dominance comparison of the target layer on the influence of each criterion layer on the target layer, a weighting matrix A is obtained, and a weighting super matrix is further constructed
The module for calculating the limit hypermatrix and the index subjective weight matrix comprises: pair-weighted supermatrixCalculating a limit supermatrixWhen in useThe limit at k → ∞ exists, converges and is unique, thenThe jth column of (a) is the limit relative ordering of each index to the index j, and further an index subjective weight matrix is obtained.
9. The system of claim 6, wherein the entropy weighting module for calculating the objective weighting of each evaluation index comprises:
a dimensionless processing module: carrying out dimensionless processing on a decision matrix, wherein the decision matrix consists of evaluation indexes and a scheme for selection;
index entropy value calculation module: calculating the metric value of each index according to the decision matrix, and standardizing the metric value to obtain entropy representing the importance of the index;
an evaluation index objective weight determination module: and determining an objective evaluation weight value of the evaluation index according to the definition and the property of the entropy.
10. The comprehensive evaluation index weight quantification system considering the functional characteristics of the microgrid as claimed in claim 6, wherein the subjective and objective weight linear combination proportion determination module comprises:
and an subjective and objective weight linear combination module: measuring subjective weight and objective weight by linear combination;
a support vector machine modeling module: carrying out corresponding index value calculation on indexes of the sample schemes according to the combined weight, perfecting labels of the sample schemes, taking the label value as 1 if the label is a power supply guarantee type microgrid, taking the label value as a non-1 value if the label is a power supply economic type microgrid, and training a support vector machine by adopting the index values and the label values of all the sample schemes;
a solving module: and judging the optimal weight ratio value according to the accuracy value of the trained support vector machine, wherein the greater the accuracy value is, the more accurate the support vector machine model is represented, and optimizing and solving are carried out on the parameters of the support vector machine by adopting a genetic algorithm.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011138774.2A CN112215512A (en) | 2020-10-22 | 2020-10-22 | Comprehensive evaluation index weight quantification method and system considering functional characteristics of microgrid |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011138774.2A CN112215512A (en) | 2020-10-22 | 2020-10-22 | Comprehensive evaluation index weight quantification method and system considering functional characteristics of microgrid |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112215512A true CN112215512A (en) | 2021-01-12 |
Family
ID=74056530
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011138774.2A Pending CN112215512A (en) | 2020-10-22 | 2020-10-22 | Comprehensive evaluation index weight quantification method and system considering functional characteristics of microgrid |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112215512A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113269371A (en) * | 2021-06-23 | 2021-08-17 | 华北电力大学(保定) | Method and system for evaluating comprehensive performance of power supply of intelligent power distribution network |
CN113327062A (en) * | 2021-06-25 | 2021-08-31 | 贵州电网有限责任公司电力科学研究院 | Information grade determining method and device, computer equipment and storage medium |
CN113486291A (en) * | 2021-06-18 | 2021-10-08 | 电子科技大学 | Petroleum drilling machine micro-grid fault prediction method based on deep learning |
CN113689118A (en) * | 2021-08-24 | 2021-11-23 | 国家电网有限公司 | Project multi-target combination optimization method and system |
CN113904349A (en) * | 2021-10-22 | 2022-01-07 | 三峡大学 | Island micro-grid low-frequency load shedding method considering load subjective and objective attributes |
CN114204554A (en) * | 2021-12-10 | 2022-03-18 | 国网江苏省电力有限公司 | Method for evaluating regulation and control operation safety for intelligent power grid system |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104573355A (en) * | 2014-12-30 | 2015-04-29 | 北华大学 | Photoacoustic spectroscopy-based transformer fault diagnosis method employing parameter optimization SVM (support vector machine) |
CN107038532A (en) * | 2017-04-17 | 2017-08-11 | 国网江苏省电力公司 | Distribution network load turning solution evaluation method based on optimum combination weight |
CN107358332A (en) * | 2017-05-18 | 2017-11-17 | 国网浙江省电力公司 | A kind of dispatching of power netwoks runs lean evaluation method |
CN109858758A (en) * | 2018-12-29 | 2019-06-07 | 中国电力科学研究院有限公司 | A kind of the combination weighting appraisal procedure and system of distribution network electric energy quality |
CN111080041A (en) * | 2018-10-18 | 2020-04-28 | 中国电力科学研究院有限公司 | Comprehensive evaluation method and system for interactivity of power distribution network |
-
2020
- 2020-10-22 CN CN202011138774.2A patent/CN112215512A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104573355A (en) * | 2014-12-30 | 2015-04-29 | 北华大学 | Photoacoustic spectroscopy-based transformer fault diagnosis method employing parameter optimization SVM (support vector machine) |
CN107038532A (en) * | 2017-04-17 | 2017-08-11 | 国网江苏省电力公司 | Distribution network load turning solution evaluation method based on optimum combination weight |
CN107358332A (en) * | 2017-05-18 | 2017-11-17 | 国网浙江省电力公司 | A kind of dispatching of power netwoks runs lean evaluation method |
CN111080041A (en) * | 2018-10-18 | 2020-04-28 | 中国电力科学研究院有限公司 | Comprehensive evaluation method and system for interactivity of power distribution network |
CN109858758A (en) * | 2018-12-29 | 2019-06-07 | 中国电力科学研究院有限公司 | A kind of the combination weighting appraisal procedure and system of distribution network electric energy quality |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113486291A (en) * | 2021-06-18 | 2021-10-08 | 电子科技大学 | Petroleum drilling machine micro-grid fault prediction method based on deep learning |
CN113486291B (en) * | 2021-06-18 | 2023-04-07 | 电子科技大学 | Petroleum drilling machine micro-grid fault prediction method based on deep learning |
CN113269371A (en) * | 2021-06-23 | 2021-08-17 | 华北电力大学(保定) | Method and system for evaluating comprehensive performance of power supply of intelligent power distribution network |
CN113327062A (en) * | 2021-06-25 | 2021-08-31 | 贵州电网有限责任公司电力科学研究院 | Information grade determining method and device, computer equipment and storage medium |
CN113689118A (en) * | 2021-08-24 | 2021-11-23 | 国家电网有限公司 | Project multi-target combination optimization method and system |
CN113689118B (en) * | 2021-08-24 | 2024-03-26 | 国家电网有限公司 | Project multi-target combination optimization method and system |
CN113904349A (en) * | 2021-10-22 | 2022-01-07 | 三峡大学 | Island micro-grid low-frequency load shedding method considering load subjective and objective attributes |
CN114204554A (en) * | 2021-12-10 | 2022-03-18 | 国网江苏省电力有限公司 | Method for evaluating regulation and control operation safety for intelligent power grid system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112215512A (en) | Comprehensive evaluation index weight quantification method and system considering functional characteristics of microgrid | |
CN109461025B (en) | Electric energy substitution potential customer prediction method based on machine learning | |
CN105023065A (en) | Power grid planning risk evaluation system and method based on grey correlation degree TOPSIS (Technique for Order Preference by Similarity to an Ideal Solution) | |
CN110782153A (en) | Modeling method and system for comprehensive energy efficiency assessment system of enterprise park | |
CN111967721A (en) | Comprehensive energy system greening level evaluation method and system | |
CN112288328A (en) | Energy internet risk assessment method based on gray chromatography | |
CN109726926A (en) | Machine tool equipment resource supply and demand matching process based on Grey Relation Algorithm under a kind of constraint of multivariate quality | |
CN117272850B (en) | Elastic space analysis method for safe operation scheduling of power distribution network | |
CN115905319B (en) | Automatic identification method and system for abnormal electricity fees of massive users | |
CN110276480A (en) | A kind of analyzing and predicting method and system for building energy consumption management | |
CN112907074A (en) | Energy efficiency sensitive index detection method and system for comprehensive energy system user | |
CN115775053A (en) | Distributed photovoltaic power short-term prediction method based on improved similar time method | |
CN114139940A (en) | Generalized demand side resource network load interaction level assessment method based on combined empowerment-cloud model | |
CN115545333A (en) | Method for predicting load curve of multi-load daily-type power distribution network | |
CN113139701B (en) | Regional energy health evaluation method based on analytic hierarchy process | |
CN110956304A (en) | Distributed photovoltaic power generation capacity short-term prediction method based on GA-RBM | |
CN113887833A (en) | Distributed energy user side time-by-time load prediction method and system | |
CN112381422A (en) | Method and device for determining performance of photovoltaic power station | |
CN112116238A (en) | Satisfaction evaluation method based on index weight system design | |
CN112070307A (en) | Method and device for predicting energy source load in region | |
CN109064353B (en) | Large building user behavior analysis method based on improved cluster fusion | |
CN116957356A (en) | Scenic spot carbon neutralization management method and system based on big data | |
CN116823008A (en) | Park energy utilization efficiency evaluation method, system, equipment and storage medium | |
CN116050912A (en) | Energy station health state evaluation method considering distance coupling and prospect theory | |
CN115965119A (en) | Method for power prediction optimization of distributed energy storage system |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210112 |