CN117272850B - Elastic space analysis method for safe operation scheduling of power distribution network - Google Patents
Elastic space analysis method for safe operation scheduling of power distribution network Download PDFInfo
- Publication number
- CN117272850B CN117272850B CN202311568397.XA CN202311568397A CN117272850B CN 117272850 B CN117272850 B CN 117272850B CN 202311568397 A CN202311568397 A CN 202311568397A CN 117272850 B CN117272850 B CN 117272850B
- Authority
- CN
- China
- Prior art keywords
- load
- resources
- adjustable
- elastic
- power
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 23
- 238000009826 distribution Methods 0.000 title claims abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 49
- 230000002776 aggregation Effects 0.000 claims abstract description 21
- 238000004220 aggregation Methods 0.000 claims abstract description 21
- 238000013507 mapping Methods 0.000 claims abstract description 11
- 230000004931 aggregating effect Effects 0.000 claims abstract description 10
- 230000003993 interaction Effects 0.000 claims abstract description 10
- 238000003860 storage Methods 0.000 claims abstract description 6
- 230000005611 electricity Effects 0.000 claims description 36
- 230000004044 response Effects 0.000 claims description 28
- 230000008859 change Effects 0.000 claims description 23
- 238000011156 evaluation Methods 0.000 claims description 18
- 238000013508 migration Methods 0.000 claims description 13
- 230000005012 migration Effects 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000011002 quantification Methods 0.000 claims description 12
- 230000006399 behavior Effects 0.000 claims description 9
- 238000013519 translation Methods 0.000 claims description 9
- 230000008878 coupling Effects 0.000 claims description 8
- 238000010168 coupling process Methods 0.000 claims description 8
- 238000005859 coupling reaction Methods 0.000 claims description 8
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 7
- 230000008569 process Effects 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 4
- 239000002131 composite material Substances 0.000 claims description 3
- 230000035945 sensitivity Effects 0.000 claims description 3
- 238000011160 research Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000006116 polymerization reaction Methods 0.000 description 1
- 230000000379 polymerizing effect Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000013138 pruning Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
- 238000013526 transfer learning Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/096—Transfer learning
-
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- 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
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0206—Price or cost determination based on market factors
-
- 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
- G06F2111/00—Details relating to CAD techniques
- G06F2111/04—Constraint-based CAD
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/04—Power grid distribution networks
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Software Systems (AREA)
- Game Theory and Decision Science (AREA)
- Accounting & Taxation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Finance (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Operations Research (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Primary Health Care (AREA)
- Medical Informatics (AREA)
- Water Supply & Treatment (AREA)
Abstract
The invention relates to a method for analyzing the elastic space of safe operation scheduling of a power distribution network, which comprises the following steps: evaluating the trusted adjustment capacity of the plurality of trusted adjustment resources; integrating and aggregating the trusted adjustment resources, classifying and aggregating the resources, and constructing a mapping relation reflecting membership degree of the trusted adjustment resources and the clustering center and an aggregation index; creating a county power grid dispatching elastic space analysis method considering source network load storage interaction, building a load elastic assessment model, quantifying load elasticity, obtaining elastic spaces of trusted adjustment resources in different scenes, and assessing the elastic spaces; according to the invention, the flexibility of the adjustable resource elastic space of the power distribution network is analyzed, so that the power grid can more accurately predict the load, the accuracy of power grid dispatching is improved, the resource utilization rate of a power system is improved, and the safe operation of the power grid is ensured.
Description
Technical Field
The invention belongs to the technical field of load prediction, and particularly relates to a method for analyzing an elastic space of safe operation scheduling of a power distribution network.
Background
With the acceleration of the construction of a novel power system, the wind power and photovoltaic grid-connected capacity is increased year by year, the continuous promotion of the electric market reform and the wide application of the internet of things technology, and the multi-energy fusion generates the replacement of different energy sources, so that the power supply generates a larger elastic space; the combination of supply and demand converts the load into an active load, and under the driving of an external price, the source and the load cooperate to generate high elasticity; the physical and information fusion wakes up a large amount of resources which fall asleep in each link of the power grid, so that each element can sense global information to self-organize and self-optimizing, and higher aggregation elasticity is generated. In order to further improve the breadth and depth of the power grid resource optimization configuration, more potential running elastic spaces are required to be excavated. At present, researches for optimizing and scheduling by comprehensively considering the running elastic space of the whole link of source-network-load-energy storage source power are fresh, the economic benefit of the power grid is analyzed, and the condition of promoting clean energy consumption is evaluated.
The scholars at home and abroad develop some researches on the power generation, power transmission operation elastic space and load elastic space, and the existing researches utilize the operation elastic space of equipment by excavating, such as: thermal power depth peak regulation elasticity, hydropower limit operation area elasticity, line dynamic capacity expansion elasticity and the like, can effectively improve equipment utilization rate and promote power grid operation benefit. However, at present, analysis and evaluation of elastic resources at home and abroad only consider single elastic load or power supply, or only concentrate on a small-scale load side system and a single power distribution network system, so that the elastic analysis is less under the condition that multiple types of elastic resources participate in scheduling, the flexibility is low, and systematic research is still lacking.
Disclosure of Invention
The invention solves the technical problems by adopting the following technical scheme:
the method for analyzing the elastic space of the safe operation scheduling of the power distribution network comprises the following steps:
evaluating the trusted adjustment capacity of the plurality of trusted adjustment resources;
integrating and aggregating the trusted adjustment resources, classifying and aggregating the resources, and constructing a mapping relation reflecting membership degree of the trusted adjustment resources and the clustering center and an aggregation index;
a county power grid dispatching elastic space analysis method considering source network load storage interaction is established, a load elastic assessment model is established, load elasticity is quantified, elastic spaces of trusted adjustment resources in different scenes are obtained, and the elastic spaces are assessed.
Further, the method for evaluating the trusted adjustment capacity of the plurality of trusted adjustment resources comprises the following steps:
constructing a power grid trusted adjustment resource pool;
constructing a data migration learning framework for user demand response potential evaluation, and performing potential evaluation on the adjustable load according to migration learning;
constructing a typical user load characteristic model;
and carrying out coupling weight on the load model based on a subjective and objective combined analytic hierarchy process-entropy weight process, and obtaining the priority score of the adjustable resource.
Further, the method for coupling weight to the load model and obtaining the priority score of the adjustable resource based on the subjective and objective combination hierarchical analysis method-entropy weight method comprises the following steps:
solving the two-stage main and auxiliary problems to obtain an adjustable capacity range boundary;
and obtaining the credible adjustment capacity of the adjustable resource under the evaluation index based on subjective and objective combination.
Further, the constructed typical user load characteristic model is as follows:
;
;
wherein,indicating that the typical load is at temperaturekAnd time oftLoad quantity at time->Normal value representing load,/->Indicating the amount of change in load->To influence the variation of the factors->A functional relation representing the variation of the relevant factor, +.>Representing the mean of the various varying factors.
Further, the method for integrally aggregating the trusted adjustment resources, classifying and aggregating the resources and constructing the mapping relation between the membership degree of the trusted adjustment resources and the clustering center and the aggregation index comprises the following steps:
multidimensional analysis is carried out on the electricity utilization behavior influence factors of the users of the electric power big data, and the resources are clustered twice;
establishing an adjustable resource clustering model, determining an initial clustering center, calculating Euclidean distance between each adjustable resource and each clustering center, distributing the adjustable resources according to categories, calculating the average value of Euclidean distance between each adjustable resource and the clustering center, checking and updating the clustering center, and outputting a preferred feature set as a primary clustering result of the adjustable resources;
and taking the constraint in the service scene as an output layer, outputting a secondary clustering result with a more accurate range through screening of a competition layer, clustering potential characteristics of the adjustable resources, accounting the membership degree of each adjustable resource to a clustering center, and obtaining the mapping relation between the membership degree of the adjustable resource and the clustering center and the aggregation index through a BP neural network.
Further, a county power grid dispatching elastic space analysis method for taking source network load storage interaction into account is created, and a load elastic assessment model is established by the following steps:
modeling load elasticity, defining a quantized index load rate of load time elasticity as a ratio of average load to maximum load, calculating daily load curve similarity, carrying out per unit on load values in corresponding time periods to obtain per unit value of load, and carrying out mean square error calculation on load quantity in the time periods to obtain load mean square error: will->The mean square error calculation is carried out to obtainThe overall load time elastic coefficient of the power consumer load curve;
judging the utilization rate of the power equipment according to the load rate, if the load rate is low, indicating that the load value adjustability of the user in each period is large, otherwise, the load value is small;
according to the similarity of the user load curves, judging the time elasticity of the user, namely comparing the mean square errorAnd reference valueIf->Such user load is resilient, whereas it is not.
Further, the quantification of the load elasticity includes quantification of the load price elasticity and quantification of the load translation capability.
Further, the quantification of the load price elasticity includes:
the power self-demand elasticity refers to the relative change of electricity price to cause the relative change of electric quantity, and the expression is as follows:
;
wherein:is the self-demanded coefficient of elasticity;Q t for a period of timetIs used for the electricity consumption of the (a);R t for a period of timetElectricity price of (2); />To execute time-of-use electricity price time periodtA power consumption change value of (a); />To execute time-of-use electricity price time periodtA value of electricity price change of (2);
the cross-over spring rate can be expressed asjTime period electricity price change pairtThe degree of influence of the change in the period of electricity consumption:
;
the power demand elasticity of various typical users is represented by constructing a demand elasticity coefficient matrix.
Further, the load translation capacity is quantified as follows: the power demand side resource load shifting capability is measured by the ratio of the power consumption increased in the power consumption valley period to the power consumption reduced in the power consumption peak period of the user:
;
wherein:representing power demand side resource load translation capability; />Representing the reduced power consumption of the user in the power consumption peak period; />Indicating an increased amount of electricity used by the user during the electricity usage valley period.
Further, the method for determining the influence degree of each elastic coefficient on the adjustable resource by the entropy weight method comprises the following steps:
will firstDaily load data of the class of loads are standardized, and a maximum load value in each class of loads is taken as a reference to obtain a load per unit value in one day of each class of loads;
calculated according to the load per unit value curveThe elastic coefficient of the class load is marked;
determining the information entropy of each index, wherein the information entropy of each group of data is as follows:
;
wherein,if->Define +.>,Y ij Is the value normalized by the elastic coefficient index;irepresent the firstiThe number of the indexes is equal to the number of the indexes,jrepresent the firstjClass loading;
calculating the weight of each index through the obtained information entropy of each index:
;
Calculating a composite score for adjustable resource response capability:
;
The sensitivity degree and response potential of various adjustable resources to different indexes can be obtained by analyzing the weight and the comprehensive score of the elastic coefficient of each type of adjustable resources.
The invention has the advantages and positive effects that:
(1) The invention establishes a credible adjustment capacity evaluation method of the power system taking various adjustment resources into account, utilizes the coupling weight of an analytic hierarchy process-entropy weight method combining transfer learning and subjective and objective, and obtains the boundary of the adjustable capacity range according to the solution of the two-stage main and auxiliary problems;
(2) The invention establishes a trusted adjustment resource integrated aggregation method, considers the influence factors of the participation of the adjustable resources in the transaction, researches an interaction aggregation model of the participation of the adjustable resources in the power system, builds a typical resource aggregation calculation method, clusters the resources twice and processes the resources through a neural network; obtaining a mapping relation reflecting membership and aggregation indexes, and obtaining a more accurate and flexible aggregation method;
(3) And establishing a county power grid dispatching elastic space analysis method considering source network load interaction, establishing a load elastic evaluation model, and quantifying load elasticity to obtain elastic spaces of adjustable resources under different scene conditions.
(4) The invention analyzes the flexibility of the adjustable resource elastic space of the power distribution network, so that the power grid can more accurately predict the load, thereby being beneficial to improving the accuracy of power grid dispatching, improving the resource utilization rate of the power system and ensuring the safe operation of the power grid.
Drawings
The technical solution of the present invention will be described in further detail below with reference to the accompanying drawings and examples, but it should be understood that these drawings are designed for the purpose of illustration only and thus are not limiting the scope of the present invention. Moreover, unless specifically indicated otherwise, the drawings are intended to conceptually illustrate the structural configurations described herein and are not necessarily drawn to scale.
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a diagram of an adjustable resource classification in a load-based manner of operation;
FIG. 3 is a diagram of a data migration learning framework for user demand response potential assessment;
FIG. 4 is a chart of an AHP-entropy weight calculation method combining subjective and objective;
FIG. 5 is a classification chart of user electricity behavior influencing factors;
FIG. 6 is a flow chart of secondary clustering;
FIG. 7 is a preferred flow chart for influencing load characteristics;
fig. 8 is a load elasticity recognition flowchart.
Detailed Description
First, it should be noted that the following detailed description of the specific structure, characteristics, advantages, and the like of the present invention will be given by way of example, however, all descriptions are merely illustrative, and should not be construed as limiting the present invention in any way. Furthermore, any single feature described or implied in the embodiments mentioned herein, or any single feature shown or implied in the figures, may nevertheless be continued in any combination or pruning between these features (or equivalents thereof) to obtain still further embodiments of the invention that may not be directly mentioned herein. In addition, for the sake of simplicity of the drawing, identical or similar features may be indicated at one point in the same drawing.
It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other.
The invention provides a method for analyzing the elastic space of safe operation scheduling of a power distribution network, which fully considers the operation characteristics and influence factors of various adjustable resources, establishes a method for evaluating the credible capacity of the adjustable resources, and flexibly classifies the aggregation of the resources according to different requirements and an elastic space analyzing method of the credible resources.
Example 1
The method for analyzing the elastic space of the safe operation scheduling of the power distribution network comprises the following steps:
establishing a credible adjustment capacity assessment method of an electric power system, considering various adjustment resources, constructing an adjustable resource library, obtaining a load characteristic model through data migration learning of user demand response potential assessment, and carrying out subjective and objective combination of a hierarchical analysis method-entropy weight method coupling on the load characteristic model to influence the weight of load behavior factors, wherein the adjustable resource can be subjected to two-stage main and auxiliary problem solving according to actual conditions to obtain the capacity of the adjustable resource;
constructing an interactive aggregation model of the adjustable resources participating in the power system, taking into consideration influence factors of the participation regulation and control of the adjustable resources, clustering the adjustable resources twice by adopting a typical resource aggregation calculation method, and constructing a mapping relation reflecting membership of the adjustable resources and a clustering center and an aggregation index by BP neural network processing;
a county power grid dispatching elastic space analysis method considering source network load storage interaction is established, a load elastic assessment model is established, load elasticity is quantified, elastic spaces of adjustable resources in different scenes are obtained, and the elastic spaces are assessed. The weights affecting the load elasticity index are coupled out.
In a first aspect, a trusted tuning capacity assessment method for establishing a plurality of tuning resources, the method comprising:
classifying the adjustable resources from time, space dimension and operation modes, and constructing a power grid credible adjusting resource pool so as to meet the aggregation methods, response types and reliable response requirements of different modes;
constructing a data migration learning framework for evaluating the demand response potential of a user, evaluating the potential of an adjustable load according to a migration learning model, issuing demand information to a demand response service system by a power grid, issuing information such as dynamic electricity price, load demand and the like to an aggregator by the demand response service system, and determining the capacity participating in response by the aggregator according to the response potential of the aggregated user; a data migration learning framework for user demand response potential assessment, as shown in fig. 3;
under the influence of multiple typical factors such as time, season, weather and the like, constructing a load characteristic model of a user, obtaining probability distribution of the user participation response adjustment load through potential analysis of the interaction of the adjustable resources, and constructing the typical user load characteristic model:
;
;
wherein,load quantity at temperature k and time t representing typical load, +.>Normal value representing load,/->Indicating the amount of change in load->To influence the variation of the factors->A functional relation representing the variation of the relevant factor, +.>Representing the mean of the various varying factors.
The migration learning formula is expressed as:wherein->Representing a source response characteristics model->New model representing learning by migration +.>Sample representing user of source domain, +.>Tag type representing user of source domain, +.>Sample representing user of target domain, +.>A label representing a user of the target domain.
Further, subjective and objective combination of the hierarchical analysis method-entropy weight method coupling weight is carried out on the load model, the hierarchical structure of the adjustable resources is analyzed based on the adjustable resource evaluation indexes, the evaluation indexes of the adjustable resources are matrixed, the matrix is further judged through professional examination, the original data matrix is normalized, the subjective weight vector is determined through consistency check on the data, the objective weight vector is determined through calculation of matrix information entropy, and the subjective and objective weights are combined to obtain the weights of the indexes. And multiplying the standardized value of each index by the coupled weight to obtain the priority score of the adjustable schedule. The specific flow is shown in fig. 4;
further, the adjustable capacity range boundary can be obtained according to the two-stage main and auxiliary problem solution, and the formula is as follows:
is the main problem to be prioritized according to the actual situation in the resource scheduling process, and is +.>Decision variables for side problems, +.>The relevant parameters for the main question are the ones that need to be determined preferentially, < >>The parameters related to the decision variables for the secondary problems are uncertain, have certain range limitation, and the value range is determined by an uncertainty set U; in the objective function->Is an objective function of a main problem; />Is a constraint of a constraint.
And obtaining the credible adjustment capacity of the adjustable resource under the evaluation index based on subjective and objective combination.
In a second aspect, a trusted adjustment resource integrated aggregation method is adopted to aggregate resources in a classified manner, and the method comprises the following steps:
multidimensional analysis is carried out on user electricity behavior influence factors of large electric power data, wherein the user electricity behavior influence factors are mainly influenced as shown in fig. 5, and the resources are clustered twice by fully considering the influence of user load characteristics and adjustment potential on the user electricity behavior, and a clustering flow is shown in fig. 6;
the first clustering flow is as follows: establishing an adjustable resource clustering model to determine an initial clustering center, calculating Euclidean distance between each adjustable resource and each clustering center, distributing the adjustable resources according to categories, calculating the average value of Euclidean distance between each adjustable resource and the clustering center, checking and updating the clustering center, and outputting a preferred feature set as a primary clustering result of the adjustable resources;
further, considering constraints under a service scene, such as social environment factors, natural environment factors and self-influencing factors, as an output layer, screening by a competition layer, outputting a secondary clustering result with a more accurate range, clustering potential characteristics of the adjustable resources, calculating the membership degree of each adjustable resource to a clustering center, and obtaining a mapping relation between the membership degree of the adjustable resource and the clustering center and an aggregation index through a BP neural network. The load influencing characteristic index is optimized according to the actual situation, and the specific flow is shown in figure 7;
and through the two clustering model and the neural network construction process, finally, the mapping between the adjustable resources and the clusters is established, and more accurate clustering is carried out on the adjustable resources.
And thirdly, constructing a scheduling elastic space analysis method to obtain the elastic coefficient of the adjustable resource. The steps include:
the load elasticity is modeled, and the similarity of the daily load curves of the users is represented by sigma. Quantification of load time elasticity, load factorDefined as average load +.>And maximum load->Is used for solving the similarity of the daily load curve +.>Carrying out per unit of the load value in the corresponding period to obtain the per unit value of the load +.>Then, the mean square error calculation is carried out on the load quantity of the time period to obtain the load mean square error +.>:
;
;
Will bePerforming mean square error calculation to obtain ∈>The overall load time elastic coefficient of the load curve of the power consumer:
;
;
further, the utilization rate of the power equipment is judged according to the load rate, if the load rate is low, the load value adjustability of the user in each period is large, and otherwise, the load value adjustability is small. For this reason, it is necessary to set a load factor reference value based on the regional load characteristicsWhen the load factor->When the user power consumption time is adjustable, the user power consumption time is adjustable; then, according to the similarity of the user load curves, judging the user timeThe magnitude of the intersymbol forces, i.e. the comparison of the mean square error +.>And reference value->If->The user load is rich in daily elasticity, otherwise, the user load is not; the flow of judging the typical user load time elasticity is shown in fig. 8;
quantifying the price elasticity of the load: the power self-demand elasticity refers to the relative change of electricity price to cause the relative change of electric quantity, and the expression is as follows:
;
wherein:is the self-demanded coefficient of elasticity; qt is the electricity consumption of the period t; rt is the electricity price of period t; />A power consumption change value for executing a time-of-use power price period t; />A power rate change value for a time period t before and after performing time-sharing power rate;
further, the user load variation is affected not only by the current period power rate variation but also by the adjacent period power rate, and the cross elasticity coefficient can be expressed asjTime period electricity price change pairtThe influence degree of the change of the time period electricity consumption is expressed as the following formula:
;
the power demand elasticity of various typical users is represented by constructing a demand elasticity coefficient matrix; quantification of load shifting capability, namely, the load shifting capability of the power demand side resource is measured by the ratio of the power consumption increased in the power consumption valley period to the power consumption reduced in the power consumption peak period of a user:
;
wherein:representing power demand side resource load translation capability; />Representing the reduced power consumption of the user in the power consumption peak period; />Indicating the increased electricity consumption of the user in the electricity consumption valley period;
determining objective weights according to the size of index variability based on demand response evaluation of an entropy weight method; the smaller the information entropy of the index, the greater the degree of variation of the index, the more information is provided, and the greater the function of the comprehensive evaluation, the greater the weight of the comprehensive evaluation.
The method for determining the influence degree of each elastic coefficient on the adjustable resource by the entropy weight method comprises the following steps:
the weighting steps of the entropy weighting method are as follows:
will firstDaily load data of the class of loads are standardized, and a maximum load value in each class of loads is taken as a reference to obtain a load per unit value in one day of each class of loads;
calculated according to the load per unit value curveFour elastic coefficients of class load +.>The method comprises the steps of carrying out a first treatment on the surface of the Wherein the method comprises the steps ofThe four elastic coefficients are respectively a load rate, a time elastic coefficient, a price elastic coefficient and a price cross elastic coefficient; the normalized value of the four index data is +.>The formula is:
;
represent the firstjClass load ofiA term modulus of elasticity;
determining the information entropy of each index, wherein the information entropy of each group of data is as follows:
;
wherein,if->Define +.>;
Further determining the weight of each index: according to the information entropy of each indexCalculating the weight of each index through information entropy>The formula is:
;
calculating a composite score for adjustable resource response capability:
;
The sensitivity degree and response potential of various adjustable resources to different indexes can be obtained by analyzing the weight and the comprehensive score of the elastic coefficient of each type of adjustable resources.
According to the invention, by establishing the credible adjustment capacity assessment method of the power system, the capacity of the load is assessed, the load is accurately clustered for the second time, the county power grid dispatching elastic space analysis method which takes account of interaction of source network and load storage is created, the load elasticity is assessed, flexible and accurate prediction of the power grid on adjustable resources is facilitated, accurate data support is provided for power grid dispatching resources, and the utilization rate of the resources is improved.
Example 2
101: a trusted tuning capacity assessment for a plurality of tuning resources;
1011: classifying the adjustable resources from time, space dimension and operation modes, constructing a power grid credible adjustment resource pool to meet the aggregation methods, response types and reliable requirements of different modes, wherein the classification of the adjustable resources according to the load adjustment time dimension is shown in a table 1, and the classification of the adjustable resources according to the load operation mode is shown in a table 2;
TABLE 1 Adjustable resource classification by load adjustment time dimension
TABLE 2 Adjustable resource classification by load operation
1012: constructing a data migration learning framework for evaluating the demand response potential of a user, performing potential evaluation according to migration learning, issuing demand information to a demand response service system by a power grid, issuing information such as dynamic electricity price, load demand and the like to an aggregator by the demand response service system, and determining the capacity participating in response by the aggregator according to the response potential of the aggregated user;
1013: under the influence of multiple typical factors such as time, season, weather and the like, constructing a load characteristic model of a user, and obtaining probability distribution of the user participating in response adjustment load through interaction potential analysis;
typical user load signature model:
;
;
1014: based on flexible resource evaluation indexes and a system, establishing a refined evaluation identification model, and coupling weights through an AHP-entropy weight method combined by subjective and objective to obtain priority evaluation of adjustable resources;
1015: solving the main and auxiliary problems according to two stages to obtain an adjustable capacity range boundary;
1016: and analyzing the resource group and each decomposed influence factor to obtain the credible adjustment capacity of the resource under different scenes.
201: integrating and polymerizing the trusted adjustment resources;
2011: and according to multidimensional analysis of the influence factors of the user electricity consumption behavior of the electric power big data, the influence of the user load characteristics and the adjustment potential on the user electricity consumption behavior is fully considered. Clustering the resources twice;
2012: establishing an initial clustering model and determining an initial clustering center;
2013: and calculating Euclidean distance between each load element and the clustering center, and distributing the data according to the categories. European distance formula:
;
2014: calculating the average value of the data objects, and updating the clustering center;
2015: calculating the square sum of the distances between the sample and the cluster centers, and representing the discrete degree of the whole sample and the center distances;
2016: outputting a preferred feature set as a result of primary clustering;
202: taking the constraint in the service scene as an output layer, and outputting a secondary clustering result with a more accurate range through screening of a competition layer;
2021: verifying the clustering result, and solving the membership value of each element;
2022: clustering the typical load by the coefficients, and taking a clustering center as a characteristic center;
2023: adding the load to be identified into a front cluster, and solving the membership degree to the feature center;
203: constructing a reaction membership-polymerization index map;
204: and finally obtaining a more accurate clustering result through the processing of the two clustering models and the BP neural network.
301: analyzing load elasticity by a scheduling elasticity space analysis method;
3011: obtaining the similarity of daily load curves, quantifying the load time elasticity and the load rateDefined as average load +.>And maximum load->Ratio of (3):
;
3012: taking a daily load curve of the power consumer for 2 weeks before pricing, taking a daily average load as a base value of the daily load, and carrying out per unit treatment on the load of each period (24 h) to obtain the load of the d-th day t period:
;
3013: the load value of the corresponding period of 2 weeks per day is subjected to per unit to obtain per unit valueThen, the mean square error calculation is carried out to obtain the load mean square error of 24 days>:/>Mean square error of the load for 24 time periods and the same time period in two weeks is represented;
;
;
3014: will bePerforming mean square error calculation to obtain ∈>The overall load time elastic coefficient of the load curve of the power consumer: />Representing the mean square error between 24 time periods within the same day of the load:
;
;
302: quantifying the load price elasticity;
3021: the power self-demand elasticity refers to the relative change of electricity price to cause the relative change of electric quantity, and the expression is as follows:
;
3022: calculating the crossed elastic coefficient:
;
TABLE 3 meanings of elastic coefficients
3023: the power demand elasticity of a typical user is represented by a demand elasticity coefficient matrix:
303: quantification of load translation capability;
3031: computing load translation capability:
;
3032: determining objective weights according to the size of index variability:
;
3033: solving the information entropy of each index:
;
;
3034: determining the weight of each index:
3035: obtaining the elastic coefficients of different indexes of the adjustable resource;
304: finally, the elastic space of the adjustable resource under different conditions is obtained.
The embodiment of the invention does not limit the types of other devices except the types of the devices, so long as the devices can complete the functions.
The foregoing examples illustrate the invention in detail, but are merely preferred embodiments of the invention and are not to be construed as limiting the scope of the invention. All equivalent changes and modifications within the scope of the present invention are intended to be covered by the present invention.
Claims (5)
1. The method for analyzing the elastic space of the safe operation scheduling of the power distribution network is characterized by comprising the following steps:
evaluating the trusted adjustment capacity of the plurality of trusted adjustment resources;
integrating and aggregating the trusted adjustment resources, classifying and aggregating the resources, and constructing a mapping relation reflecting membership degree of the trusted adjustment resources and the clustering center and an aggregation index;
establishing a county power grid dispatching elastic space analysis method, establishing a load elastic assessment model, quantifying load elasticity, obtaining elastic spaces of credible adjustment resources in different scenes, and assessing the elastic spaces;
the method for evaluating the trusted adjustment capacity of the various trusted adjustment resources comprises the following steps:
constructing a power grid trusted adjustment resource pool;
constructing a data migration learning framework for user demand response potential evaluation, and performing potential evaluation on the adjustable load according to migration learning;
constructing a typical user load characteristic model;
coupling weight is carried out on the load model based on a subjective and objective combined analytic hierarchy process-entropy weight process, and priority scores of adjustable resources are obtained;
the method for coupling weight to the load model and obtaining the priority score of the adjustable resource based on the subjective and objective combination analytic hierarchy process-entropy weight process comprises the following steps:
solving the two-stage main and auxiliary problems to obtain an adjustable capacity range boundary;
obtaining the credible adjustment capacity of the adjustable resource under the evaluation index based on subjective and objective combination;
the constructed typical user load characteristic model is as follows:
;
;
wherein,indicating that the typical load is at temperaturekAnd time oftLoad quantity at time->The normal value of the load is indicated,indicating the amount of change in load->To influence the variation of the factors->A functional relation representing the variation of the relevant factor, +.>Representing the mean value of various changing factors;
the method for integrating and aggregating the trusted adjustment resources, classifying and aggregating the resources and constructing the mapping relation between the membership of the trusted adjustment resources and the clustering center and the aggregation index comprises the following steps:
multidimensional analysis is carried out on the electricity utilization behavior influence factors of the users of the electric power big data, and the resources are clustered twice;
establishing an adjustable resource clustering model, determining an initial clustering center, calculating Euclidean distance between each adjustable resource and each clustering center, distributing the adjustable resources according to categories, calculating the average value of Euclidean distance between each adjustable resource and the clustering center, checking and updating the clustering center, and outputting a feature set as a primary clustering result of the adjustable resources;
taking constraints in a service scene as an output layer, screening by a competition layer, outputting a secondary clustering result, clustering potential characteristics of adjustable resources, accounting membership of each adjustable resource to a clustering center, and obtaining a mapping relation reflecting the membership of the adjustable resource and the clustering center and an aggregation index through a BP neural network;
the county power grid dispatching elastic space analysis method for establishing the source network load storage interaction comprises the following steps of:
modeling load elasticity, defining a quantized index load rate of load time elasticity as a ratio of average load to maximum load, calculating daily load curve similarity, carrying out per unit on load values in corresponding time periods to obtain per unit value of load, and carrying out mean square error calculation on load quantity in the time periods to obtain load mean square error: will->Performing mean square error calculation to obtain ∈>The overall load time elastic coefficient of the power consumer load curve;
judging the utilization rate of the power equipment according to the load rate, if the load rate is low, indicating that the load value adjustability of the user in each period is large, otherwise, the load value is small;
according to the similarity of the user load curves, judging the time elasticity of the user, namely comparing the mean square errorAnd reference value->If->Such user load is resilient, whereas it is not.
2. The method for analyzing the flexible space of the safe operation scheduling of the power distribution network according to claim 1, wherein the quantification of the load elasticity comprises quantification of the load price elasticity and quantification of the load translation capacity.
3. The method for analyzing the flexible space of the safe operation scheduling of the power distribution network according to claim 2, wherein the quantification of the load price flexibility comprises the following steps:
the power self-demand elasticity refers to the relative change of electricity price to cause the relative change of electric quantity, and the expression is as follows:
;
wherein:is the self-demanded coefficient of elasticity;Q t for a period of timetIs used for the electricity consumption of the (a);R t for a period of timetElectricity price of (2); />To execute time-of-use electricity price time periodtA power consumption change value of (a); />To execute time-of-use electricity price time periodtA value of electricity price change of (2);
the cross-over spring rate can be expressed asjTime period electricity price change pairtThe degree of influence of the change in the period of electricity consumption:
;
the power demand elasticity of various typical users is represented by constructing a demand elasticity coefficient matrix.
4. A method for analyzing the elastic space of the safe operation schedule of a power distribution network according to claim 3, wherein the quantification of the load translation capability is as follows: the power demand side resource load shifting capability is measured by the ratio of the power consumption increased in the power consumption valley period to the power consumption reduced in the power consumption peak period of the user:
;
wherein:representing power demand side resource load translation capability; />Representing the reduced power consumption of the user in the power consumption peak period; />Indicating an increased amount of electricity used by the user during the electricity usage valley period.
5. The method for analyzing the elastic space of the safe operation schedule of the power distribution network according to claim 4, wherein the method for determining the influence degree of each elastic coefficient on the adjustable resource by the entropy weight method is as follows:
will firstDaily load data of the class of loads are standardized, and a maximum load value in each class of loads is taken as a reference to obtain a load per unit value in one day of each class of loads;
calculated according to the load per unit value curveThe elastic coefficient of the class load is marked;
determining the information entropy of each index, wherein the information entropy of each group of data is as follows:
;
wherein,if->Define +.>,/>Is the value normalized by the elastic coefficient index;irepresent the firstiThe number of the indexes is equal to the number of the indexes,jrepresent the firstjClass loading;
calculating the weight of each index through the obtained information entropy of each index:
;
Calculating a composite score for adjustable resource response capability:
;
The sensitivity degree and response potential of various adjustable resources to different indexes can be obtained by analyzing the weight and the comprehensive score of the elastic coefficient of each type of adjustable resources.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311568397.XA CN117272850B (en) | 2023-11-23 | 2023-11-23 | Elastic space analysis method for safe operation scheduling of power distribution network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311568397.XA CN117272850B (en) | 2023-11-23 | 2023-11-23 | Elastic space analysis method for safe operation scheduling of power distribution network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117272850A CN117272850A (en) | 2023-12-22 |
CN117272850B true CN117272850B (en) | 2024-01-30 |
Family
ID=89210973
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202311568397.XA Active CN117272850B (en) | 2023-11-23 | 2023-11-23 | Elastic space analysis method for safe operation scheduling of power distribution network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117272850B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117664244B (en) * | 2024-01-31 | 2024-05-17 | 合肥锦上汇赢数字科技有限公司 | Multi-sensor fused structure on-line monitoring data processing system |
CN117978679B (en) * | 2024-04-01 | 2024-06-04 | 北京大学 | Heterogeneous Internet of things entropy weight determining method and device and electronic equipment |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111027741A (en) * | 2019-10-28 | 2020-04-17 | 国网天津市电力公司电力科学研究院 | Method for constructing space-time dimension-oriented generalized load model analysis library |
CN113793010A (en) * | 2021-09-07 | 2021-12-14 | 国网浙江省电力有限公司营销服务中心 | Construction method for multi-load combined control strategy and air conditioner control method |
CN114048976A (en) * | 2021-10-28 | 2022-02-15 | 上海电力大学 | Variable frequency air conditioner load regulation and control method considering multiple response potential influence factors |
CN114707858A (en) * | 2022-03-31 | 2022-07-05 | 国网浙江省电力有限公司电力科学研究院 | Elastic optimization oriented aggregator and user interactive game method |
CN115411777A (en) * | 2022-10-08 | 2022-11-29 | 国网四川省电力公司经济技术研究院 | Power distribution network flexibility evaluation and resource allocation method and system |
-
2023
- 2023-11-23 CN CN202311568397.XA patent/CN117272850B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111027741A (en) * | 2019-10-28 | 2020-04-17 | 国网天津市电力公司电力科学研究院 | Method for constructing space-time dimension-oriented generalized load model analysis library |
CN113793010A (en) * | 2021-09-07 | 2021-12-14 | 国网浙江省电力有限公司营销服务中心 | Construction method for multi-load combined control strategy and air conditioner control method |
CN114048976A (en) * | 2021-10-28 | 2022-02-15 | 上海电力大学 | Variable frequency air conditioner load regulation and control method considering multiple response potential influence factors |
CN114707858A (en) * | 2022-03-31 | 2022-07-05 | 国网浙江省电力有限公司电力科学研究院 | Elastic optimization oriented aggregator and user interactive game method |
CN115411777A (en) * | 2022-10-08 | 2022-11-29 | 国网四川省电力公司经济技术研究院 | Power distribution network flexibility evaluation and resource allocation method and system |
Non-Patent Citations (4)
Title |
---|
基于负荷弹性系数法的典型行业理论响应潜力评估分析;王洪莹等;《 河北电力技术》;第第41卷卷(第第5期期);全文 * |
考虑分布式电源出力间歇性的微电网可靠性评估;崔凯等;《电力系统及其自动化学报》;第第30 卷卷(第第9 期期);全文 * |
计及灵活性资源的配电网韧性研究评述;张海春等;《电力建设》;全文 * |
面向虚拟电厂的需求响应潜力评估方法研究;张波等;《浙江电力》;第第 42 卷卷(第第 6 期期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN117272850A (en) | 2023-12-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN117272850B (en) | Elastic space analysis method for safe operation scheduling of power distribution network | |
Fu et al. | Clustering-based short-term load forecasting for residential electricity under the increasing-block pricing tariffs in China | |
CN111754037B (en) | Long-term load hybrid prediction method for regional terminal integrated energy supply system | |
CN112149890A (en) | Comprehensive energy load prediction method and system based on user energy label | |
CN114792156B (en) | Photovoltaic output power prediction method and system based on curve characteristic index clustering | |
Sengar et al. | Ensemble approach for short term load forecasting in wind energy system using hybrid algorithm | |
CN103473621A (en) | Wind power station short-term power prediction method | |
CN115099511A (en) | Photovoltaic power probability estimation method and system based on optimized copula | |
Mayer et al. | Probabilistic modeling of future electricity systems with high renewable energy penetration using machine learning | |
CN114611842B (en) | Whole-county roof distributed photovoltaic power prediction method | |
CN116826710A (en) | Peak clipping strategy recommendation method and device based on load prediction and storage medium | |
CN112633762A (en) | Building energy efficiency obtaining method and equipment | |
CN108898273A (en) | A kind of user side load characteristic clustering evaluation method based on morphological analysis | |
CN111798333A (en) | Energy utilization evaluation and electricity utilization safety analysis method and system | |
Xue et al. | A framework for short-term energy consumption prediction based on room air conditioner group characteristics | |
Zhang et al. | A segmented evaluation model for building energy performance considering seasonal dynamic fluctuations | |
CN113887809A (en) | Power distribution network supply and demand balance method, system, medium and computing equipment under double-carbon target | |
Su et al. | Optimal placement and capacity sizing of energy storage systems via NSGA-II in active distribution network | |
Das et al. | A study on the application of artificial intelligence techniques for predicting the heating and cooling loads of buildings | |
Fujiwara et al. | Load forecasting method for Commercial facilities by determination of working time and considering weather information | |
CN116470491A (en) | Photovoltaic power probability prediction method and system based on copula function | |
CN113837486B (en) | RNN-RBM-based distribution network feeder long-term load prediction method | |
Yang et al. | Ultra-short-term load prediction of integrated energy system based on load similar fluctuation set classification | |
CN110717779A (en) | Electric power transaction system, method and application thereof | |
CN113780686A (en) | Distributed power supply-oriented virtual power plant operation scheme optimization method |
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 |