CN113780686A - Distributed power supply-oriented virtual power plant operation scheme optimization method - Google Patents

Distributed power supply-oriented virtual power plant operation scheme optimization method Download PDF

Info

Publication number
CN113780686A
CN113780686A CN202111225531.7A CN202111225531A CN113780686A CN 113780686 A CN113780686 A CN 113780686A CN 202111225531 A CN202111225531 A CN 202111225531A CN 113780686 A CN113780686 A CN 113780686A
Authority
CN
China
Prior art keywords
index
power plant
virtual power
comprehensive
operation scheme
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202111225531.7A
Other languages
Chinese (zh)
Inventor
费斐
顾闻
陈凯玲
史松峰
韩东
徐雪莲
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid Shanghai Electric Power Co Ltd
Original Assignee
State Grid Shanghai Electric Power Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by State Grid Shanghai Electric Power Co Ltd filed Critical State Grid Shanghai Electric Power Co Ltd
Priority to CN202111225531.7A priority Critical patent/CN113780686A/en
Publication of CN113780686A publication Critical patent/CN113780686A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • 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
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
    • Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • General Engineering & Computer Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Development Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Tourism & Hospitality (AREA)
  • Mathematical Physics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Health & Medical Sciences (AREA)
  • Pure & Applied Mathematics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Educational Administration (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Game Theory and Decision Science (AREA)
  • Evolutionary Computation (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Water Supply & Treatment (AREA)
  • Computing Systems (AREA)
  • Primary Health Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Algebra (AREA)
  • Databases & Information Systems (AREA)
  • Software Systems (AREA)
  • Public Health (AREA)

Abstract

The invention relates to a distributed power supply-oriented virtual power plant operation scheme optimization method, which comprises the following steps: 1) determining indexes of comprehensive benefit evaluation, and establishing a comprehensive evaluation index set of virtual power plant optimized operation; 2) taking the dimension of each comprehensive benefit evaluation index and the difference between numerical value quantity levels into consideration, and performing normalization processing on each index; 3) converting qualitative virtual power plant comprehensive benefits into quantitative evaluation values by adopting comprehensive weights determined by a G1-expert clustering weighting method, and establishing a virtual power plant comprehensive benefit evaluation system; 4) and for the given operation schemes of the plurality of virtual power plants, performing comprehensive benefit evaluation by adopting a comprehensive benefit evaluation system of the virtual power plants, and determining the optimal operation scheme with the best comprehensive benefit. Compared with the prior art, the method has the advantages of high feasibility, rapidness, reliability, wide application range and the like.

Description

Distributed power supply-oriented virtual power plant operation scheme optimization method
Technical Field
The invention relates to the field of virtual power plant optimization operation, in particular to a distributed power supply-oriented virtual power plant operation scheme optimization method.
Background
The virtual power plant is a special type of power plant composed of different types of distributed energy sources, and is also an integrated energy management system. The virtual power plant aggregates distributed energy sources such as distributed power sources, energy storage equipment and electric vehicles through an advanced communication technology and a software system, and participates in the operation of a power market and a power system. After the virtual power plant is put into actual operation, renewable energy can be fully utilized, and higher income is generated. The comprehensive benefits of the virtual power plant are reflected in the aspects of technology and economy. Therefore, how to optimize the operation scheme of the virtual power plant facing the distributed power source has attracted a great deal of attention.
The virtual power plant can get close to the traditional power plant by aggregating various distributed power supplies after being put into practical operation, and fully utilizes the complementarity among the various distributed power supplies, reduces the influence of renewable energy grid connection, and then participates in the electric power market to obtain income. Some documents establish a virtual power plant optimization model containing wind-solar energy storage, and compare the economic benefits of different optimization schemes; in addition, some other documents consider demand response in a virtual power plant, establish corresponding optimization models, and compare economic benefits of different optimization schemes, so as to explain the economy of the established models; however, the above documents do not consider the contribution of the virtual power plant in the renewable energy consumption, and at the same time, the optimal operation scheme of the virtual power plant needs to consider whether the scheduling requirement can be met and the influence on the environment, and it is not comprehensive and deep enough to consider the economic benefit. Most of the existing documents take economic benefit as a standard for evaluating the optimized operation scheme of the virtual power plant, but the evaluation on the technical benefit is less, and further exploration is still needed.
Therefore, a distributed power supply-oriented virtual power plant operation scheme optimization method is urgently needed to realize comprehensive benefit evaluation on different virtual power plant optimization operation schemes and select an operation scheme with the best comprehensive benefit.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provide a distributed power supply-oriented virtual power plant operation scheme optimization method which is rapid, reliable, high in feasibility, wide in application range and wide in consideration of the out-of-force characteristic.
The purpose of the invention can be realized by the following technical scheme:
a distributed power supply-oriented virtual power plant operation scheme optimization method comprises the following steps:
1) determining indexes of comprehensive benefit evaluation, and establishing a comprehensive evaluation index set of virtual power plant optimized operation;
2) taking the dimension of each comprehensive benefit evaluation index and the difference between numerical value quantity levels into consideration, and performing normalization processing on each index;
3) converting qualitative virtual power plant comprehensive benefits into quantitative evaluation values by adopting comprehensive weights determined by a G1-expert clustering weighting method, and establishing a virtual power plant comprehensive benefit evaluation system;
4) and for the given operation schemes of the plurality of virtual power plants, performing comprehensive benefit evaluation by adopting a comprehensive benefit evaluation system of the virtual power plants, and determining the optimal operation scheme with the best comprehensive benefit.
In the step 1), the indexes of the comprehensive benefit evaluation specifically include an economic index, an environmental protection index, a power deviation rate index and a renewable energy utilization index.
The economic index is specifically an economic index of the virtual power plant participating in the active power coordination optimization scheduling of the power grid, and the economic index comprises the following components:
Figure BDA0003313783560000021
wherein C is the operation income of the virtual power plant,
Figure BDA0003313783560000022
for the benefit of the virtual power plant actual output during the period t,
Figure BDA0003313783560000023
in order to simulate the electricity purchasing cost of the power plant in the period t,
Figure BDA0003313783560000024
for the maintenance cost of the period t,
Figure BDA0003313783560000025
the cost of load translation compensation for the period t,
Figure BDA0003313783560000026
the cost is compensated for the load transfer for the period t,
Figure BDA0003313783560000027
and the cost of interaction between the electric automobile and the main network is t.
The environmental protection index comprises CO2Emission and SO2The emission amount corresponds to the expression:
Figure BDA0003313783560000028
Figure BDA0003313783560000029
wherein the content of the first and second substances,
Figure BDA00033137835600000210
discharge coefficient, σ, of q-th pollutant for outsourcingGWP.qIs the global warming potential coefficient of the q pollutant, nemTotal number of pollutant species discharged，
Figure BDA00033137835600000211
Total power purchased from the grid, η, for a virtual power plantgenEta, for the efficiency of power generation in the plantgridIs the transmission line loss rate, sigmaAP.qIs the acidification potential coefficient of the qth pollutant.
The expression of the power deviation rate index is as follows:
Figure BDA0003313783560000031
wherein n isdAs power deviation ratio, DkThe variable is a variable 0-1 which can completely meet the scheduling requirement in the kth time period, 0 is a variable which can not completely meet the scheduling requirement, 1 is a variable which can completely meet the scheduling requirement, and T is a scheduling total time period.
The index of the utilization rate of the renewable energy sources is evaluated by the consumption rate of the renewable energy sources, and the index comprises the following components:
Figure BDA0003313783560000032
wherein N isEURFor the consumption of renewable energy, Pw,tIs the actual output of wind power in the time period of t, Ppv,tIs the actual output of photovoltaic of period t, P'w,tIs the maximum output of wind power in a period of t'pv,tThe maximum photovoltaic output is obtained in the period t.
In the step 2), an extreme method is adopted to carry out non-dimensionalization and consistency processing on the indexes to obtain an evaluation index standardization matrix, so that the index score is in the range of [0,100 ].
The step 3) specifically comprises the following steps:
31) the weight of n experts on m indexes is obtained by adopting a G1 method, and an empirical judgment matrix W is constructed, wherein the method comprises the following steps:
Figure BDA0003313783560000033
wherein, wi.jJudging the value of the weight of the ith index for the jth expert;
32) constructing a compatibility matrix D according to the opinion compatibility D (x, y) of the expert x and the expert y, wherein
D＝(D1,D2,…,Dn)＝[d(x,y)]m×n
Figure BDA0003313783560000041
Wherein, wi,x、wi,yRespectively judging the weight of the ith index for the expert x and the expert y;
33) determining an optimal clustering threshold, and clustering by adopting a direct clustering method, wherein n experts are divided into l classes;
34) obtaining information entropy H (W) corresponding to the weight sequence according to the weight sequence of each expert in each classjk) And confirming the weight of each expert according to the weight, and obtaining the comprehensive weight w by weightings,iIntegrated weight ws,iThe expression of (a) is:
Figure BDA0003313783560000042
Figure BDA0003313783560000043
Figure BDA0003313783560000044
Figure BDA0003313783560000045
wherein phi isk、φgThe number of experts in the k-th and g-th classes after classification, l is the total number of classes, WjkThe weight sequence given by the jth expert in the kth class, m is the total number of indexes,wi,jkis a weight sequence WjkOf (1) the ith weight value, λkAre inter-class weights, ajkAre intra-class weights.
In the step 33), the value range of the clustering threshold θ is [0,1], and the corresponding clustering threshold when the change rate of the clustering threshold θ is maximum is selected as the optimal clustering threshold.
In the step 4), according to the comprehensive weight ws,iAnd carrying out weighted calculation with the corresponding index scores to obtain the comprehensive benefits of each operation scheme, and selecting the operation scheme with the highest comprehensive benefit as the optimal operation scheme.
Compared with the prior art, the invention has the following advantages:
firstly, the feasibility is high: the method comprehensively considers the economic index, the environmental protection index, the power deviation rate index and the renewable energy utilization index, comprehensively evaluates the comprehensive benefits of the virtual power plant from the two aspects of the technology and the economy, is more feasible, and better accords with the actual operation condition of the virtual power plant.
Secondly, the method is rapid and reliable: the method disclosed by the invention can quickly and reliably calculate each index score of the virtual power plant optimized operation scheme to obtain a reliable and accurate evaluation result, thereby obtaining an optimal operation scheme.
Thirdly, the application range is wide: the evaluation method disclosed by the invention mainly utilizes a G1-expert clustering weighting method to convert qualitative comprehensive benefits into quantitative evaluation values, is also suitable for calculating other systems containing various distributed energy sources such as a microgrid and the like, can keep rapidity and accuracy, and has great potential for solving other comprehensive benefit evaluation problems in a power system.
Drawings
FIG. 1 is a power deviation ratio index illustration.
FIG. 2 shows the power purchase and CO for each scheme2And (5) comparing the discharge amount.
Fig. 3 is a comparison of the out-of-force characteristics of the respective schemes, wherein fig. (3a) is the out-of-force characteristic of scheme 1, fig. (3b) is the out-of-force characteristic of scheme 2, fig. (3c) is the out-of-force characteristic of scheme 3, and fig. (3d) is the out-of-force characteristic of scheme 4.
Fig. 4 is a comparison of the stored energy of the energy storage devices in each scheme.
FIG. 5 is a comparison of the electric storage capacity of the electric vehicles in the above schemes.
FIG. 6 is a comparison of the scores of each index and the comprehensive benefit score for each scheme.
FIG. 7 is a comparison of the scores of the indexes and the comprehensive benefit scores in each scheme.
FIG. 8 is a flow chart of a method of the present invention.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments.
As shown in fig. 8, the present invention provides a distributed power supply oriented virtual power plant operation scheme optimization method, which includes the following steps:
1) defining indexes of comprehensive benefit evaluation, including an economic index, an environmental protection index, a power deviation rate index and a renewable energy utilization index, and establishing a comprehensive evaluation index set of virtual power plant optimized operation;
2) taking the dimension of each comprehensive benefit evaluation index and the difference between numerical value quantity levels into consideration, and performing normalization processing on each index;
3) based on the comprehensive weight determined by the G1-expert clustering weighting method, converting the qualitative virtual power plant comprehensive benefit into a quantitative evaluation value, and establishing a virtual power plant comprehensive benefit evaluation system;
4) and for a given plurality of virtual power plant optimized operation schemes, carrying out comprehensive benefit evaluation by adopting a comprehensive benefit evaluation system of the virtual power plants, and determining the optimal operation scheme with the best comprehensive benefit.
In the step 1), the virtual power plant can fully utilize renewable energy sources by aggregating distributed power sources, the external characteristics of the virtual power plant are close to those of the traditional power plant, and higher income can be generated after the virtual power plant is put into operation. Therefore, to evaluate the comprehensive benefits of the virtual power plant, comprehensive evaluation needs to be performed from two aspects of technical performance and economic performance, and then four indexes of comprehensive benefit evaluation are defined, namely an economic performance index, an environmental protection performance index, a power deviation rate index and a renewable energy utilization rate index, and specific introduction of each index is as follows:
(1) the economic index is as follows:
the virtual power plant has the advantages of reducing fluctuation of power grid load, reducing environmental pollution, optimizing resource scheduling and the like, and after the virtual power plant participates in power grid scheduling, the economic index of the virtual power plant cannot follow the economic index of a traditional power generation system, so that the economic index of the virtual power plant participating in power grid active coordination optimization scheduling is provided, namely the operation income of the virtual power plant.
Figure BDA0003313783560000061
Wherein C is the operation income of the virtual power plant,
Figure BDA0003313783560000062
for the benefit of the virtual power plant actual output during the period t,
Figure BDA0003313783560000063
in order to simulate the electricity purchasing cost of the power plant in the period t,
Figure BDA0003313783560000064
for the maintenance cost of the period t,
Figure BDA0003313783560000065
the cost of load translation compensation for the period t,
Figure BDA0003313783560000066
the cost is compensated for the load transfer for the period t,
Figure BDA0003313783560000067
and the cost of interaction between the electric automobile and the main network is t.
(2) Environmental protection index: is divided into CO2Emission and SO2And (4) discharging the amount.
Converting the effect of various greenhouse gases on the greenhouse effect into CO2To obtain equivalent CO2The discharge amount is as follows:
Figure BDA0003313783560000068
in the formula (I), the compound is shown in the specification,
Figure BDA0003313783560000069
the discharge coefficient of the q pollutant of outsourcing electricity; sigmaGWP.qGlobal Warming Potential (GWP) coefficient for the qth pollutant; n isemTotal number of pollutant species discharged;
Figure BDA00033137835600000610
total power purchased from the grid for the virtual power plant; etagen38.8 percent is taken as the power generation efficiency of a power plant; etagridThe loss rate of the transmission line is 7 percent.
The effect of various acidified gases on the acid rain effect is converted into SO2To obtain an equivalent SO2The discharge amount is as follows:
Figure BDA00033137835600000611
in the formula: sigmaAP.qIs the Acidification Potential (AP) coefficient of the qth pollutant.
TABLE 1 pollutant emission coefficients for natural gas and coal
Figure BDA00033137835600000612
Figure BDA0003313783560000071
TABLE 2 Global warming, acidification, and pollution Effect potential coefficients of contaminants
Contaminants GWP coefficient AP coefficient REP coefficient
CO
2 1
CH4 21
N2O 310 0.7
SO2 1 1.9
NOx 0.7 0.3
PM 2.5 1
(3) Power deviation ratio index:
the ratio of the number of time segments when the output of the virtual power plant completely (partially or cannot) meet the dispatching requirement to the total dispatching time segment under each scheme is as follows:
Figure BDA0003313783560000072
wherein n isdAs power deviation ratio, DkThe variable is a variable 0-1 which can completely meet the scheduling requirement in the kth time period, 0 is a variable which can not completely meet the scheduling requirement, 1 is a variable which can completely meet the scheduling requirement, and T is a scheduling total time period.
The condition that the dispatching requirement is completely met is defined as that the actual output of the virtual power plant is completely equal to the target output curve; partially meeting the scheduling requirement is defined as being within 10% of the curve of the actual output and the target output of the virtual power plant; the condition that the dispatching requirement cannot be met is defined to be out of a 10% interval of an actual output and target output curve of the virtual power plant; the respective response schedule requirement levels are shown in fig. 1.
(4) Renewable energy utilization index:
the consumption rate of renewable energy is adopted for evaluation, and the following are:
Figure BDA0003313783560000073
in the formula: the denominator is the maximum total output of the renewable energy; actual contribution of molecule as renewable energy, NEURFor the consumption of renewable energy, Pw,tIs the actual output of wind power in the time period of t, Ppv,tFor photovoltaic reality during t periodOutput, P'w,tIs the maximum output of wind power in a period of t'pv,tThe maximum photovoltaic output is obtained in the period t.
In the step 2), due to different dimensions of the indexes and differences among numerical value numbers, incommercibility is caused, and inconvenience is brought to comprehensive evaluation. And different indexes have different properties, so that the index types need to be uniformized, otherwise, the quality of each scheme is difficult to judge according to the comprehensive evaluation result. In order to solve the above problems, the extreme method is used to perform dimensionless and uniform processing on the indicators:
when there are m evaluation indexes, it is marked as X ═ X1,x2,...,xmN system schemes participate in the evaluation, and are marked as Y ═ Y1,y2,...,ynH, then scheme yjThe ith index of (1) may be uijThat is, (i ═ 1, 2., m, j ═ 1, 2., n), an index matrix U ═ U · can be obtained from m × n evaluation indexes of n system solutionsij]m×nNamely:
Figure BDA0003313783560000081
and dividing the evaluation index into a cost index and a benefit index according to the relation between the index value and the expected result. Wherein the smaller the index value of the cost index is, the larger the index score is, and the opposite is true for the benefit index.
The cost index score function is:
Figure BDA0003313783560000082
in the formula: u. ofijAnd rijThe index value and the score of the index of the ith item of the jth scheme respectively; u. ofi，maxAnd ui，minRepresenting the historical maximum and minimum values of i, respectively.
The benefit-type indicator score function is:
Figure BDA0003313783560000083
through the normalization processing, an evaluation index normalization matrix R ═ R after data preprocessing can be obtainedij]m×nIndex score rijIn the [0,100]]Within the range.
In step 3), determining the comprehensive weight of the evaluation index according to a G1 method and an expert clustering weighting method, converting qualitative virtual power plant comprehensive benefits into quantitative evaluation values, and establishing a virtual power plant comprehensive benefit evaluation system, wherein the specific description is as follows:
1. g1 method:
the G1 method is an empowerment method developed on the basis of AHP, can convert the experience judgment of experts into the weight of each index, fully reflect the attention degree of the experts to the content of each index, in the practical application of the existing AHP method, because of the influence of the experience knowledge level of the experts and the personal preference, the judgment matrix constructed by the AHP method is difficult to meet the requirement of consistency, the judgment matrix needs to be corrected by using a characteristic vector, a genetic algorithm, an induction matrix method and the like, but the result is greatly influenced by the correction method, even the index ordering obtained by different methods possibly has mutual contradiction, and the G1 method does not need to construct the judgment matrix and carry out consistency check, has order retention and can reduce the calculated amount by times.
The principle and calculation steps of the G1 method are as follows: without loss of generality, let a1,a2,...,am(m is more than or equal to 2) is m indexes subjected to index type consistency and dimensionless processing:
(1) determining order relationships
Definition 1: if the index aiThe degree of importance of a relative evaluation criterion (or target) is not inferior to that of ajWhen it is, then it is marked as ai≥aj(the symbol ≧ represents no worse than the relationship).
Definition 2: if the index a1,a2,...,amHaving a relation a with respect to some evaluation criterion (or target)1 *≥a2 *≥...≥am *The evaluation index a is weighed1,a2,...,amIs not less thanAn order relationship is established, where a1 *Represents { a1The sequence relation is more than or equal to the ith evaluation index (i is 1,2, …, m) after the sequence is arranged.
(2) Give ak-1And akJudging the ratio of relative importance degrees of the two components;
let the expert about the evaluation index ak-1And akRatio w of importance ofk-1/wkThe rational judgment is respectively as follows:
wk-1/wk＝rk(k＝m,m-1,m-2,…,3,2)
rkthe assignment of (c) can be referred to table 3.
TABLE 3 rkValue assigning table
rk Degree of importance
1.0 Index ak-1And an index akOf equal importance
1.1 Index ak-1And an index akThe ratio of which is between equally important and slightly important
1.2 Index ak-1And an index akOf slight importance
1.3 Index ak-1And an index akThe ratio of which is between slightly and significantly important
1.4 Index ak-1And an index akOf significant importance
1.5 Index ak-1And an index akThe ratio of which is between significant and strong importance
1.6 Index ak-1And an index akOf strong importance
1.7 Index ak-1And an index akThe ratio of which is between strongly and extremely important
1.8 Index ak-1And an index akOf extreme importance
(3) Weight coefficient wkIs calculated by
If the expert gives rkRational assignment of (1), then wmComprises the following steps:
Figure BDA0003313783560000101
wk-1＝rkwk(k＝m,m-1,m-2,…3,2)
2. expert clustering empowerment method:
in the actual application process, the influence of individual bias and fuzzy recognition of a single expert is overcome by adopting an expert group decision method, and the accuracy of decision is improved. But the personal experience and professional preference of each expert are different, and the experts have different understanding on the same problem, so that the weights determined by the G1 method are different, and even contradictory opinions exist. Therefore, the idea of system clustering is adopted to weight the expert opinion clustering, the randomness of the evaluation result is reduced, the subjective bias and the cognition ambiguity of a single expert are weakened, the expert opinion is less obeyed to the majority, and the expert opinion is definitely better than the hesitation. The steps of calculating the weight by adopting an expert clustering weighting method are as follows:
(1) please ask n experts to respectively determine the weights of m indexes by using a G1 method, and obtain an empirical judgment matrix as follows:
Figure BDA0003313783560000102
in the formula: w is ai.jAnd judging the weight of the ith index for the jth expert.
(2) Determining the opinion compatibility of the expert x and the expert y, and expressing the opinion compatibility in the form of cosine of an included angle:
Figure BDA0003313783560000103
and judging the weight according to respective experience of n experts to obtain a compatibility matrix D between every two experts, wherein the compatibility matrix D comprises the following components:
D＝(D1,D2,…,Dn)＝[d(x,y)]m×n
(3) clustering by adopting a direct clustering method, and taking all different elements except a diagonal line in an upper triangle (or a lower triangle) of the compatibility matrix D, arranging the elements in a descending order and expressing the elements as follows:
1＝θ1＞θ2＞θ3…
taking the clustering threshold value theta ═ thetak∈[0,1]When d (x, y) is not less than thetak(x ≠ y), D is determinedxAnd DyThe clustering method has the same characteristics and is divided into a class, the clustering threshold value theta is different in value, the classification result is different, and the closer theta is to 1, the finer the classification is.
Let B1、B2The threshold value for clustering is thetakTwo categories of time, if
Figure BDA0003313783560000104
Then, they are called similar, all similar classes are combined into one class, and the obtained class is the clustering threshold value thetakThe equivalence class of time.
In the actual expert group decision making process, the difference between the evaluation results of the experts is possibly very small, namely the similarity degree of the sequencing vectors given by the experts is higher, and the change rate C of theta can be adopted for selecting the optimal value of the clustering threshold thetapTo determine:
Figure BDA0003313783560000111
wherein p is the clustering frequency of the clustering threshold theta from large to small, npAnd np-1Number of objects in the p-th and p-1-th clusters, θpAnd thetap-1Respectively, the threshold value for the p-th and p-1-th clustering, if
Figure BDA0003313783560000116
The threshold for the p-th cluster is considered to be an optimal value.
As can be seen from the above equation, the rate of change C of the clustering threshold θpThe larger the cluster is, the larger the difference between the classes is, the more obvious the boundary between the classes is, and C is takenpTheta at maximum valuepThe optimal clustering threshold value can ensure that the difference between different classes obtained by the p-th clustering is the largest and the boundary is the most obvious, thereby realizing the purpose and significance of classification.
(4) N experts are classified into l classes, wherein the number of experts in the k class is phik，Wjk＝[w1,jk,w2,jk,...,wm,jk]TAnd (3) giving a weight sequence for the jth expert in the kth class, wherein if the number of experts in the class is large, the evaluation judgment given by the class reflects the opinions of most experts, and a larger inter-class weight is given. For the weight in the class, the smaller the information entropy of the weight determined by each expert in the same class is, the clearer the thought of the expert is, the smaller the uncertainty is, the larger the weight should be givenAnd (4) weighting. WjkInformation entropy of H (W)jk) Comprises the following steps:
Figure BDA0003313783560000112
Figure BDA0003313783560000113
Figure BDA0003313783560000114
(5) thus, the weights of the experts can be determined, and the weights judged by the experts are weighted to obtain the comprehensive weight ws,i。
Figure BDA0003313783560000115
Comprehensive weight W fused with multiple expert opinionss＝[ws,1 ws,2 … ws,m]The number of the experts in the class where the experts are located is considered, and the information content contained in the sequencing vector given by each expert is also considered.
Combining the two methods to score r according to the indexijAnd the integrated weight ws,iThe comprehensive evaluation result of the ith scheme can be obtained as follows:
Figure BDA0003313783560000121
in the step 4), for a plurality of given virtual power plant optimized operation schemes, a comprehensive evaluation index set of the virtual power plant optimized operation is established according to the previous three steps, indexes of each scheme are calculated by using a G1-expert clustering weighting method, scores of each index are obtained, and finally the virtual power plant optimized operation scheme with the best comprehensive benefit is determined through comparison.
Examples
In order to perform comprehensive benefit evaluation of different optimized operation schemes of the virtual power plant, 4 optimized operation schemes of the same virtual power plant are set, and various data of the 4 optimized operation schemes are illustrated in fig. 1-4.
Scheme 1: the set objective function is to minimize the difference between the virtual plant target power and the actual output.
Scheme 2: the set objective function is to maximize the virtual plant operating yield.
Scheme 3: the set objective function is to minimize the virtual plant carbon dioxide emissions.
Scheme 4: meanwhile, the external characteristics, economy and environmental protection of the output of the virtual power plant are considered, and multiple targets are taken as optimization targets.
According to the comprehensive benefit evaluation method provided by the invention, a comprehensive evaluation index set of the four schemes is established, indexes of each scheme are calculated, and the obtained calculation results of each index are shown in table 4.
TABLE 4 calculation of comprehensive evaluation index for each case
Figure BDA0003313783560000122
For comparison, the original statistical data is normalized to obtain an index score, as shown in fig. 6, where the economic index is a benefit index, the environmental protection index is a cost index, and the other indexes are percentages and do not need normalization.
As can be seen from table 4 and fig. 6, scheme 2 performed far better than schemes 1, 3, and 4, and scheme 4 performed better than schemes 1 and 3 in terms of overall economic benefit; in CO2、SO2On the discharge amount, the performances of the schemes 1, 3 and 4 are much higher than those of the scheme 2; in the power deviation rate index, the scheme 1 performs best, the schemes 3 and 4 times, and each index of the scheme 2 is lower than the other three indexes; on the renewable energy consumption rate, 4 schemes perform almost, and scheme 2 is slightly better. It can be seen that each scheme has good or bad performance on each index, and the different schemes are difficult to directly compare through each index, so that the schemes need to be necessarily comparedAnd a comprehensive evaluation method is adopted to show the advantages and disadvantages of the comprehensive benefits. In order to reasonably determine the index weight, the comprehensive weight is determined by adopting a G1-expert clustering weighting method in the project, and the comprehensive benefits of the optimized operation of the virtual power plant under different schemes are evaluated.
According to the step of weighting by G1-expert clustering, 5 experts are invited to determine the importance ranking of the first-level indexes and the importance coefficient between every two experts by adopting a G1 method, and the weights determined by the experts are further solved. The comprehensive weight W of the first-level index can be obtained by calculations＝[0.255 0.183 0.388 0.173]. Similarly, the weight of each secondary index can be obtained by using a G1-expert clustering weighting method.
And finally, calculating to obtain the comprehensive benefits of the optimized operation of the virtual power plant under different schemes according to the normalized data and the comprehensive weight of each index, as shown in fig. 7.
As can be seen from fig. 7, the ranking scheme of the comprehensive benefit score 4 > scheme 3 > scheme 1 > scheme 2, the schemes 1 and 3 have the highest score on the power deviation rate, and the scores on the environmental protection performance and the renewable energy utilization rate are also higher, but the score on the economic performance is too low, which affects the comprehensive benefit score; the scheme 2 has the highest score on the economical efficiency, which is far beyond other schemes, but has the lowest score on the environmental protection performance and the power deviation rate, and the weight ratio of the power deviation rate is the highest, so the comprehensive benefit score is the lowest; the scheme 4 considering multi-objective optimization has more balanced scores on each index, has better economic performance and power deviation rate index with higher weight, and has no poor scores on indexes of environmental protection and renewable energy utilization rate, so the comprehensive benefit is the best. Therefore, the optimal operation of the virtual power plant can be realized by the optimal scheduling method comprehensively considering multiple targets. The results show that the comprehensive benefit evaluation method for the distributed power supply-oriented virtual power plant can reliably and efficiently evaluate the comprehensive benefits of different virtual power plant optimized operation schemes, and intuitively provides the evaluation results through scoring.
In summary, the invention provides a distributed power supply-oriented virtual power plant comprehensive benefit evaluation method, firstly, indexes of comprehensive benefit evaluation are defined, wherein the indexes comprise an economic index, an environmental protection index, a power deviation rate index and a renewable energy utilization index, and a comprehensive evaluation index set of virtual power plant optimized operation is established according to different optimized operation schemes; meanwhile, the dimension of each comprehensive benefit evaluation index and the difference between numerical value quantity grades are considered, and an extreme method is adopted to carry out normalization processing on each index, so that the quality of the comprehensive benefit of each scheme can be conveniently judged.
And then, an expert group decision method is adopted to improve the decision accuracy, the weight of each index is determined by using a G1 method, and the idea of system clustering is used for weighting the expert opinion clustering, so that the randomness of the evaluation result is reduced. The method converts qualitative virtual power plant comprehensive benefits into quantitative evaluation values, and further establishes a virtual power plant comprehensive benefit evaluation system.
And finally, for a plurality of given virtual power plant optimized operation schemes, carrying out comprehensive benefit evaluation by using the established comprehensive benefit evaluation method, and determining the optimized operation scheme with the best comprehensive benefit.
The method comprises the steps of firstly, defining indexes of comprehensive benefit evaluation in detail, carrying out normalization processing on the indexes by adopting an extreme value method, conveniently comparing the comprehensive benefits of all schemes subsequently, then converting the comprehensive benefits into quantitative evaluation values by adopting a G1-expert clustering weighting method, obtaining scores of all indexes of different optimized operation schemes, and carrying out comprehensive evaluation and comparison on the comprehensive benefits of the different optimized operation schemes. Therefore, the method provided by the invention has the advantages of high reliability, high calculation speed and the like. In addition, the economic index, the environmental protection index, the power deviation rate index and the renewable energy utilization index are considered in the comprehensive benefit evaluation method of the virtual power plant optimized operation scheme, comprehensive benefits of the virtual power plant are evaluated comprehensively from the two aspects of the technology and the economy, the evaluation method is more feasible, and the actual operation condition of the virtual power plant is better met. Finally, the method provided by the invention is also suitable for calculating other systems containing various distributed energy sources, such as a micro-grid and the like, can keep rapidity and accuracy, and has great potential for solving other comprehensive benefit evaluation problems in a power system.

Claims (10)

1. A distributed power supply-oriented virtual power plant operation scheme optimization method is characterized by comprising the following steps:
1) determining indexes of comprehensive benefit evaluation, and establishing a comprehensive evaluation index set of virtual power plant optimized operation;
2) taking the dimension of each comprehensive benefit evaluation index and the difference between numerical value quantity levels into consideration, and performing normalization processing on each index;
3) converting qualitative virtual power plant comprehensive benefits into quantitative evaluation values by adopting comprehensive weights determined by a G1-expert clustering weighting method, and establishing a virtual power plant comprehensive benefit evaluation system;
4) and for the given operation schemes of the plurality of virtual power plants, performing comprehensive benefit evaluation by adopting a comprehensive benefit evaluation system of the virtual power plants, and determining the optimal operation scheme with the best comprehensive benefit.
2. The distributed power supply-oriented virtual power plant operation scheme optimization method according to claim 1, wherein in the step 1), the indexes of comprehensive benefit evaluation specifically include an economic index, an environmental protection index, a power deviation rate index and a renewable energy utilization index.
3. The distributed power supply-oriented virtual power plant operation scheme optimization method according to claim 2, wherein the economic indicators are economic indicators of the virtual power plant participating in power grid active power coordination optimization scheduling, and the economic indicators include:
Figure FDA0003313783550000011
wherein C is the operation income of the virtual power plant,
Figure FDA0003313783550000012
for the collection of the virtual power plant actual output in the t periodThe advantages that the method is good for,
Figure FDA0003313783550000013
in order to simulate the electricity purchasing cost of the power plant in the period t,
Figure FDA0003313783550000014
for the maintenance cost of the period t,
Figure FDA0003313783550000015
the cost of load translation compensation for the period t,
Figure FDA0003313783550000016
the cost is compensated for the load transfer for the period t,
Figure FDA0003313783550000017
and the cost of interaction between the electric automobile and the main network is t.
4. The distributed power supply-oriented virtual power plant operation scheme optimization method according to claim 2, wherein the environmental protection index comprises CO2Emission and SO2The emission amount corresponds to the expression:
Figure FDA0003313783550000018
Figure FDA0003313783550000019
wherein the content of the first and second substances,
Figure FDA0003313783550000021
the discharge coefficient of the q pollutant of outsourcing power supply,
Figure FDA0003313783550000022
is a global change of the q pollutantCoefficient of thermal potential, nemIn order to be the total number of pollutant species emitted,
Figure FDA0003313783550000023
total power purchased from the grid, η, for a virtual power plantgenEta, for the efficiency of power generation in the plantgridThe loss rate of the power transmission line is,
Figure FDA0003313783550000024
is the acidification potential coefficient of the qth pollutant.
5. The distributed power supply-oriented virtual power plant operation scheme optimization method according to claim 2, wherein the expression of the power deviation ratio index is as follows:
Figure FDA0003313783550000025
wherein n isdAs power deviation ratio, DkThe variable is a variable 0-1 which can completely meet the scheduling requirement in the kth time period, 0 is a variable which can not completely meet the scheduling requirement, 1 is a variable which can completely meet the scheduling requirement, and T is a scheduling total time period.
6. The distributed power supply-oriented virtual power plant operation scheme optimization method according to claim 2, wherein the renewable energy utilization index is evaluated by a consumption rate of renewable energy, and the evaluation includes:
Figure FDA0003313783550000026
wherein N isEURFor the consumption of renewable energy, Pw,tIs the actual output of wind power in the time period of t, Ppv,tIs the actual output of photovoltaic of period t, P'w,tIs the maximum output of wind power in a period of t'pv,tThe maximum photovoltaic output is obtained in the period t.
7. The distributed power supply-oriented virtual power plant operation scheme optimization method according to claim 1, wherein in the step 2), the indexes are subjected to non-dimensionalization and consistency processing by an extremum method to obtain an evaluation index normalization matrix, so that the index score is in a range of [0,100 ].
8. The distributed power supply-oriented virtual power plant operation scheme optimization method according to claim 1, wherein the step 3) specifically comprises the following steps:
31) the weight of n experts on m indexes is obtained by adopting a G1 method, and an empirical judgment matrix W is constructed, wherein the method comprises the following steps:
Figure FDA0003313783550000027
wherein, wi.jJudging the value of the weight of the ith index for the jth expert;
32) constructing a compatibility matrix D according to the opinion compatibility D (x, y) of the expert x and the expert y, wherein
D＝(D1,D2,…,Dn)＝[d(x,y)]m×n
Figure FDA0003313783550000031
Wherein, wi,x、wi,yRespectively judging the weight of the ith index for the expert x and the expert y;
33) determining an optimal clustering threshold, and clustering by adopting a direct clustering method, wherein n experts are divided into l classes;
34) obtaining information entropy H (W) corresponding to the weight sequence according to the weight sequence of each expert in each classjk) And confirming the weight of each expert according to the weight, and obtaining the comprehensive weight w by weightings,iIntegrated weight ws,iThe expression of (a) is:
Figure FDA0003313783550000032
Figure FDA0003313783550000033
Figure FDA0003313783550000034
Figure FDA0003313783550000035
wherein phi isk、φgThe number of experts in the k-th and g-th classes after classification, l is the total number of classes, WjkThe weight sequence given to the jth expert in the kth class, m is the total number of indexes, wi,jkIs a weight sequence WjkOf (1) the ith weight value, λkAre inter-class weights, ajkAre intra-class weights.
9. The distributed power supply-oriented virtual power plant operation scheme optimization method according to claim 8, wherein in the step 33), a value range of the clustering threshold θ is [0,1], and a corresponding clustering threshold when a change rate of the clustering threshold θ is maximum is selected as an optimal clustering threshold.
10. The distributed power supply-oriented virtual power plant operation scheme optimization method according to claim 8, wherein in the step 4), the optimization is performed according to the comprehensive weight ws,iAnd carrying out weighted calculation with the corresponding index scores to obtain the comprehensive benefits of each operation scheme, and selecting the operation scheme with the highest comprehensive benefit as the optimal operation scheme.
CN202111225531.7A 2021-10-21 2021-10-21 Distributed power supply-oriented virtual power plant operation scheme optimization method Pending CN113780686A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111225531.7A CN113780686A (en) 2021-10-21 2021-10-21 Distributed power supply-oriented virtual power plant operation scheme optimization method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111225531.7A CN113780686A (en) 2021-10-21 2021-10-21 Distributed power supply-oriented virtual power plant operation scheme optimization method

Publications (1)

Publication Number Publication Date
CN113780686A true CN113780686A (en) 2021-12-10

Family

ID=78873296

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111225531.7A Pending CN113780686A (en) 2021-10-21 2021-10-21 Distributed power supply-oriented virtual power plant operation scheme optimization method

Country Status (1)

Country Link
CN (1) CN113780686A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI815666B (en) * 2022-09-16 2023-09-11 國立成功大學 Hybrid system and method for distributed virtual power plants integrated intelligent net zero

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101788622A (en) * 2010-01-07 2010-07-28 四川中鼎科技有限公司 Debugging test method for automatic power-generating control system
CN107292489A (en) * 2017-05-18 2017-10-24 国网浙江省电力公司 A kind of dispatching of power netwoks runs lean evaluation system
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
CN109861290A (en) * 2019-03-14 2019-06-07 国网上海市电力公司 A kind of integrated energy system Optimization Scheduling considering a variety of flexible loads
CN111340274A (en) * 2020-02-17 2020-06-26 国网冀北电力有限公司 Virtual power plant participation-based comprehensive energy system optimization method and system
CN112234617A (en) * 2020-10-15 2021-01-15 国网上海市电力公司 Virtual power plant multi-objective optimization scheduling method considering output external characteristics
CN112465236A (en) * 2020-12-03 2021-03-09 上海电力大学 Community comprehensive energy system scheduling method considering comprehensive satisfaction

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101788622A (en) * 2010-01-07 2010-07-28 四川中鼎科技有限公司 Debugging test method for automatic power-generating control system
CN107292489A (en) * 2017-05-18 2017-10-24 国网浙江省电力公司 A kind of dispatching of power netwoks runs lean evaluation system
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
CN109861290A (en) * 2019-03-14 2019-06-07 国网上海市电力公司 A kind of integrated energy system Optimization Scheduling considering a variety of flexible loads
CN111340274A (en) * 2020-02-17 2020-06-26 国网冀北电力有限公司 Virtual power plant participation-based comprehensive energy system optimization method and system
CN112234617A (en) * 2020-10-15 2021-01-15 国网上海市电力公司 Virtual power plant multi-objective optimization scheduling method considering output external characteristics
CN112465236A (en) * 2020-12-03 2021-03-09 上海电力大学 Community comprehensive energy system scheduling method considering comprehensive satisfaction

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI815666B (en) * 2022-09-16 2023-09-11 國立成功大學 Hybrid system and method for distributed virtual power plants integrated intelligent net zero

Similar Documents

Publication Publication Date Title
CN109829604A (en) A kind of grid side energy-accumulating power station operational effect comprehensive estimation method
CN107451686B (en) Micro-grid energy optimization method of genetic algorithm considering random prediction error
CN108921376B (en) Optimal selection method and system for electricity reliability improvement object of intelligent power distribution network
CN112182720B (en) Building energy consumption model evaluation method based on building energy management application scene
CN110796307A (en) Distributed load prediction method and system for comprehensive energy system
CN117272850B (en) Elastic space analysis method for safe operation scheduling of power distribution network
CN115099511A (en) Photovoltaic power probability estimation method and system based on optimized copula
CN112952807A (en) Multi-objective optimization scheduling method considering wind power uncertainty and demand response
CN115936220A (en) Garden comprehensive energy system planning and operation optimization method and terminal
CN112633762A (en) Building energy efficiency obtaining method and equipment
CN114139940A (en) Generalized demand side resource network load interaction level assessment method based on combined empowerment-cloud model
CN116826710A (en) Peak clipping strategy recommendation method and device based on load prediction and storage medium
CN113327047B (en) Power marketing service channel decision method and system based on fuzzy comprehensive model
CN110570091A (en) Load identification method based on improved F-score feature selection and particle swarm BP neural network
CN113780686A (en) Distributed power supply-oriented virtual power plant operation scheme optimization method
CN113708418A (en) Micro-grid optimization scheduling method
Su et al. Optimal placement and capacity sizing of energy storage systems via NSGA-II in active distribution network
CN112381422A (en) Method and device for determining performance of photovoltaic power station
CN111091301A (en) Optimization method for provincial power grid sustainable development strategy
CN112633631B (en) Method for evaluating complementarity of multi-power-supply system
CN113033886B (en) Power distribution network planning construction evaluation method
CN116823008A (en) Park energy utilization efficiency evaluation method, system, equipment and storage medium
CN115034618A (en) Community comprehensive energy system benefit evaluation method based on fuzzy evaluation
CN114819337A (en) Multi-task learning-based comprehensive energy system multi-load prediction method
CN114971380A (en) Method and system for evaluating commercial operation mode of shared energy storage power station

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