CN116384692A - Data-driven-based environmental economic dispatching method and system for wind-energy-containing power system - Google Patents
Data-driven-based environmental economic dispatching method and system for wind-energy-containing power system Download PDFInfo
- Publication number
- CN116384692A CN116384692A CN202310371533.XA CN202310371533A CN116384692A CN 116384692 A CN116384692 A CN 116384692A CN 202310371533 A CN202310371533 A CN 202310371533A CN 116384692 A CN116384692 A CN 116384692A
- Authority
- CN
- China
- Prior art keywords
- data
- model
- wind
- data driving
- environmental
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000007613 environmental effect Effects 0.000 title claims abstract description 40
- 238000005457 optimization Methods 0.000 claims abstract description 45
- 230000006870 function Effects 0.000 claims abstract description 33
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 24
- 238000003062 neural network model Methods 0.000 claims abstract description 18
- 238000013140 knowledge distillation Methods 0.000 claims abstract description 14
- 238000010248 power generation Methods 0.000 claims abstract description 14
- 238000003912 environmental pollution Methods 0.000 claims abstract description 13
- 238000005516 engineering process Methods 0.000 claims abstract description 10
- 238000007620 mathematical function Methods 0.000 claims abstract description 4
- 238000004590 computer program Methods 0.000 claims description 14
- 238000003860 storage Methods 0.000 claims description 9
- 238000013528 artificial neural network Methods 0.000 claims description 8
- 238000010977 unit operation Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 230000000739 chaotic effect Effects 0.000 claims description 3
- 230000005611 electricity Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 2
- 230000008014 freezing Effects 0.000 claims description 2
- 238000007710 freezing Methods 0.000 claims description 2
- 238000013507 mapping Methods 0.000 claims description 2
- 241000235395 Mucor Species 0.000 abstract 2
- 239000003795 chemical substances by application Substances 0.000 description 12
- 238000010586 diagram Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 6
- 230000008901 benefit Effects 0.000 description 4
- 239000002803 fossil fuel Substances 0.000 description 4
- 238000004088 simulation Methods 0.000 description 4
- 241000863434 Myxococcales Species 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 239000003344 environmental pollutant Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 231100000719 pollutant Toxicity 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Feedback Control In General (AREA)
Abstract
The invention belongs to the technical field of power systems, and provides an environmental economic dispatching method and system of a wind-containing power system based on data driving, which are based on a data driving agent model, a knowledge distillation technology and an improved multi-objective mucor algorithm, and based on the obtained actual parameters of a wind-containing power grid with any structure, the method aims at simultaneously minimizing the power generation cost and the environmental pollution, considers the running trend of the actual power grid, replaces the original power generation cost model and the original environmental pollution model which are described by mathematical functions by using a data driving fuzzy neural network model, quickly constructs a real-time data driving fuzzy neural network model by using a knowledge distillation scheme, obtains a group of non-dominant solution sets based on the improved multi-objective mucor algorithm, forms the pareto optimal front of two optimization targets of the power generation cost and the environmental pollution, and obtains an optimal dispatching decision basis of a group of the period by using a membership function method; and the convergence speed and accuracy of the optimization algorithm are improved.
Description
Technical Field
The invention belongs to the technical field of power systems, and particularly relates to an environment economic dispatch scheduling method and system for a wind-energy-containing power system based on data driving.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The current power grid is increasingly enlarged in scale, various new energy sources are integrated into the power grid, the environmental pollution is increasingly serious, and on the premise of ensuring that the power supply quality is not affected, the method has important technical problems that the environmental and economic benefits are very well researched, and is also key content for promoting energy conservation and emission reduction of power enterprises.
Typically, after a load predictor predicts the electricity demand for a certain period of time, scheduling will play a decisive role in power supply, which will involve load balancing problems, network loss problems, environmental problems and economic benefits. On the premise of guaranteeing the power supply requirement, the problems of reducing the network loss, reducing the environmental pollution and increasing the power enterprise benefit are important to study.
At present, in order to solve the technical problems, the main research thought of the existing scheme is as follows: the method comprises the steps of (1) simultaneously considering the generation cost and the pollution gas emission problem of the thermal power generating unit and the fan, (2) considering different constraint conditions in the power generation and scheduling process, and (3) selecting a proper algorithm to analyze and solve on the basis of meeting the scheduling time requirement.
The inventors found that the existing method has the following technical defects:
1. most only consider the problems of active constraint and load balance of the generator, and meanwhile, an approximate calculation method is adopted for the line loss, so that the actual load balance problem is influenced; although the traditional method also considers the running condition of an actual power grid, the actual condition that a large amount of renewable energy sources are connected with the grid and participate in scheduling is not considered, and the scheduling problem of the existing power system cannot be met.
2. The scheduling model constructed in the prior art is based on the acquired historical data, and is scheduled by an offline method, so that the real-time scheduling requirement cannot be met, and the efficiency is low.
3. In the application of the algorithm, because the optimal environmental economic dispatch model of the wind-energy-containing power system is a nonlinear and non-convex mathematical model, the traditional multi-objective myxobacteria algorithm has the problems of insufficient convergence capacity and slow convergence speed, thereby greatly prolonging the optimization time and failing to meet the real-time dispatch requirement.
Disclosure of Invention
In order to solve at least one technical problem in the background art, the invention provides a data-driven wind-containing power system environment economic dispatch method and system, which are based on a data-driven proxy model, knowledge distillation and improved multi-objective mucosae algorithm, and realize that the power generation cost of a generator set is minimized, the emission of polluted gas is minimized, the use of fossil fuel is reduced to the greatest extent, the operation time is greatly reduced, and decision basis can be provided for power enterprises in time on the premise of meeting the power load.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
the invention provides a data-driven wind-energy-containing power system environment economic dispatch method, which comprises the following steps:
based on the acquired running parameters of the wind-energy-containing power grid, taking the minimization of the power generation cost and the minimization of the environmental pollution as targets at the same time, and taking the actual running trend of the power grid into consideration, constructing an environmental economy dispatching multi-target optimization model of the wind-energy-containing power system;
acquiring unit operation data, replacing a multi-objective optimization model by adopting a data-driven fuzzy neural network model, and constructing an online data-driven proxy model by utilizing a knowledge distillation technology;
on-line data driving agent model is solved based on multi-objective mucosae algorithm, global optimal solution of the solved model is obtained through membership function and is used as optimal scheduling decision basis to complete optimal scheduling of environmental economy of wind-energy-containing power system.
A second aspect of the present invention provides a data-driven based wind energy power system environmental economy dispatch system comprising:
the target optimization model construction module is used for constructing an environmental economic dispatch multi-target optimization model of the power system containing wind energy by taking the actual power grid running trend into consideration with the aim of simultaneously minimizing the power generation cost and the environmental pollution based on the acquired wind energy-containing power grid running parameters;
the data driving module is used for acquiring unit operation data, replacing the multi-objective optimization model by adopting a data driving fuzzy neural network model, and constructing an online data driving agent model by utilizing a knowledge distillation technology;
the scheduling module is used for solving the online data-driven agent model based on the multi-objective mucosae algorithm, and obtaining the global optimal solution of the solved model through the membership function as an optimal scheduling decision basis so as to complete the optimal scheduling of the environmental economy of the wind-containing power system.
A third aspect of the present invention provides a computer-readable storage medium.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the data driven based wind energy power system environmental economic dispatch method as described in the first aspect above.
A fourth aspect of the invention provides a computer device.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps in the data-driven wind energy-containing power system environmental economic dispatch method according to the first aspect described above when the program is executed.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention realizes the environmental economic dispatch of the wind-energy-containing power system based on a data-driven agent model, knowledge distillation and an improved multi-objective mucosae algorithm by considering the actual situation that a large amount of renewable energy sources are connected with the grid and participate in the dispatch, and minimizes the power generation cost of a generator set on the premise of meeting the power load, simultaneously minimizes the emission of polluted gas, furthest reduces the use of fossil fuel, greatly reduces the operation time and can provide decision basis for power enterprises in time.
2. Reconstructing an objective function by using a data-driven agent-assisted method based on the fuzzy neural network model, and replacing the original objective function with the rapid calculation based on the data-driven fuzzy neural network model; in order to realize quick establishment of the fuzzy neural network proxy model, knowledge distillation technology and real-time data are utilized to fine tune the offline fuzzy neural network proxy model, so that modeling time is saved.
3. The invention improves the traditional multi-objective myxobacteria algorithm as a basis, overcomes the defects caused by the traditional weight and method, simultaneously adapts to a multi-objective optimization method, initializes the population by utilizing sinusoidal chaotic mapping to further improve diversity, and then improves convergence by establishing an external archive to store the optimal pareto front and utilizing individuals in the pareto front in the archive to guide population optimization, improves convergence capacity and convergence speed, shortens optimization time, thereby meeting the requirement of real-time scheduling.
Additional aspects of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention.
FIG. 1 is a flow chart of a method of scheduling a wind-containing power system in accordance with a first embodiment of the present disclosure;
FIG. 2 is a schematic diagram of a structure of a fuzzy neural network model used to replace an original objective function according to a first embodiment of the present disclosure;
FIG. 3 is an algorithm flow diagram based on a data driven proxy model and an improved multi-objective myxobacteria algorithm in a first embodiment of the present disclosure;
FIG. 4 is a schematic diagram of an IEEE 40-unit test system with fans for simulation objects employed in a first embodiment of the present disclosure;
FIG. 5 is a pareto optimal front generated for an IEEE 40-unit system with fans (load 10500 MW) taking into account all of the constraints above in an embodiment of the disclosure;
fig. 6 is a block diagram of a wind energy-containing power system environmental economic dispatch system in a second embodiment of the present disclosure.
Detailed Description
The invention will be further described with reference to the drawings and examples.
It should be noted that the following detailed description is illustrative and is intended to provide further explanation of the invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present invention. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
Aiming at the technical problems mentioned in the background art of the invention, the invention adopts a data-driven agent model, a knowledge distillation technology and an improved multi-objective mucosae algorithm, based on the obtained actual parameters of the wind-energy-containing power grid with any structure, the invention aims at simultaneously minimizing the power generation cost and the environmental pollution, considers the running trend of the actual power grid, replaces the original power generation cost model and environmental pollution model which are described by using mathematical functions by using a data-driven fuzzy neural network model, quickly constructs a real-time data-driven fuzzy neural network model by using a knowledge distillation scheme, obtains a group of non-dominant solution sets based on the improved multi-objective mucosae algorithm, forms the pareto optimal front edges of two optimization targets of the power generation cost and the environmental pollution, and obtains an optimal scheduling decision basis of a group of time periods by using a membership function method; the convergence speed and accuracy of the optimization algorithm are improved, and the scheduling operation time of the wind-energy-containing power system is effectively shortened.
Example 1
Referring to fig. 1, the present embodiment provides a data-driven-based environmental economic dispatch method for a wind-powered power system, including the following steps:
step 1: acquiring operation parameters of a wind-energy-containing power system;
in step 1, the operating parameters of the wind-containing power system include:
node parameters; active load and reactive load in a scheduling period; node voltage amplitude, phase angle, and maximum and minimum voltage that the node can bear; the node of the generator outputs active power and reactive power, and the node can bear the maximum and minimum active and reactive power of the output; maximum active power and reactive power which each generator is allowed to output; and branch parameters including branch resistance, reactance, susceptance per unit value, capacity allowed by long/short distance transmission branch, and maximum and minimum phase angles allowed by the branch, system parameters of the blower.
Step 2: based on the operation parameters of the wind-energy-containing power system, the environmental economic dispatch optimization model of the wind-energy-containing power system is built by taking the minimum pollutant gas emission and fossil fuel cost as targets and taking the active, reactive upper and lower limit constraints, power balance constraints, node voltage amplitude constraints and line tide constraints of the motor as constraint conditions;
in step 2, optimization objective 1: the fossil fuel cost function is:
wherein C (·) represents a cost function, ng is the number of the thermal units, N w The number of fans is f i (P i ) The output of the ith thermal unit is P i Cost at time, a i 、b i 、c i 、d i 、e i G is the fuel cost coefficient of the ith generator j (W j ) The output force of the j-th fan is W j Cost of q j Is the cost coefficient of the jth fan, C rw,j For the overestimated cost coefficient of the jth fan, C rw,j E(Y oe,j ) For the overestimated cost of the jth fan, C pw,j For underestimated cost coefficient of jth fan, C pw,j E(Y ue,j ) The underestimated cost for the jth fan.
Optimization objective 2: the pollutant gas emission objective function is:
wherein alpha is i 、β i 、γ i 、ε i 、λ i And (5) the pollution gas emission coefficient of the ith generator.
Upper and lower limits of active and reactive power constraint of the generator:
power balance constraint:
node voltage magnitude constraint:
line tide constraint:
in the method, in the process of the invention,for the lower limit of the output active power of the ith generator,/->For the lower limit of the output active power of the ith generator,/->Is the lower limit of the output power of the jth fan, < ->Is the upper limit of the output power of the jth fan,for the lower limit of the output reactive power of the ith generator,/->For the lower limit of the output reactive power of the ith generator, N bus V is the number of nodes in the power grid k Node voltage representing the kth node, +.>Node voltage minimum value representing kth node,/->Represents the maximum value of the node voltage of the kth node, S tk Representing the flow of water on the line between node t and node k,/->Representing the maximum power flow of the line between node t and node k.
The target function and the constraint condition are synthesized, and the obtained environmental economy scheduling multi-target optimization model representation of the wind power system can be comprehensively expressed as:
f (P) and E (P) represent optimization objective 1 and optimization objective 2, respectively, g (P) and h (P) are the involved equality and inequality constraints, respectively, M 1 、M 2 The number of equality and inequality constraints, respectively.
Step 3: acquiring historical operation data of a wind-energy-containing power system, and constructing an offline data driving agent model based on a fuzzy neural network according to the historical operation data;
constructing a data-driven proxy model according to possible solutions of the objective functions, so as to convert the original objective functions which are calculated in an expensive way into a fuzzy neural network model which is easy to solve;
the construction process for constructing the offline data driving agent model based on the fuzzy neural network according to the historical operation data comprises the following steps:
step 301: acquiring historical operation data, namely, taking the output power of a unit as input data of an input layer;
step 302: processing the input data through a membership function layer by utilizing fuzzy mathematics, and converting each dimension of the input data into three fuzzy sets;
step 303: defining fuzzy rules at a fuzzy reasoning layer;
step 304: determining confidence coefficients of all rules through a normalization layer;
step 305: converting the fuzzy data into output data through an output layer;
step 306: training the network until the minimum root mean square error is smaller than a first threshold, wherein in the embodiment, the first threshold is 0.003;
step 4: acquiring real-time operation data of a wind-energy-containing power system, and establishing an online data driving proxy model by utilizing real-time data and knowledge distillation technology, wherein the method specifically comprises the following steps of:
step 401: freezing the network structure and network parameters of the established offline fuzzy neural network data driving agent model;
step 402: adding real-time data to finely adjust the normalization layer and the output layer;
step 403: training until a convergence condition that the minimum root mean square error is smaller than a second threshold value is met; in this embodiment, the second threshold is 0.003;
step 404: and taking the trained fuzzy neural network as an online fuzzy neural network data driving proxy model.
Step 5: and solving the data-driven agent model by adopting an improved multi-objective mucosae algorithm, and obtaining a global optimal solution of the solved model through a membership function to serve as an optimal scheduling decision basis for power scheduling, so that the optimal scheduling of the environmental economy of the wind-energy-containing power system is completed.
Under the condition of meeting the load requirement of the current period, solving the multi-target optimization model by adopting an improved multi-target mucosae algorithm, solving a group of non-dominant solutions, and obtaining the pareto optimal front edge of two optimization targets of environmental economic dispatch;
the multi-objective optimization is different from the single-objective optimization, in which an optimal solution can be obtained, but in which, as for the multi-objective optimization, the environmental objective and the economic objective are related in this embodiment, the two objectives are in a competing relationship, and it is difficult to obtain a certain optimal solution; only two trade-off solutions of the optimization objective can be obtained, which is a non-dominant solution set, as shown in fig. 3, and the specific solution process is:
(1) Initializing a population by using a sine chaotic sequence;
(2) Calculating an initial population fitness value and performing non-dominant ranking; in calculating the fitness value, as shown in fig. 2, a proxy model is applied to replace the original objective function for calculation evaluation.
(3) Calculating a crowding distance;
(4) The population with the non-dominant ranking level of 1 is recorded as an initial population of the external elite archive;
(5) Enter the circulation
(6) Randomly selecting a position vector in an external elite archive to guide population optimization;
(7) Calculating the fitness value of the new population and performing non-dominant ranking;
(8) Mixing the population with the non-dominant ranking level 1 with the external elite archive, performing non-dominant ranking, and archiving the population with the non-dominant ranking level 1 as a new external elite archive;
(9) Judging whether the maximum iteration times are reached, if so, outputting an external elite file, otherwise, returning to the step (5) to continue the loop.
In the implementation of the calculation examples, the initialization parameters used in the improved multi-objective mucosae algorithm can be initially assigned only empirically, but these initial values are obviously not optimal parameters. In the operation process of the algorithm, a certain parameter can be properly adjusted while other parameters are kept unchanged, and then the advantages and disadvantages of the simulation result are observed.
For the obtained non-dominant solutions, in this embodiment, the number of obtained non-dominant solutions is 15;
all the solutions are optimal solutions, but the scheduling decision can only select one group from all the current solutions, which requires the power department to formulate a corresponding scheduling strategy according to actual conditions.
The embodiment provides a membership function-based judging method, wherein a non-dominant solution with a maximum membership value is selected as a scheduling decision basis of the period, and the specific solving method is as follows:
(1) Aiming at two optimization targets of environment and economic operation, for each target function, the membership function value corresponding to the non-dominant solution is calculated, and the method is as follows:
wherein F is i,k For the kth solution of the ith optimization objective,and->The minimum and maximum values of the ith optimization objective, respectively.
(2) Mu for each individual non-dominant solution i,k Regularization to give mu j The method comprises the following steps:
wherein N is 1 =2, the number of optimization targets, and M is the number of non-dominant solutions.
(3) Final solution mu j And taking the non-dominant solution corresponding to the maximum value as a scheduling decision basis of the current period.
The power grid parameters used by the calculation data in the scheduling method adopted in the embodiment can be the acquired actual power grid operation parameters, and also can be any simulation object, such as an IEEE 40-units test system.
The simulation example selects an IEEE 40-units test system, and the system structure schematic diagram is shown in FIG. 4. Using fig. 4 as an example, the load for the current scheduling period is 10500MW, and the resulting pareto optimal front is shown in fig. 5.
Example two
As shown in fig. 6, the present embodiment provides a data-driven-based environmental economic dispatch system for a wind-powered power system, including:
the target optimization model construction module is used for constructing an environmental economic dispatch multi-target optimization model of the power system containing wind energy by taking the actual power grid running trend into consideration with the aim of simultaneously minimizing the power generation cost and the environmental pollution based on the acquired wind energy-containing power grid running parameters;
the data driving module is used for acquiring unit operation data, replacing the multi-objective optimization model by adopting a data driving fuzzy neural network model, and constructing an online data driving agent model by utilizing a knowledge distillation technology;
the scheduling module is used for solving the online data-driven agent model based on the multi-objective mucosae algorithm, and obtaining the global optimal solution of the solved model through the membership function as an optimal scheduling decision basis so as to complete the optimal scheduling of the environmental economy of the wind-containing power system.
Example III
The present embodiment provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps in the data-driven based energy-containing power system environmental economy scheduling method according to the above embodiment.
Example IV
The embodiment provides a computer device, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the program to implement the steps in the method for environmental economic dispatch of a wind power system based on data driving according to the embodiment.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, magnetic disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random access Memory (Random AccessMemory, RAM), or the like.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. The environmental economic dispatching method for the wind energy-containing power system based on data driving is characterized by comprising the following steps of:
based on the acquired running parameters of the wind-energy-containing power grid, taking the minimization of the power generation cost and the minimization of the environmental pollution as targets at the same time, and taking the actual running trend of the power grid into consideration, constructing an environmental economy dispatching multi-target optimization model of the wind-energy-containing power system;
acquiring unit operation data, replacing a multi-objective optimization model by adopting a data-driven fuzzy neural network model, and constructing an online data-driven proxy model by utilizing a knowledge distillation technology;
on-line data driving agent model is solved based on multi-objective mucosae algorithm, global optimal solution of the solved model is obtained through membership function and is used as optimal scheduling decision basis to complete optimal scheduling of environmental economy of wind-energy-containing power system.
2. The method for environmental economic dispatch of a wind power system based on data driving according to claim 1, wherein the replacing the multi-objective optimization model with the data driving fuzzy neural network model and constructing the online data driving agent model by using knowledge distillation technology comprises the following steps:
according to the unit operation history data, replacing an electric power system environment economic dispatch multi-objective optimization model described by using mathematical functions by adopting a data-driven fuzzy neural network model to obtain an offline data-driven proxy model;
and on-line data driving agent model based on the data driving fuzzy neural network model is constructed according to the real-time operation data of the unit based on the off-line data driving agent model.
3. The method for environmental economic dispatch of a wind power system based on data driving according to claim 2, wherein the constructing an online data driving agent model based on a data driving fuzzy neural network model according to real-time operation data of a unit based on an offline data driving agent model comprises:
freezing the network structure and network parameters of the established offline data driving agent model;
adding the output power of the real-time unit to finely adjust the normalization layer and the output layer;
training until a convergence condition that the minimum root mean square error is smaller than a second threshold value is met, and obtaining the online data driving agent model.
4. The method for data-driven wind-powered electricity system environmental economy scheduling according to claim 1, wherein the obtaining an offline data-driven proxy model by replacing the electricity system environmental economy scheduling multi-objective optimization model described by a mathematical function with the data-driven fuzzy neural network model according to the unit operation history data comprises:
taking the output power of the history unit as input data of an input layer;
processing the input data through a membership function layer by utilizing fuzzy mathematics, and converting each dimension of the input data into three fuzzy sets;
defining fuzzy rules at a fuzzy reasoning layer based on the fuzzy set; determining confidence coefficients of all rules through a normalization layer; converting the data of the fuzzy set into output data through an output layer; the network is trained until the minimum root mean square error is less than a first threshold.
5. The method for environmental economic dispatch of wind power system based on data driving as claimed in claim 1, wherein in the model of solving data driving fuzzy neural network based on multi-objective mucosae algorithm, the population is initialized by sinusoidal chaotic mapping, the optimal pareto front is stored by establishing external archive and individual guidance population optimization in the pareto front in the archive is utilized, finally membership values of all non-dominant solutions are obtained, and the non-dominant solution with the largest membership value is the decision basis of the time period optimization dispatch.
6. The method for environmental economic dispatch of a data-driven wind-powered power system of claim 1, wherein the obtaining a global optimal solution of the solved model by membership functions comprises:
calculating a membership function value corresponding to a non-dominant solution of the multi-objective optimization model optimization objective function;
regularized calculation is carried out on the membership function value;
and (3) solving a non-dominant solution corresponding to the regularized and calculated membership function value when the regularized and calculated membership function value reaches the maximum value, namely a global optimal solution.
7. A data-driven wind-containing power system environmental economy scheduling method according to claim 1, wherein the acquired wind-containing power grid operation parameters include: node parameters; active load and reactive load in a scheduling period; node voltage amplitude, phase angle, and maximum and minimum voltage that the node can bear; the node of the generator outputs active power and reactive power, and the node can bear the maximum and minimum active and reactive power of the output; maximum active power and reactive power which each generator is allowed to output; and branch parameters including branch resistance, reactance, susceptance per unit value, capacity allowed by long/short distance transmission branch, and maximum and minimum phase angles allowed by the branch, system parameters of the blower.
8. Data-driven wind-energy-containing power system environment economic dispatch system is characterized by comprising:
the target optimization model construction module is used for constructing an environmental economic dispatch multi-target optimization model of the power system containing wind energy by taking the actual power grid running trend into consideration with the aim of simultaneously minimizing the power generation cost and the environmental pollution based on the acquired wind energy-containing power grid running parameters;
the data driving module is used for acquiring unit operation data, replacing the multi-objective optimization model by adopting a data driving fuzzy neural network model, and constructing an online data driving agent model by utilizing a knowledge distillation technology;
the scheduling module is used for solving the online data-driven agent model based on the multi-objective mucosae algorithm, and obtaining the global optimal solution of the solved model through the membership function as an optimal scheduling decision basis so as to complete the optimal scheduling of the environmental economy of the wind-containing power system.
9. A computer readable storage medium having stored thereon a computer program, which when executed by a processor performs the steps of the data-driven wind energy based power system environmental economic dispatch method according to any one of claims 1-7.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor, when executing the program, implements the steps of the data-driven based wind energy power system environmental economic dispatch method of any one of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310371533.XA CN116384692A (en) | 2023-04-03 | 2023-04-03 | Data-driven-based environmental economic dispatching method and system for wind-energy-containing power system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310371533.XA CN116384692A (en) | 2023-04-03 | 2023-04-03 | Data-driven-based environmental economic dispatching method and system for wind-energy-containing power system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116384692A true CN116384692A (en) | 2023-07-04 |
Family
ID=86964143
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310371533.XA Pending CN116384692A (en) | 2023-04-03 | 2023-04-03 | Data-driven-based environmental economic dispatching method and system for wind-energy-containing power system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116384692A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118226757A (en) * | 2024-05-21 | 2024-06-21 | 西北工业大学 | Energy management method and system for fuel cell aircraft |
-
2023
- 2023-04-03 CN CN202310371533.XA patent/CN116384692A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118226757A (en) * | 2024-05-21 | 2024-06-21 | 西北工业大学 | Energy management method and system for fuel cell aircraft |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Xi et al. | A novel multi-agent DDQN-AD method-based distributed strategy for automatic generation control of integrated energy systems | |
Qais et al. | Enhanced whale optimization algorithm for maximum power point tracking of variable-speed wind generators | |
Mohammadi et al. | A review on application of artificial intelligence techniques in microgrids | |
CN108964042A (en) | Regional power grid operating point method for optimizing scheduling based on depth Q network | |
CN105071433B (en) | A kind of configuration scheme of distributed generation resource | |
Feng et al. | Scheduling of short-term hydrothermal energy system by parallel multi-objective differential evolution | |
CN104050517A (en) | Photovoltaic power generation forecasting method based on GRNN | |
CN112018762B (en) | Electric vehicle charging optimization scheduling method considering transmission and distribution cooperation with reactive voltage constraint | |
CN113872213B (en) | Autonomous optimization control method and device for power distribution network voltage | |
CN111917111B (en) | Method, system, equipment and storage medium for online evaluation of distributed photovoltaic power supply acceptance capacity of power distribution network | |
CN116384692A (en) | Data-driven-based environmental economic dispatching method and system for wind-energy-containing power system | |
Tian et al. | Application of improved whale optimization algorithm in parameter identification of hydraulic turbine at no-load | |
CN116845982A (en) | Multi-energy power system optimization scheduling method based on improved multi-objective non-dominant sorting Harris eagle algorithm and comprising wind, light, water and fire pumped storage | |
Araghi et al. | Enhancing the net energy of wind turbine using wind prediction and economic NMPC with high-accuracy nonlinear WT models | |
El-Fergany | Solution of economic load dispatch problem with smooth and non-smooth fuel cost functions including line losses using genetic algorithm | |
Cui et al. | Approximate scenario-based economic model predictive control with application to wind energy conversion system | |
Pattanaik et al. | Opposition-based differential evolution for hydrothermal power system | |
Odonkor et al. | Optimization of energy use strategies in building clusters using pareto bands | |
Chen et al. | Reward adaptive wind power tracking control based on deep deterministic policy gradient | |
CN115528750A (en) | Data model hybrid drive unit combination method for power grid safety and stability | |
Liu et al. | The economic dispatch of wind integrated power system based on an improved differential evolution algorithm | |
Fang et al. | Energy scheduling and decision learning of combined cooling, heating and power microgrid based on deep deterministic policy gradient | |
Karad et al. | Enhanced control of doubly fed induction generator based wind turbine system using soft computing assisted fractional order controller | |
Bouzem et al. | Probabilistic and Reliability Analysis of an Intelligent Power Control for a Doubly Fed Induction Generator-Based Wind Turbine System | |
Li et al. | A gray rbf model improved by genetic algorithm for electrical power forecasting |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |