CN111967646A - Renewable energy source optimal configuration method for virtual power plant - Google Patents
Renewable energy source optimal configuration method for virtual power plant Download PDFInfo
- Publication number
- CN111967646A CN111967646A CN202010685434.5A CN202010685434A CN111967646A CN 111967646 A CN111967646 A CN 111967646A CN 202010685434 A CN202010685434 A CN 202010685434A CN 111967646 A CN111967646 A CN 111967646A
- Authority
- CN
- China
- Prior art keywords
- power plant
- renewable energy
- virtual power
- output
- virtual
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 230000006870 function Effects 0.000 claims abstract description 61
- 238000010248 power generation Methods 0.000 claims abstract description 56
- 238000005457 optimization Methods 0.000 claims abstract description 39
- 238000012549 training Methods 0.000 claims abstract description 16
- 230000002068 genetic effect Effects 0.000 claims abstract description 12
- 230000008901 benefit Effects 0.000 claims abstract description 6
- 238000004146 energy storage Methods 0.000 claims description 26
- 238000004364 calculation method Methods 0.000 claims description 16
- 210000002569 neuron Anatomy 0.000 claims description 14
- 210000002364 input neuron Anatomy 0.000 claims description 9
- 210000004205 output neuron Anatomy 0.000 claims description 9
- 238000009826 distribution Methods 0.000 claims description 8
- 230000005540 biological transmission Effects 0.000 claims description 7
- 230000005611 electricity Effects 0.000 claims description 6
- 238000007599 discharging Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 238000005520 cutting process Methods 0.000 claims description 3
- 230000035945 sensitivity Effects 0.000 claims description 3
- 210000000352 storage cell Anatomy 0.000 claims description 3
- 238000005286 illumination Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 239000002699 waste material Substances 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
- H02J3/46—Controlling of the sharing of output between the generators, converters, or transformers
- H02J3/466—Scheduling the operation of the generators, e.g. connecting or disconnecting generators to meet a given demand
-
- 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)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Biophysics (AREA)
- Strategic Management (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Tourism & Hospitality (AREA)
- Artificial Intelligence (AREA)
- Marketing (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Primary Health Care (AREA)
- Genetics & Genomics (AREA)
- Physiology (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a virtual power plant renewable energy source optimal configuration method, and aims to solve the technical problems that renewable energy sources are high in grid-connected cost and easy to influence a power grid in the prior art. It includes: establishing a virtual power plant electric energy output model according to the virtual power plant electric energy output form; establishing a virtual power plant optimization objective function based on the virtual power plant economic benefit maximization; establishing a renewable energy power generation punishment cost model of the virtual power plant according to an extreme learning machine algorithm, and performing model training; and solving the optimization objective function of the virtual power plant by using a genetic algorithm to obtain the renewable energy source optimization configuration result of the virtual power plant. The method can quickly and accurately obtain the optimal renewable energy source optimal configuration result of the virtual power plant, increase the economical efficiency of the operation of the virtual power plant, and simultaneously reduce the influence of grid connection on a power grid.
Description
Technical Field
The invention relates to a virtual power plant renewable energy source optimization configuration method, and belongs to the technical field of virtual power plant optimization.
Background
In recent years, with the problem of large consumption of fossil energy and environmental pollution becoming more serious, the nation proposes a strategy of connecting a distributed power supply to a power distribution network for function, so that renewable energy sources such as wind power generation and photovoltaic power generation are rapidly developed and occupy higher and higher proportion in energy structures. The renewable energy has the characteristics of large quantity, small capacity and large distribution range, and although the use of the renewable energy can relieve the pressure of fossil energy and protect the environment, the grid connection cost of the renewable energy is very high, and the grid connection of the renewable energy can generate great influence on the stable operation of a power grid.
The virtual power plant is a virtual integrated control system, can integrate a distributed power supply, a controllable load and an energy storage system in a power system together to realize the transmission of electric energy and the operation of equipment together, and can transmit energy in a power grid to users by modulating the logical relationship between the distributed power supply and a smart power grid, thereby further realizing a comprehensive power plant with economic value. At present, research on a virtual power plant mainly focuses on directions of a model framework, optimized scheduling, operation control, market bidding and the like, and related research finds that the virtual power plant can finely control distributed power supplies, variable loads and energy storage devices dispersed in a certain area through advanced technologies such as control, metering, communication and the like, and integrally manage the distributed power supplies so as to effectively aggregate and manage the distributed power supplies. Although research into virtual power plants has been successful, there is a need to develop more efficient and reliable virtual power plants in the face of increasing energy demand.
Disclosure of Invention
Aiming at the technical problems that the renewable energy grid connection cost is high and the power grid is easily influenced in the prior art, and a virtual power plant needs to be further optimized, the invention provides a virtual power plant renewable energy optimization configuration method.
In order to achieve the purpose, the invention is realized by adopting the following technical scheme:
the invention provides a virtual power plant renewable energy source optimal configuration method, which specifically comprises the following steps:
s1, establishing a virtual power plant electric energy output model according to the virtual power plant electric energy output form;
s2, establishing a virtual power plant optimization objective function based on the virtual power plant economic benefit maximization;
s3, establishing a renewable energy power generation punishment cost function of the virtual power plant, and simplifying the calculation of the renewable energy power generation punishment cost function through training an extreme learning machine;
and S4, solving the virtual power plant optimization objective function by using a genetic algorithm to obtain the virtual power plant renewable energy source optimization configuration result.
Further, the electric energy output form of the virtual power plant comprises fan power generation output, photovoltaic power generation output, gas turbine power generation output and energy storage battery power generation output.
Further, the formula of the virtual power plant optimization objective function is as follows:
where f represents the output power of the virtual power plant, ρdRepresenting the selling price of the virtual power plant for supplying power to the user, PdnRepresenting the load of node n, CgnRepresenting the cost of power generation of the gas turbine, CenRepresents the charging and discharging cost of the energy storage battery, CcnRepresents the cutting cost of the interruptible load, EkRepresenting the total penalty cost, rho, of the renewable energy power generation of the virtual power plantERepresenting electricity prices, P, at the time of purchase of electricity from virtual power plantsSThe electric energy power purchased by the virtual power plant to the power distribution network is represented, and N is 1,2, …, and N is the total number of nodes of the virtual power plant.
Further, PSThe following formula is satisfied:
wherein, PgnRepresenting the output power of the gas turbine at node n, PpnRepresenting the output power of the photovoltaic generation at node n, PwnRepresenting the output power of the wind turbine at node n, PenRepresenting the discharge power, P, of the energy storage cell at node ncnRepresenting the amount of load shed on node n.
Further, the line transmission power P of the virtual power plantlThe formula of (1) is as follows:
Plthe following constraints are satisfied:
-Wl≤Pl≤Wl (4)
wherein, WlThe boundary value of the transmission power of the first line is represented, wherein L is 1, …, L, the virtual power plant has L lines in common, KlnIndicating that the injected power at node n corresponds to the sensitivity coefficient of the l-th line.
Further, the renewable energy power generation penalty cost function is:
wherein E isnRepresents the penalty cost of renewable energy generation on node n, anRepresenting the maximum value of the penalty cost of the renewable energy unit on the node n, beta is the confidence level, PnRepresenting the actual output power, P, of the renewable energy unit at node nn SRepresenting the planned output power of the renewable energy unit at node n, cnPenalty cost coefficient, rho (P), representing the unplanned output of the renewable energy source unit on the node nn) Representing the renewable energy output power probability density function at node n.
Further, the extreme learning machine has N input neurons and N output neurons, wherein the N input neurons represent the output power (P) of the renewable energy unit on the N nodes1,P2,…,Pi,…,PN)TAnd N output neurons represent power generation penalty costs (E) corresponding to the renewable energy source units on N nodes1,E2,…,En,…,EN)TOutput layer variable EnAnd an input layer PiThe functional relationship of (a) is as follows:
wherein, betajnRepresenting hidden layer neuron No. j and No. hConnection weight vector between n output neurons, omegaijRepresents the connection weight vector between the i-th input neuron and the j-th hidden neuron, PiRepresenting the output power, theta, of the renewable energy unit at node ijThe threshold value of hidden layer neuron No. j is represented, i is 1,2, …, N, j is 1,2, …, H is the total number of hidden layer neurons, and G represents the activation function of hidden layer neurons.
Further, the method for simplifying the calculation of the penalty cost function of renewable energy power generation by training the extreme learning machine comprises the following steps:
1) given the output power (P) of a set of renewable energy units1,P2,…,Pn,…PN)TCalculating (P) according to the penalty cost function of renewable energy power generation1,P2,…,Pn,…PN)TCorresponding renewable energy generation penalty cost (E)1,E2,…,En,…EN)T；
2) Repeating the step 1), obtaining the output power of a plurality of groups of renewable energy source units and corresponding penalty cost, and forming a training sample of the extreme learning machine;
3) taking the output power of the renewable energy source unit in the step 2) as the input of the extreme learning machine, taking the corresponding penalty cost as the output of the extreme learning machine, training the extreme learning machine, and according to the output layer variable EnAnd an input layer PwiCalculating a connection weight vector of the extreme learning machine by using the function relation formula to finish training of the extreme learning machine;
4) and calculating the punishment cost of the renewable energy power generation by using the trained extreme learning machine.
Further, the step S4 specifically includes the following steps:
s41, setting the length of each individual to be N, wherein each individual represents a renewable energy source configuration scheme of the virtual power plant, taking the virtual power plant optimization objective function in the step S2 as a fitness function of the genetic algorithm, and setting the maximum iteration times of the genetic algorithm;
s42, manually setting the number of population individuals, giving random values to all individuals in the population, generating an initial population, and initializing iteration times;
s43, calculating the fitness of all individuals in the current population according to the virtual power plant optimization objective function;
s44, selecting, crossing and mutating the current population, updating the population, and automatically increasing the iteration times by 1;
s45, judging whether the iteration number reaches the maximum iteration number, if so, performing S46, otherwise, performing S43;
and S46, calculating the fitness of all individuals of the current population according to the virtual power plant optimization objective function to obtain an individual with the maximum fitness, wherein the individual is the optimal solution of the renewable energy source configuration of the virtual power plant.
Compared with the prior art, the invention has the following beneficial effects:
the invention provides a virtual power plant renewable energy source optimal configuration method, which comprises the steps of establishing a virtual power plant electric energy output model and a virtual power plant optimization objective function according to the electric energy output characteristics of a virtual power plant, solving the optimization objective function by adopting a genetic algorithm to obtain an optimal solution of virtual power plant renewable energy source optimal configuration, intensively managing renewable energy sources by continuously optimizing the virtual power plant, realizing efficient and reliable application of the renewable energy sources, increasing the economical efficiency of the operation of the virtual power plant, reducing the influence of renewable energy source grid connection on a power grid, and simultaneously providing reference for the subsequent configuration development aiming at the virtual power plant.
Drawings
Fig. 1 is a flowchart illustrating steps of a renewable energy source optimal configuration method for a virtual power plant according to the present invention.
Fig. 2 is a flowchart of a virtual power plant renewable energy source optimal configuration method in an embodiment of the present invention.
Fig. 3 is a network topology structure diagram of the extreme learning machine algorithm in the embodiment of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings. The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
The invention provides a renewable energy source optimal configuration method for a virtual power plant, which aims to optimize the configuration condition of renewable energy sources, reduce the influence of renewable energy source grid connection on a power grid, improve the economical efficiency of virtual power plant operation and better promote the development of the virtual power plant.
As shown in fig. 1 and 2, the method of the present invention specifically includes the following steps:
and S1, establishing a virtual power plant electric energy output model according to the virtual power plant electric energy output form. According to the method, firstly, the electric energy output form of the virtual power plant needs to be determined according to the specific situation of the virtual power plant, and then different output models are constructed according to different output forms, wherein the electric energy output form of the virtual power plant comprises fan power generation output, photovoltaic power generation output, gas turbine power generation output and energy storage battery power generation output.
When the electric energy output form is the fan power generation output, the fan power generation output adopts Weibull probability distribution as a calculation reference, and the probability density model is as follows:
v represents the natural wind speed of the area where the virtual power plant is located at the current moment, λ represents the shape parameter of Weibull distribution, k represents the scale parameter of Weibull distribution, and the values of λ and k are related to the local wind condition and need to be taken according to the actual condition.
The electric energy output model of the fan power generation is as follows:
wherein, PwnIndicating the output power, v, of the wind turbineciIndicating wind cut-in speed, v, of the fancoIndicating fan cut-out wind speed, vrIndicating rated wind speed, P, of the fanWRRepresenting windAnd (5) rated power of the motor set.
When the electric energy output form is photovoltaic power generation output, the photovoltaic power generation illumination intensity probability density model is as follows:
wherein E (t) represents the illumination intensity of the area where the virtual power plant is located at the current moment, EmaxThe maximum illumination intensity of the area where the virtual power plant is located is represented, and beta and alpha respectively represent shape parameters under illumination.
Beta and alpha are determined by the average value and standard deviation of E (t), and the specific calculation formula is as follows:
where μ represents the average value of E (t), and σ represents the standard deviation of E (t).
The electric energy output model of photovoltaic power generation is as follows:
Ppn＝E(t)ηPVSPV (11)
wherein, PpnRepresenting the output power, η, of the photovoltaic power generationPVRepresents photovoltaic power generation efficiency, SPVIndicating the area of illumination.
When the electric energy output form is the generated output of the gas turbine, the electric energy output model generated by the gas turbine is as follows:
wherein, PTRepresenting the output power, V, of the gas turbineMT(t) gas volume, η, of the gas turbine trumpete(t) represents the power generation efficiency of the gas turbine at time t, RLHVT(t) represents the heat energy emitted by the combustion of the gas per unit volume, and Δ t represents the amount of change in time.
When the electric energy output form is the generated output of the energy storage battery, the electric energy output model generated by the energy storage battery needs to meet the following constraint conditions:
constraint 1: and (3) state constraint of the energy storage battery:
udisch(t)+upre(t)+uch(t)＝1 (13)
wherein u isdisch(t)、upre(t)、uch(t) are respectively the state variables of the energy storage battery, and when the energy storage battery is in the discharge state, udisch(t)＝1，upre(t)＝uch(t) ═ 0; when the energy storage battery is in a charging state, uch(t)＝1，udisch(t)＝upre(t) ═ 0; when the energy storage battery is in a dormant state, upre(t)＝1，udisch(t)＝uch(t)＝0。
Constraint 2: pulse factor constraint of energy storage battery:
0.8≤Npulse(t)≤1 (14)
Npulse(t)＝Npulse(t+1) (15)
wherein N ispulse(t) represents the pulse factor of the energy storage battery at time t.
Constraint 3: and (3) charge and discharge power constraint of the energy storage battery:
0≤Px(t)≤Npulse(t)·Prate (16)
-1.2Npulse(t)·Prate≤Px(t)≤0 (17)
wherein, PrateIndicating the rated output power, P, of the energy storage cellxAnd (t) represents the charging and discharging power of the energy storage battery at the time t.
And S2, establishing a virtual power plant optimization objective function based on the virtual power plant economic benefit maximization. When a renewable distributed power source, gas turbine power, energy storage battery power and interruptible load are used as resources for regulation and control, the distributed renewable energy sources are used for power generation as far as possible on the premise of ensuring the safe and reliable operation of a power system, and the output random characteristics of wind energy, solar energy and the like are considered, so that the method establishes a virtual power plant optimization objective function on the basis of maximizing economic benefits, and the formula of the virtual power plant optimization objective function is as follows:
where f represents the output power of the virtual power plant, ρdRepresenting the selling price of the virtual power plant for supplying power to the user, PdnRepresenting the load of node n, CgnRepresenting the cost of power generation of the gas turbine, CenRepresents the charging and discharging cost of the energy storage battery, CcnRepresents the cutting cost of the interruptible load, EkRepresenting the total penalty cost of renewable energy power generation of the virtual power plant, EkIs the sum of the penalty costs of renewable energy power generation of N nodes of the virtual power plant, rhoERepresenting electricity prices, P, at the time of purchase of electricity from virtual power plantsSThe electric energy power purchased by the virtual power plant to the power distribution network is represented, and N is 1,2, …, and N is the total number of nodes of the virtual power plant.
In order to ensure the normal operation of the virtual power plant, the virtual power plant optimization objective function needs to satisfy the following constraints:
1) global power balance constraints for virtual power plants:
wherein, PgnRepresenting the output power of the gas turbine at node n, PpnRepresenting the output power of the photovoltaic generation at node n, PwnRepresenting the output power of the wind turbine at node n, PenRepresenting the discharge power, P, of the energy storage cell at node ncnRepresenting the amount of load shed on node n.
2) Line transmission power P of virtual power plantlAnd (3) constraint:
-Wl≤Pl≤Wl (21)
wherein, WlThe boundary value of the transmission power of the first line is represented, wherein L is 1, …, L, the virtual power plant has L lines in common, KlnIndicating that the injected power at node n corresponds to the sensitivity coefficient of the l-th line.
3) Output constraints of the distributed power supply:
0≤Pwn≤Pwn,max (22)
0≤Ppn≤Ppn,max (23)
0≤Pcn≤Pcn,max (24)
Pgn,min≤Pgn≤Pgn,max (25)
wherein, Pwn,maxIndicating the maximum output power, P, of the fanpn,maxRepresenting the maximum output power, P, of the photovoltaic unitcn,maxIndicating the maximum interruptible load on node n, Pgn,maxRepresenting the maximum output power, P, of the gas turbinegn,minIndicating the minimum output power, P, of the gas turbineen,d,maxRepresenting the maximum discharge power, P, of the energy storage cellen,ch,maxRepresenting the maximum charging power of the energy storage battery.
S3, establishing a renewable energy power generation penalty cost function of the virtual power plant, and simplifying the calculation of the renewable energy power generation penalty cost function through training an extreme learning machine.
Because the power generation output of the renewable energy source has stronger uncertainty, the resource waste of the renewable energy source can be caused when the dispatching power of a wind field or a photovoltaic power supply is lower than the maximum output, and when the dispatching power of the power supply is higher than the maximum output, the standby capacity of the system is required to be used for complementing, and in order to more reasonably dispatch the renewable energy source, the method introduces the power generation punishment cost of the renewable energy source.
The conventional renewable energy generation penalty cost function is:
wherein E isnRepresents the penalty cost of renewable energy generation on node n, anRepresenting the maximum value of the penalty cost of the renewable energy unit on the node n, beta is the confidence level, PnRepresenting the actual output power, P, of the renewable energy unit at node nn SRepresenting the planned output power of the renewable energy unit at node n, cnPenalty cost coefficient, rho (P), representing the unplanned output of the renewable energy source unit on the node nn) Representing the renewable energy output power probability density function at node n.
The calculation of the renewable energy power generation penalty cost function is complex, the calculated amount of the method can be increased, and the renewable energy optimal configuration efficiency can be reduced, so that the method introduces a computer learning algorithm to simplify the renewable energy power generation penalty cost function.
The extreme learning machine is a neural network, the network topology structure of the extreme learning machine is shown in fig. 3, and the extreme learning machine comprises an input layer, a hidden layer and an output layer, wherein the input of the extreme learning machine is the output power of the renewable energy source, and the output of the extreme learning machine is the punishment cost of the generation of the renewable energy source.
The extreme learning machine has N input neurons and N output neurons, wherein the N input neurons represent the output power (P) of the renewable energy unit on N nodes1,P2,…,Pi,…,PN)TAnd N output neurons represent power generation penalty costs (E) corresponding to the renewable energy source units on N nodes1,E2,…,En,…,EN)TOutput layer variable EnAnd an input layer PiThe functional relationship of (a) is as follows:
wherein, in order to easily distinguish the input layer variables from the output layer variables during the calculation process, in the formula (28)) In which subscript i, beta is introducedjnRepresents the connection weight vector, omega, between the hidden layer neuron No. j and the output neuron No. nijRepresents the connection weight vector, beta, between the i-th input neuron and the j-th hidden layer neuronjnAnd ωijCan be obtained by training an extreme learning machine, PiRepresenting the output power, theta, of the renewable energy unit at node ijThe threshold value of hidden layer neuron No. j is represented, i is 1,2, …, N, j is 1,2, …, H is the total number of hidden layer neurons, and G represents the activation function of hidden layer neurons.
The formula for G is as follows:
the method for simplifying the calculation of the penalty cost function of renewable energy power generation by training the extreme learning machine comprises the following steps:
1) given the output power (P) of a set of renewable energy units1,P2,…,Pn,…PN)TCalculating (P) according to the penalty cost function of renewable energy power generation1,P2,…,Pn,…PN)TCorresponding renewable energy generation penalty cost (E)1,E2,…,En,…EN)T。
2) And (3) repeating the step 1), obtaining the output power of a plurality of groups of renewable energy source units and corresponding penalty cost, and forming a training sample of the extreme learning machine.
3) Taking the output power of the renewable energy source unit in the step 2) as the input of the extreme learning machine, taking the corresponding penalty cost as the output of the extreme learning machine, training the extreme learning machine, and according to the output layer variable EnAnd an input layer PwiThe function relation formula of the extreme learning machine calculates the connection weight vector of the extreme learning machine to complete the training of the extreme learning machine.
4) And calculating the punishment cost of the renewable energy power generation by using the trained extreme learning machine. The trained calculation learning machine can directly and automatically obtain the power generation penalty cost of the renewable energy source according to the input output power of the renewable energy source unit, the calculation accuracy is high, the calculation amount is smaller and the calculation speed is higher compared with the calculation process of the formula (27), and the calculation time of a complex penalty cost function is saved.
The method obtains the power generation penalty cost of the renewable energy sources on each node through the extreme learning machine, and then sums to obtain the total penalty cost E of the renewable energy sources of the virtual power plantkI.e. by
Will EkThe value of (2) is substituted into a virtual power plant optimization objective function and can be used for calculating an optimization objective function value.
S4, solving the virtual power plant optimization objective function by using a genetic algorithm to obtain a virtual power plant renewable energy source optimization configuration result, and specifically comprising the following steps:
s41, setting the individual length to be N, representing N line nodes of the virtual power plant, wherein the gene of each node is a four-dimensional row vector and respectively representing the wind power, the photovoltaic power, the gas turbine power and the stored energy charge and discharge power of the current node. Each individual contains n data representing a renewable energy configuration scheme for the virtual power plant. And (4) taking the virtual power plant optimization objective function in the step S2 as a fitness function of the genetic algorithm to judge the advantages and disadvantages of individuals, and setting the maximum iteration times of the genetic algorithm to interrupt iteration.
S42, manually setting the number of population individuals according to actual conditions, giving random values to all individuals in the population, generating an initial population, and initializing the number of iterations, wherein the number of the initial iterations is 0.
S43, calculating the fitness of all individuals in the current population according to the virtual power plant optimization objective function, wherein the fitness is the individual optimization objective function value.
And S44, selecting, crossing and mutating the current population, updating the population, and automatically increasing the iteration number by 1.
S45, judging whether the iteration number reaches the maximum iteration number, if yes, carrying out the step S46, and if not, carrying out the step S43.
S46, calculating the fitness of all individuals of the current population according to the virtual power plant optimization objective function to obtain an individual with the maximum fitness (namely the individual with the maximum optimization objective function value), wherein the individual is the optimal solution of the renewable energy configuration of the virtual power plant.
According to the method, a virtual power plant electric energy output model and a virtual power plant optimization objective function are established according to the electric energy output characteristics of the virtual power plant, the optimization objective function is solved by adopting a genetic algorithm, the virtual power plant renewable energy source optimization configuration data is obtained, renewable energy sources can be managed in a centralized manner through continuous optimization of the virtual power plant, efficient and reliable application of the renewable energy sources is realized, the economical efficiency of the operation of the virtual power plant is increased, the influence of the grid connection of the renewable energy sources on a power grid is reduced, and meanwhile, a reference is provided for the subsequent configuration development aiming at the virtual power plant.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (9)
1. A virtual power plant renewable energy source optimal configuration method is characterized by comprising the following steps:
s1, establishing a virtual power plant electric energy output model according to the virtual power plant electric energy output form;
s2, establishing a virtual power plant optimization objective function based on the virtual power plant economic benefit maximization;
s3, establishing a renewable energy power generation punishment cost function of the virtual power plant, and simplifying the calculation of the renewable energy power generation punishment cost function through training an extreme learning machine;
and S4, solving the virtual power plant optimization objective function by using a genetic algorithm to obtain the virtual power plant renewable energy source optimization configuration result.
2. The method of claim 1, wherein the virtual power plant electric energy output form comprises a fan power generation output, a photovoltaic power generation output, a gas turbine power generation output and an energy storage battery power generation output.
3. The method for optimizing configuration of renewable energy sources of a virtual power plant according to claim 1, wherein the formula of the optimization objective function of the virtual power plant is as follows:
where f represents the output power of the virtual power plant, ρdRepresenting the selling price of the virtual power plant for supplying power to the user, PdnRepresenting the load of node n, CgnRepresenting the cost of power generation of the gas turbine, CenRepresents the charging and discharging cost of the energy storage battery, CcnRepresents the cutting cost of the interruptible load, EkRepresenting the total penalty cost, rho, of the renewable energy power generation of the virtual power plantERepresenting electricity prices, P, at the time of purchase of electricity from virtual power plantsSThe electric energy power purchased by the virtual power plant to the power distribution network is represented, and N is 1,2, …, and N is the total number of nodes of the virtual power plant.
4. The method for optimizing the renewable energy resources of a virtual power plant according to claim 3, wherein P isSThe following formula is satisfied:
wherein, PgnRepresenting the output power of the gas turbine at node n, PpnRepresenting the output power of the photovoltaic generation at node n, PwnRepresenting the output power of the wind turbine at node n, PenRepresenting the discharge power, P, of the energy storage cell at node ncnRepresenting the amount of load shed on node n.
5. A virtual device according to claim 4The renewable energy source optimal configuration method of the simulated power plant is characterized in that the line transmission power P of the virtual power plantlThe formula of (1) is as follows:
Plthe following constraints are satisfied:
-Wl≤Pl≤Wl
wherein, WlThe boundary value of the transmission power of the first line is represented, wherein L is 1, …, L, the virtual power plant has L lines in common, KlnIndicating that the injected power at node n corresponds to the sensitivity coefficient of the l-th line.
6. The method for optimally configuring renewable energy sources of a virtual power plant according to claim 1, wherein the penalty cost function for generating renewable energy sources is:
wherein E isnRepresents the penalty cost of renewable energy generation on node n, anRepresenting the maximum value of the penalty cost of the renewable energy unit on the node n, beta is the confidence level, PnRepresenting the actual output power of the renewable energy unit on node n,
representing the planned output power of the renewable energy unit at node n, cnPenalty cost coefficient, rho (P), representing the unplanned output of the renewable energy source unit on the node nn) Representing the renewable energy output power probability density function at node n.
7. The method for optimizing the renewable energy resources of the virtual power plant according to claim 6, wherein the extreme learning machine has N input neurons andn output neurons, wherein N input neurons represent the output power (P) of the renewable energy resource unit on N nodes1,P2,…,Pi,…,PN)TAnd N output neurons represent power generation penalty costs (E) corresponding to the renewable energy source units on N nodes1,E2,…,En,…,EN)TOutput layer variable EnAnd an input layer PiThe functional relationship of (a) is as follows:
wherein, betajnRepresents the connection weight vector, omega, between the hidden layer neuron No. j and the output neuron No. nijRepresents the connection weight vector between the i-th input neuron and the j-th hidden neuron, PiRepresenting the output power, theta, of the renewable energy unit at node ijThe threshold value of hidden layer neuron No. j is represented, i is 1,2, …, N, j is 1,2, …, H is the total number of hidden layer neurons, and G represents the activation function of hidden layer neurons.
8. The method for optimizing the configuration of the renewable energy sources of the virtual power plant according to claim 7, wherein the method for simplifying the calculation of the penalty cost function for generating the renewable energy sources by training an extreme learning machine comprises the following steps:
1) given the output power (P) of a set of renewable energy units1,P2,…,Pn,…PN)TCalculating (P) according to the penalty cost function of renewable energy power generation1,P2,…,Pn,…PN)TCorresponding renewable energy generation penalty cost (E)1,E2,…,En,…EN)T；
2) Repeating the step 1), obtaining the output power of a plurality of groups of renewable energy source units and corresponding penalty cost, and forming a training sample of the extreme learning machine;
3) outputting power of the renewable energy source unit in the step 2)As the input of the extreme learning machine, the corresponding penalty cost is used as the output of the extreme learning machine, the extreme learning machine is trained, and the output layer variable E is used for outputtingnAnd an input layer PwiCalculating a connection weight vector of the extreme learning machine by using the function relation formula to finish training of the extreme learning machine;
4) and calculating the punishment cost of the renewable energy power generation by using the trained extreme learning machine.
9. The optimal configuration method for renewable energy sources of a virtual power plant according to claim 1, wherein the step S4 specifically comprises the following steps:
s41, setting the length of each individual to be N, wherein each individual represents a renewable energy source configuration scheme of the virtual power plant, taking the virtual power plant optimization objective function in the step S2 as a fitness function of the genetic algorithm, and setting the maximum iteration times of the genetic algorithm;
s42, manually setting the number of population individuals, giving random values to all individuals in the population, generating an initial population, and initializing iteration times;
s43, calculating the fitness of all individuals in the current population according to the virtual power plant optimization objective function;
s44, selecting, crossing and mutating the current population, updating the population, and automatically increasing the iteration times by 1;
s45, judging whether the iteration number reaches the maximum iteration number, if so, performing S46, otherwise, performing S43;
and S46, calculating the fitness of all individuals of the current population according to the virtual power plant optimization objective function to obtain an individual with the maximum fitness, wherein the individual is the optimal solution of the renewable energy source configuration of the virtual power plant.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010685434.5A CN111967646A (en) | 2020-07-16 | 2020-07-16 | Renewable energy source optimal configuration method for virtual power plant |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010685434.5A CN111967646A (en) | 2020-07-16 | 2020-07-16 | Renewable energy source optimal configuration method for virtual power plant |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111967646A true CN111967646A (en) | 2020-11-20 |
Family
ID=73360676
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010685434.5A Withdrawn CN111967646A (en) | 2020-07-16 | 2020-07-16 | Renewable energy source optimal configuration method for virtual power plant |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111967646A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113269346A (en) * | 2021-03-29 | 2021-08-17 | 广西电网有限责任公司电力科学研究院 | Virtual power plant interval optimization method and system considering flexible load participation |
| CN117154731A (en) * | 2023-08-08 | 2023-12-01 | 淮阴工学院 | Virtual power plant based on block chain technology |
-
2020
- 2020-07-16 CN CN202010685434.5A patent/CN111967646A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113269346A (en) * | 2021-03-29 | 2021-08-17 | 广西电网有限责任公司电力科学研究院 | Virtual power plant interval optimization method and system considering flexible load participation |
| CN117154731A (en) * | 2023-08-08 | 2023-12-01 | 淮阴工学院 | Virtual power plant based on block chain technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2023274425A1 (en) | Multi-energy capacity optimization configuration method for wind-solar-water-fire storage system | |
| CN105071389B (en) | The alternating current-direct current mixing micro-capacitance sensor optimizing operation method and device of meter and source net load interaction | |
| Zhang et al. | A hybrid particle swarm optimization with small population size to solve the optimal short-term hydro-thermal unit commitment problem | |
| CN111934360B (en) | Virtual power plant-energy storage system energy collaborative optimization regulation and control method based on model predictive control | |
| CN108206543A (en) | A kind of energy source router and its running optimizatin method based on energy cascade utilization | |
| CN112508221A (en) | Day-ahead scheduling decision method considering source-load uncertainty under limited energy storage | |
| CN116667325B (en) | Micro-grid-connected operation optimization scheduling method based on improved cuckoo algorithm | |
| CN116061742B (en) | Charging control method and system for electric automobile in time-of-use electricity price photovoltaic park | |
| CN112836849A (en) | Virtual power plant scheduling method considering wind power uncertainty | |
| CN114519459A (en) | Scene analysis and hybrid energy storage based optimal scheduling method for thermoelectric combined system | |
| CN113437752A (en) | Operation control method for comprehensive energy system containing hybrid energy storage | |
| CN111967646A (en) | Renewable energy source optimal configuration method for virtual power plant | |
| CN117578409A (en) | Multi-energy complementary optimization scheduling method and system in power market environment | |
| CN112101632A (en) | Building load optimal scheduling method based on distributed estimation algorithm | |
| CN108512238A (en) | Smart home two benches Optimization Scheduling based on Demand Side Response | |
| CN112510690B (en) | Optimal scheduling method and system considering wind-fire-storage combination and demand response reward and punishment | |
| CN111525556B (en) | Multi-target optimal power flow calculation method considering wind power confidence risk | |
| CN112883630A (en) | Day-ahead optimized economic dispatching method for multi-microgrid system for wind power consumption | |
| CN111342456A (en) | Method and system for modeling energy system of transformer area | |
| CN116436085A (en) | Micro-energy network group hierarchical optimization control method and system based on scene construction | |
| CN116562423A (en) | Deep reinforcement learning-based electric-thermal coupling new energy system energy management method | |
| CN115796533A (en) | Virtual power plant double-layer optimization scheduling method and device considering clean energy consumption | |
| CN113554219B (en) | Method and device for planning shared energy storage capacity of renewable energy power station | |
| CN114465226A (en) | Method for establishing multi-level standby acquisition joint optimization model of power system | |
| CN114626180A (en) | Power distribution network centralized energy storage optimal configuration method and device |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20201120 |