CN116345505A - Flexible power supply and hydrogen production power system with predictive energy supply - Google Patents
Flexible power supply and hydrogen production power system with predictive energy supply Download PDFInfo
- Publication number
- CN116345505A CN116345505A CN202310346491.4A CN202310346491A CN116345505A CN 116345505 A CN116345505 A CN 116345505A CN 202310346491 A CN202310346491 A CN 202310346491A CN 116345505 A CN116345505 A CN 116345505A
- Authority
- CN
- China
- Prior art keywords
- power
- hydrogen production
- load
- energy
- hydrogen
- 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.)
- Granted
Links
- 229910052739 hydrogen Inorganic materials 0.000 title claims abstract description 110
- 239000001257 hydrogen Substances 0.000 title claims abstract description 110
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 title claims abstract description 108
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 65
- 238000003860 storage Methods 0.000 claims abstract description 30
- 238000004146 energy storage Methods 0.000 claims abstract description 29
- 239000000446 fuel Substances 0.000 claims abstract description 16
- 238000004364 calculation method Methods 0.000 claims abstract description 7
- 238000005457 optimization Methods 0.000 claims abstract description 5
- 230000000295 complement effect Effects 0.000 claims abstract description 4
- 230000002431 foraging effect Effects 0.000 claims description 18
- 241000287127 Passeridae Species 0.000 claims description 16
- 238000006243 chemical reaction Methods 0.000 claims description 13
- 239000011159 matrix material Substances 0.000 claims description 13
- 238000000034 method Methods 0.000 claims description 12
- 238000009826 distribution Methods 0.000 claims description 10
- 238000011161 development Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 3
- 230000019637 foraging behavior Effects 0.000 claims description 3
- 230000007246 mechanism Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000012163 sequencing technique Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000002028 premature Effects 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000029087 digestion Effects 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000011065 in-situ storage Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- 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
- H02J3/28—Arrangements for balancing of the load in a network by storage of energy
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- 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
- G06Q10/04—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
- 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
- H02J15/00—Systems for storing electric energy
- H02J15/008—Systems for storing electric energy using hydrogen as energy vector
-
- 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
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- 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
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- 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
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/22—The renewable source being solar energy
- H02J2300/24—The renewable source being solar energy of photovoltaic origin
- H02J2300/26—The renewable source being solar energy of photovoltaic origin involving maximum power point tracking control for photovoltaic sources
-
- 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
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/30—The power source being a fuel cell
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Economics (AREA)
- Power Engineering (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Pure & Applied Mathematics (AREA)
- Operations Research (AREA)
- Marketing (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Tourism & Hospitality (AREA)
- Computational Mathematics (AREA)
- Software Systems (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Quality & Reliability (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
Abstract
The invention discloses a flexible power supply and hydrogen production power system with predictive energy supply, which comprises a load prediction module, an energy source complementation module, a hydrogen production and storage module, an energy storage module and a load end. The load prediction module outputs load data to a regulation and control center through a prediction model; the energy complementary module outputs photovoltaic maximum power from a solar panel through an MPPT controller and purchase power required by an AC/DC converter from a power grid; the hydrogen production and storage module generates hydrogen through a DC/AC converter and an electrolytic tank; the energy storage module stores redundant electric energy and redundant hydrogen under load energy supply and hydrogen production and hydrogen storage to the fuel cell. The invention can predict the electric energy required by the load in advance, the channels of the output ends of the input ends are matched through optimization calculation of the regulation center, full power supply is ensured, the energy storage and hydrogen production are utilized to eliminate abundant electric energy, the working system of the optimal energy storage module and the hydrogen production and storage module for the target load is optimized and iterated through an algorithm, the intervention in the power grid peak time is reduced, and the purchase cost of the power grid is reduced.
Description
Technical Field
The invention relates to the technical field of hydrogen energy storage and power grid peak output reduction, in particular to a flexible power supply and hydrogen production power system with predictive energy supply.
Background
As a new energy, the tidal performance of the photovoltaic is very obvious, and under the normal condition, the illumination enrichment area of China is far away from the power load area, supply and demand mismatch often occurs, the safety and the stability of a power grid are not facilitated, and certain difficulty exists in grid connection. Meanwhile, the problem of electric quantity consumption can be caused by the fluctuation of the generated energy, although the average light rejection rate of the photovoltaic power generation in China is about 2% in 2020 in recent years, the problem of high light rejection rate still exists about 4.8% in northwest regions where the electric quantity is difficult to consume, and at present, the national power grid encourages the addition of matched energy storage facilities in a photovoltaic concentration region or digestion in situ. The hydrogen energy is an ideal energy interconnection medium, namely, the energy produced by the photovoltaic generator set is used for producing hydrogen by electrolyzing water on site, so that the energy storage and peak regulation can be realized at the same time, the waste caused by mismatch of supply and demand is reduced, the elasticity of a photoelectric system is improved, and the two problems of storage and grid connection are solved. Meanwhile, the cooperation of hydrogen production and photovoltaics is also beneficial to the direct acquisition of low-cost electric energy by hydrogen production factories, and is also an ideal win-win mode for the hydrogen production industry with electricity charge as core cost. In the aspect of industrial application, industrial application and transportation are two application scenes of the most clear hydrogen energy. Aiming at the two current high energy consumption industries, the hydrogen energy is expected to replace the traditional energy, the transformation of high emission capacity is assisted, and the carbon emission pressure is lightened.
The hydrogen energy is not primary energy, and belongs to secondary energy like electric energy, and is converted from primary energy. This conversion process is energy consuming and at the same time necessitates a portion of the energy to be "spent", so energy conversion efficiency must be addressed. Energy conversion is costly and therefore economic efficiency must be addressed. If the conventional device relies on the photovoltaic alone to realize energy storage through hydrogen energy, the premise is that the conversion efficiency and the economic benefit of the photo-hydrogen storage are larger than those of the photo-hydrogen storage. This is certainly a false proposition in reality. For example, once power is taken from a power grid, the energy conversion efficiency of two links is about 95% through AC-DC conversion of a charger and charging-discharging of a battery on the vehicle, and the electric energy sent to a motor on the electric vehicle is nearly 0.9 degrees, namely, the energy conversion efficiency of light-battery-energy storage is about 90%, which clearly greatly increases the cost waste.
Disclosure of Invention
The invention aims to: aiming at the problems in the prior art, the invention provides a flexible power supply and hydrogen production power system with predictive energy supply, and provides a method for predicting load through an algorithm, which calculates the corresponding relation between power and time, predicts the electric energy required by the load in advance and is convenient to regulate and control; the channels which are matched with the output ends of the input ends are calculated through the regulation and control center, full power supply is guaranteed, energy storage and hydrogen production are utilized to eliminate abundant electric energy, the working system of the optimal energy storage module and the hydrogen production and storage module on the target load is optimized through an algorithm, and the intervention beneficial effect when the power grid peak is reduced is achieved.
The technical scheme is as follows: the invention provides a flexible power supply and hydrogen production power system with predictive energy supply, which comprises a load prediction module, an energy complementation module, a hydrogen production and storage module, an energy storage module and a load end, wherein the load prediction module is used for predicting the energy of the flexible power supply and hydrogen production;
the load prediction module comprises load data obtained through a load end and a prediction model; the energy complementary module comprises a solar panel, a DC/DC converter, an MPPT controller, a power grid and an AC/DC converter; the energy storage module comprises a storage battery pack and a fuel cell; the hydrogen production and storage module comprises a DC/AC converter, an electrolytic tank and a hydrogen storage tank;
the solar panel is connected with the MPPT controller through a DC/DC converter and inputs the MPPT controller into a regulation and control center in a direct current mode; the power grid outputs electric energy by using an AC/DC converter, is connected with the regulation and control center through an output end, and supplies the converted electric energy to a load end for consumption through the DC/AC converter; load data generated after the load end operation is finished are connected with the input end of the prediction model; the prediction model is an improved tuna algorithm optimized ELM prediction model, namely an ITSO-ELM prediction model, the load data is utilized to predict the load power of the electric energy required by the load end at the next moment, and the prediction data is input into the regulation and control center;
on the premise that the electric energy generated by the solar panel and the power grid meets the load end load requirement, the regulation and control center respectively transmits the residual electric energy to the energy storage module and the electrolytic tank; the output end of the electrolytic tank is connected with a hydrogen tank, and the produced hydrogen is stored in the hydrogen tank; the output end of the hydrogen tank is connected with the hydrogen fuel cell, and the surplus output stored in the hydrogen tank is converted into the energy of the hydrogen fuel cell; the output end of the hydrogen fuel cell is connected with the regulation and control center, and the electric energy of the hydrogen fuel cell is input into the regulation and control center; the butterfly-sparrow mixed optimization algorithm, namely the BOA-SSA comprehensive regulation algorithm, is arranged in the regulation center, and optimal hydrogen production power and optimal grid intervention power are output in an optimized iteration mode by using the BOA-SSA comprehensive regulation algorithm according to the power output by the photovoltaic, the power purchased by the power grid and the predicted load power at the next moment and with the maximum hydrogen production power and the minimum grid intervention power as objective functions; thereby confirming the optimal point of the mutual conversion of the charge capacity value of the energy storage module and the electric quantity of the hydrogen production and storage module.
Further, the implementation process of the ITSO-ELM prediction model is as follows:
step 1: determining an input x of the ELM predictive model, the input being load data x, determining an output h of a j-th hidden layer node j (x) The output is the electric energy required by the predicted load, and the calculation formula is as follows:
h j (x)=g(w i ,b i ,x)=g(w i ·x+b i )
in the formula g(wi ,b i X) represents a nonlinear activation function with certain approximation capability, w i Weight, b i Is a deviation value;
step 2: determining the output H (x) of the hidden layer of the ELM prediction model, wherein the calculation formula is as follows:
H(x)=[h 1 (x),h 2 (x),…,h L (x)]
step 3: when a signal enters an output layer through a hidden layer, the output of the ELM prediction model is recorded as T, and the expression formula is as follows:
in the formula βj Representing the output weight between the j hidden layer node and the output layer;
step 4: solving the output layer weight beta, searching the minimum training error by a least square method solving equation, and solving an objective function as follows:
wherein: xi represents training error, H + Representing the generalized inverse matrix of H, and beta represents the least squares solution sought;
step 5: and optimizing the weight and the deviation value in the ELM model by adopting an ITSO algorithm.
Further, the optimization of the weights and the deviation values in the ELM model by adopting the ITSO algorithm specifically comprises the following steps:
step 5.1: setting the maximum iteration times, the upper limit and the lower limit of the algorithm, setting the search space of the algorithm according to the upper limit and the lower limit, uniformly and randomly generating initial populations in the search space, wherein each population has a group of corresponding weights and deviation values, and the initialization formula is as follows:
ub and lb are the upper and lower limits of the algorithm;
step 5.2: the algorithm simulates two cooperative foraging behaviors of the tuna, namely spiral foraging and parabolic foraging, and when the spiral foraging is executed, the expression of the positions of the weight and the deviation value corresponding to the population is as follows:
when (when)When the weight corresponding to the population and the position of the deviation value are expressed as follows:
when (when)The positions of the weights and the bias values corresponding to the population are expressed as follows:
wherein: t represents the current iteration number, t max Represents the maximum number of iterations, N represents the population number,represents the position of the ith individual after the t+1st iteration,/for> and />Respectively represent the current optimal individual and the random individual, alpha 1 and α2 A weight coefficient indicating a tendency of controlling the movement of the individual to the optimal individual and the previous individual, and β indicating a development vector associated with the optimal individual or the random individual;
step 5.3: when parabolic foraging is performed, the positions of the weights and bias values corresponding to the population can be expressed as:
wherein TF is a random number of-1 or 1, which represents the development direction of the population; p is a key parameter adaptively changing along with the iteration times, and represents the development amplitude of the population;
step 5.4: after the population completes spiral foraging and parabolic foraging, a Gaussian variation-optimal domain mechanism is introduced to disturb the population position, the fitness of individuals before and after disturbance is compared, excellent individuals are reserved, and an improved position updating formula is shown as follows:
in the formula ,Fave Average fitness for the current individual; gaussian is a Gaussian operator;representing new individuals after disturbance, when the fitness value of the ith tuna is better than F ave In this case, the gaussian variation was performed.
Further, the BOA-SSA comprehensive regulation algorithm is realized as follows:
21 Initializing sparrow groups, wherein each sparrow group has a corresponding maximum hydrogen production power, a minimum power grid intervention power group value, and input power P output by photovoltaic v Grid acquisition power P e Predicted load power P n The objective function is as follows:
maxP H =P v +P e -P n -P loss
wherein ,PH Represents hydrogen production power, P e-min Representing minimized power of grid intervention, P loss Power lost during transmission;
22 The initial population is carried into an objective function for evaluation, the population is ranked, the maximum hydrogen production power and the minimum power grid intervention power corresponding to the population with the front ranking degree are used as discoverers, and the populations with the rear ranking degree are used as followers;
23 Updating the finder location, the formula is as follows:
wherein i, j represents the position information of the ith sparrow in the j-th dimension, iter max Expressed as the maximum number of iterations, R 2 The method is an alarm value, RT is a safety threshold, Q is a normal distribution random number, L is a 1Xd matrix, and elements of the matrix are all 1;
24 Updating the follower position according to the finder position, the formula is as follows;
and x is worst Representing the current global worst position, x p Representing the optimal position occupied by the current finder, representing a 1xd matrix, each element of which is randomly assigned 1 or-1, A being represented as a 1xd matrix, A + =A T (AA T ) -1 ;
25 Randomly selecting reconnaissance early warning with 20% of the proportion and updating the position of the reconnaissance early warning, wherein the formula is as follows;
wherein ,and for the current global optimal position, beta is taken as a step control parameter, and is subjected to normal distribution random numbers with a mean value of 0 and a variance of 1. f (f) i Representing the fitness value of the current sparrow individual, f g Representing the current global best fitness value, f w Representing the current global worst fitness value, epsilon being a constant, acting to avoidZero value appears in the denominator, K is a random number, and K represents the direction of sparrow movement and is a step control parameter;
26 If not, returning to the step 23), otherwise, outputting the optimal maximum hydrogen production power and the minimum power grid intervention power group value.
Further, the BOA factor correction finder location is introduced in step 23):
The beneficial effects are that:
1. the invention comprehensively considers the power grid intervention problem in the hydrogen production and storage link, further considers the problem that energy conversion of two links occurs due to power grid intervention in the hydrogen storage link, and ensures that the regulation and control center module is maximally maintained in the hydrogen production and storage link under the condition of full load energy supply, minimizes the power grid intervention, and reduces the purchase cost of the power grid.
2. The invention innovatively combines predictive energy supply and hydrogen production, calculates the optimal point of the mutual conversion of the charge capacity value of the energy storage module and the electric quantity of the hydrogen production and storage module by utilizing the electric energy value and the regulation and control center required by the predictive load at every moment in the future, and utilizes the energy storage and the hydrogen production to digest abundant electric energy, thereby greatly improving the utilization rate of energy sources.
3. The BOA-SSA algorithm provided by the invention not only improves the defect of lack of information exchange among individuals in the original algorithm, but also expands the search space to a certain extent and improves the global optimizing capability of the algorithm; and the improved ITSO is adopted to optimize the parameter set of the ELM model, so that the model can be prevented from sinking into local optimum in the training process. Compared with other optimized ELM models, the ITSO-ELM has better prediction effect.
Drawings
FIG. 1 is a schematic diagram of the structure of the present invention;
FIG. 2 is a flow chart of an ITSO-ELM prediction model proposed by the present invention;
FIG. 3 is a flow chart of the BOA-SSA algorithm according to the present invention;
FIG. 4 is a graph of hydrogen production versus two types of equipment;
fig. 5 is a graph comparing grid acquisition costs for two devices.
Detailed Description
The invention is described in further detail below with reference to the accompanying drawings.
As shown in figure 1, the invention provides a flexible power supply and hydrogen production power system with predictive energy supply, which comprises a load prediction module, an energy complementation module, a hydrogen production and storage module, an energy storage module and a load end.
The load prediction module comprises load data obtained by a load end and a prediction model. The energy complementary module comprises a solar panel, a DC/DC converter, an MPPT controller, a power grid and an AC/DC converter; the energy storage module comprises a storage battery pack and a fuel cell; the hydrogen production and storage module comprises a DC/AC converter, an electrolytic tank and a hydrogen storage tank.
The solar panel is connected with the MPPT controller through a DC/DC converter and is input into the regulation and control center in a direct current mode; the power grid outputs electric energy by using an AC/DC converter, is connected with the regulation and control center through an output end, and supplies the converted electric energy to a load end for consumption; load data generated after the operation of the load end is finished are connected with the input end of the prediction model; the prediction model is an improved tuna algorithm optimized ELM prediction model, namely an ITSO-ELM prediction model, the load data is utilized to predict the load power of the electric energy required by the load end at the next moment, and the prediction data is input into the regulation and control center.
And on the premise that the electric energy generated by the solar panel and the power grid meets the load demand of the load end, the regulation and control center respectively transmits the residual electric energy to the energy storage module and the electrolytic tank. The output end of the electrolytic tank is connected with a hydrogen tank, and the produced hydrogen is stored in the hydrogen tank; the output end of the hydrogen tank is connected with the hydrogen fuel cell, and the surplus output stored in the hydrogen tank is converted into the energy of the hydrogen fuel cell; the output end of the hydrogen fuel cell is connected with the regulation center, and the electric energy of the hydrogen fuel cell is input into the regulation center.
The butterfly-sparrow mixed optimization algorithm, namely the BOA-SSA comprehensive regulation algorithm, is arranged in the regulation center, and optimal hydrogen production power and optimal grid intervention power are optimized and output in an iterative mode by using the BOA-SSA comprehensive regulation algorithm according to the power output by the photovoltaic, the power purchased by the grid and the predicted load power at the next moment and by taking the maximum hydrogen production power and the minimum grid intervention power as objective functions; thereby confirming the optimal point of the mutual conversion of the charge capacity value of the energy storage module and the electric quantity of the hydrogen production and storage module. The energy storage and hydrogen production are utilized to eliminate surplus electric energy, meanwhile, the relation between the charge capacity value of the energy storage module and the electric quantity of the hydrogen production module is calculated through an algorithm, and the algorithm is utilized to optimize and iterate the working system of the optimal energy storage module and the hydrogen production and storage module on the target load, so that the intervention beneficial effect in the process of reducing the power grid peak is achieved.
As shown in fig. 2, the flexible power supply and hydrogen production power system with predictive energy supply provided by the invention has the following implementation process of an ITSO-ELM predictive model:
step one: determining an input x of the ELM predictive model, the input being load data x, determining an output h of a j-th hidden layer node j (x) The output is the electric energy required by the predicted load, and the calculation formula is as follows:
h j (x)=g(w i ,b i ,x)=g(w i ·x+b i )
in the formula g(wi ,b i X) represents a nonlinear activation function with certain approximation capability, w i Weight, b i Is a deviation value;
step two: determining the output H (x) of the hidden layer of the EML prediction model, wherein the calculation formula is as follows:
H(x)=[h 1 (x),h 2 (x),…,h L (x)]
step three: when a signal enters an output layer through a hidden layer, the output of the ELM prediction model is recorded as T, and the expression formula is as follows:
in the formula βj Representing the output weight between the j hidden layer node and the output layer;
step four: solving the output layer weight beta, searching the minimum training error by a least square method solving equation, and solving an objective function as follows:
wherein: xi represents training error, H + Representing the generalized inverse matrix of H, and beta represents the least squares solution sought;
step five: and optimizing the weight and the deviation value in the ELM model by adopting an ITSO algorithm, wherein the specific steps of the ITSO algorithm are as follows:
step six: setting the maximum iteration times, the upper limit and the lower limit of the algorithm, setting the search space of the algorithm according to the upper limit and the lower limit, uniformly and randomly generating initial populations in the search space, wherein each population has a group of corresponding weights and deviation values, and the initialization formula is as follows:
step seven: the algorithm simulates two cooperative foraging behaviors of tuna, namely spiral foraging and parabolic foraging, and when spiral foraging is performed, the expression of the population position is as follows:
when (when)When the weight corresponding to the population and the position of the deviation value are expressed as follows:
when (when)The positions of the weights and the bias values corresponding to the population are expressed as follows:
wherein: t represents the current iteration number, t max Represents the maximum number of iterations, N represents the population number,represents the position of the ith individual after the t+1st iteration,/for> and />Respectively represent the current optimal individual and the random individual, alpha 1 and α2 A weight coefficient indicating a tendency of controlling the movement of an individual to an optimal individual and a preceding individual, and β indicating a development vector associated with the optimal individual or a random individual.
Step eight: when parabolic foraging is performed, the positions of the weights and bias values corresponding to the population can be expressed as:
wherein TF is a random number of-1 or 1, which represents the development direction of the population; p is a key parameter adaptively changing along with the iteration number, and represents the development amplitude of the population.
Step eight: in order to prevent the algorithm from being in premature, after the population finishes spiral foraging and parabolic foraging, a Gaussian variation-optimal field mechanism is introduced to disturb the population position, the fitness of individuals before and after disturbance is compared, excellent individuals are reserved, and an improved position updating formula is shown as follows:
in the formula ,Fave Average fitness for the current individual; gaussian is a Gaussian operator;representing the new individual after the perturbation. When the fitness value of the ith tuna is better than F ave In this case, the gaussian variation was performed.
As shown in fig. 3, the regulation indexes of the invention are that firstly, hydrogen production power is maximized, secondly, power grid intervention power is minimized, and the implementation process of the BOA-SSA comprehensive regulation algorithm is as follows:
step one: initializing sparrow groups, wherein each sparrow group has a group of corresponding maximum hydrogen production power, minimum power grid intervention power group value, and inputting power P output by photovoltaic v Grid acquisition power P e Predicted load power P n The objective function is as follows;
maxP H =P v +P e -P n -P loss
wherein PH Represents hydrogen production power, P e-min Representing minimized power of grid intervention, P loss Power lost during transmission.
Step two: and (3) carrying out evaluation on the initial population by taking the initial population into an objective function, sequencing the population, taking the maximum hydrogen production power and the minimum power grid intervention power group value corresponding to the population with the front sequencing degree as discoverers, and taking the population with the rear sequencing degree as followers.
Step three: updating the finder position, wherein the formula is as follows:
i, j represents the positional information of the ith sparrow in the j-th dimension. Ter (iter) max Expressed as the maximum number of iterations, Q is expressed as a normal distribution random number, L is expressed as a 1Xd matrix and its elements are all 1.
In the SSA algorithm before improvement in the step three, when R < ST, each dimension of the discoverer is becoming smaller and converged to 0, and when R is larger than or equal to ST, the discoverer randomly moves to the current position according to normal distribution. Therefore, the algorithm tends to converge to the 0 point and approach to the global optimal solution at the beginning of iteration, and premature convergence of the algorithm is easy to occur and falls into local optimal. The BOA factor correction finder location is introduced:
wherein r is a BOA factor, is a random number subject to normal distribution. After the BOA factor is introduced, the sparrow individuals can exchange information with the optimal individuals during each iteration, so that the information of the current optimal solution is fully utilized, and the defect of lack of information exchange among individuals in the original algorithm is overcome.
Step four: updating the follower position according to the finder position, wherein the formula is as follows;
and x is worst Representing the current global worst position, xp represents the optimal position occupied by the current finder, and represents a 1xd matrix, each element of which is randomly assigned a value of 1 or-1.
Step five: randomly selecting reconnaissance early warning and updating the position of the reconnaissance early warning according to the 20% duty ratio, wherein the formula is as follows;
wherein ,and for the current global optimal position, beta is taken as a step control parameter, and is subjected to normal distribution random numbers with a mean value of 0 and a variance of 1. K is a random number, f i Representing the fitness value of the current sparrow individual, f g Representing the current global best fitness value, f w The current global worst fitness value is represented, epsilon is a constant and acts to avoid zero values in the denominator. K represents the direction of sparrow movement and is the step control parameter.
Step six: and (23) judging whether the condition is met, otherwise, outputting the optimal maximum hydrogen production power and minimizing the intervention power group value of the power grid.
In the following, related experiments are performed on the invention, and a traditional system refers to a system which does not consider a prediction model, optimizes a hydrogen production and storage module without using a regulation and control center and does not consider the intervention degree of a power grid.
As shown in FIG. 4, the load prediction model is introduced, and predicted load data is used as input under the condition of meeting the load energy supply requirement, so that the energy storage hydrogen production is kept at the maximum output, and compared with the traditional system, the hydrogen production amount of the system provided by the invention is kept at 3.27-3.58kw per hour, which is obviously superior to the hydrogen production amount of the traditional system which is kept at 2.78-2.9kw per hour.
As shown in fig. 5, the proposed regulation center innovatively considers the condition of power grid intervention, so that the power grid avoids participating in the link of hydrogen storage and hydrogen production as much as possible, the conversion power of the power grid is reduced, the purchase of purchase power is reduced, the cost is further saved, compared with the traditional system, the conventional system does not consider the factor, the purchase cost of the power grid is 1.42 ten thousand yuan to 1.55 ten thousand yuan, and the cost is obviously superfluous from 0.88 ten thousand yuan to 1.12 ten thousand yuan.
The foregoing embodiments are merely illustrative of the technical concept and features of the present invention, and are intended to enable those skilled in the art to understand the present invention and to implement the same, not to limit the scope of the present invention. All equivalent changes or modifications made according to the spirit of the present invention should be included in the scope of the present invention.
Claims (5)
1. The flexible power supply and hydrogen production power system with the predictive energy supply is characterized by comprising a load prediction module, an energy complementation module, a hydrogen production and storage module, an energy storage module and a load end;
the load prediction module comprises load data obtained through a load end and a prediction model; the energy complementary module comprises a solar panel, a DC/DC converter, an MPPT controller, a power grid and an AC/DC converter; the energy storage module comprises a storage battery pack and a fuel cell; the hydrogen production and storage module comprises a DC/AC converter, an electrolytic tank and a hydrogen storage tank;
the solar panel is connected with the MPPT controller through a DC/DC converter and inputs the MPPT controller into a regulation and control center in a direct current mode; the power grid outputs electric energy by using an AC/DC converter, is connected with the regulation and control center through an output end, and supplies the converted electric energy to a load end for consumption through the DC/AC converter; load data generated after the load end operation is finished are connected with the input end of the prediction model; the prediction model is an improved tuna algorithm optimized ELM prediction model, namely an ITSO-ELM prediction model, the load data is utilized to predict the load power of the electric energy required by the load end at the next moment, and the prediction data is input into the regulation and control center;
on the premise that the electric energy generated by the solar panel and the power grid meets the load end load requirement, the regulation and control center respectively transmits the residual electric energy to the energy storage module and the electrolytic tank; the output end of the electrolytic tank is connected with a hydrogen tank, and the produced hydrogen is stored in the hydrogen tank; the output end of the hydrogen tank is connected with the hydrogen fuel cell, and the surplus output stored in the hydrogen tank is converted into the energy of the hydrogen fuel cell; the output end of the hydrogen fuel cell is connected with the regulation and control center, and the electric energy of the hydrogen fuel cell is input into the regulation and control center; the butterfly-sparrow mixed optimization algorithm, namely the BOA-SSA comprehensive regulation algorithm, is arranged in the regulation center, and optimal hydrogen production power and optimal grid intervention power are output in an optimized iteration mode by using the BOA-SSA comprehensive regulation algorithm according to the power output by the photovoltaic, the power purchased by the power grid and the predicted load power at the next moment and with the maximum hydrogen production power and the minimum grid intervention power as objective functions; thereby confirming the optimal point of the mutual conversion of the charge capacity value of the energy storage module and the electric quantity of the hydrogen production and storage module.
2. The flexible power supply and hydrogen production system with predictive energy supply of claim 1, wherein the ITSO-ELM predictive model is implemented as follows:
step 1: determining an input x of the ELM predictive model, the input being load data x, determining an output h of a j-th hidden layer node j (x) The output is the electric energy required by the predicted load, and the calculation formula is as follows:
h j (x)=g(w i ,b i ,x)=g(w i ·x+b i )
in the formula g(wi ,b i X) represents a nonlinear activation function with certain approximation capability, w i Weight, b i Is a deviation value;
step 2: determining the output H (x) of the hidden layer of the ELM prediction model, wherein the calculation formula is as follows:
H(x)=[h 1 (x),h 2 (x),…,h L (x)]
step 3: when a signal enters an output layer through a hidden layer, the output of the ELM prediction model is recorded as T, and the expression formula is as follows:
in the formula βj Representing the output weight between the j hidden layer node and the output layer;
step 4: solving the output layer weight beta, searching the minimum training error by a least square method solving equation, and solving an objective function as follows:
wherein: xi represents training error, H + Representing the generalized inverse matrix of H, and beta represents the least squares solution sought;
step 5: and optimizing the weight and the deviation value in the ELM model by adopting an ITSO algorithm.
3. The flexible power supply and hydrogen production system with predictive power supply of claim 2, wherein optimizing weights and bias values in ELM model using ITSO algorithm comprises the steps of:
step 5.1: setting the maximum iteration times, the upper limit and the lower limit of the algorithm, setting the search space of the algorithm according to the upper limit and the lower limit, uniformly and randomly generating initial populations in the search space, wherein each population has a group of corresponding weights and deviation values, and the initialization formula is as follows:
ub and lb are the upper and lower limits of the algorithm;
step 5.2: the algorithm simulates two cooperative foraging behaviors of the tuna, namely spiral foraging and parabolic foraging, and when the spiral foraging is executed, the expression of the positions of the weight and the deviation value corresponding to the population is as follows:
when (when)When the weight corresponding to the population and the position of the deviation value are expressed as follows:
when (when)The positions of the weights and the bias values corresponding to the population are expressed as follows:
wherein: t represents the current iteration number, t max Represents the maximum number of iterations, N represents the population number,represents the position of the ith individual after the t+1st iteration,/for> and />Respectively represent the current optimal individual and the random individual, alpha 1 and α2 A weight coefficient indicating a tendency of controlling the movement of the individual to the optimal individual and the previous individual, and β indicating a development vector associated with the optimal individual or the random individual;
step 5.3: when parabolic foraging is performed, the positions of the weights and bias values corresponding to the population can be expressed as:
wherein TF is a random number of-1 or 1, which represents the development direction of the population; p is a key parameter adaptively changing along with the iteration times, and represents the development amplitude of the population;
step 5.4: after the population completes spiral foraging and parabolic foraging, a Gaussian variation-optimal domain mechanism is introduced to disturb the population position, the fitness of individuals before and after disturbance is compared, excellent individuals are reserved, and an improved position updating formula is shown as follows:
4. The flexible power supply and hydrogen production power system with predictive energy supply according to claim 1, wherein the BOA-SSA integrated regulation algorithm is implemented as follows:
21 Initializing sparrow groups, wherein each sparrow group has a corresponding maximum hydrogen production power, a minimum power grid intervention power group value, and input power P output by photovoltaic v Grid acquisition power P e Predicted load power P n The objective function is as follows:
maxP H =P v +P e -P n -P loss
wherein ,PH Represents hydrogen production power, P e-min Representing minimized power of grid intervention, P loss Power lost during transmission;
22 The initial population is carried into an objective function for evaluation, the population is ranked, the maximum hydrogen production power and the minimum power grid intervention power corresponding to the population with the front ranking degree are used as discoverers, and the populations with the rear ranking degree are used as followers;
23 Updating the finder location, the formula is as follows:
wherein i, j represents the position information of the ith sparrow in the j-th dimension, iter max Expressed as the maximum number of iterations, R 2 The method is an alarm value, RT is a safety threshold, Q is a normal distribution random number, L is a 1Xd matrix, and elements of the matrix are all 1;
24 Updating the follower position according to the finder position, the formula is as follows;
and x is worst Representing the current global worst position, x p Representing the optimal position occupied by the current finder, representing a 1xd matrix, each element of which is randomly assigned 1 or-1, A being represented as a 1xd matrix, A + =A T (AA T ) -1 ;
25 Randomly selecting reconnaissance early warning with 20% of the proportion and updating the position of the reconnaissance early warning, wherein the formula is as follows;
wherein ,and for the current global optimal position, beta is taken as a step control parameter, and is subjected to normal distribution random numbers with a mean value of 0 and a variance of 1. f (f) i Representing the fitness value of the current sparrow individual, f g Representing the current global best fitness value, f w The current global worst fitness value is represented, epsilon is a constant, zero value of a denominator is avoided, K is a random number, and K represents the direction of sparrow movement and is a step control parameter;
26 If not, returning to the step 23), otherwise, outputting the optimal maximum hydrogen production power and the minimum power grid intervention power group value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310346491.4A CN116345505B (en) | 2023-04-03 | 2023-04-03 | Flexible power supply and hydrogen production power system with predictive energy supply |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310346491.4A CN116345505B (en) | 2023-04-03 | 2023-04-03 | Flexible power supply and hydrogen production power system with predictive energy supply |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116345505A true CN116345505A (en) | 2023-06-27 |
CN116345505B CN116345505B (en) | 2023-10-20 |
Family
ID=86885529
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310346491.4A Active CN116345505B (en) | 2023-04-03 | 2023-04-03 | Flexible power supply and hydrogen production power system with predictive energy supply |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116345505B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117254531A (en) * | 2023-11-07 | 2023-12-19 | 深圳稳石氢能科技有限公司 | AEM-based renewable energy intelligent scheduling system |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114928114A (en) * | 2022-05-12 | 2022-08-19 | 中国科学院广州能源研究所 | Rapid calculation method for comprehensive prediction energy management of offshore wind power diversified consumption |
-
2023
- 2023-04-03 CN CN202310346491.4A patent/CN116345505B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114928114A (en) * | 2022-05-12 | 2022-08-19 | 中国科学院广州能源研究所 | Rapid calculation method for comprehensive prediction energy management of offshore wind power diversified consumption |
Non-Patent Citations (2)
Title |
---|
张伟康等: "混合策略改进的麻雀搜索算法", 计算机工程与应用, vol. 57, no. 24, pages 74 - 82 * |
胡丹等: "基于改进金枪鱼算法优化ELM模型的光伏功率预测", 计算机工程与应用, vol. 44, no. 8, pages 97 - 104 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117254531A (en) * | 2023-11-07 | 2023-12-19 | 深圳稳石氢能科技有限公司 | AEM-based renewable energy intelligent scheduling system |
CN117254531B (en) * | 2023-11-07 | 2024-01-26 | 深圳稳石氢能科技有限公司 | AEM-based renewable energy intelligent scheduling system |
Also Published As
Publication number | Publication date |
---|---|
CN116345505B (en) | 2023-10-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113394817B (en) | Multi-energy capacity optimal configuration method of wind, light, water and fire storage system | |
CN116345505B (en) | Flexible power supply and hydrogen production power system with predictive energy supply | |
CN116667325B (en) | Micro-grid-connected operation optimization scheduling method based on improved cuckoo algorithm | |
CN112311017A (en) | Optimal collaborative scheduling method for virtual power plant and main network | |
CN113807566A (en) | Community energy scheduling method based on renewable energy and uncertain internal load | |
CN112883630A (en) | Day-ahead optimized economic dispatching method for multi-microgrid system for wind power consumption | |
CN114971071A (en) | Park comprehensive energy system time sequence planning method considering wind-solar access and electric heating hybrid energy storage | |
CN115293457A (en) | Seasonal hydrogen storage optimization configuration method of comprehensive energy system based on distributed collaborative optimization strategy | |
CN113624052B (en) | Combined cooling heating and power system and waste heat recovery method thereof | |
CN113488990B (en) | Micro-grid optimal scheduling method based on improved bat algorithm | |
CN113221325A (en) | Multi-source energy storage type regional comprehensive energy low-carbon operation optimization method considering electricity to gas | |
CN116865233A (en) | Low-carbon economic operation optimization method for micro-grid containing electricity-to-gas equipment | |
Koochaki et al. | Optimal design of solar-wind hybrid system using teaching-learning based optimization applied in charging station for electric vehicles | |
Han et al. | Deep reinforcement learning based approach for real-time dispatch of integrated energy system with hydrogen energy utilization | |
CN113991654A (en) | Energy internet hybrid energy system and scheduling method thereof | |
CN113077071A (en) | Wind and light storage capacity configuration method considering full life cycle of electric vehicle charging station | |
Toughzaoui et al. | System Sizing and Energy Management Optimization using a Hybrid Model | |
Salodkar et al. | Review of hydrogen fuel cell as an emergent field in green technology | |
CN116581742B (en) | Chameleon algorithm-based flexible electric load scheduling system and chameleon algorithm-based flexible electric load scheduling method for regulating and controlling intelligent cloud platform | |
CN113852121B (en) | Real-time energy management method of electro-hydrogen multi-energy complementary comprehensive energy system | |
CN117526374B (en) | Control method and device of new energy hydrogen production system matched with real-time output of fluctuation power supply | |
CN117767369B (en) | Energy storage site selection and hierarchical configuration method considering medium-long term planning | |
CN115907220A (en) | Method and system for online optimization operation of hydrogen-containing energy system in uncertain environment | |
CN117575515A (en) | Optimized operation method and system for comprehensive energy conversion based on hydrogen conversion | |
CN117252389A (en) | 100% novel energy system optimal scheduling method based on distributed multi-target colshade |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |