CN115189377B - Photovoltaic power generation capacity prediction-based microgrid optimal scheduling method, device and equipment - Google Patents
Photovoltaic power generation capacity prediction-based microgrid optimal scheduling method, device and equipment Download PDFInfo
- Publication number
- CN115189377B CN115189377B CN202210918641.XA CN202210918641A CN115189377B CN 115189377 B CN115189377 B CN 115189377B CN 202210918641 A CN202210918641 A CN 202210918641A CN 115189377 B CN115189377 B CN 115189377B
- Authority
- CN
- China
- Prior art keywords
- power
- energy storage
- storage element
- bat
- error
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000010248 power generation Methods 0.000 title claims abstract description 51
- 238000000034 method Methods 0.000 title claims description 39
- 238000004146 energy storage Methods 0.000 claims abstract description 106
- 238000003860 storage Methods 0.000 claims abstract description 64
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 claims abstract description 49
- 229910052739 hydrogen Inorganic materials 0.000 claims abstract description 49
- 239000001257 hydrogen Substances 0.000 claims abstract description 49
- 241000287127 Passeridae Species 0.000 claims abstract description 34
- 238000012706 support-vector machine Methods 0.000 claims abstract description 29
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 28
- 239000002245 particle Substances 0.000 claims abstract description 24
- 238000010845 search algorithm Methods 0.000 claims abstract description 21
- 238000012423 maintenance Methods 0.000 claims description 44
- 239000000446 fuel Substances 0.000 claims description 32
- 238000005457 optimization Methods 0.000 claims description 22
- 230000006870 function Effects 0.000 claims description 19
- 238000010977 unit operation Methods 0.000 claims description 19
- 230000015654 memory Effects 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 9
- 230000006872 improvement Effects 0.000 claims description 7
- 238000007599 discharging Methods 0.000 claims description 6
- 230000009467 reduction Effects 0.000 claims description 3
- 230000004044 response Effects 0.000 abstract description 6
- 238000013461 design Methods 0.000 description 16
- 230000008569 process Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 230000002431 foraging effect Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005868 electrolysis reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 239000004459 forage Substances 0.000 description 1
- 238000002789 length control Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013486 operation strategy Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- 230000003442 weekly effect Effects 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
- 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
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/004—Generation forecast, e.g. methods or systems for forecasting future energy generation
-
- 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
- H02J3/32—Arrangements for balancing of the load in a network by storage of energy using batteries with converting means
-
- 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
- H02J3/381—Dispersed generators
-
- 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
- H02J7/00—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries
- H02J7/34—Parallel operation in networks using both storage and other dc sources, e.g. providing buffering
- H02J7/35—Parallel operation in networks using both storage and other dc sources, e.g. providing buffering with light sensitive cells
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Power Engineering (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Primary Health Care (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Water Supply & Treatment (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Public Health (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a photovoltaic power generation capacity prediction-based microgrid optimal scheduling device and equipment, which comprise: predicting the photovoltaic power generation power based on a support vector machine model improved by a sparrow search algorithm; constructing constraint conditions, and performing optimizing scheduling on the energy of the energy storage element by adopting an improved particle swarm algorithm to generate a day-ahead scheduling plan; adjusting the real-time working state of the energy storage element according to the power error to generate an intra-day scheduling plan; and carrying out comprehensive scheduling on the microgrid based on the day-ahead scheduling plan and the day-in scheduling plan. According to the invention, the day-ahead scheduling plan can satisfy the minimization of the daily operation cost of the system while absorbing photoelectric fluctuation and compensating power balance, and meanwhile, the charge state of the storage battery and the hydrogen storage level of the hydrogen tank are maintained in an expected state, so that the economical and stable operation of the microgrid is realized; and the day scheduling strategy can quickly control the energy storage element, reduce the uncertainty of the algorithm, realize the real-time management of energy, eliminate the system error and accelerate the response time.
Description
Technical Field
The invention belongs to the technical field of microgrid scheduling optimization, and particularly relates to a microgrid optimal scheduling method, device and equipment based on photovoltaic power generation amount prediction.
Background
The continuous development of the micro-grid technology leads the micro-grid energy storage system to be diversified day by day, and how to build a more stable and economic energy storage micro-grid system containing multiple micro-sources becomes one of the problems to be solved urgently. Photovoltaic power generation has randomness and volatility, and hydrogen energy is used as a clean sustainable energy source and is commonly used as an energy storage element of a microgrid system. In order to solve the problem of power shortage or energy waste of the microgrid system to a greater extent, the hydrogen-containing energy storage system optimization scheduling strategy is formulated based on photovoltaic power generation prediction data, and the method has an important development prospect.
In the prior art, a commonly used method for predicting photovoltaic power generation capacity mainly comprises an Artificial Neural Network (ANN), a long-short term memory artificial neural network (LSTM), a Support Vector Machine (SVM) and the like, and a commonly used method for generating a microgrid capacity configuration and operation strategy of a hydrogen-containing energy storage system mainly performs capacity configuration through a particle swarm algorithm and aims at minimizing daily power fluctuation of the system. However, although the method for carrying out microgrid optimization scheduling based on photovoltaic power generation amount prediction can improve the prediction accuracy of photovoltaic power generation amount data to a certain extent and ensure the safety and economy of the energy storage microgrid, the problems that the real-time performance of system control is insufficient, the response time of scheduling energy storage elements in the day is too long and the like still exist.
Disclosure of Invention
The invention aims to provide a photovoltaic power generation prediction-based microgrid optimal scheduling method, device and equipment, which are used for solving the technical problems that the real-time performance of system control is insufficient and the response time of scheduling energy storage elements in a day is too long in the prior art.
In order to achieve the purpose, the invention adopts the following technical scheme:
on the one hand, the microgrid optimization scheduling method based on photovoltaic power generation amount prediction is provided, and comprises the following steps:
predicting the photovoltaic power generation power based on a support vector machine model improved by a sparrow search algorithm to obtain a predicted power value;
performing optimizing scheduling on the energy of the energy storage element by adopting an improved particle swarm algorithm by taking the predicted power value as basic data, taking the minimum daily operation cost of the system as a target function and taking the energy storage element and the power balance as constraint conditions to generate a day-ahead scheduling plan;
adjusting the real-time working state of the energy storage element according to the power error between the predicted power value and the actual power value to generate an intra-day scheduling plan;
and comprehensively scheduling the microgrid based on the day-ahead scheduling plan and the day-in scheduling plan to obtain the optimal operation state of the microgrid.
In one possible design, the improvement of the sparrow search algorithm on the support vector machine comprises:
and optimizing the parameter penalty factor and the kernel function radius in the support vector machine model by using a sparrow search algorithm so that the improved support vector machine model predicts the photovoltaic power generation power based on the optimal parameter penalty factor and the kernel function radius.
In one possible design, the expression for the minimum system daily operating cost as an objective function is:
C total =min(C t +C y ); (1)
C t =C pv_t /n pv L pv +C bat_t /n bat L bat + C el_t /n el L el +C fc_t /n fc L fc +C Ht_t /n Ht L Ht ; (2)
C y =k pv P pv +k bat P bat +k el P el + k fc P fc +k Ht P Ht ; (3)
wherein, C t Represents the daily investment cost, C pv_t Represents the total investment cost of the photovoltaic array, C bat_t Represents the total investment cost of the accumulator, C el_t Represents the total investment cost of the electrolytic cell, C fc_t Represents the total investment cost of the fuel cell, C Ht_t Represents the total investment cost of the hydrogen storage tank, n pv Representing the operating efficiency of the photovoltaic array, n bat Indicates the operating efficiency of the battery, n el Denotes the operating efficiency of the cell, n fc Represents the operating efficiency of the fuel cell, n Ht Indicates the operating efficiency of the hydrogen storage tank, L pv Denotes the lifetime of the photovoltaic array, L bat Indicates the life of the battery, L el Denotes the life of the cell, L fc Indicates the life of the fuel cell, L Ht Indicates the life of the hydrogen storage tank, C y Represents daily operating maintenance cost, k pv Represents the unit operating maintenance cost, k, of the photovoltaic array bat Represents the unit operation maintenance cost of the storage battery, k el Showing electrolytic cellsCost of unit operation and maintenance, k fc Represents the unit operation maintenance cost, k, of the fuel cell Ht Represents the unit operation maintenance cost, P, of the hydrogen storage tank pv Represents the unit operating maintenance cost, P, of the photovoltaic array bat Represents the unit operating maintenance cost of the accumulator, P el Represents the maintenance cost per unit operation of the cell, P fc Represents the unit operating maintenance cost, P, of the fuel cell Ht Representing the unit operating maintenance cost of the hydrogen storage tank.
In one possible design, the energy storage elements and power balance as constraints include power balance constraints, battery constraints, and hydrogen storage system constraints; wherein,
the expression for the power balance constraint is:
P pv (t)-P load (t)=P bat_ch (t)+P fc (t)+ P bat_dis (t)+P el (t); (4)
wherein, P pv (t) represents the actual power value of the photovoltaic power generation array at time t, P load (t) represents the actual value of the load at time t, P bat_ch (t)、P fc (t)、P bat_dis (t) and P el (t) an actual power value of the battery charge, an actual power value of the fuel cell, an actual power value of the battery discharge, and an actual power value of the electrolytic cell at time t, respectively;
the expression for the battery constraint is:
P batmin <P bat <P batmin SOC min <SOC<SOC max ; (5)
wherein, P batmin And P batmax Respectively representing the lower limit and the upper limit of charge and discharge of the storage battery, SOC min And SOC max Respectively representing the lower limit and the upper limit of the state of charge of the storage battery;
the expression of the constraint condition of the hydrogen energy storage system is as follows:
P elmin <P el <P elmax P fcmin <P fc <P fcmax (6)
SOH min <SOH<SOH max
wherein, P elmin And P elmax Respectively representing the lower and upper limits of the power of the cell, P fcmin And P fcmax Respectively representing the lower and upper power limits, SOH, of the fuel cell min And SOH max Respectively representing the lower limit and the upper limit of the capacity of the hydrogen storage tank.
In one possible design, an improvement of the particle swarm algorithm comprises:
optimizing an inertia factor w and a learning factor c of the particle swarm optimization so that the particle swarm optimization searches the working state of the energy storage element when the daily operation cost of the energy storage system is minimum based on the optimized inertia factor and the learning factor; wherein,
the optimized expression of the inertia factor w is as follows:
w=w max +[(MI-IT)-(w max -w min )]/MI; (7)
wherein, w max And w min Respectively representing the upper limit and the lower limit of an inertia factor, MI representing the maximum iteration number, and IT representing the current iteration number;
the optimized expression of the learning factor c is as follows:
c=c min +(c max -c min )IT 2 /MI 2 ; (8)
wherein, c max And c min Respectively represent learning factors the upper and lower limits of (c).
In one possible design, adjusting at least a charge/discharge state of the battery according to a power error between the power value and the actual power value includes:
calculating a predicted power value P of the photovoltaic power generation array at the time t pv_pre (t) predicted power value P at time t with load load_pre (t) first power error Δ P 1 The calculation formula is as follows:
ΔP 1 =P pv_pre (t)-P load_pre (t); (9)
calculating the actual power value P of the photovoltaic power generation array at the time t pv (t) actual power value P of load at t moment load (t) Second power error Δ P 2 The calculation formula is as follows:
ΔP 2 =P pv (t)-P load (t); (10)
according to the first power error Δ P 1 And a second power error Δ P 2 And determining the corresponding working state and the corresponding scheduling scheme of the energy storage element.
In one possible design, the first power error Δ P is based on 1 And a second power error Δ P 2 Determining the corresponding working state and the corresponding scheduling scheme of the energy storage element by taking the value of (a), comprising the following steps:
if the first power error is Δ P 1 And a second power error Δ P 2 Are all not negative and have a first power error Δ P 1 Not less than the second power error Δ P 2 If the energy storage element is determined to be in the first working state, the energy storage element is controlled to reduce charging, and the first reduction is delta P de1 =ΔP 1 -ΔP 2 ;
If the first power error is Δ P 1 And a second power error Δ P 2 Are all not negative and have a first power error Δ P 1 Less than the second power error Δ P 2 Determining that the energy storage element is in the second working state, controlling the energy storage element to increase charging, wherein the first increase is delta P in1 =ΔP 1 -ΔP 2 ;
If the first power error Δ P 1 Not negative and second power error Δ P 2 If the voltage is negative, determining a third working state of the energy storage element, controlling the energy storage element to stop charging and discharge, wherein the discharge amount is delta P dis =ΔP 2 ;
If the first power error Δ P 1 Is negative and the second power error Δ P 2 If not, determining the fourth working state of the energy storage element, controlling the energy storage element to stop discharging and charge, wherein the charge amount is delta P cha =ΔP 2 ;
If the first power error is Δ P 1 And a second power error Δ P 2 Are all negative and the first power error Δ P 1 Not less than the second power error Δ P 2 Determining the fifth working state of the energy storage element,controlling the energy storage element to increase discharge by a second increase amount Δ P in2 =|ΔP 2 |-|ΔP 1 |;
If the first power error Δ P 1 And a second power error Δ P 2 Are all negative and the first power error Δ P 1 Less than the second power error Δ P 2 Determining a sixth working state of the energy storage element, controlling the energy storage element to reduce discharge, wherein the second increment is delta P de2 =|ΔP 1 |-|ΔP 2 |。
In one possible design, adjusting the real-time operating state of the energy storage element according to a power error between the predicted power value and the actual power value includes:
and adjusting at least the real-time working state of the storage battery according to the power error between the power value and the actual power value.
The second aspect provides a microgrid optimal scheduling device based on photovoltaic power generation amount prediction, which comprises:
the power value prediction module is used for predicting the photovoltaic power generation power based on a sparrow search algorithm improved support vector machine model to obtain a predicted power value;
the first plan generation module is used for carrying out optimizing scheduling on the energy of the energy storage element by adopting an improved particle swarm algorithm by taking the predicted power value as basic data, taking the minimum daily operating cost of the system as a target function and taking the balance between the energy storage element and the power as a constraint condition so as to generate a day-ahead scheduling plan;
the second plan generating module is used for adjusting the real-time working state of the energy storage element according to the power error between the predicted power value and the actual power value so as to generate an intra-day scheduling plan;
and the comprehensive scheduling module is used for performing comprehensive scheduling on the microgrid based on the day-ahead scheduling plan and the day-inside scheduling plan to obtain the optimal running state of the microgrid.
A third aspect provides a computer device comprising a memory, a processor and a transceiver communicatively connected in sequence, wherein the memory is configured to store a computer program, the transceiver is configured to transmit and receive messages, and the processor is configured to read the computer program and perform the method as set forth in any one of the possible designs of the first aspect.
A fourth aspect provides a computer-readable storage medium having stored thereon instructions which, when executed on a computer, perform the method as set forth in any one of the possible designs of the first aspect.
A fifth aspect provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method as set forth in any one of the possible designs of the first aspect.
Has the beneficial effects that:
based on the hydrogen-containing energy storage photovoltaic power generation system microgrid, the invention provides a sectional type scheduling strategy, which comprises a day-ahead scheduling plan and a day-in scheduling plan. The day-ahead scheduling plan adopts a sparrow search algorithm to improve a support vector machine prediction model, and uses the photovoltaic power generation power predicted value as a balance object, and uses an improved particle swarm algorithm to search the working state of each energy storage element of the energy storage system under the condition of optimal daily operation economy; because a day-ahead scheduling plan has a tiny error, the day-in scheduling plan adjusts the working state of the energy storage element in real time according to the error between the photovoltaic actual power and the predicted power, so that the real-time control of the microgrid is realized; the improved prediction model has high prediction precision, small error and high calculation speed, and provides powerful data support for a scheduling plan, so that the day-ahead scheduling plan can meet the requirement of minimizing the daily operation cost of a system while absorbing photoelectric fluctuation and compensating power balance, and meanwhile, the charge state of a storage battery and the hydrogen storage level of a hydrogen tank are maintained in an expected state, and economic and stable operation of the microgrid is realized; and the day scheduling strategy can quickly control the energy storage element, reduce the uncertainty of the algorithm, realize the real-time management of energy, eliminate the system error and accelerate the response time of the system microgrid.
Drawings
Fig. 1 is a block diagram of a microgrid system provided in the present invention;
fig. 2 is a flowchart of a microgrid optimization scheduling method based on photovoltaic power generation prediction provided by the invention;
FIG. 3 is a prediction flow chart of a support vector machine model improved by the sparrow search algorithm provided by the invention;
FIG. 4 is a flow chart of the optimization of the particle swarm optimization algorithm provided by the present invention;
FIG. 5 is a flow chart of an intra-day dispatch plan provided by the present invention.
Detailed Description
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the present invention will be briefly described below with reference to the accompanying drawings and the embodiments or the description in the prior art, it is obvious that the following description of the structure of the drawings is only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts. It should be noted that the description of the embodiments is provided to help understanding of the present invention, but the present invention is not limited thereto.
Examples
As shown in fig. 1 to fig. 5, the method for photovoltaic power generation amount prediction based microgrid optimization scheduling includes, but is not limited to, steps S1 to S4:
s1, predicting photovoltaic power generation power based on a sparrow search algorithm improved support vector machine model to obtain a predicted power value;
as shown in fig. 1, it should be noted that the hydrogen-containing energy storage system microgrid structure in the embodiment of the present application adopts an existing island microgrid system, and the island microgrid system includes photovoltaic arrays, electrolysis baths, hydrogen storage tanks, fuel cells, storage batteries, unidirectional DC-DC, bidirectional DC-DC and other elements; the photovoltaic array is used as a main distributed energy source to provide energy for a direct current load, redundant energy is used for charging a storage battery or supplying the redundant energy to an electrolytic cell to generate hydrogen and storing the hydrogen in a hydrogen storage tank, and the storage battery and the fuel cell are used for supplementing the shortage under the condition that the generated energy of the photovoltaic array is insufficient, so that the normal operation of the system is ensured.
As shown in fig. 3, in step S1, the improvement of the support vector machine by the sparrow search algorithm includes:
and optimizing the parameter penalty factor and the kernel function radius in the support vector machine model (SVM) by utilizing a Sparrow Search Algorithm (SSA), so that the improved support vector machine model predicts the photovoltaic power generation power based on the optimal parameter penalty factor and the kernel function radius.
The sparrow search algorithm is based on the existing algorithm principle, namely the sparrow foraging and warning behaviors are used as inspiration, efficient global search is achieved, the occurrence of local optimal conditions is avoided, and the sparrow search algorithm has the advantages of being high in convergence speed, strong in search capacity, stable in structure and the like; similarly, the support vector machine model is based on the existing algorithm principle, and can perform linear regression on the nonlinear problem through high-low dimension mapping, so that the photovoltaic power generation amount prediction is realized. The innovation of the embodiment of the application is that a sparrow search algorithm is used for improving the parameter penalty factor and the kernel function radius in the support vector machine model, so that the prediction precision of the support vector machine model can be improved, and preferably, the mean square error can be used as an evaluation index of the prediction precision.
In fig. 3, a specific procedure for optimizing the parameter penalty factor and the kernel function radius in the Support Vector Machine (SVM) by using the Sparrow Search Algorithm (SSA) includes:
1) Setting the initial sparrow population number as n, the dimension number of the problem to be optimized as m, and the sparrow population expression as follows:
preferably, the number of sparrows population n =30 and the problem dimension number m =2 are adopted in this embodiment, and it should be understood that the above values are only an example of this embodiment, and in other application scenarios, the number of sparrows population and the problem dimension number may also be set according to application requirements, which is not limited here.
2) Dividing the population into two parts, namely a finder and an adder; preferably, the discoverer accounts for 70% and the others are the enrollees, and it can be understood that the above value is only an example of this embodiment, and in other application scenarios, the number of sparrow populations and the number of problem dimensions can be set according to application requirements, which is not limited herein; then in each iterative optimization process, the finder position update formula is:
wherein t is the current iteration frequency, i is the current dimension, and xt, j, i is the position of the jth sparrow in the dimension i during the tth iteration; iitmax is the maximum iteration number of the population, and preferably, the maximum iteration number is set to be 40 in the embodiment; alpha is a random number in an interval of (0, 1), Q is a random number which obeys normal distribution, L is a unit vector of a dimension m, R2 and RST are respectively an alarm value and a safety threshold value, and generally R2 belongs to [0,1] and RST belongs to [0.5,1] according to experience, preferably RST =0.6;
3) When R2 is less than RST, the population is free from danger around foraging, and a finder can continue to expand the search range; if R2 is larger than or equal to RST, indicating that the weekly feeding of the discoverer reaches a safety threshold, the discoverer timely gives an alarm to lead the sparrow population to a safe position for foraging; during foraging, the participants pay close attention to the dynamic state of the discoverer, and once the discoverer finds a better food source, the participants can follow the discoverer to a better position, wherein the position of the participants is updated according to the formula
Wherein XP is the optimal position searched by the current finder, xb is the global worst position, a is a 1 × m matrix, where each element is assigned a value of 1 or-1, and a + = AT (AAT) -1;
4) When j is larger than n/2, the j-th subscriber cannot obtain food and needs to fly to another position to continuously search for the food; sparrows that do not have access to food and are aware of danger are called cautioners; the initial position of the population of alert people is randomly generated,
usually, the population number accounts for 10% -20% of the total number, preferably, 20%, and the position updating formula is as follows:
wherein Xg is a global optimal position, beta and K are step length control parameters, beta is a random number, the obedient mean value is 0, the variance is normal distribution of 1, K represents the movement direction of the sparrows, the value is a random number of [ -1,1], fj is the fitness value of the current sparrow individual, fg and fb are respectively global optimal and worst fitness values, and epsilon is a constant so as to avoid zero-score error.
5) When fj > fg, the global optimum position Xg and its surrounding security are indicated, if fj = fg, it is indicated that the alert is in the population, in order to reduce the risk of sparrow catching, at this time R2 is greater than or equal to RST, and the mode of updating is returned to the joiner, and the finder brings the population to other secure places to forage.
Based on the disclosure, in this embodiment, a sparrow search algorithm is used to optimize a parameter penalty factor and a kernel function radius of a support vector machine, and one value of the two parameters obtained in four seasons of spring, summer, autumn and winter is shown in table one:
watch 1
SVM | Spring season | (Summer) | Autumn | Winter season |
c | 64 | 256 | 1024 | 256 |
g | 0.70711 | 0.0055243 | 0.0019531 | 0.088388 |
SSA-SVM | Spring season | (Summer) | Autumn season | Winter season |
c | 134.9569 | 226.062 | 840.209 | 399.311 |
g | 0.91172 | 0.0174861 | 0.034933 | 0.060344 |
Therefore, after the parameter optimization of the sparrow searching algorithm,
s2, performing optimizing scheduling on the energy of the energy storage element by adopting an improved particle swarm algorithm by taking the predicted power value as basic data, taking the minimum daily operation cost of the system as a target function and taking the balance between the energy storage element and the power as constraint conditions to generate a day-ahead scheduling plan;
in step S2, the expression that the system daily operation cost is minimum as the objective function is:
C total =min(C t +C y ); (1)
C t =C pv_t /n pv L pv +C bat_t /n bat L bat + C el_t /n el L el +C fc_t /n fc L fc +C Ht_t /n Ht L Ht ; (2)
C y =k pv P pv +k bat P bat +k el P el + k fc P fc +k Ht P Ht ; (3)
wherein, C t Represents the daily investment cost, C pv_t Represents the total investment cost of the photovoltaic array, C bat_t Represents the total investment cost, C, of the accumulator el_t Represents the total investment cost of the electrolytic cell, C fc_t Represents the total investment cost of the fuel cell, C Ht_t Represents the total investment cost of the hydrogen storage tank, n pv Representing the operating efficiency of the photovoltaic array, n bat Indicates the operating efficiency of the battery, n el Denotes the operating efficiency of the cell, n fc Represents the operating efficiency of the fuel cell, n Ht Indicates the operating efficiency of the hydrogen storage tank, L pv Denotes the lifetime of the photovoltaic array, L bat Indicates the life of the battery, L el Denotes the life of the cell, L fc Indicates the life of the fuel cell, L Ht Indicates the life of the hydrogen storage tank, C y Represents daily operating maintenance cost, k pv Represents the unit operating maintenance cost, k, of the photovoltaic array bat Represents the unit operation maintenance cost of the storage battery, k el Represents the unit operating maintenance cost, k, of the cell fc Represents the unit operation maintenance cost, k, of the fuel cell Ht Represents the unit operation maintenance cost of the hydrogen storage tank, P pv Represents the unit operating maintenance cost, P, of the photovoltaic array bat Represents the unit operating maintenance cost of the accumulator, P el Sheets representing electrolytic cellsBit running maintenance cost, P fc Represents the unit operating maintenance cost, P, of the fuel cell Ht Representing the unit operating maintenance cost of the hydrogen storage tank.
In step S2, the energy storage element and the power balance are taken as constraint conditions including a power balance constraint condition, a storage battery constraint condition and a hydrogen energy storage system constraint condition; wherein,
the expression for the power balance constraint is:
P pv (t)-P load (t)=P bat_ch (t)+P fc (t)+ P bat_dis (t)+P el (t); (4)
wherein, P pv (t) represents the actual power value of the photovoltaic power generation array at time t, P load (t) represents the actual value of the load at time t, P bat_ch (t)、P fc (t)、P bat_dis (t) and P el (t) represents the actual power value of the battery charge, the actual power value of the fuel cell, the actual power value of the battery discharge and the actual power value of the electrolyzer at time t, respectively;
the expression for the battery constraint is:
P batmin <P bat <P batmin SOC min <SOC<SOC max ; (5)
wherein, P batmin And P batmax Respectively representing the lower limit and the upper limit of charge and discharge of the storage battery, SOC min And SOC max Respectively representing a lower limit and an upper limit of the state of charge of the storage battery;
the expression of the constraint condition of the hydrogen energy storage system is as follows:
P elmin <P el <P elmax P fcmin <P fc <P fcmax (6)
SOH min <SOH<SOH max
wherein, P elmin And P elmax Respectively representing the lower and upper limits of the power of the cell, P fcmin And P fcmax Respectively representing the lower and upper power limits, SOH, of the fuel cell min And SOH max Respectively indicate the capacity of the hydrogen storage tankA limit and an upper limit.
In step S2, the improvement of the particle swarm algorithm includes:
optimizing an inertia factor w and a learning factor c of the particle swarm algorithm so that the particle swarm algorithm searches the working state of the energy storage element with the lowest daily operation cost of the energy storage system based on the optimized inertia factor and learning factor; wherein,
the optimized expression of the inertia factor w is as follows:
w=w max +[(MI-IT)-(w max -w min )]/MI; (7)
wherein, w max And w min Respectively representing the upper limit and the lower limit of an inertia factor, MI representing the maximum iteration number, and IT representing the current iteration number;
the optimized expression of the learning factor c is as follows:
c=c min +(c max -c min )IT 2 /MI 2 ; (8)
wherein, c max And c min Respectively representing the upper and lower limits of the learning factor.
The method has the advantages of good effect, high convergence speed and simple structure aiming at the optimization of the multi-constraint problem, and is commonly used for the optimization of the nonlinear problem; however, the inertia factor and the learning factor of the existing particle swarm algorithm are fixed, which makes the algorithm fall into a locally optimal solution easily, and in order to solve this problem, in this embodiment, upper and lower limits are set for values of the inertia factor and the learning factor of the particle swarm algorithm, preferably, the acceleration factor c takes a value of [0.1,0.2] interval, the inertia factor w takes a value of [0.001,0.5] interval, and the maximum iteration number is 200, so that the inertia factor and the learning factor are in a non-fixed variation state, and the variation rate when updating the factors is favorable for searching for a global minimum, so that the working state of the energy storage element with the smallest daily operation cost of the energy storage system can be obtained.
As shown in fig. 4, the optimizing process of the improved particle swarm optimization algorithm in this embodiment includes:
1) Initializing parameters, calculating fitness, and updating individual optimum and global optimum;
2) Updating the learning factor and the inertia factor;
3) Updating the particle position;
4) And (4) judging whether a termination condition (iteration times) is reached, if so, outputting an optimal value, and if not, returning to the step 2).
S3, adjusting the real-time working state of the energy storage element according to the power error between the predicted power value and the actual power value to generate an intra-day scheduling plan;
in step S3, adjusting the real-time operating state of the energy storage element according to the power error between the predicted power value and the actual power value, including:
and adjusting the real-time working state of the storage battery at least according to the power error between the power value and the actual power value.
As shown in fig. 5, it should be noted that the intra-day scheduling plan is used to eliminate the error of photovoltaic power generation prediction, so as to achieve a fast response of the energy storage system. Based on a day-ahead scheduling plan, the charging and discharging strategy of the hydrogen-containing energy storage system is corrected on the basis of considering the actual photovoltaic output power, when the actual photovoltaic power has an error with a predicted value, the storage battery is charged and discharged firstly, and then the residual energy is converted into hydrogen through an electrolytic cell and stored in a hydrogen storage tank, or the fuel cell supplements the difference power.
In step S3, adjusting at least the charge/discharge state of the battery according to the power error between the power value and the actual power value includes:
s31, calculating a predicted power value P of the photovoltaic power generation array at the time t pv_pre (t) predicted power value P at time t with load load_pre (t) first power error Δ P 1 The calculation formula is as follows:
ΔP 1 =P pv_pre (t)-P load_pre (t); (9)
s32, calculating the actual power value P of the photovoltaic power generation array at the moment t pv (t) actual power value P of load at t moment load (t) second power error Δ P 2 The calculation formula is as follows:
ΔP 2 =P pv (t)-P load (t); (10)
step S33, according to the first power error delta P 1 And a second power error Δ P 2 Determining the corresponding working state and the corresponding scheduling scheme of the energy storage element by taking the value of (a), comprising the following steps:
1) If the first power error Δ P 1 And a second power error Δ P 2 Are all not negative and have a first power error Δ P 1 Not less than the second power error Δ P 2 Then, the energy storage element is determined to be in a first working state, the energy storage element is controlled to reduce charging, and the first reduction amount is delta P de1 =ΔP 1 -ΔP 2 ;
2) If the first power error is Δ P 1 And a second power error Δ P 2 Are all not negative and have a first power error Δ P 1 Less than a second power error Δ P 2 Determining that the energy storage element is in the second working state, controlling the energy storage element to increase charging, wherein the first increase is delta P in1 =ΔP 1 -ΔP 2 ;
3) If the first power error is Δ P 1 Not negative and second power error Δ P 2 If the voltage is negative, determining a third working state of the energy storage element, controlling the energy storage element to stop charging and discharge, wherein the discharge amount is delta P dis =ΔP 2 ;
4) If the first power error is Δ P 1 Is negative and the second power error Δ P 2 If not, determining the fourth working state of the energy storage element, controlling the energy storage element to stop discharging and charge, wherein the charge amount is delta P cha =|ΔP 2 |;
5) If the first power error Δ P 1 And a second power error Δ P 2 Are all negative and the first power error Δ P 1 Not less than the second power error Δ P 2 Determining the fifth working state of the energy storage element, controlling the energy storage element to increase the discharge, wherein the second increase is delta P in2 =|ΔP 2 |-|ΔP 1 |;
6) If the first power error Δ P 1 And a second power error Δ P 2 Are all negative and the first power error Δ P 1 Is less than the secondPower error Δ P 2 Determining a sixth working state of the energy storage element, controlling the energy storage element to reduce discharge, wherein the second increment is delta P de2 =|ΔP 1 |-|ΔP 2 |。
In fig. 5, it should be noted that the first operating state to the sixth operating state represent the scheduling plans of the energy storage system in the corresponding operating states, which are as follows:
1) A first state: preferentially reducing the power of the electrolytic cell, and reducing the charging quantity of the storage battery by the residual power;
2) And a second state: preferentially increasing the charging amount of the storage battery, and converting the surplus power into hydrogen for storage by the electrolytic bath;
3) And a third state: stopping charging, wherein the storage battery is fully discharged to provide a part of the shortage power for the system, and the rest part is provided by the power generation of the fuel cell;
4) And a fourth state: stopping discharging, wherein one part of the residual power of the photovoltaic power generation system is used for charging the storage battery, and the other part of the residual power is converted into hydrogen through the electrolytic bath and stored;
5) And a fifth state: the storage battery is fully discharged, and the rest shortage is provided by the fuel cell;
6) And a sixth state: the amount of discharge of the fuel cell is reduced preferentially, and the remaining portion reduces battery discharge.
Preferably, when the error between the predicted power value and the actual power value is small, the real-time operating state of the energy storage element is adjusted according to the power error between the predicted power value and the actual power value, and the method includes:
and adjusting at least the real-time working state of the storage battery according to the power error between the power value and the actual power value, namely realizing the error correction only by adjusting the charging and discharging states of the storage battery.
And S4, carrying out comprehensive scheduling on the microgrid based on the day-ahead scheduling plan and the day-in scheduling plan to obtain the optimal operation state of the microgrid.
Based on the above disclosure, the present embodiment provides a segmented scheduling strategy, which includes a day-ahead scheduling plan and a day-inside scheduling plan. The day-ahead scheduling plan adopts a sparrow search algorithm to improve a support vector machine prediction model, and uses the photovoltaic power generation power predicted value as a balance object, and uses an improved particle swarm algorithm to search the working state of each energy storage element of the energy storage system under the condition of optimal daily operation economy; because a day-ahead scheduling plan has a tiny error, the day-in scheduling plan adjusts the working state of the energy storage element in real time according to the error between the photovoltaic actual power and the predicted power, so that the real-time control of the microgrid is realized; the improved prediction model has high prediction precision, small error and high calculation speed, and provides powerful data support for a scheduling plan, so that the day-ahead scheduling plan can meet the requirement of minimizing the daily operation cost of a system while absorbing photoelectric fluctuation and compensating power balance, and simultaneously, the charge state of a storage battery and the hydrogen storage level of a hydrogen tank are maintained in an expected state, and economic and stable operation of the microgrid is realized; and the day scheduling strategy can quickly control the energy storage element, reduce the uncertainty of the algorithm, realize the real-time management of energy, eliminate the system error and accelerate the response time of the system microgrid.
The second aspect provides a photovoltaic power generation amount prediction-based microgrid optimization scheduling device, which comprises:
the power value prediction module is used for predicting the photovoltaic power generation power based on a sparrow search algorithm improved support vector machine model to obtain a predicted power value;
the first plan generation module is used for carrying out optimizing scheduling on the energy of the energy storage element by adopting an improved particle swarm algorithm by taking the predicted power value as basic data, taking the minimum daily operating cost of the system as a target function and taking the balance between the energy storage element and the power as a constraint condition so as to generate a day-ahead scheduling plan;
the second plan generating module is used for adjusting the real-time working state of the energy storage element according to the power error between the predicted power value and the actual power value so as to generate an intra-day scheduling plan;
and the comprehensive scheduling module is used for performing comprehensive scheduling on the microgrid based on the day-ahead scheduling plan and the day-inside scheduling plan to obtain the optimal running state of the microgrid.
For the working process, working details and technical effects of the foregoing apparatus provided in the second aspect of this embodiment, reference may be made to the method described in any one of the first aspect or the first aspect, which is not described herein again.
In a third aspect, the present invention provides a computer device comprising a memory, a processor and a transceiver communicatively connected in sequence, wherein the memory is used for storing a computer program, the transceiver is used for sending and receiving messages, and the processor is used for reading the computer program and executing the method as set forth in any one of the possible designs of the first aspect.
For example, the Memory may include, but is not limited to, a Random-Access Memory (RAM), a Read-Only Memory (ROM), a Flash Memory (Flash Memory), a First-in First-out (FIFO), and/or a First-in Last-out (FILO), and the like; the processor may not be limited to the use of a microprocessor model number STM32F105 family; the transceiver may be, but is not limited to, a WiFi (wireless fidelity) wireless transceiver, a bluetooth wireless transceiver, a GPRS (General Packet Radio Service) wireless transceiver, and/or a ZigBee (ZigBee protocol, low power local area network protocol based on ieee802.15.4 standard) wireless transceiver, etc. In addition, the computer device may also include, but is not limited to, a power module, a display screen, and other necessary components.
For the working process, working details and technical effects of the foregoing computer device provided in the third aspect of this embodiment, reference may be made to the method described in the first aspect or any one of the possible designs of the first aspect, which is not described herein again.
In a fourth aspect, the present invention provides a computer readable storage medium having stored thereon instructions which, when executed on a computer, perform the method as set forth in any one of the possible designs of the first aspect.
The computer-readable storage medium refers to a carrier for storing data, and may include, but is not limited to, floppy disks, optical disks, hard disks, flash memories, flash disks and/or Memory sticks (Memory sticks), etc., and the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
For the working process, the working details and the technical effects of the foregoing computer-readable storage medium provided in the fourth aspect of this embodiment, reference may be made to the method in any one of the above first aspect or the possible designs of the first aspect, and details are not described herein again.
In a fifth aspect, the present invention provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method as set forth in any one of the possible designs of the first aspect.
For the working process, the working details and the technical effects of the computer program product containing the instructions provided in the fifth aspect of the present embodiment, reference may be made to the method described in the first aspect or any one of the possible designs of the first aspect, and details are not described herein again.
Finally, it should be noted that: the above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. A microgrid optimization scheduling method based on photovoltaic power generation amount prediction is characterized by comprising the following steps:
predicting the photovoltaic power generation power based on a support vector machine model improved by a sparrow search algorithm to obtain a predicted power value;
performing optimizing scheduling on the energy of the energy storage element by adopting an improved particle swarm algorithm by taking the predicted power value as basic data, taking the minimum daily operation cost of the system as a target function and taking the energy storage element and the power balance as constraint conditions to generate a day-ahead scheduling plan;
adjusting the real-time working state of the energy storage element according to the power error between the predicted power value and the actual power value to generate an intra-day scheduling plan;
comprehensively scheduling the microgrid based on a day-ahead scheduling plan and a day-in scheduling plan to obtain an optimal operation state of the microgrid;
the expression that the minimum daily operation cost of the system is taken as a target function is as follows:
C total =min(C t +C y );(1)
C t =C pv_t /n pv L pv +C bat_t /n bat L bat +C el_t /n el L el +C fc_t /n fc L fc +C Ht_t /n Ht L Ht ;(2)
C y =k pv P pv +k bat P bat +k el P el +k fc P fc +k Ht P Ht ;(3)
wherein, C t Represents the daily investment cost, C pv_t Represents the total investment cost of the photovoltaic array, C bat_t Represents the total investment cost, C, of the accumulator el_t Represents the total investment cost of the electrolyzer, C fc_t Represents the total investment cost of the fuel cell, C Ht_t Represents the total investment cost of the hydrogen storage tank, n pv Representing the operating efficiency of the photovoltaic array, n bat Indicates the operating efficiency of the battery, n el Denotes the operating efficiency of the cell, n fc Represents the operating efficiency of the fuel cell, n Ht Indicates the operating efficiency of the hydrogen storage tank, L pv Denotes the lifetime of the photovoltaic array, L bat Indicates the life of the battery, L el Denotes the life of the cell, L fc Indicates the life of the fuel cell, L Ht Indicates the life of the hydrogen storage tank, C y Represents daily operating maintenance cost, k pv Represents the unit operating maintenance cost, k, of the photovoltaic array bat Represents the unit operation maintenance cost of the storage battery, k el Represents the unit operating maintenance cost, k, of the cell fc Represents the unit operation maintenance cost, k, of the fuel cell Ht Represents the unit operation maintenance cost of the hydrogen storage tank, P pv Represents the unit operating maintenance cost, P, of the photovoltaic array bat Represents the unit operating maintenance cost of the accumulator, P el Represents the unit operating maintenance cost of the cell, P fc Indicating unit operation maintenance of fuel cellsThis, P Ht Represents the unit operation and maintenance cost of the hydrogen storage tank;
according to the power error of the power value and the actual power value, the real-time working state of the energy storage element is adjusted, and the method comprises the following steps:
calculating a predicted power value P of the photovoltaic power generation array at the time t pv_pre (t) predicted power value P at time t with load load_pre (t) first power error Δ P 1 The calculation formula is as follows:
ΔP 1 =P pv_pre (t)-P load_pre (t);(9)
calculating the actual power value P of the photovoltaic power generation array at the time t pv (t) actual power value P of load at t moment load (t) second power error Δ P 2 The calculation formula is as follows:
ΔP 2 =P pv (t)-P load (t);(10)
according to the first power error Δ P 1 And a second power error Δ P 2 And determining the corresponding working state and the corresponding scheduling scheme of the energy storage element.
2. The photovoltaic power generation amount prediction-based microgrid optimization scheduling method of claim 1, wherein improvement of a support vector machine by a sparrow search algorithm comprises the following steps:
and optimizing the parameter penalty factor and the kernel function radius in the support vector machine model by using a sparrow search algorithm so that the improved support vector machine model predicts the photovoltaic power generation power based on the optimal parameter penalty factor and the kernel function radius.
3. The photovoltaic power generation amount prediction-based microgrid optimization scheduling method of claim 1, wherein the energy storage elements and power balance serving as constraint conditions comprise power balance constraint conditions, storage battery constraint conditions and hydrogen energy storage system constraint conditions; wherein,
the expression for the power balance constraint is:
P pv (t)-P load (t)=P bat_ch (t)+P fc (t)+P bat_dis (t)+P el (t);(4)
wherein, P pv (t) represents the actual power value of the photovoltaic power generation array at time t, P load (t) represents the actual value of the load at time t, P bat_ch (t)、P fc (t)、P bat_dis (t) and P el (t) an actual power value of the battery charge, an actual power value of the fuel cell, an actual power value of the battery discharge, and an actual power value of the electrolytic cell at time t, respectively;
the expression of the battery constraint condition is:
P batmin <P bat <P batmin
SOC min <SOC<SOC max ;(5)
wherein, P batmin And P batmax Respectively representing the lower limit and the upper limit of charge and discharge of the storage battery, SOC min And SOC max Respectively representing a lower limit and an upper limit of the state of charge of the storage battery;
the expression of the constraint condition of the hydrogen energy storage system is as follows:
wherein, P elmin And P elmax Respectively, the lower and upper limits of the power of the cell, P fcmin And P fcmax Respectively representing the lower and upper power limits, SOH, of the fuel cell min And SOH max Respectively representing the lower limit and the upper limit of the capacity of the hydrogen storage tank.
4. The photovoltaic power generation capacity prediction-based microgrid optimization scheduling method of claim 1, wherein the improvement of the particle swarm algorithm comprises the following steps:
optimizing an inertia factor w and a learning factor c of the particle swarm algorithm so that the particle swarm algorithm searches the working state of the energy storage element with the lowest daily operation cost of the energy storage system based on the optimized inertia factor and learning factor; wherein,
the optimized expression of the inertia factor w is as follows:
w=w max +[(MI-IT)-(w max -w min )]/MI;(7)
wherein, w max And w min Respectively representing the upper limit and the lower limit of an inertia factor, MI representing the maximum iteration number, and IT representing the current iteration number;
the optimized expression of the learning factor c is as follows:
c=c min +(c max -c min )IT 2 /MI 2 ;(8)
wherein, c max And c min Respectively representing the upper and lower limits of the learning factor.
5. The photovoltaic power generation amount prediction-based microgrid optimization scheduling method according to claim 1, characterized in that the first power error Δ P is used for predicting the first power generation amount 1 And a second power error Δ P 2 Determining the corresponding working state and the corresponding scheduling scheme of the energy storage element by taking the value of (a), comprising the following steps:
if the first power error is Δ P 1 And a second power error Δ P 2 Are all not negative and have a first power error Δ P 1 Not less than the second power error Δ P 2 Then, the energy storage element is determined to be in a first working state, the energy storage element is controlled to reduce charging, and the first reduction amount is delta P de1 =ΔP 1 -ΔP 2 ;
If the first power error is Δ P 1 And a second power error Δ P 2 Are all not negative and have a first power error Δ P 1 Less than the second power error Δ P 2 Determining that the energy storage element is in the second working state, controlling the energy storage element to increase charging, wherein the first increase is delta P in1 =ΔP 1 -ΔP 2 ;
If the first power error is Δ P 1 Not negative and second power error Δ P 2 If the voltage is negative, determining a third working state of the energy storage element, controlling the energy storage element to stop charging and discharge, wherein the discharge amount is delta P dis =ΔP 2 ;
If the first power error Δ P 1 Is negative and the second power error deltaP 2 If not, determining the fourth working state of the energy storage element, controlling the energy storage element to stop discharging and charge, wherein the charge amount is delta P cha =|ΔP 2 |;
If the first power error is Δ P 1 And a second power error Δ P 2 Are all negative and the first power error Δ P 1 Not less than the second power error Δ P 2 Determining the fifth working state of the energy storage element, controlling the energy storage element to increase the discharge, wherein the second increase is delta P in2 =|ΔP 2 |-|ΔP 1 |;
If the first power error is Δ P 1 And a second power error Δ P 2 Are all negative and the first power error Δ P 1 Less than the second power error Δ P 2 Determining a sixth working state of the energy storage element, controlling the energy storage element to reduce discharge, wherein the second increment is delta P de2 =|ΔP 1 |-|ΔP 2 |。
6. The photovoltaic power generation amount prediction-based microgrid optimization scheduling method of claim 1, wherein the step of adjusting the real-time working state of the energy storage element according to the power error between the predicted power value and the actual power value comprises the following steps:
and adjusting at least the real-time working state of the storage battery according to the power error between the power value and the actual power value.
7. The utility model provides a scheduling device is optimized to microgrid based on prediction of photovoltaic power generation capacity which characterized in that includes:
the power value prediction module is used for predicting the photovoltaic power generation power based on a sparrow search algorithm improved support vector machine model to obtain a predicted power value;
the first plan generation module is used for carrying out optimizing scheduling on the energy of the energy storage element by adopting an improved particle swarm algorithm by taking the predicted power value as basic data, taking the minimum daily operating cost of the system as a target function and taking the balance between the energy storage element and the power as a constraint condition so as to generate a day-ahead scheduling plan;
the second plan generating module is used for adjusting the real-time working state of the energy storage element according to the power error between the predicted power value and the actual power value so as to generate an intra-day scheduling plan;
the comprehensive scheduling module is used for comprehensively scheduling the microgrid based on the day-ahead scheduling plan and the day-in scheduling plan to obtain the optimal operation state of the microgrid;
the expression that the minimum daily operation cost of the system is taken as a target function is as follows:
C total =min(C t +C y );(1)
C t =C pv_t /n pv L pv +C bat_t /n bat L bat +C el_t /n el L el +C fc_t /n fc L fc +C Ht_t /n Ht L Ht ;(2)
C y =k pv P pv +k bat P bat +k el P el +k fc P fc +k Ht P Ht ;(3)
wherein, C t Represents the daily investment cost, C pv_t Represents the total investment cost, C, of the photovoltaic array bat_t Represents the total investment cost of the accumulator, C el_t Represents the total investment cost of the electrolyzer, C fc_t Represents the total investment cost of the fuel cell, C Ht_t Represents the total investment cost of the hydrogen storage tank, n pv Representing the operating efficiency of the photovoltaic array, n bat Representing the operating efficiency of the battery, n el Denotes the operating efficiency of the cell, n fc Indicates the operating efficiency of the fuel cell, n Ht Indicates the operating efficiency of the hydrogen storage tank, L pv Denotes the lifetime of the photovoltaic array, L bat Indicates the life of the battery, L el Denotes the life of the cell, L fc Indicates the life of the fuel cell, L Ht Indicates the life of the hydrogen storage tank, C y Represents daily operating maintenance cost, k pv Represents the unit operating maintenance cost, k, of the photovoltaic array bat Represents the unit operation maintenance cost of the storage battery, k el Represents the unit operating maintenance cost, k, of the cell fc Indicating unit operation of fuel cellLine maintenance cost, k Ht Represents the unit operation maintenance cost of the hydrogen storage tank, P pv Represents the unit operating maintenance cost, P, of the photovoltaic array bat Represents the unit operating maintenance cost of the accumulator, P el Represents the maintenance cost per unit operation of the cell, P fc Represents the unit operation maintenance cost, P, of the fuel cell Ht Represents the unit operation and maintenance cost of the hydrogen storage tank;
according to the power error of the power value and the actual power value, the real-time working state of the energy storage element is adjusted, and the method comprises the following steps:
calculating a predicted power value P of the photovoltaic power generation array at the time t pv_pre (t) predicted power value P with load at time t load_pre (t) first power error Δ P 1 The calculation formula is as follows:
ΔP 1 =P pv_pre (t)-P load_pre (t);(9)
calculating the actual power value P of the photovoltaic power generation array at the time t pv (t) actual power value P of load at t moment load (t) second power error Δ P 2 The calculation formula is as follows:
ΔP 2 =P pv (t)-P load (t);(10)
according to the first power error Δ P 1 And a second power error Δ P 2 And determining the corresponding working state and the corresponding scheduling scheme of the energy storage element.
8. A computer device comprising a memory, a processor and a transceiver communicatively connected in sequence, wherein the memory is configured to store a computer program, the transceiver is configured to transmit and receive messages, and the processor is configured to read the computer program and perform the method of any one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210918641.XA CN115189377B (en) | 2022-08-01 | 2022-08-01 | Photovoltaic power generation capacity prediction-based microgrid optimal scheduling method, device and equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210918641.XA CN115189377B (en) | 2022-08-01 | 2022-08-01 | Photovoltaic power generation capacity prediction-based microgrid optimal scheduling method, device and equipment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115189377A CN115189377A (en) | 2022-10-14 |
CN115189377B true CN115189377B (en) | 2023-04-18 |
Family
ID=83521260
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210918641.XA Active CN115189377B (en) | 2022-08-01 | 2022-08-01 | Photovoltaic power generation capacity prediction-based microgrid optimal scheduling method, device and equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115189377B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019165701A1 (en) * | 2018-02-28 | 2019-09-06 | 东南大学 | Random robust coupling optimization scheduling method for alternating-current and direct-current hybrid micro-grids |
CN111969593A (en) * | 2020-07-24 | 2020-11-20 | 南昌大学 | Combined heat and power microgrid model prediction control optimization scheduling method based on hybrid energy storage |
CN113659627A (en) * | 2021-08-25 | 2021-11-16 | 中南大学 | Optimal scheduling method for micro-grid containing photovoltaic power generation and liquid air energy storage |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9373960B2 (en) * | 2013-03-13 | 2016-06-21 | Oracle International Corporation | Computerized system and method for distributed energy resource scheduling |
CN110224444B (en) * | 2019-05-16 | 2022-01-11 | 广东电网有限责任公司 | Multi-time scale coordination control method for island microgrid |
CN112865190A (en) * | 2020-12-31 | 2021-05-28 | 中国电力科学研究院有限公司 | Optimal scheduling method and system for photovoltaic and charging demand-based optical storage charging station |
CN113484785A (en) * | 2021-07-07 | 2021-10-08 | 李忠 | Battery health state estimation and residual life prediction method based on sparrow search and least square support vector machine |
-
2022
- 2022-08-01 CN CN202210918641.XA patent/CN115189377B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2019165701A1 (en) * | 2018-02-28 | 2019-09-06 | 东南大学 | Random robust coupling optimization scheduling method for alternating-current and direct-current hybrid micro-grids |
CN111969593A (en) * | 2020-07-24 | 2020-11-20 | 南昌大学 | Combined heat and power microgrid model prediction control optimization scheduling method based on hybrid energy storage |
CN113659627A (en) * | 2021-08-25 | 2021-11-16 | 中南大学 | Optimal scheduling method for micro-grid containing photovoltaic power generation and liquid air energy storage |
Also Published As
Publication number | Publication date |
---|---|
CN115189377A (en) | 2022-10-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2017000853A1 (en) | Active power distribution network multi-time scale coordinated optimization scheduling method and storage medium | |
US20200191117A1 (en) | Adaptive dynamic planning control method and system for energy storage station, and storage medium | |
CN104734200B (en) | A kind of active distribution network Optimization Scheduling based on virtual generating | |
CN111969593B (en) | Combined heat and power microgrid model prediction control optimization scheduling method based on hybrid energy storage | |
CN105680474B (en) | Control method for restraining rapid power change of photovoltaic power station through energy storage | |
CN107565607A (en) | A kind of micro-capacitance sensor Multiple Time Scales energy dispatching method based on Spot Price mechanism | |
CN109599881B (en) | Power grid frequency and voltage modulation method based on lithium manganate battery energy storage system | |
CN108462198A (en) | A kind of microgrid Optimization Scheduling of providing multiple forms of energy to complement each other based on multi-agent technology | |
CN109713666A (en) | It is a kind of based on K-means cluster electricity market under distributed energy storage economic adjusting and control method | |
CN111786417A (en) | Distributed new energy consumption-oriented active power distribution network multi-target interval optimization scheduling method | |
CN116231765B (en) | Virtual power plant output control method | |
CN112101632B (en) | Building load optimal scheduling method based on distributed estimation algorithm | |
CN115147245B (en) | Virtual power plant optimal scheduling method for industrial load participating in peak shaving auxiliary service | |
Huangfu et al. | An optimal energy management strategy with subsection bi-objective optimization dynamic programming for photovoltaic/battery/hydrogen hybrid energy system | |
CN103915851B (en) | A kind of step-length and all variable energy-storage system optimal control method of desired output of going forward one by one | |
CN114362218B (en) | Scheduling method and device for multi-type energy storage in micro-grid based on deep Q learning | |
CN112968515B (en) | Energy management strategy and system for emergency power supply of fuel cell | |
CN115189377B (en) | Photovoltaic power generation capacity prediction-based microgrid optimal scheduling method, device and equipment | |
CN114530848B (en) | Multi-time scale dynamic partitioning method for optical storage virtual power plant | |
CN116054250A (en) | Scheduling method of wind-solar-energy-storage-coupled hydrogen production system based on energy storage grouping | |
CN113852109B (en) | Fair load margin distributed regulation and control method for heterogeneous micro-grid group | |
CN114418453A (en) | Micro-grid multi-time scale energy management system based on electric power market | |
CN111740443B (en) | Multi-time scale collaborative optimization scheduling method for independent micro-grid of multi-distributed power supply | |
CN114039384A (en) | Source-storage coordination optimization scheduling method based on new energy consumption | |
CN114792995A (en) | Photovoltaic power generation and energy storage cooperative control method based on power prediction |
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 |