CN112001490A - Method and system for determining confidence capacity of grid-connected photovoltaic system - Google Patents
Method and system for determining confidence capacity of grid-connected photovoltaic system Download PDFInfo
- Publication number
- CN112001490A CN112001490A CN202010654225.4A CN202010654225A CN112001490A CN 112001490 A CN112001490 A CN 112001490A CN 202010654225 A CN202010654225 A CN 202010654225A CN 112001490 A CN112001490 A CN 112001490A
- Authority
- CN
- China
- Prior art keywords
- photovoltaic
- time step
- load
- capacity
- permeability
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 230000035699 permeability Effects 0.000 claims abstract description 73
- 238000013528 artificial neural network Methods 0.000 claims abstract description 40
- 238000012549 training Methods 0.000 claims abstract description 25
- 238000013507 mapping Methods 0.000 claims abstract description 16
- 238000009826 distribution Methods 0.000 claims description 31
- 238000004364 calculation method Methods 0.000 abstract description 10
- 238000004088 simulation Methods 0.000 description 33
- 238000011156 evaluation Methods 0.000 description 21
- 238000010248 power generation Methods 0.000 description 16
- 230000006870 function Effects 0.000 description 13
- 238000010586 diagram Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 11
- 230000000694 effects Effects 0.000 description 8
- 230000035515 penetration Effects 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 5
- 238000012546 transfer Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 230000011664 signaling Effects 0.000 description 4
- 239000013598 vector Substances 0.000 description 4
- 238000003646 Spearman's rank correlation coefficient Methods 0.000 description 3
- 230000007423 decrease Effects 0.000 description 3
- 230000002441 reversible effect Effects 0.000 description 3
- 238000003860 storage Methods 0.000 description 3
- 230000001174 ascending effect Effects 0.000 description 2
- 210000004027 cell Anatomy 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 210000002569 neuron Anatomy 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 238000002310 reflectometry Methods 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 241000196324 Embryophyta Species 0.000 description 1
- 241000321453 Paranthias colonus Species 0.000 description 1
- 241001085205 Prenanthella exigua Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005282 brightening Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 230000003467 diminishing effect Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Strategic Management (AREA)
- Mathematical Analysis (AREA)
- Pure & Applied Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Computational Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Mathematical Optimization (AREA)
- Operations Research (AREA)
- Tourism & Hospitality (AREA)
- Public Health (AREA)
- Game Theory and Decision Science (AREA)
- Probability & Statistics with Applications (AREA)
- Databases & Information Systems (AREA)
- Water Supply & Treatment (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Primary Health Care (AREA)
- Algebra (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
Abstract
The invention discloses a method and a system for determining confidence capacity of a grid-connected photovoltaic system, wherein the method comprises the following steps: obtaining photovoltaic permeability, time step and photovoltaic load related similarity indexes; substituting the photovoltaic permeability, the time step and the photovoltaic load related similarity index into a pre-trained empirical model to determine the confidence capacity of the photovoltaic system; the empirical model is obtained by training the mapping relation between the confidence capacity and the photovoltaic permeability, the time step and the photovoltaic load related similarity index by using an artificial neural network. The present invention can estimate the confidence capacity for any given photovoltaic permeability, time step and photovoltaic load related similarity index without the need to use complex, time-consuming inverse monte carlo SMC calculations.
Description
Technical Field
The invention relates to the technical field of power generation, in particular to a method and a system for determining the confidence capacity of a grid-connected photovoltaic system.
Background
In recent years, large-scale grid-connected photovoltaic power stations have rapidly risen in order to meet increasing energy consumption and realize sustainable environments. With the increase of photovoltaic permeability, a photovoltaic power station contributes not only to a power value but also to a capacity value of a power system or a distribution network, and therefore, a definition of a confidence capacity is proposed. At present, photovoltaic power generation is widely applied, and confidence capacity evaluation is an important problem in photovoltaic power generation planning and scheduling.
There are currently reliability-based methods and approximations to evaluate the photovoltaic confidence capacity. The method for evaluating the confidence capacity based on the reliability indexes such as the power shortage probability, the power shortage expected value and the like is used for evaluating the confidence capacity of the photovoltaic power station from the aspect of contribution of the photovoltaic power station to the reliability of a power system. The reliability-based method mainly includes an effective load capacity method, an equivalent conventional power method and an equivalent enterprise power method, wherein the effective load capacity method adopts effective load capacity (ELCC) to measure the confidence capacity of the photovoltaic system. ELCC characterizes the capacity at which system load can be increased while keeping reliability before and after the intermittent power generation access system unchanged. The index can visually represent the newly increased load capacity of the system after the generator set is newly added. In practice, the confidence capacity of the planned conventional power generation can be measured by the capacity reduced by the accessed intermittent energy, and in the process of measuring the confidence capacity, the process of calculating the reliability by adopting the reverse Monte Carlo SMC method is complex and time-consuming, so that the calculation efficiency is low.
Disclosure of Invention
In order to solve the above disadvantages in the prior art, the present invention provides a method for determining a confidence capacity of a grid-connected photovoltaic system, including:
obtaining photovoltaic permeability, time step and photovoltaic load related similarity indexes;
substituting the photovoltaic permeability, the time step and the photovoltaic load related similarity index into a pre-trained empirical model to determine the confidence capacity of the photovoltaic system;
the empirical model is obtained by training the mapping relation between the confidence capacity and the photovoltaic permeability, the time step and the photovoltaic load related similarity index by using an artificial neural network.
Preferably, the training of the empirical model comprises:
setting a plurality of photovoltaic capacities;
for each photovoltaic capacity, simulating under different time step lengths to obtain corresponding photovoltaic output power distribution;
forming a sample set based on all time step lengths corresponding to all photovoltaic capacities and photovoltaic output power distribution;
establishing an artificial neural network based on different photovoltaic permeabilities, time step lengths and photovoltaic load related similarity values;
and training the artificial neural network based on the sample set to obtain a mapping relation between the confidence capacity and the photovoltaic permeability, the time step length and the photovoltaic load related similarity index.
Preferably, the empirical model is a mapping relationship between the signalling capacity and photovoltaic permeability, the time step and the photovoltaic load related similarity index, as shown in the following formula:
κCC＝g(r,Δt,η)
in the formula: kappaCCIs the confidence capacity of the photovoltaic system; r is photovoltaic permeability; Δ t is the time step; η is the chronological photovoltaic-load related similarity index.
Preferably, the photovoltaic-load related similarity index η is represented by the following formula:
η＝v×γC
in the formula: v is a ramp rate indicator of the power of the photovoltaic output as a function of time, gammaCIs the dependence of the photovoltaic output power on the load distribution.
Preferably, the power of the photovoltaic output is a slope rate indicator v that varies with time, as shown in the following formula:
in the formula: n represents the number of photovoltaic output units;
is a load time sequence;
is the absolute maximum fluctuation of the photovoltaic output and load in the time step Δ t;
a normalized ramp rate representing a time series of photovoltaic output power;
representing the corresponding photovoltaic capacity of the (i + 1) th photovoltaic output unit at the time step delta t;
representing the corresponding photovoltaic capacity of the ith photovoltaic output unit at the time step delta t;
representing the normalized load ramp rate over time T; l is(i+1)ΔtRepresenting the fluctuation of the photovoltaic output and load of the (i + 1) th photovoltaic output unit at the time step delta t; l isiΔtRepresenting the fluctuation of the photovoltaic output and load of the ith photovoltaic output unit at the time step deltat.
Preferably, the artificial neural network is a back propagation neural network.
Based on the same invention concept, the invention also provides a system for determining the confidence capacity of the grid-connected photovoltaic system, which comprises the following steps:
the acquisition module is used for acquiring photovoltaic permeability, a time step and a photovoltaic load related similarity index;
the determining module is used for substituting the photovoltaic permeability, the time step and the photovoltaic load related similarity index into a pre-trained empirical model to determine the confidence capacity of the photovoltaic system;
the empirical model is obtained by training the mapping relation between the confidence capacity and the photovoltaic permeability, the time step and the photovoltaic load related similarity index by using an artificial neural network.
Preferably, the system further comprises a training module; the training module is specifically configured to:
setting a plurality of photovoltaic capacities;
for each photovoltaic capacity, simulating under different time step lengths to obtain corresponding photovoltaic output power distribution;
forming a sample set based on all time step lengths corresponding to all photovoltaic capacities and photovoltaic output power distribution;
establishing an artificial neural network based on different photovoltaic permeabilities, time step lengths and photovoltaic load related similarity values;
and training the artificial neural network based on the sample set to obtain a mapping relation between the confidence capacity and the photovoltaic permeability, the time step length and the photovoltaic load related similarity index.
Preferably, the empirical model is a mapping relationship between the signalling capacity and photovoltaic permeability, the time step and the photovoltaic load related similarity index, as shown in the following formula:
κCC＝g(r,Δt,η)
in the formula: kappaCCIs the confidence capacity of the photovoltaic system; r is photovoltaic permeability; Δ t is the time step; η is a chronological photovoltaic load related similarity index.
Preferably, the photovoltaic load-related similarity index η is represented by the following formula:
η＝v×γC
in the formula: v is a ramp rate indicator of the power of the photovoltaic output as a function of time, gammaCIs the dependence of the photovoltaic output power on the load distribution.
Compared with the closest prior art, the technical scheme provided by the invention has the following beneficial effects:
according to the technical scheme provided by the invention, after the photovoltaic permeability, the time step length and the photovoltaic load related similarity index are obtained; substituting the photovoltaic permeability, the time step and the photovoltaic load related similarity index into a pre-trained empirical model to determine the confidence capacity of the photovoltaic system; the empirical model in the technical scheme is obtained by training the mapping relation between the confidence capacity and the photovoltaic permeability, the time step and the photovoltaic load related similarity index by using an artificial neural network. The present invention can estimate the confidence capacity for any given photovoltaic permeability, time step and photovoltaic load related similarity index without the need to use complex, time-consuming inverse monte carlo SMC calculations.
Drawings
Fig. 1 is a flowchart of a method for determining a confidence capacity of a grid-connected photovoltaic system according to the present invention;
FIG. 2 is a schematic diagram of the secant method for ELCC evaluation provided by the present invention;
FIG. 3 is a schematic diagram of an artificial neural network architecture for photovoltaic confidence capacity assessment provided by the present invention;
FIG. 4 is a diagram illustrating an ELCC iterative simulation in accordance with an embodiment of the present invention;
FIG. 5 is a graph of a fitted curve of photovoltaic confidence capacity versus η exponent in an embodiment of the present disclosure;
FIG. 6 is a schematic graph of the time step size of PV-load related-similarity index at different PV permeabilities in an example of the present invention;
FIG. 7 is a graphical illustration of the effect of photovoltaic permeability on signaling capacity in an embodiment of the invention;
FIG. 8 is a plot of the photovoltaic confidence capacity box at different time intervals for 100MW and 1000MW photovoltaic power stations in an embodiment of the present invention;
FIG. 9 is a graphical illustration of the effect of time interval and photovoltaic permeability on photovoltaic confidence capacity in an example of the invention;
fig. 10 is a schematic diagram of a photovoltaic confidence capacity evaluation result in an embodiment of the present invention.
Detailed Description
For a better understanding of the present invention, reference is made to the following description taken in conjunction with the accompanying drawings and examples.
Example 1: as shown in fig. 1, the present invention provides a method for determining a confidence capacity of a grid-connected photovoltaic system, including:
s1, acquiring photovoltaic permeability, time step and photovoltaic load related similarity indexes;
s2, substituting the photovoltaic permeability, the time step and the photovoltaic load related similarity index into a pre-trained empirical model to determine the confidence capacity of the photovoltaic system;
the empirical model is obtained by training the mapping relation between the confidence capacity and the photovoltaic permeability, the time step and the photovoltaic load related similarity index by using an artificial neural network.
The invention firstly establishes an array Plane (POA) irradiance model, and when the standard component of irradiance at a certain moment is known, irradiance reaching an inclined photovoltaic component can be calculated according to the following formulas (1) to (5). Wherein the standard components of irradiance comprise: direct Normal Irradiance (DNI), global level irradiance (GHI), and diffuse level irradiance (DHI) of solar irradiance.
POA irradiance EPOAAs shown in the following formula:
EPOA＝Eb+Eg+Ed (1)
in the formula: ebIs a POA beam component, EgIs POA is the ground reflection component, EdIs the POA diffusion component.
Wherein the POA beam component EbCan be obtained by the following formula:
Eb＝DNI×cos(AOI) (2)
AOI＝cos-1[cos(θZ)cos(θT)+sin(θZ)sin(θT)×cos(θA-θα)] (3)
in the formula: AOI is the angle of incidence, θTIs the inclination of the array, θaIs the azimuth of the array, 0 deg. north, 90 deg. east, 180 deg. south, 270 deg. west, clockwise. Azimuth angle theta of the sunAAnd zenith angle thetaZCan be derived from the Sun Position Algorithm (SPA) model described by Reda and Andreas.
The ground reflection component EgCan be obtained by the following formula:
in the formula: ρ is the albedo, which describes the reflectivity of the earth's surface. Albedo represents the GHI reflected, with low reflectivity for dark areas and high values for bright white areas. In the present invention, for dry concrete and fresh snow on the ground, ρ is 0.2 and ρ is 0.8, respectively.
The invention adopts a Sandia empirical model of sky scattered radiation to calculate E according to the following formuladComponent (b):
in the formula: thetaTIs the inclination of the array, θZFor the zenith angle derived from the Sun Position Algorithm (SPA) model described by Reda and Andreas, in equation (5), the first term is an isotropic sky scattered radiation model and the second term is an empirical correction term to account for the brightening effects of the sun's surroundings and horizon.
The invention provides a photovoltaic output model based on a low-pass filter, and provides a first-order transfer function to depict a nonlinear relation between photovoltaic output power and irradiance on the basis of frequency domain analysis, wherein the nonlinear relation is represented by the following formula:
in the formula: g (t) is the GHI time series, p (t) is the simulated photovoltaic power output time series. The area S (hectare) of the photovoltaic power station is a main factor influencing the fluctuation smoothness of photovoltaic power generation.
Converting the transfer function from analog to digital filter, the discrete transfer function can be written as:
in the formula:
z＝esfand f is the sampling frequency of the measured irradiance time series, P*(W) is the nominal power of the transformer, G*(1000W/m2) Representing the reference irradiance. For the sake of simplicity, the components of a photovoltaic power plant are considered to be absolutely reliable, irrespective of faultsAnd (4) characteristics. The photovoltaic power density in the invention represents the unit area direct current output power of the solar panel, and the ground fixed inclination is 65-dcW/m2And adopted as a rule of thumb. Thus, the installed capacity of a photovoltaic power plant with an area of 1 hectare is P*＝0.65MW。
The invention provides a method for calculating the reliability of a photovoltaic system based on reverse Monte Carlo (SMC) simulation, and the Effective Load Carrying Capacity (ELCC) of the photovoltaic system is determined by adopting a secant method. Fig. 2 shows the reliability curves of the basic power system, the power system with the additional conventional generator and the power system with the photovoltaic generator set.
The secant method comprises the following implementation steps:
the first step is as follows: calculating the expected load shortage value of the basic power system without the photovoltaic generator set by utilizing SMC simulation, and recording the expected load shortage value as R0And annual peak load Lpk0And C of a conventional generatorconAnd in FIG. 2 with point S (L)pk0,R0) And (4) showing. C is to bePVCalculating reliability R when photovoltaic power generation unit is added to basic systemA＝R(Ccon+CPV,Lpk0) With A (L)pk0,RA) And (4) showing. Peak load increase to L in the yearpk0+CPVThen, C is addedPVPhotovoltaic system reliability can be expressed as RB＝R(CCON+CPV,Lpk0+CPV) And B (L) in combinationpk0+CPV,RB) And (4) showing.
The second step is that: calculating the straight line segment AB and f (x) R0Cross point S of1Determining the corresponding annual peak load L1. Estimating a new reliability level R by SMC simulationC＝R(CCON+CPV,L1) If | RC-R0If l >, then segments BC and f (x) R continue to be calculated0Cross point S of2And C is used for replacing A. This process is run iteratively until | RC-R0Where 0.001 is a desired error threshold.
The third step: the effective on-load capability ELCC of the PV system is determined and, when the convergence condition is satisfied,suppose the intersection point is D (L)D，R0) The calculated peak load may be expressed as LD＝Lpk0+ Δ L. This means that C is installedPVThe photovoltaic system can take on the additional Δ L load and maintain a specified level of reliability. Capacity value is determined by the base system Lpk0Annual peak load of and annual peak load L of the photovoltaic power generation systemDThe difference determines the confidence capacity, which can be determined by (8), and it is clear that the value Δ L of the extra capacity of the photovoltaic plant belongs to [0, CPV]And (3) a range.
In the steps, the confidence capacity of the planned conventional power generation can be measured by the capacity which can reduce the capacity of the accessed intermittent energy, and the confidence capacity of the newly added intermittent energy is not measured by using the ELCC directly.
According to the three steps, the reliability of the photovoltaic system is calculated according to the reverse Monte Carlo (SMC) simulation, and the effective on-load capability (ELCC) of the photovoltaic system needs to be determined by adopting a secant method, and the method specifically comprises the following steps: firstly, determining the reliability curves of a basic power system, a power system with an additional conventional generator and a power system with a photovoltaic generator set, then determining the intersection point of the curves, and calculating the straight line segments AB and f (x) R0Cross point S of1Determining the corresponding annual peak load L1. Estimating a new reliability level R by SMC simulationC＝R(CCON+CPV,L1) If | RC-R0If l >, then segments BC and f (x) R continue to be calculated0Cross point S of2And C is used for replacing A. This process is run iteratively until | RC-R0L >,. The calculation process through the SMC is complex, and meanwhile, when the confidence capacity of the photovoltaic system is calculated, the estimation of a new reliability level R through the SMC simulation needs to be repeated continuouslyC＝R(CCON+CPV,L1) If | RC-R0If l >, then segments BC and f (x) R continue to be calculated0Cross point S of2Replacing A with C, a process which takes a lot of time。
The invention provides a new measurement method for simultaneously describing the variability and the time correlation of photovoltaic output and load distribution, wherein a new slope rate index v of the photovoltaic output changing according to time is introduced:
in the formula: n represents the number of PV output cells,
a time series of the load is represented,
representing the absolute maximum fluctuation of the PV output and load, in time steps at. The numerator term represents the normalized ramp rate of the PV power time series and the denominator term represents the normalized load ramp rate over T time.
A PV-load related similarity index eta in time sequence is defined, and main factors influencing the ELCC evaluation of the photovoltaic system are described and defined as follows:
η＝v×γC (10)
eta is a PV-load related similarity index according to the time sequence, and v is a slope rate index changing according to the time, namely the change rate of the photovoltaic output; gamma rayCIs the dependence of photovoltaic output on load distribution.
In practice the confidence capacity kappa of the photovoltaic systemCCMainly composed of PV permeability r, time step delta t, change rate v of photovoltaic output and correlation gamma of photovoltaic output and load distributionCThe specific expression is as follows:
κCC＝f(r,Δt,v,γc) (11)
establishing a Back Propagation (BP) neural network for estimating the confidence capacity of the photovoltaic system for different PV permeabilities, time scales and correlations, and calculating the photovoltaic confidence capacity based on an empirical model of the artificial neural network, the empirical model being represented by the following formula:
κCC＝g(r,Δt,η) (12)
in the formula: r is the PV permeability, Δ t is the time step and the PV-load related-similarity index η.
The invention provides an empirical model which is constructed based on an artificial neural network, and the construction steps are as follows:
(1) selecting different PV capacities and performing extensive simulations at various simulation intervals yields an Artificial Neural Network (ANN) sample set. Extensive simulations were performed on PV capacity vectors (10, 50, 100, 200, 300, 400, 500, 600, 700, 800, 900, 1000) MW and at various simulation time intervals (2, 3, 4, 5, 7, 10, 15, 20, 30, 35, 40, 45, 50, 60 minutes), at specified photovoltaic capacities and specified time steps, 30 scenarios were obtained by stochastic permutation of the photovoltaic output, different photovoltaic output distributions were obtained by stochastic transformation of the 364 day photovoltaic output time series on a daily time scale, a sample set of 5040 units was obtained by simulation;
(2) a Back Propagation (BP) neural network established aiming at different photovoltaic permeability, time scale and photovoltaic load related similarity values is used for estimating the confidence capacity of the photovoltaic system, and a Levenberg-Marquardt back propagation training algorithm is adopted to train the neural network;
(3) and after training is finished, recording all connection weights of the network, establishing an empirical model, and performing simulation evaluation on the PV confidence capacity by using the trained network.
The relationship between the confidence capacity and different photovoltaic permeability, time step and photovoltaic load related similar values in the empirical model is shown as the following formula:
κCC＝g(r,Δt,η) (13)
in the formula: r is PV permeability; Δ t is the time step; eta is the photovoltaic load related similarity index.
In this example, photovoltaic permeability is photovoltaic capacity/total capacity; the photovoltaic load related similarity index needs to be obtained according to photovoltaic output power distribution and load distribution.
The invention considers the intermittency of photovoltaic power generation, provides a new measuring method to describe the time correlation between photovoltaic output and load distribution, namely a slope rate index v changing according to time, and effectively verifies the influence of factors such as photovoltaic penetration, simulation time granularity, the correlation between changing photovoltaic and load time sequence and the like on the evaluation of the confidence capacity of a photovoltaic system.
The confidence capacity evaluation method provided by the invention can be applied to the confidence capacity evaluation under any condition, the law of the decrease of the marginal capacity value is verified, and the optimal time scale of the confidence capacity evaluation is obtained by utilizing the established model.
The present embodiment adopts an IEEE RTS-79 system as a basic power system, and has 32 conventional generators with capacity value of 3405MW and peak load of 2850 MW. Annual load data, capacity and availability of conventional generators are obtained from the IEEE RTS-79 system, with an average 3s irradiance obtained over a moving time window over a given time interval. And when the reliability is calculated, determining the load value by adopting a linear interpolation method. Given the load and PV time series, the output state of a conventional generator was sampled using only SMC simulation in performing the reliability calculations.
The method for evaluating the confidence capacity by using the empirical model based on the artificial neural network provided by the invention comprises the following steps:
PV penetration is a key factor for ELCC estimation, and in general, photovoltaic power plants have high confidence capacity with low photovoltaic penetration, and low confidence capacity values with high PV penetration.
PV penetration is defined by the formula:
due to the intermittency of solar irradiance, the optimal photovoltaic confidence capacity evaluation interval should be selected.
In addition, in order to reflect the influence of the PV and load changes on the ELCC evaluation, a new time-varying ramp rate index v is provided:
in the formula: n represents the number of PV output cells,
a time series of the load is represented,
representing the absolute maximum fluctuation of the PV output and load, in time steps at. The numerator term represents the normalized ramp rate of the PV power time series and the denominator term represents the normalized load ramp rate over T time.
The correlation between PV and load distribution is also an important factor influencing the credit evaluation of photovoltaic power generation capacity, and
and V2＝{LΔt,L2Δt,...,LnΔtAre the time series of PV output and load demand, respectively. The invention introduces a Spearman rank correlation coefficient rhoSTo describe V1And V2The correlation between them.
Will vector V1And V2Sorting in ascending order and according to variables
And LiΔtPosition in ascending order vector records level xiAnd yi. Variable di＝xi-yiIs a rank xiAnd yiThe Spearman rank correlation coefficient describes only the trend of the two curves, regardless of their average distance. To facilitate the description of the average distance between two time series, the Frechet distance is introduced. The Frechet distance measures two continuous straight or curved lines (V)1And V2) A measure of similarity therebetween, V in equation (17)1And V2Discrete Frechet distance ofdF(V1,V2) Provides a good approximation of the continuous metric and can be implemented with a simple algorithm:
dF(V1,V2)＝min{||D|||D is a coupling between V1 and V2} (17)
V1and V2D is according to V1And V2The order of the midpoints, and the length of modulo D is the length of the longest link in D, i.e. D
Where the dist () function represents the euclidean norm, the discrete Frechet distance is defined as the maximum point state distance that is minimized in all parameterizations, while other point state distances on the curve have no effect on the Frechet distance. To account for all point state distances. The present invention selects the mean Frechet distance definition. Average discrete Frechet distanceα(V1,V2) Can be defined by the sum of the discrete Frechet distances, as defined below:
wherein
And L'I＝LiΔt/max(V1,V2) Normalized PV Power Generation and load demand, respectively, to obtain the Spearman rank correlation coefficient ρSAnd normalized average discrete Frechet distanceαAfter that, a metric γ is definedCIt represents both the correlation and the average distance (or similarity) between two curves:
if ρSThe value is higher and the lower limit value is higher,αwith smaller values, i.e., PV distribution substantially matches the load distribution and the curves are close, the PV output matches the load demand well, in which case a higher PV confidence capacity can be achieved.
In practice, ELCC κ for photovoltaic power plantsCCMainly composed of PV permeability r, time step delta t, change rate v of photovoltaic output and correlation gamma of photovoltaic output and load distributionCThe specific expression is as follows:
κCC＝f(r,Δt,v,γc) (21)
in consideration of the above factors, a PV-load related similarity index η in time series is defined, describing main factors affecting the ELCC evaluation of the photovoltaic system:
η＝v×γC (22)
equation (21) can be rewritten as:
κCC＝g(r,Δt,η) (23)
here, η is a comprehensive measure of the time step, correlation and average discrete distance describing the PV and load distributions.
Fig. 3 is a Back Propagation (BP) neural network established for different PV permeabilities r, time steps at, and PV-load related similarity indices η to estimate the confidence capacity of a photovoltaic system. Wherein, wijRepresenting the weight between nodes i and j, the bias of the neuron, bias, is represented by θi(k) And thetaj(k) And (4) showing. The invention indicates that the hidden layer neuron NHLN is only a possible choice, not an optimal choice, and a quantum (Levenberg-Marqudt, LM) back propagation training algorithm is adopted to train the neural network. The hidden layer and the output layer respectively adopt hyperbolic tangent Sigmoid transfer function "tansig" and linear transfer function "purelin". The learning rate and maximum iterations are set to 0.05 and 3000.
To obtain the ANN sample set, extensive simulations were performed on PV capacity vectors (10, 50, 100, 200, 300, 400, 500, 600, 700, 800, 900, 1000) MW and at various simulation intervals (2, 3, 4, 5, 7, 10, 15, 20, 30, 35, 40, 45, 50, 60 minutes). At each simulation (designated photovoltaic capacity and designated time step), 30 scenes are obtained through the random permutation of the sunlight output, in order to obtain different photovoltaic output distributions, the sunlight output time sequence of 364 days is randomly transformed on the time scale of each day, and a sample set of 5040 units is obtained through simulation. After the artificial neural network finishes the training process, all the connection weights of the network are recorded, the trained ANN has the capability of reasoning and popularization, an empirical model proposed in the formula (10) is established, and the trained network can be used for evaluating the PV confidence capacity without performing time-consuming SMC simulation under the conditions of given PV permeability r, time step delta t and PV-load correlation-similarity index eta.
Fig. 4 shows a simulation process of the confidence capacity evaluation of a 100MW photovoltaic system in 1-h time step. The ELCC of the photovoltaic device was calculated in each SMC simulation iteration and the ELCC curve is given in fig. 4. Assuming that the photovoltaic power density is 65-dcW/m2153.8 hectare area of 100MW photovoltaic system. The parameters estimated for the ELCC of a 100MW photovoltaic power station are: r is 0.0285, v is 0.1629, ρS＝0.4683，a＝0.4523，γC1.0353, η 0.1687. The invention adopts a Garver approximation method to calculate the photovoltaic confidence capacity, and compares the photovoltaic confidence capacity with the SMC simulation result, and the calculation result is consistent with the calculation result of the method.
To illustrate the proposed relationship between photovoltaic load-related similarity index and photovoltaic confidence capacity, a multi-scenario simulation was performed on the PV output curve and annual load distribution in the formula IEEE RTS-79 system. Each point in fig. 5 represents a scene for a particular PV output time series, and in each scene simulation, the PV outputs for each day are randomly arranged daily to obtain a particular PV output distribution. And obtaining a fitting curve by adopting a linear fitting technology, wherein the fitting curve represents a positive correlation relation between the photovoltaic confidence capacity and the photovoltaic load correlation similarity index.
The PV-load related similarity η also varies with time interval as shown in fig. 6, indicating that η varies with simulation time interval and PV permeability. It can be seen that at different simulation intervals, the PV-load correlation-similarity index increases with increasing simulation interval; the higher the PV permeability, the larger the PV-load correlation-similarity index at the same simulation time step, since the high PV permeability results in a smaller average distance between the photovoltaic output and the load demand; the higher the photovoltaic permeability is, the larger the power station area is, and the more obvious the smoothing effect on the photovoltaic power generation output is; the lower the photovoltaic permeability, the less the simulation time scale has an effect on the PV-load related-similarity index.
When the artificial neural network is trained, the photovoltaic confidence capacity assessment can be achieved by utilizing the generalization capability of the ANN. Fig. 7 illustrates the influence of PV permeability on the confidence capacity at 1-h time resolution, and the research results are consistent, which shows that the PV confidence capacity will saturate with the increase of PV installation capacity, and the conclusion that the marginal capacity value of the photovoltaic system is reduced can be obtained, and the rule of diminishing marginal utility is met. The results of table 1 show that the marginal capacity value of photovoltaic power generation decreases as the number of photovoltaic devices increases.
TABLE 1 decreasing marginal capacity value under 1-h temporal resolution of photovoltaic systems
The photovoltaic confidence capacity box plots for the 100MW and 1000MW photovoltaic power stations at different time intervals are given in fig. 8. The simulation time step size had a significant impact on the 100MW and 1000MW photovoltaic confidence capacity estimates. The results show that the selection of the photovoltaic output time interval and the load distribution has a great influence on the evaluation of the photovoltaic confidence capacity, and the optimal time step is also determined by the PV permeability.
From fig. 9, it can be found that the lower photovoltaic permeability (200MW photovoltaic capacity) results in a range of change in the confidence capacity (30.1862%, 42.2492%) that is greater than the range of change in the confidence capacity (8.0520%, 12.2028%) of the higher photovoltaic permeability (1000MW photovoltaic capacity). This is mainly due to the smoothing effect of large photovoltaic power plants.
FIG. 10 is a trained ANN-based empirical model demonstrating the effect of time intervals and photovoltaic penetration on photovoltaic power generation capability credit assessment. In FIG. 10, it can be found that the results are in certain degrees from Table 1The gap, but still within an acceptable range. It can be seen that the photovoltaic confidence capacity evaluation depends on the choice of time interval, and as the time interval is extended, the photovoltaic confidence capacity will be more affected. This can be understood from fig. 6 that as the time interval increases, the PV-load similarity correlation index will become higher and higher, resulting in a larger PV confidence capacity value; the optimal time step of the photovoltaic confidence capacity assessment varies with the degree of photovoltaic penetration, and in fig. 9, the influence of the time step on the evaluation of the photovoltaic power generation capacity credit decreases with increasing photovoltaic penetration. In practical application, a larger time scale can be selected for photovoltaic confidence capacity evaluation, so that the photovoltaic permeability is improved, the calculation speed is increased, and the calculation accuracy is kept. The trained artificial neural network shown in fig. 3 can be used to evaluate the confidence capacity for a given time step. This process is repeated for different time steps to obtain a sequence of confidence capacities that can be used to determine the optimal time interval. This process is repeated for different time steps to obtain a sequence of confidence capacities that can be used to determine the optimal time interval. Table 2 shows Δ t at different PV permeabilities at η -0.1687optA reference value. Detailed results of photovoltaic confidence capacity evaluation using the proposed empirical model are given in fig. 10.
TABLE 2 optimal time step for photovoltaic confidence capacity evaluation at different photovoltaic permeabilities
After simulation and simulation verification, the large grid-connected photovoltaic confidence capacity evaluation method based on the empirical model can be found out, and the confidence capacity can be accurately estimated under the similar conditions of any given photovoltaic permeability, time step and photovoltaic load under the condition that the complex and time-consuming SMC calculation is avoided.
Example 2: based on the same invention concept, the invention also provides a system for determining the confidence capacity of the grid-connected photovoltaic system, which comprises the following steps:
the acquisition module is used for acquiring photovoltaic permeability, a time step and a photovoltaic load related similarity index;
the determining module is used for substituting the photovoltaic permeability, the time step and the photovoltaic load related similarity index into a pre-trained empirical model to determine the confidence capacity of the photovoltaic system;
the empirical model is obtained by training the mapping relation between the confidence capacity and the photovoltaic permeability, the time step and the photovoltaic load related similarity index by using an artificial neural network.
In an embodiment, the system further comprises a training module; the training module is specifically configured to:
setting a plurality of photovoltaic capacities;
for each photovoltaic capacity, simulating under different time step lengths to obtain corresponding photovoltaic output power distribution;
forming a sample set based on all time step lengths corresponding to all photovoltaic capacities and photovoltaic output power distribution;
establishing an artificial neural network based on different photovoltaic permeabilities, time step lengths and photovoltaic load related similarity values;
and training the artificial neural network based on the sample set to obtain a mapping relation between the confidence capacity and the photovoltaic permeability, the time step length and the photovoltaic load related similarity index.
In an embodiment, the empirical model is a mapping between the signaling capacity and the photovoltaic permeability, the time step and the photovoltaic load related similarity index, as shown in the following formula:
κCC＝g(r,Δt,η)
in the formula: kappaCCIs the confidence capacity of the photovoltaic system; r is photovoltaic permeability; Δ t is the time step; η is a chronological photovoltaic load related similarity index.
In an embodiment, the photovoltaic load related similarity index η is as follows:
η＝v×γC
in the formula: v is a ramp rate indicator of the power of the photovoltaic output as a function of time, gammaCFor photovoltaic output power and load distributionAnd (4) correlation.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The present invention is not limited to the above embodiments, and any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention are included in the scope of the claims of the present invention which are filed as the application.
Claims (10)
1. A method for determining confidence capacity of a grid-connected photovoltaic system is characterized by comprising the following steps:
obtaining photovoltaic permeability, time step and photovoltaic load related similarity indexes;
substituting the photovoltaic permeability, the time step and the photovoltaic load related similarity index into a pre-trained empirical model to determine the confidence capacity of the photovoltaic system;
the empirical model is obtained by training the mapping relation between the confidence capacity and the photovoltaic permeability, the time step and the photovoltaic load related similarity index by using an artificial neural network.
2. The method of claim 1, wherein the training of the empirical model comprises:
setting a plurality of photovoltaic capacities;
for each photovoltaic capacity, simulating under different time step lengths to obtain corresponding photovoltaic output power distribution;
forming a sample set based on all time step lengths corresponding to all photovoltaic capacities and photovoltaic output power distribution;
establishing an artificial neural network based on different photovoltaic permeabilities, time step lengths and photovoltaic load related similarity values;
and training the artificial neural network based on the sample set to obtain a mapping relation between the confidence capacity and the photovoltaic permeability, the time step length and the photovoltaic load related similarity index.
3. The method of claim 2, wherein the empirical model maps confidence capacity with photovoltaic permeability, time step size, and photovoltaic load related similarity index as follows:
κCC＝g(r,Δt,η)
in the formula: kappaCCIs the confidence capacity of the photovoltaic system; r is photovoltaic permeability; Δ t is the time step; η is the chronological photovoltaic-load related similarity index.
4. The method of claim 3, wherein the photovoltaic-load related similarity index η is represented by the following formula:
η＝v×γC
in the formula: v is a ramp rate indicator of the power of the photovoltaic output as a function of time, gammaCIs the dependence of the photovoltaic output power on the load distribution.
5. The method of claim 4, wherein the power of the photovoltaic output is ramped in a time-varying rate indicator v, as shown in the following equation:
in the formula: n represents the number of photovoltaic output units;
is a load time sequence;
is the absolute maximum fluctuation of the photovoltaic output and load in the time step Δ t;
a normalized ramp rate representing a time series of photovoltaic output power;
representing the corresponding photovoltaic capacity of the (i + 1) th photovoltaic output unit at the time step delta t;
representing the corresponding photovoltaic capacity of the ith photovoltaic output unit at the time step delta t;
representing the normalized load ramp rate over time T; l is(i+1)ΔtRepresenting the fluctuation of the photovoltaic output and load of the (i + 1) th photovoltaic output unit at the time step delta t; l isiΔtRepresenting the fluctuation of the photovoltaic output and load of the ith photovoltaic output unit at the time step deltat.
6. The method of claim 2, wherein the artificial neural network is a back propagation neural network.
7. A grid-connected photovoltaic system confidence capacity determination system is characterized by comprising:
the acquisition module is used for acquiring photovoltaic permeability, a time step and a photovoltaic load related similarity index;
the determining module is used for substituting the photovoltaic permeability, the time step and the photovoltaic load related similarity index into a pre-trained empirical model to determine the confidence capacity of the photovoltaic system;
the empirical model is obtained by training the mapping relation between the confidence capacity and the photovoltaic permeability, the time step and the photovoltaic load related similarity index by using an artificial neural network.
8. The system of claim 7, further comprising a training module; the training module is specifically configured to:
setting a plurality of photovoltaic capacities;
for each photovoltaic capacity, simulating under different time step lengths to obtain corresponding photovoltaic output power distribution;
forming a sample set based on all time step lengths corresponding to all photovoltaic capacities and photovoltaic output power distribution;
establishing an artificial neural network based on different photovoltaic permeabilities, time step lengths and photovoltaic load related similarity values;
and training the artificial neural network based on the sample set to obtain a mapping relation between the confidence capacity and the photovoltaic permeability, the time step length and the photovoltaic load related similarity index.
9. The system of claim 8, wherein the empirical model maps confidence capacity with photovoltaic permeability, time step size, and photovoltaic load related similarity index as follows:
κCC＝g(r,Δt,η)
in the formula: kappaCCIs the confidence capacity of the photovoltaic system; r is photovoltaic permeability; Δ t is the time step; η is a chronological photovoltaic load related similarity index.
10. The method of claim 9, wherein the photovoltaic load-related similarity index η is represented by the following formula:
η＝v×γC
in the formula: v is a ramp rate indicator of the power of the photovoltaic output as a function of time, gammaCIs the dependence of the photovoltaic output power on the load distribution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010654225.4A CN112001490A (en) | 2020-07-08 | 2020-07-08 | Method and system for determining confidence capacity of grid-connected photovoltaic system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010654225.4A CN112001490A (en) | 2020-07-08 | 2020-07-08 | Method and system for determining confidence capacity of grid-connected photovoltaic system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112001490A true CN112001490A (en) | 2020-11-27 |
Family
ID=73466799
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010654225.4A Pending CN112001490A (en) | 2020-07-08 | 2020-07-08 | Method and system for determining confidence capacity of grid-connected photovoltaic system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112001490A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117220597A (en) * | 2023-11-08 | 2023-12-12 | 徐州工程学院 | Quick frequency response rate monitoring system of photovoltaic power station |
-
2020
- 2020-07-08 CN CN202010654225.4A patent/CN112001490A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117220597A (en) * | 2023-11-08 | 2023-12-12 | 徐州工程学院 | Quick frequency response rate monitoring system of photovoltaic power station |
| CN117220597B (en) * | 2023-11-08 | 2024-01-30 | 徐州工程学院 | Quick frequency response rate monitoring system of photovoltaic power station |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Stathopoulos et al. | Wind power prediction based on numerical and statistical models | |
| Elminir et al. | Prediction of hourly and daily diffuse fraction using neural network, as compared to linear regression models | |
| Hering et al. | Powering up with space-time wind forecasting | |
| Ding et al. | Empirical model for capacity credit evaluation of utility-scale PV plant | |
| Saeed et al. | An optimal approach of wind power assessment using Chebyshev metric for determining the Weibull distribution parameters | |
| Nuño et al. | On the simulation of aggregated solar PV forecast errors | |
| CN111833202B (en) | Farmland evapotranspiration short-term prediction method considering crop coefficient dynamic change and rainfall | |
| US20100036650A1 (en) | Method for Determining Heterogeneous Bottom Friction Distributions using a Numerical Wave Model | |
| Shahriari et al. | Using the analog ensemble method as a proxy measurement for wind power predictability | |
| CN114330935B (en) | New energy power prediction method and system based on multiple combination strategies integrated learning | |
| US12100951B2 (en) | System for estimating renewable energy generation quantity in real-time | |
| CN115586591B (en) | Automatic forecasting method and device for storm surge | |
| CN110350535A (en) | A kind of meter and large-scale wind power and the grid-connected distribution network voltage probability of stability appraisal procedure of electric car | |
| CN117526274A (en) | New energy power prediction method, electronic equipment and storage medium in extreme climate | |
| CN110781458A (en) | Method for predicting surface solar irradiance based on mixed regression model | |
| CN115100376A (en) | Electromagnetic spectrum map implementation method based on improved inverse distance interpolation method | |
| Meenal et al. | Review on mathematical models for the prediction of solar radiation | |
| CN111811465A (en) | Method for predicting sea wave effective wave height based on multi-sine function decomposition neural network | |
| CN105138729A (en) | Filling method based on PSO-GRNN (Particle Swarm Optimization-Generalized Regression Neural Network) for defect wind speed values of wind turbines in wind power plant | |
| CN112001490A (en) | Method and system for determining confidence capacity of grid-connected photovoltaic system | |
| Kurniawan et al. | Two-step artificial neural network to estimate the solar radiation at Java Island. | |
| CN112070320B (en) | Ultra-short-term wind power prediction method and system based on dynamic harmonic regression | |
| CN118336671A (en) | Urban building photovoltaic power generation capacity probability prediction method based on autoregressive circulation network | |
| CN117277304A (en) | Photovoltaic power generation ultra-short-term power prediction method and system considering sunrise and sunset time | |
| Chang et al. | Neural network with multi-trend simulating transfer function for forecasting typhoon wave |
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 |