CN110543929A - wind speed interval prediction method and system based on Lorenz system - Google Patents
wind speed interval prediction method and system based on Lorenz system Download PDFInfo
- Publication number
- CN110543929A CN110543929A CN201910805484.XA CN201910805484A CN110543929A CN 110543929 A CN110543929 A CN 110543929A CN 201910805484 A CN201910805484 A CN 201910805484A CN 110543929 A CN110543929 A CN 110543929A
- Authority
- CN
- China
- Prior art keywords
- wind speed
- prediction
- interval
- prediction result
- sequence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 230000009194 climbing Effects 0.000 claims abstract description 36
- 238000013528 artificial neural network Methods 0.000 claims abstract description 33
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 22
- 238000012549 training Methods 0.000 claims description 24
- 239000002245 particle Substances 0.000 claims description 19
- 210000002569 neuron Anatomy 0.000 claims description 18
- 238000005457 optimization Methods 0.000 claims description 18
- 238000012360 testing method Methods 0.000 claims description 15
- 238000012937 correction Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 6
- 230000007774 longterm Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 description 21
- 238000012706 support-vector machine Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000000739 chaotic effect Effects 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 244000144992 flock Species 0.000 description 1
- 230000019637 foraging behavior Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 230000015654 memory Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- 238000000489 vacuum metal deposition Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
- G01P5/00—Measuring speed of fluids, e.g. of air stream; Measuring speed of bodies relative to fluids, e.g. of ship, of aircraft
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Aviation & Aerospace Engineering (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a wind speed interval prediction method and system based on a Lorenz system. The prediction method comprises the following steps: acquiring an original wind speed sequence; carrying out Variational Modal Decomposition (VMD) on the wind speed sequence to obtain a denoising sequence and a noise remainder; establishing a long-time neural network prediction model (LSTM), and performing preliminary prediction on the denoising sequence to obtain a preliminary prediction result; correcting the preliminary prediction result by defining a wind speed climbing event (WSR) and a wind speed climbing rate to obtain a corrected wind speed prediction result; describing the influence of a large aerodynamic system on wind speed through a Lorenz equation, and obtaining a Lorenz Disturbance Sequence (LDS); fitting the LDS through a B spline interpolation method, fixing a confidence interval on a fitting result, and acquiring an upper limit and a lower limit of a wind speed disturbance interval; summing the corrected wind speed prediction result and the wind speed disturbance interval to obtain an interval prediction result of the wind speed; the wind speed interval prediction method or system provided by the invention obviously improves the precision and reliability of the prediction model, and can obtain a high-precision prediction result.
Description
Technical Field
the invention relates to the field of wind speed prediction, in particular to a wind speed interval prediction method and system based on a Lorenz system.
Background
In recent years, global energy situation is becoming more severe and energy demand is increasing. Wind energy has attracted attention as a clean renewable energy source in new energy applications around the world, and wind power grid-connected technology has become a hot spot of international research. The International Energy Agency (IEA) reports that the wind power generation is expected to increase by 3.25 hundred million kilowatts in 2019. However, the fluctuation of wind often causes the instability of the power system after wind power integration. Therefore, the effective wind speed prediction can promote the intelligent development of the wind power industry, and the accurate wind speed prediction is an important premise for large-scale wind power development and utilization.
Disclosure of Invention
The invention aims to provide a wind speed interval prediction method and system based on a Lorenz system, which are used for obtaining a high-precision prediction result and improving the reliability of a prediction model.
In order to achieve the purpose, the invention provides the following scheme:
a Lorenz system based wind speed interval prediction method, the method comprising:
acquiring an original wind speed sequence; carrying out Variational Modal Decomposition (VMD) on the wind speed sequence to obtain a denoising sequence and a noise remainder;
establishing a long-time neural network prediction model (LSTM), and performing preliminary prediction on the denoising sequence to obtain a preliminary prediction result;
correcting the preliminary prediction result by defining a wind speed climbing event (WSR) and a wind speed climbing rate to obtain a corrected wind speed prediction result;
describing the influence of a large aerodynamic system on wind speed through a Lorenz equation, and obtaining a Lorenz Disturbance Sequence (LDS);
fitting the LDS through a B spline interpolation method, fixing a confidence interval on a fitting result, and acquiring an upper limit and a lower limit of a wind speed disturbance interval;
And summing the corrected wind speed prediction result and the wind speed disturbance interval to obtain an interval prediction result of the wind speed.
Optionally, the acquiring a denoising sequence and a noise residual specifically includes:
Acquiring original wind speed data;
setting the decomposition number; iteratively calculating a set containing all modes and their center frequencies under the determined number of decompositions; acquiring an intrinsic mode function component and a noise remainder of the wind speed signal;
And reconstructing the intrinsic mode function component of the wind speed signal to obtain a denoised wind speed sequence.
Optionally, the establishing a long-and-short-term neural network prediction model, performing preliminary prediction on the denoising sequence, and obtaining a preliminary prediction result, where the specific process includes:
Dividing the denoised wind speed sequence into a training set and a test set according to the ratio of 9: 1;
Setting a network structure of a long-time and short-time neural network, wherein the network structure comprises the number of input layer neurons, the number of hidden layer neurons and the number of output layer neurons;
training by inputting a training set into a long-time neural network;
And inputting the test set into the trained long-time neural network to obtain an initial prediction result of the wind speed.
optionally, the defining the wind speed climbing event and the wind speed climbing rate, correcting the preliminary prediction result, and obtaining a corrected wind speed prediction result, specifically including:
Calculating the wind speed gradient; introducing definition of wind speed climbing according to the wind speed gradient;
when the absolute value of the gradient is larger than a threshold value 1, and the positive gradient increase at the current moment exceeds a positive gradient threshold value 2 or the negative gradient decrease at the current moment exceeds a negative gradient threshold value 3, correcting the predicted value of the wind speed at the next moment by using the error at the current moment;
and converting the threshold values 1, 2 and 3 into a multi-objective optimization problem, and solving the optimization problem by using a Particle Swarm Optimization (PSO) with the objective of minimizing the root mean square error.
optionally, the method for describing the influence of the aerodynamic system on the wind speed through the Lorenz equation and obtaining the LDS specifically includes:
giving initial conditions (0, 1, 1), solving a Lorenz equation, and obtaining a three-dimensional LDS;
and converting the three-dimensional LDS into a one-dimensional disturbance sequence according to the Chebyshev distance.
Optionally, fitting the LDS by using a B-spline interpolation method, fixing a confidence interval to a fitting result, and obtaining an upper limit and a lower limit of a wind speed disturbance interval specifically include:
Fitting the distribution of the LDS through the B spline difference to obtain a B spline difference fitting function;
Respectively fixing the confidence intervals to be 90% and 98%, and calculating upper and lower fractional point of the fitting function;
the upper quantile is set as the upper limit of the interval prediction, and the lower quantile is set as the lower limit of the interval prediction.
optionally, the summing the corrected wind speed prediction result and the wind speed disturbance interval to obtain the interval prediction result of the wind speed specifically includes:
Adding or subtracting the upper and lower partial points under the 90% confidence interval to the corrected wind speed prediction result to obtain a wind speed interval prediction result under the 90% confidence interval;
and adding or subtracting the upper and lower partial points under the 98% confidence interval to the corrected wind speed prediction result to obtain the wind speed interval prediction result under the 98% confidence interval.
the invention also provides a wind speed interval prediction system based on the Lorenz system, which comprises the following components:
the wind speed data acquisition and denoising module is used for acquiring an original wind speed sequence; carrying out variation modal decomposition on the wind speed sequence to obtain a denoising sequence and a noise remainder;
the wind speed data preliminary prediction module is used for establishing a long-time neural network prediction model, carrying out preliminary prediction on the denoising sequence and obtaining a preliminary prediction result;
the wind speed climbing-based preliminary prediction result correction module is used for correcting the preliminary prediction result by defining a wind speed climbing event and a wind speed climbing rate to obtain a corrected wind speed prediction result;
the LDS obtaining module is used for describing the influence of the aerodynamic system on the wind speed through a Lorenz equation and obtaining the LDS;
The disturbance upper and lower limit acquisition module is used for fitting the LDS through a B spline interpolation method, fixing a confidence interval on a fitting result and acquiring the upper limit and the lower limit of a wind speed disturbance interval;
and the prediction module is used for summing the corrected wind speed prediction result and the wind speed disturbance interval to obtain an interval prediction result of the wind speed.
optionally, the wind speed data obtaining and denoising module specifically includes:
the intrinsic mode component obtaining unit is used for obtaining original wind speed data; setting the decomposition number; iteratively calculating a set containing all modes and their center frequencies under the determined number of decompositions; acquiring an intrinsic mode function component and a noise remainder of the wind speed signal;
and the denoising wind speed sequence unit is used for reconstructing the intrinsic mode function component of the wind speed signal to obtain a denoising wind speed sequence.
Optionally, the wind speed data preliminary prediction module specifically includes:
The dividing and dividing wind speed sequence unit is used for dividing the de-noised wind speed sequence into a training set and a test set according to the ratio of 9: 1;
setting a network structure unit of the long-time and short-time neural network, wherein the network structure unit is used for including the number of input layer neurons, the number of hidden layer neurons and the number of output layer neurons;
the training model unit is used for training by inputting a training set into the long-time neural network;
And the prediction unit is used for inputting the test set into the trained long-time and short-time neural network to obtain a preliminary prediction result of the wind speed.
Optionally, the preliminary prediction result correction module based on wind speed climbing specifically includes:
defining a wind speed climbing unit for calculating a wind speed gradient; introducing definition of wind speed climbing according to the wind speed gradient;
defining a correction method unit, which is used for correcting the predicted value of the wind speed at the next moment by using the error of the current moment when the absolute value of the gradient is larger than a threshold A and the increase of the positive gradient at the current moment exceeds a positive gradient threshold B or the decrease of the negative gradient at the current moment exceeds a negative gradient threshold C;
and the threshold solving unit is used for converting the thresholds A, B and C into a multi-objective optimization problem, and solving the optimization problem by using PSO (particle swarm optimization) with the objective of minimizing the root mean square error.
Optionally, the acquiring the LDS module specifically includes:
The three-dimensional LDS obtaining unit is used for giving initial conditions (0, 1, 1), solving a Lorenz equation and obtaining a three-dimensional LDS;
and the one-dimensional LDS unit is used for converting the three-dimensional LDS into the one-dimensional LDS according to the Chebyshev distance.
optionally, the module for acquiring the upper and lower limits of disturbance specifically includes:
the fitting unit is used for fitting the distribution of the LDS through the B spline difference value to obtain a B spline difference value fitting function;
the quantile point calculating unit is used for respectively fixing the confidence intervals of 90% and 98% and calculating upper and lower quantile points of the fitting function;
and determining an interval prediction upper limit unit and an interval prediction lower limit unit, wherein the upper quantile point is set as the upper limit of the interval prediction, and the lower quantile point is set as the lower limit of the interval prediction.
Optionally, the prediction module specifically includes:
the lower interval prediction result unit under the 90% confidence interval is used for adding and subtracting the upper and lower partial points under the 90% confidence interval to the corrected wind speed prediction result to obtain a wind speed interval prediction result under the 90% confidence interval;
And the interval prediction result unit under the 98% confidence interval is used for obtaining the wind speed interval prediction result under the 98% confidence interval by adding and subtracting the upper and lower partial points under the 98% confidence interval to the corrected wind speed prediction result.
compared with the prior art, the invention has the following technical effects:
the wind speed prediction method and the system are a wind speed interval prediction process based on a Lorenz system. Firstly, a signal decomposition technology VMD is adopted to carry out a noise reduction process, secondly, a long-time neural network is used for predicting data subjected to noise reduction processing, then, a wind speed gradient is introduced, a preliminary prediction result is corrected, a corrected wind speed prediction result is obtained, on the basis, a Lorentz disturbance theory is introduced to describe a large aerodynamic system, a Lorenz equation is solved to obtain an LDS, B-spline interpolation is adopted to fit the distribution of the LDS, and the upper limit and the lower limit of interval prediction are obtained by fixing different confidence intervals of a fitting function. The influence of the aerodynamic system on the wind speed is considered, and the accuracy of the short-term wind speed prediction model and the reliability of the prediction result are effectively improved by the provided wind speed interval prediction method.
drawings
in order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
FIG. 1 is a flow chart of a wind speed interval prediction method based on Lorenz system in embodiment 1 of the present invention;
FIG. 2 is a flowchart of a prediction method according to embodiment 2 of the present invention;
Fig. 3 is a block diagram of a prediction system according to embodiment 3 of the present invention;
FIG. 4 is a diagram illustrating the predicted results of 6 single models on the data set 1 according to the present invention;
FIG. 5 is a graph showing the predicted results of 6 single models on the data set 2 according to the present invention;
FIG. 6 is a graph illustrating the corrected predicted result on the data set 1 according to the present invention;
FIG. 7 is a graph illustrating the corrected predicted result on the data set 2 according to the present invention;
FIG. 8 is a graph illustrating the interval prediction results of the present invention on dataset 1 with a confidence interval of 90%;
FIG. 9 is a graph illustrating the interval prediction results of the present invention on dataset 1 with a confidence interval of 98%;
FIG. 10 is a graph illustrating the interval prediction results of the present invention on data set 2 with a confidence interval of 90%;
FIG. 11 is a graph illustrating the interval prediction results of the present invention on data set 2 with a confidence interval of 98%.
Detailed Description
the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
in order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
FIG. 1 is a flow chart illustrating a wind speed interval prediction method according to the present invention. As shown in fig. 1, the wind speed interval prediction method based on the Lorenz system includes the following steps:
step 11: the method comprises the steps of obtaining an original wind speed sequence, carrying out variational modal decomposition on the wind speed sequence, and obtaining a denoising sequence and a noise remainder.
Currently, VMDs can filter out sequences with frequency characteristics, leaving a noisy portion in clutter. In the invention, a signal processing method variational modal decomposition method is utilized to decompose and reconstruct the wind speed, and denoising is carried out to obtain a denoising sequence and a noise remainder. The method comprises the following specific steps:
Step 111: the denoising sequence constructs a constraint variational model under the current modal number: firstly, for each modal component (AK (t) and the instantaneous amplitude and the instantaneous phase respectively representing uk (t), a non-decreasing function is obtained, and t is sampling time, and an analytic signal of the modal component is obtained through Hilbert transformation; then, estimating the center frequency of each analytic signal, and transforming the frequency spectrum of each analytic signal to a fundamental frequency band; and finally, estimating the bandwidth of each modal component by using a Gaussian smooth index of the frequency shift signal, and constructing a constraint variation model shown in the formula (1).
where the center frequency of the component signal uk (t) is the partial derivative of t to the function, j2 is-1, and x (t) is the de-noising sequence.
step 112: introducing a secondary penalty factor alpha and a Lagrange multiplication operator lambda (t), changing the constraint problem into an unconstrained problem, wherein the expanded Lagrange expression is as follows:
Step 113: and obtaining an expression (3) through processes such as Fourier equidistant transformation and the like, and realizing the self-adaptive decomposition of the signal.
Where is the Fourier transform of λ (t), x (t), respectively. The center frequency is updated by the following equation:
step 114: and (4) iteratively updating until convergence meets the following conditions:
step 12: and establishing a long-time neural network prediction model, and performing preliminary prediction on the denoising sequence to obtain a preliminary prediction result.
with the continuous development of deep learning technology, the concept of time series is applied in the structural design of the Recurrent Neural Network (RNN). Therefore, RNN has good time series analysis ability. The long-term neural network is used as an improved RNN, inherits the analysis capability of the RNN on time sequence data, and makes up for the deficiency of the RNN in long-term memory. Because the long-term neural network model can effectively keep longer-term memory, certain results are obtained in the field of wind speed prediction.
step 121: dividing the denoised wind speed sequence into a training set and a test set according to the ratio of 9: 1, wherein the first 90% of data is used as the training set, and the second 10% of data is used as the test set;
Step 122: determining the structure of a long-time and short-time neural network, wherein the number of neurons in an input layer is 3, the number of neurons in a hidden layer is 5, and the number of neurons in an output layer is 1;
step 123: constructing an input matrix according to formula (6) by using the data of the training set and the test set respectively,
v1, v2, v3... denotes the 1 st, 2, 3.. wind speed values;
step 124: inputting the constructed input matrix of the training set into the long-short-time neural network according to rows, training the long-short-time neural network, and inputting the constructed input matrix of the test set into the trained long-short-time neural network according to rows to obtain a preliminary wind speed prediction result.
step 13: correcting the preliminary prediction result by defining a wind speed climbing event and a wind speed climbing rate, and acquiring a corrected wind speed prediction result, wherein the method specifically comprises the following steps of:
step 131: a wind speed ramp event is defined according to equation 7,
|v(t+Δ)-v(t)|/Δ＞v (7)
v (t0) is the wind speed value at the time of t0, delta t is a time interval, and vval is a threshold value of wind speed climbing;
step 132: the wind speed gradient is defined according to equation 8,
k(i)＝(v(i)-v(i-1))/imterval (8)
v (i) is the ith wind speed value, interval is the time interval;
Step 133: judging whether the ith or i-1 th wind speed value is larger than a wind speed climbing threshold value WRRval, namely judging whether the formula 9 or the formula 10 is satisfied,
|k(i-1)|＞WRR (9)
|k(i)|＞WRR (10)
If yes, the wind speed climbing correction is converted into a multi-objective optimization problem, and when the forward climbing is increased to a certain extent and exceeds a forward threshold value WRRup, namely a formula 11,
or the negative going ramp is reduced to a certain extent beyond the negative threshold WRRdown, i.e. equation 12,
the predicted value of the wind speed at the next moment is corrected according to the formula 13,
Representing the wind speed predicted value before wind speed climbing correction and representing the wind speed predicted value after wind speed climbing correction;
Step 134: if neither formula 9 nor formula 10 is satisfied, the predicted wind speed value at that time is not corrected, that is, the predicted wind speed value is kept unchanged before and after correction.
Step 135: for the determination of the three thresholds, using Particle Swarm Optimization (PSO);
PSO was originally proposed by Eberhart and Kennedy in 1995, the basic concept of which stems from studies of foraging behavior of bird flocks. Simulating said bird individuals with a particle, each particle being considered as a search individual in an N-dimensional search space, the current position of the particle being a candidate solution to the corresponding optimization problem, the flight of the particle being the search process of the individual. Speed, which represents how fast the movement is, and position, which represents the direction of the movement. The optimal solution searched by each particle independently is called an individual extremum, and the optimal individual extremum in the particle swarm is used as the current global optimal solution. And continuously iterating, and updating the speed and the position. And finally obtaining the optimal solution meeting the termination condition.
step 1351: initializing, firstly setting the maximum iteration number to be 5 times, the number of independent variables of an objective function to be 3 WRRup, WRRdown and WRRval, the maximum speed of a particle to be 1.5, the learning factor to be 1, the position information to be the whole search space, randomly initializing the speed and the position in a speed interval and the search space, setting the particle swarm size to be 10, and randomly initializing one flying speed for each particle.
Step 1352: and solving individual extreme values and a global optimal solution, defining an objective function as a root mean square error between the predicted wind speed and the actual wind speed, finding an optimal solution (pbest) for each particle by the individual extreme values, and finding a global value (gbest) from the optimal solutions, wherein the global optimal solution is called the current global optimal solution. And comparing with the historical global optimum, and updating.
step 1353: the speed and position are updated according to equations 14 and 15,
v＝v+c×rand()×(pbest-x)+c×rand()×(gbest-x) (14)
x＝v+x (15)
n, N being the total number of particles, vi being the velocity of the particles, rand () being a random number between (0, 1), xi being the current position of the particles, c1, c2 being learning factors;
step 1354: the termination condition is that the difference between the set iteration times or algebras meets the minimum limit 1e 10-8;
step 14: the influence of the aerodynamic system on the wind speed is described by Lorenz equation, and the LDS is obtained.
in 1963, the meteorologist edward lorentz calculated the non-periodic phenomenon from a defined equation (later called lorentz equation). The lorentz system is the earliest chaotic motion dissipation system found in numerical experiments. Its equation of state (lorentz equation) is a simplified model of weather forecasting. The method comprises the following specific steps:
Step 141: establishing a Lorenz equation as formula 14, setting parameters sigma to be 10, b to be 8/3, r to be 28, setting an initial value to be (0, 1, 1), and obtaining a three-dimensional LDS;
step 142: performing dimension reduction processing on the three-dimensional LDS according to a Chebyshev distance formula, and converting the three-dimensional LDS into a one-dimensional LDS;
d(C-C)＝max(|x-x|，|y-y|，|z-z|) (17)
Step 15: and fitting the LDS through a B spline interpolation method, fixing a confidence interval on a fitting result, and acquiring the upper limit and the lower limit of the wind speed disturbance interval.
Step 151: drawing a frequency histogram for the LDS, and setting the number of intervals of the frequency histogram to be 25;
Step 152: fitting the frequency histogram by using a B spline interpolation method to obtain a fitting function;
step 153: setting a confidence interval, obtaining a confidence upper limit and a confidence lower limit according to the fitting function, wherein the confidence upper limit takes a positive value, the confidence lower limit takes a negative value, and the upper limit and the lower limit of the wind speed disturbance interval are obtained;
step 16: and summing the corrected wind speed prediction result and the wind speed disturbance interval to obtain an interval prediction result of the wind speed.
Step 161: adding the corrected wind speed prediction result to the upper limit of the disturbance interval to obtain the upper limit of the wind speed interval prediction;
step 162: subtracting the lower limit of the disturbance interval from the corrected wind speed prediction result to obtain the predicted lower limit of the wind speed interval
In order to verify that the method has good prediction performance on the wind speed data of the actual wind power plant, a data simulation experiment is performed by adopting the wind speed of the Sotavento wind power plant in California, Spain, and FIG. 2 is a flow chart of the prediction method provided by the embodiment. As shown in fig. 2, the specific process includes:
step 21: obtaining an original wind speed sequence
in order to better verify the prediction capability of the method provided by the invention, 2 data sets of a seashore wind power plant of california, spain are selected to establish a prediction model. Data set 1 time was 2018, 9 month, 1 day 00: 9/7/00 to 2018 22: 40. the time for the second data set was 2019, 3, 9, 80: 3, month, 16, 00 to 2019, 06: 30. they represent wind speeds for different seasons with a time interval of 10 minutes, 1000 wind speeds in dataset 1 and 996 wind speeds in dataset 2. Since there are four scattered gaps in dataset 2, we do them using linear interpolation as shown in equation (18).
xt represents the t-th time, yt represents the corresponding wind speed value at that time, x represents an arbitrary time between xt and xt + i, and y represents the corresponding unknown wind speed value.
For each data set, the first 900 data (90% of the total data) were used as training set and the last 100 data were used as test set. That is, the prediction period is 16 hours and 30 minutes.
Step 22: defining an error indicator
for deterministic prediction, the most common Mean Square Error (MSE), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE) were chosen for evaluation. Their calculation formula is as follows.
yt represents the real wind speed at time t and represents the predicted wind speed at time t.
For the interval prediction, both the interval coverage (the ratio of the number of intervals including the actual wind speed) and the average interval diameter should be considered. Therefore, equation (23) and equation (24) are defined to describe the section coverage and the average section diameter, respectively.
nt represents whether the t-th interval covers the t-th real wind speed value, if the Nt is 1, the t-th real wind speed is covered, if the Nt is 0, the t-th real wind speed is not covered, Rcover represents the interval coverage rate, and daverage represents the average interval diameter. Obviously, the higher the coverage rate, the smaller the average diameter, and the better the prediction effect of the interval, which indicates that the prediction accuracy is still higher when the prediction interval is smaller.
step 23: deterministic prediction and discussion
step 231: first, the prediction results of 6 single wind speed prediction models, i.e., an autoregressive moving average model (ARMA), a Support Vector Machine (SVM), a Gradient Boosting Decision Tree (GBDT), an extreme gradient boosting tree (XGBoost), a back propagation neural network (BP), and an LSTM, were compared, and the errors on the two data sets were calculated, as shown in tables 1 and 2.
step 232: parameters of the respective model are determined. The autocorrelation coefficient parameter p and the partial autocorrelation coefficient parameter q of the ARMA are determined according to a minimum information criterion (AIC). The most common radial basis function is selected as the core function of the SVM. The learning rates and training set numbers of GBDT and XGBOST are obtained by minimizing MAE, and the lifting tree numbers of the two models are set to be 100. The BP has three layers, the number of nodes is 3-30-1, the LSTM is also set to three layers, and the number of nodes is 3-5-1. The number of hidden layer nodes set in LSTM herein is less than BP because too many nodes increase computation time, especially for LSTM (in our programming environment, more than one minute is consumed when six nodes are used), which greatly increases the computation time of the whole model), and even though LSTM has fewer hidden layer nodes, its prediction performance is better than BP.
TABLE 1 Single model prediction error on dataset 1
TABLE 2 Single model prediction error on dataset 2
step 233: and (5) analyzing the table calculation result. As can be seen from tables 1 and 2, all error indicators for the LSTM neural network are minimal on any data set. As can be seen from table 1, the error of GBDT is the largest. Compared with GBDT, the MSE of LSTM is reduced by 69.83%, the MAE is reduced by 46.78%, the RMSE is reduced by 45.08%, and the MAPE is reduced by 53.85%. In other words, LSTM has the highest prediction accuracy in the commonly used single prediction model. As can be seen from table 2, the error of the support vector machine is the largest. Compared with SVM, the MSE of LSTM is reduced by 84.63%, MAE is reduced by 61.09%, RMSE is reduced by 60.79%, and MAPE is reduced by 67.47%. That is, LSTM has the highest prediction accuracy compared to the reference prediction model.
step 234: the results of the six models predicted on the two data sets are shown in fig. 4 and 5, respectively. As is clear from fig. 4 and 5, there is a significant one-step lag in the prediction of LSTM, so we denoise the data and modify the prediction according to WSR, thereby improving LSTM. The prediction errors for the two data sets are shown in tables 3 and 4, respectively.
TABLE 3 corrected prediction error comparison on dataset 1
TABLE 4 corrected prediction error comparison on dataset 1
in tables 4 and 5, we underline the minimum error achieved by WD-LSTM for different decomposition level numbers (lev) (lev from 2 to 5 in both tables). For different IMF numbers (range 4 to 8 in Table 4 and range 3 to 7 in Table 5), we bold the minimum error achieved by VMD-LSTM. From these two tables, it can be seen that the error of WD-LSTM is minimized when the number of WD decomposition layers is 2. Moreover, most of the VMD-LSTM errors are less than the minimum error of WD-LSTM before WSR correction. This fully demonstrates that the denoising effect of VMD is much better than that of WD. On both data sets, the error of each model is significantly reduced after the predicted result is corrected by the WSR. The reduction ratio is between 5% and 30%. The minimum error on dataset 1 is obtained by VMD-LSTM-PSOR (IMF ═ 6) and the minimum error on dataset 2 is obtained by VMD-LSTM-PSOR (IMF ═ 4).
step 235: and (5) analyzing the corrected prediction result. Fig. 6 and 7 are predicted results of LSTM, VMD-LSTM and VMD-LSTM-psar for dataset 1 when IMF is 6 and dataset 2 when IMF is 4, respectively. From both figures, it can be seen that there is a significant one-step lag in the solid line representing the LSTM prediction. After VMD pretreatment, the fluctuation of the wind speed sequence is weakened, and the wind speed curve tends to be stable. And finally, correcting the prediction result by using the WSR with particle swarm optimization to enable the wind field to be closer to the actual wind speed curve, wherein the line representing the VMD-LSTM-PSOR prediction result is closest to the line representing the actual wind speed.
step 24: interval prediction results and discussion
step 241: the LDS was fitted with KDE and B-spline interpolation, respectively. Based on the deterministic prediction result, interval prediction of wind speed is obtained according to different confidence intervals. The coverage, average diameter and uncovered points are shown in table 5.
TABLE 5 analysis of Interval prediction results
step 242: and analyzing interval prediction results. Table 5 calculates the interval prediction results from different fitting methods at 90% confidence interval and 98% confidence interval, respectively. For data set 1, on the one hand, the mean diameters of KDE and B-spline interpolation are almost the same for the 90% confidence interval (1.5009 m/s and 1.5075m/s, respectively), but the coverage of B-splines is 2% higher than KDE. B-spline interval prediction covers points 2 and 74, but KDE does not. The situation is similar for the 98% confidence interval. The mean diameters were almost the same, but the coverage of the B-spline was 3% higher than KDE. B-spline interval prediction includes three points, points 19, 81 and 95, but KDE does not. The result shows that when the confidence intervals are the same and the average diameter is basically the same, the fitting effect of KDE on LDS is not as good as that of B-spline interpolation, and the confidence intervals of B-spline interpolation can cover more real wind speed points. On the other hand, for the same fitting method, the larger the confidence interval, the larger the mean diameter, which is consistent with statistical principles, but does not lead to higher coverage. Coverage also changes because a higher confidence interval means that the interval prediction may have a higher upper bound and a higher lower bound (for a KDE-fitted LDS, 90% of the confidence intervals cover points 19, 81 and 85 and 98% of the confidence intervals do not, conversely, 98% of the confidence intervals cover point 84 and 90% of the confidence intervals do not. This means that fitting to LDS can achieve higher coverage and better interval prediction results without using high confidence intervals.
step 243: we plot the results of interval prediction on two datasets as shown in fig. 8, 9, 10, 11, respectively. Fig. 8 and 10 plot the interval prediction results at 90% confidence intervals, and fig. 9 and 11 plot the interval prediction results at 98% confidence intervals. The interval prediction results cover most of the actual wind speed points, which shows that the LDS-based wind speed interval prediction is effective, the prediction results obtained by fitting LDS through B-spline interpolation are superior to that of KDE fitting LDS, and the latter is a more effective method and is consistent with that shown in Table 5.
FIG. 3 is a schematic structural diagram of a wind speed prediction system according to the present invention. As shown in fig. 3, the prediction system includes:
a wind speed data obtaining and denoising module 31, configured to obtain an original wind speed sequence; and carrying out variation modal decomposition on the wind speed sequence to obtain a denoising sequence and a noise remainder.
the wind speed data acquiring and denoising module 31 specifically includes:
acquiring original wind speed data;
setting the decomposition number; iteratively calculating a set containing all modes and their center frequencies under the determined number of decompositions; acquiring an intrinsic mode function component and a noise remainder of the wind speed signal;
And reconstructing the intrinsic mode function component of the wind speed signal to obtain a denoised wind speed sequence.
And the wind speed data preliminary prediction module 32 is used for establishing a long-time neural network prediction model, performing preliminary prediction on the denoising sequence and obtaining a preliminary prediction result.
The wind speed data preliminary prediction module 32 specifically includes:
dividing the denoised wind speed sequence into a training set and a test set according to the ratio of 9: 1;
Setting a network structure of a long-time and short-time neural network, wherein the network structure comprises the number of input layer neurons, the number of hidden layer neurons and the number of output layer neurons;
Training by inputting a training set into a long-time neural network;
and inputting the test set into the trained long-time neural network to obtain an initial prediction result of the wind speed.
A wind speed climbing-based preliminary prediction result correction module 33, configured to correct the preliminary prediction result by defining a wind speed climbing event and a wind speed climbing rate, and obtain a corrected wind speed prediction result;
the preliminary prediction result correction module 33 based on wind speed climbing specifically includes:
calculating the wind speed gradient; introducing definition of wind speed climbing according to the wind speed gradient;
when the absolute value of the gradient is larger than a threshold A, and the positive gradient increase at the current moment exceeds a positive gradient threshold B or the negative gradient decrease at the current moment exceeds a negative gradient threshold C, correcting the predicted value of the wind speed at the next moment by using the error at the current moment;
and converting the thresholds A, B and C into a multi-objective optimization problem, and solving the optimization problem by using PSO (particle swarm optimization) with the objective of minimizing the root mean square error.
and the LDS module 34 is used for describing the influence of the aerodynamic system on the wind speed through a Lorenz equation and obtaining the LDS.
The acquiring LDS module 34 specifically includes:
giving initial conditions (0, 1, 1), solving a Lorenz equation, and obtaining a three-dimensional LDS;
and converting the three-dimensional LDS into a one-dimensional disturbance sequence according to the Chebyshev distance.
And the disturbance upper and lower limit acquisition module 35 is configured to fit the LDS by a B-spline interpolation method, fix a confidence interval to the fitting result, and acquire an upper limit and a lower limit of the wind speed disturbance interval.
The disturbance upper and lower limit obtaining module 35 specifically includes:
fitting the distribution of the LDS through the B spline difference to obtain a B spline difference fitting function;
respectively fixing the confidence intervals to be 90% and 98%, and calculating upper and lower fractional point of the fitting function;
the upper quantile is set as the upper limit of the interval prediction, and the lower quantile is set as the lower limit of the interval prediction.
and the prediction module 36 is configured to sum the corrected wind speed prediction result and the wind speed disturbance interval to obtain an interval prediction result of the wind speed.
the prediction module 36 specifically includes:
adding or subtracting the upper and lower partial points under the 90% confidence interval to the corrected wind speed prediction result to obtain a wind speed interval prediction result under the 90% confidence interval;
And adding or subtracting the upper and lower partial points under the 98% confidence interval to the corrected wind speed prediction result to obtain the wind speed interval prediction result under the 98% confidence interval.
The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.
the principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (14)
1. a short-term wind speed prediction method based on wind speed characteristics, the prediction method comprising:
acquiring an original wind speed sequence; carrying out Variational Modal Decomposition (VMD) on the wind speed sequence to obtain a denoising sequence and a noise remainder;
Establishing a long-time neural network prediction model (LSTM), and performing preliminary prediction on the denoising sequence to obtain a preliminary prediction result;
Correcting the preliminary prediction result by defining a wind speed climbing event (WSR) and a wind speed climbing rate to obtain a corrected wind speed prediction result;
describing the influence of a large aerodynamic system on wind speed through a Lorenz equation, and obtaining a Lorenz Disturbance Sequence (LDS);
fitting the LDS through a B spline interpolation method, fixing a confidence interval on a fitting result, and acquiring an upper limit and a lower limit of a wind speed disturbance interval;
and summing the corrected wind speed prediction result and the wind speed disturbance interval to obtain an interval prediction result of the wind speed.
2. the short-term wind speed prediction method according to claim 1, wherein the obtaining of the denoising sequence and the noise residual specifically comprises:
acquiring original wind speed data;
setting the decomposition number; iteratively calculating a set containing all modes and their center frequencies under the determined number of decompositions; acquiring an intrinsic mode function component and a noise remainder of the wind speed signal;
and reconstructing the intrinsic mode function component of the wind speed signal to obtain a denoised wind speed sequence.
3. the short-term wind speed prediction method according to claim 1, wherein the long-term and short-term neural network prediction model is established, the denoising sequence is preliminarily predicted, and a preliminary prediction result is obtained, and the specific process includes:
Dividing the denoised wind speed sequence into a training set and a test set according to the ratio of 9: 1;
setting a network structure of a long-time and short-time neural network, wherein the network structure comprises the number of input layer neurons, the number of hidden layer neurons and the number of output layer neurons;
Training by inputting a training set into a long-time neural network;
And inputting the test set into the trained long-time neural network to obtain an initial prediction result of the wind speed.
4. The short-term wind speed prediction method according to claim 1, wherein the defining a wind speed climbing event and a wind speed climbing rate, and correcting the preliminary prediction result to obtain a corrected wind speed prediction result specifically comprise:
calculating the wind speed gradient; introducing definition of wind speed climbing according to the wind speed gradient;
When the absolute value of the gradient is larger than a threshold value 1, and the positive gradient increase at the current moment exceeds a positive gradient threshold value 2 or the negative gradient decrease at the current moment exceeds a negative gradient threshold value 3, correcting the predicted value of the wind speed at the next moment by using the error at the current moment;
And converting the threshold values 1, 2 and 3 into a multi-objective optimization problem, and solving the optimization problem by using a Particle Swarm Optimization (PSO) with the objective of minimizing the root mean square error.
5. the short-term wind speed prediction method according to claim 1, wherein the influence of the aerodynamic system on the wind speed is described by a Lorenz equation, and an LDS is obtained, and specifically comprises:
giving initial conditions (0, 1, 1), solving a Lorenz equation, and obtaining a three-dimensional LDS;
And converting the three-dimensional LDS into a one-dimensional disturbance sequence according to the Chebyshev distance.
6. the short-term wind speed prediction method according to claim 1, wherein the fitting is performed on the LDS by a B-spline interpolation method, and a confidence interval is fixed to a fitting result to obtain an upper limit and a lower limit of a wind speed disturbance interval, and specifically comprises:
fitting the distribution of the LDS through the B spline difference to obtain a B spline difference fitting function;
respectively fixing the confidence intervals to be 90% and 98%, and calculating upper and lower fractional point of the fitting function;
The upper quantile is set as the upper limit of the interval prediction, and the lower quantile is set as the lower limit of the interval prediction.
7. the short-term wind speed prediction method according to claim 1, wherein the summing the corrected wind speed prediction result and the wind speed disturbance interval to obtain the interval prediction result of the wind speed specifically comprises:
Adding or subtracting the upper and lower partial points under the 90% confidence interval to the corrected wind speed prediction result to obtain a wind speed interval prediction result under the 90% confidence interval;
and adding or subtracting the upper and lower partial points under the 98% confidence interval to the corrected wind speed prediction result to obtain the wind speed interval prediction result under the 98% confidence interval.
8. a short term wind speed prediction system, characterized in that the prediction system comprises:
the wind speed data acquisition and denoising module is used for acquiring an original wind speed sequence; carrying out variation modal decomposition on the wind speed sequence to obtain a denoising sequence and a noise remainder;
the wind speed data preliminary prediction module is used for establishing a long-time neural network prediction model, carrying out preliminary prediction on the denoising sequence and obtaining a preliminary prediction result;
The wind speed climbing-based preliminary prediction result correction module is used for correcting the preliminary prediction result by defining a wind speed climbing event and a wind speed climbing rate to obtain a corrected wind speed prediction result;
the LDS obtaining module is used for describing the influence of the aerodynamic system on the wind speed through a Lorenz equation and obtaining the LDS;
The disturbance upper and lower limit acquisition module is used for fitting the LDS through a B spline interpolation method, fixing a confidence interval on a fitting result and acquiring the upper limit and the lower limit of a wind speed disturbance interval;
And the prediction module is used for summing the corrected wind speed prediction result and the wind speed disturbance interval to obtain an interval prediction result of the wind speed.
9. the short-term wind speed prediction system of claim 8, wherein the wind speed data acquisition and de-noising module specifically comprises:
The intrinsic mode component obtaining unit is used for obtaining original wind speed data; setting the decomposition number; iteratively calculating a set containing all modes and their center frequencies under the determined number of decompositions; acquiring an intrinsic mode function component and a noise remainder of the wind speed signal;
and the denoising wind speed sequence unit is used for reconstructing the intrinsic mode function component of the wind speed signal to obtain a denoising wind speed sequence.
10. The short-term wind speed prediction system of claim 8, wherein the wind speed data preliminary prediction module specifically comprises:
the dividing and dividing wind speed sequence unit is used for dividing the de-noised wind speed sequence into a training set and a test set according to the ratio of 9: 1;
setting a network structure unit of the long-time and short-time neural network, wherein the network structure unit is used for including the number of input layer neurons, the number of hidden layer neurons and the number of output layer neurons;
The training model unit is used for training by inputting a training set into the long-time neural network;
And the prediction unit is used for inputting the test set into the trained long-time and short-time neural network to obtain a preliminary prediction result of the wind speed.
11. The short-term wind speed prediction system of claim 8, wherein the preliminary prediction result correction module based on wind speed ramp comprises:
defining a wind speed climbing unit for calculating a wind speed gradient; introducing definition of wind speed climbing according to the wind speed gradient;
Defining a correction method unit, which is used for correcting the predicted value of the wind speed at the next moment by using the error of the current moment when the absolute value of the gradient is greater than a threshold value 1, and the increase of the positive gradient at the current moment exceeds a positive gradient threshold value 2 or the decrease of the negative gradient at the current moment exceeds a negative gradient threshold value 3;
and the threshold solving unit is used for converting the thresholds 1, 2 and 3 into a multi-objective optimization problem, and solving the optimization problem by using the PSO with the objective of minimizing the root mean square error.
12. the short term wind speed prediction system of claim 8, wherein the acquiring LDS module specifically comprises:
the three-dimensional LDS obtaining unit is used for giving initial conditions (0, 1, 1), solving a Lorenz equation and obtaining a three-dimensional LDS;
and the one-dimensional LDS unit is used for converting the three-dimensional LDS into the one-dimensional LDS according to the Chebyshev distance.
13. The short-term wind speed prediction system of claim 8, wherein the obtain disturbance upper and lower limits module specifically comprises:
the fitting unit is used for fitting the distribution of the LDS through the B spline difference value to obtain a B spline difference value fitting function;
the quantile point calculating unit is used for respectively fixing the confidence intervals of 90% and 98% and calculating upper and lower quantile points of the fitting function;
And determining an interval prediction upper limit unit and an interval prediction lower limit unit, wherein the upper quantile point is set as the upper limit of the interval prediction, and the lower quantile point is set as the lower limit of the interval prediction.
14. the short term wind speed prediction system of claim 8, wherein the prediction module specifically comprises:
the lower interval prediction result unit under the 90% confidence interval is used for adding and subtracting the upper and lower partial points under the 90% confidence interval to the corrected wind speed prediction result to obtain a wind speed interval prediction result under the 90% confidence interval;
and the interval prediction result unit under the 98% confidence interval is used for obtaining the wind speed interval prediction result under the 98% confidence interval by adding and subtracting the upper and lower partial points under the 98% confidence interval to the corrected wind speed prediction result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910805484.XA CN110543929B (en) | 2019-08-29 | 2019-08-29 | Wind speed interval prediction method and system based on Lorenz system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910805484.XA CN110543929B (en) | 2019-08-29 | 2019-08-29 | Wind speed interval prediction method and system based on Lorenz system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110543929A true CN110543929A (en) | 2019-12-06 |
| CN110543929B CN110543929B (en) | 2023-11-14 |
Family
ID=68712231
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910805484.XA Active CN110543929B (en) | 2019-08-29 | 2019-08-29 | Wind speed interval prediction method and system based on Lorenz system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110543929B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111950759A (en) * | 2020-05-18 | 2020-11-17 | 武汉科技大学 | Short-term wind speed prediction method based on two-stage decomposition, LSTM and AT |
| CN112132360A (en) * | 2020-09-29 | 2020-12-25 | 中交建冀交高速公路投资发展有限公司 | Wind speed short-time confidence interval prediction method and system based on LSTM and GMM |
| CN112183866A (en) * | 2020-09-29 | 2021-01-05 | 中南大学 | Short-term wind speed exceeding probability prediction method and system |
| CN112765544A (en) * | 2020-12-30 | 2021-05-07 | 国网湖南省电力有限公司 | Strong wind power correction and forecast method under influence of typhoon of power transmission line |
| CN112785052A (en) * | 2021-01-14 | 2021-05-11 | 吉林大学 | Wind speed and wind direction prediction method based on particle filter algorithm |
| CN113516320A (en) * | 2021-09-14 | 2021-10-19 | 国能日新科技股份有限公司 | Wind speed correction and predicted wind speed optimization method and device based on multi-objective genetic algorithm |
| CN114814963A (en) * | 2022-03-03 | 2022-07-29 | 吉林大学 | B-spline channel extraction-based time domain electromagnetic data very low frequency noise suppression method |
| CN115345387A (en) * | 2022-10-18 | 2022-11-15 | 哈尔滨工业大学(深圳)(哈尔滨工业大学深圳科技创新研究院) | Wind field wind speed prediction method and device and storage medium |
| CN115688588A (en) * | 2022-11-04 | 2023-02-03 | 自然资源部第一海洋研究所 | Sea surface temperature daily change amplitude prediction method based on improved XGB method |
| CN117217421A (en) * | 2023-11-07 | 2023-12-12 | 东北大学 | Visual analysis method and system for auxiliary decision making of thick plate production plan |
| CN117725368A (en) * | 2024-02-07 | 2024-03-19 | 浙江公路水运工程咨询集团有限公司 | Highway slope displacement prediction method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101699518A (en) * | 2009-10-30 | 2010-04-28 | 华南理工大学 | Method for beautifying handwritten Chinese character based on trajectory analysis |
| US7831419B2 (en) * | 2005-01-24 | 2010-11-09 | Smith International, Inc. | PDC drill bit with cutter design optimized with dynamic centerline analysis having an angular separation in imbalance forces of 180 degrees for maximum time |
| CN104794546A (en) * | 2015-04-29 | 2015-07-22 | 武汉大学 | Wind power climbing forecasting method based on deep confidence network classifying method |
| CN108154260A (en) * | 2017-12-15 | 2018-06-12 | 南京信息工程大学 | A kind of short-term wind power forecast method |
| CN108520269A (en) * | 2018-03-10 | 2018-09-11 | 华北电力大学（保定） | A kind of wind speed forecasting method and forecasting wind speed system |
| CN108846508A (en) * | 2018-05-30 | 2018-11-20 | 华北电力大学（保定） | A kind of wind speed forecasting method and system based on atmospheric perturbation |
-
2019
- 2019-08-29 CN CN201910805484.XA patent/CN110543929B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7831419B2 (en) * | 2005-01-24 | 2010-11-09 | Smith International, Inc. | PDC drill bit with cutter design optimized with dynamic centerline analysis having an angular separation in imbalance forces of 180 degrees for maximum time |
| CN101699518A (en) * | 2009-10-30 | 2010-04-28 | 华南理工大学 | Method for beautifying handwritten Chinese character based on trajectory analysis |
| CN104794546A (en) * | 2015-04-29 | 2015-07-22 | 武汉大学 | Wind power climbing forecasting method based on deep confidence network classifying method |
| CN108154260A (en) * | 2017-12-15 | 2018-06-12 | 南京信息工程大学 | A kind of short-term wind power forecast method |
| CN108520269A (en) * | 2018-03-10 | 2018-09-11 | 华北电力大学（保定） | A kind of wind speed forecasting method and forecasting wind speed system |
| CN108846508A (en) * | 2018-05-30 | 2018-11-20 | 华北电力大学（保定） | A kind of wind speed forecasting method and system based on atmospheric perturbation |
Non-Patent Citations (1)
| Title |
|---|
| 张亚刚 等: "基于Lorenz扰动分布和VMD的神经网络风速预测研究", 《华北电力大学学报》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111950759A (en) * | 2020-05-18 | 2020-11-17 | 武汉科技大学 | Short-term wind speed prediction method based on two-stage decomposition, LSTM and AT |
| CN112132360A (en) * | 2020-09-29 | 2020-12-25 | 中交建冀交高速公路投资发展有限公司 | Wind speed short-time confidence interval prediction method and system based on LSTM and GMM |
| CN112183866A (en) * | 2020-09-29 | 2021-01-05 | 中南大学 | Short-term wind speed exceeding probability prediction method and system |
| CN112765544A (en) * | 2020-12-30 | 2021-05-07 | 国网湖南省电力有限公司 | Strong wind power correction and forecast method under influence of typhoon of power transmission line |
| CN112765544B (en) * | 2020-12-30 | 2023-09-15 | 国网湖南省电力有限公司 | Method for correcting and forecasting strong wind power under influence of typhoon of power transmission line |
| CN112785052B (en) * | 2021-01-14 | 2022-04-19 | 吉林大学 | Wind speed and wind direction prediction method based on particle filter algorithm |
| CN112785052A (en) * | 2021-01-14 | 2021-05-11 | 吉林大学 | Wind speed and wind direction prediction method based on particle filter algorithm |
| CN113516320B (en) * | 2021-09-14 | 2021-12-10 | 国能日新科技股份有限公司 | Wind speed correction and predicted wind speed optimization method and device based on multi-objective genetic algorithm |
| CN113516320A (en) * | 2021-09-14 | 2021-10-19 | 国能日新科技股份有限公司 | Wind speed correction and predicted wind speed optimization method and device based on multi-objective genetic algorithm |
| CN114814963A (en) * | 2022-03-03 | 2022-07-29 | 吉林大学 | B-spline channel extraction-based time domain electromagnetic data very low frequency noise suppression method |
| CN115345387A (en) * | 2022-10-18 | 2022-11-15 | 哈尔滨工业大学(深圳)(哈尔滨工业大学深圳科技创新研究院) | Wind field wind speed prediction method and device and storage medium |
| CN115688588A (en) * | 2022-11-04 | 2023-02-03 | 自然资源部第一海洋研究所 | Sea surface temperature daily change amplitude prediction method based on improved XGB method |
| CN117217421A (en) * | 2023-11-07 | 2023-12-12 | 东北大学 | Visual analysis method and system for auxiliary decision making of thick plate production plan |
| CN117725368A (en) * | 2024-02-07 | 2024-03-19 | 浙江公路水运工程咨询集团有限公司 | Highway slope displacement prediction method |
| CN117725368B (en) * | 2024-02-07 | 2024-05-31 | 浙江公路水运工程咨询集团有限公司 | Highway slope displacement prediction method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110543929B (en) | 2023-11-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110543929A (en) | wind speed interval prediction method and system based on Lorenz system | |
| CN110309603B (en) | Short-term wind speed prediction method and system based on wind speed characteristics | |
| Chen et al. | Short-term wind speed forecasting with principle-subordinate predictor based on Conv-LSTM and improved BPNN | |
| CN109284677B (en) | Bayesian filtering target tracking algorithm | |
| CN110942194A (en) | Wind power prediction error interval evaluation method based on TCN | |
| Zhou et al. | Short-term wind power prediction optimized by multi-objective dragonfly algorithm based on variational mode decomposition | |
| CN110910004A (en) | Reservoir dispatching rule extraction method and system with multiple uncertainties | |
| CN109255728B (en) | Photovoltaic power generation power neural network prediction method based on chaotic phase space optimization reconstruction | |
| CN110766200A (en) | Method for predicting generating power of wind turbine generator based on K-means mean clustering | |
| CN111027775A (en) | Step hydropower station generating capacity prediction method based on long-term and short-term memory network | |
| Li et al. | Short-term prediction of the power of a new wind turbine based on IAO-LSTM | |
| CN111242353A (en) | Wind power combined prediction modeling and prediction method | |
| CN114548532A (en) | VMD-based TGCN-GRU ultra-short-term load prediction method and device and electronic equipment | |
| CN110879927A (en) | Sea clutter amplitude statistical distribution field modeling method for sea target detection | |
| CN115310669A (en) | Ultra-short-term wind power prediction method based on secondary decomposition and IWOA-LSSVM | |
| CN115186923A (en) | Photovoltaic power generation power prediction method and device and electronic equipment | |
| CN115423145A (en) | Photovoltaic power prediction method based on Kmeans-VMD-WT-LSTM method | |
| Sun et al. | Short-term power load prediction based on VMD-SG-LSTM | |
| CN113449920A (en) | Wind power prediction method, system and computer readable medium | |
| CN113435595A (en) | Two-stage optimization method for extreme learning machine network parameters based on natural evolution strategy | |
| CN117592593A (en) | Short-term power load prediction method based on improved quadratic modal decomposition and WOA optimization BILSTM-intent | |
| CN117154680A (en) | Wind power prediction method based on non-stationary transducer model | |
| CN111476402A (en) | Wind power generation capacity prediction method coupling meteorological information and EMD technology | |
| CN116307250A (en) | Short-term load prediction method and system based on typical daily feature selection | |
| CN113933915B (en) | Short-term and temporary extrapolation forecasting method based on space-time disturbance information interaction integration nesting |
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 |