CN115099448A - Short-term load prediction method based on VMD-Prophet - Google Patents
Short-term load prediction method based on VMD-Prophet Download PDFInfo
- Publication number
- CN115099448A CN115099448A CN202210392592.0A CN202210392592A CN115099448A CN 115099448 A CN115099448 A CN 115099448A CN 202210392592 A CN202210392592 A CN 202210392592A CN 115099448 A CN115099448 A CN 115099448A
- Authority
- CN
- China
- Prior art keywords
- prediction
- vmd
- prophet
- load
- short
- 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 39
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 22
- 230000006870 function Effects 0.000 claims description 12
- 241000512668 Eunectes Species 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 7
- 230000003190 augmentative effect Effects 0.000 claims description 6
- 238000002474 experimental method Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 238000012549 training Methods 0.000 abstract description 9
- 238000012360 testing method Methods 0.000 abstract description 6
- 241000728173 Sarima Species 0.000 abstract description 4
- 238000011156 evaluation Methods 0.000 abstract description 2
- 238000011161 development Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 229910052731 fluorine Inorganic materials 0.000 description 1
- 125000001153 fluoro group Chemical group F* 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a short-term load prediction method based on VMD-Prophet, which can be used for improving the accuracy of short-term power load prediction. The method comprises the following steps: on the basis of a Prophet prediction model, introducing VMD decomposition, and dividing a prepared data set into a training set and a test set by using the prepared data set, wherein the training set is used for training the model, and the test set is used for evaluating the precision of the final model; inputting the decomposed subsequences into a Prophet prediction model respectively for prediction, and then accumulating prediction results of the subsequences to obtain a final prediction result; then, evaluating the prediction result by adopting two indexes of the average absolute value percentage error and the root mean square error; finally, the load of the future day is predicted, the same evaluation index is adopted, and experimental results show that the prediction results of other LSTM and SARIMA used for load prediction and a Prophet model which does not perform VMD decomposition on the input signal are not as good as those of the VMD-Prophet prediction model, so that the advantages of the method in the aspect of short-term load prediction are proved, and the accuracy of short-term load prediction can be improved.
Description
The technical field is as follows:
the invention relates to the field of power load prediction, and provides a short-term load prediction method based on VMD-Prophet, which is suitable for performing short-term load prediction and improving the prediction effect.
Background art:
under the background of the high-speed development of economy in China, the prediction of the power load becomes an important and difficult task. The high-precision short-term load prediction has important significance for making a high-efficiency and economic power generation plan, reasonably arranging unit output, ensuring the safety and stability of the power system, improving economic benefit and reducing unnecessary energy consumption by a dispatching management department of the power system. Meanwhile, with the development of smart grids, high-precision load prediction is increasingly required.
The VMD-Prophet prediction model decomposes an input original load sequence into subsequences with better regularity, and compared with empirical mode decomposition and wavelet decomposition, the VMD can restore original signals better and has better noise robustness. The time series prediction framework Prophet has better flexibility compared with the traditional time series prediction method, is easy to adapt to the seasonality of multiple seasons, and makes different assumptions on the trend through analysis. The measured values do not need to be distributed at equal intervals, interpolation missing values are not needed, and the fitting speed is high. The method and the device are combined to be applied to short-term load prediction, and the accuracy of load prediction can be effectively improved.
The invention content is as follows:
in order to solve the problems, the invention provides a short-term load prediction method based on VMD-Prophet.
A short-term load prediction method based on VMD-Prophet is characterized by comprising the following steps:
s1: before an original load sequence is brought into a Prophet model for prediction, performing Variational Modal Decomposition (VMD) on the original load sequence to obtain a subsequence with better regularity;
s2: the VMD decomposition can be used to decompose the fluctuating signal into K eigenmode function sub-signals of different frequency bands, and the specific process is as follows:
when the VMD is used for K-order decomposition, it can be regarded as the following constraint variation problem, as shown in formula (1):
where f (t) is the undigested main signal, { u { k }＝{u 1 ,…,u k And ω k }＝{ω 1 ,…,ω k Represents the set of K-order modes and the center frequency, respectively. δ (t) is a dirac distribution, which represents a convolution,
as a function of mode u k Corresponding to center frequency omega k J is an imaginary number.
Introducing an augmented Lagrange function, and solving the optimal solution of the constraint variation problem, wherein the optimal solution is shown as a formula (2):
in the formula: alpha is a secondary penalty factor used for reducing the interference of Gaussian noise; λ is the lagrange multiplier. And solving the optimal solution of the constraint variation problem and the augmented Lagrangian function by using a multiplier alternating direction method.
The final VMD update process is as follows, as shown in equations (3) to (5):
in the formula
Are respectively f (t),
And λ n (t) Fourier transform; tau is an updating parameter; and n is an iteration parameter.
If the predetermined discrimination accuracy ε > 0 satisfies the following relationship, as shown in equation (6), the VMD converges and the update is stopped.
S3: respectively bringing the decomposed load subsequences into a Prophet prediction model for prediction, and finally accumulating the prediction results of all the subsequences to obtain the final prediction result;
s4: and evaluating the prediction result by using two indexes of a mean absolute value percent error (MAPE) and a Root Mean Square Error (RMSE), wherein the indexes are shown in the following formula (7) and formula (8):
in the formula: x is the number of predicted As a result of load prediction, x real The load is the real value.
S5: the VMD algorithm parameters are respectively set as: initial center frequency ω is 0 and convergence criterion e is 10 -7 After repeated experiments, the secondary penalty factor and the resolution order are finally set to be alpha equal to 2000 and K equal to 3.
S6: based on an Anaconda platform, the programming language is Python, a virtual environment with a Python version of 3.7 is created, and the construction of a VMD-Prophet prediction model is completed in Spyder;
s7: the prediction of the VMD-Prophet prediction model for each load subsequence is realized in Spyder through Python programming;
s8: the effect of the VMD-Prophet predictive model on load prediction was tested in Spyder.
Further, the VMD algorithm described in S2 decomposes the original load sequence into subsequences with better regularity, and extracts some trend components or noise components existing in the prediction process and affecting the prediction result separately, so as to reduce the influence of the trend components or noise components on the short-term power load overall prediction.
Further, the Prophet prediction model of S3 has better flexibility, can easily adapt to seasonality in multiple seasons, and makes different assumptions on trends through analysis; in addition, the measured values do not need to be distributed at equal intervals, interpolation missing values are not needed, and the fitting speed is high.
Further, the evaluation index described in S4 evaluates the prediction result by the percentage error of the average absolute value and the root mean square error, and quantifies the prediction result.
Further, the VMD-Prophet load prediction model described in S6 can be implemented in a virtual environment created by the Anaconda platform by Python programming in Spyder, and directly perform the decomposition and prediction of the load sequence.
As described above, the short-term load prediction method based on VMD-Prophet according to the present invention has the following effects:
1. firstly, dividing prepared data into a training set and a test set, wherein the training set is used for training a model, the test set is used for evaluating the precision of a final model, then, on the basis of a Prophet prediction model, VMD decomposition is introduced, an original load sequence is decomposed into subsequences with better regularity, meanwhile, the influence of a trend component or a noise component on short-term power load overall prediction is reduced, and the decomposed subsequences are respectively input into the Prophet prediction model for prediction;
2. the best prediction of the VMD-Prophet model was demonstrated when compared to other models for load prediction LSTM, SARIMA, and Prophet without VMD decomposition of the input signal.
The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
Description of the drawings:
FIG. 1 is a prediction flow chart of a short-term load prediction method based on VMD-Prophet according to the present invention;
FIG. 2 is a VMD decomposition result diagram of the VMD-Prophet-based short-term load prediction method of the present invention;
FIG. 3 is a comparison graph of model prediction curves of the raw data, LSTM, SARIMA, Prophet and VMD-Prophet of the short-term load prediction method based on VMD-Prophet of the present invention.
FIG. 4 shows the accuracy of the VMD-Prophet-based short-term load prediction method and models for future day load prediction.
The specific implementation mode is as follows:
reference is made to fig. 1-4. The invention relates to a short-term load prediction method based on VMD-Prophet, which comprises the following specific steps:
1. a short-term load prediction method based on VMD-Prophet is characterized by comprising the following steps:
s1: before an original load sequence is brought into a Prophet model for prediction, performing Variational Modal Decomposition (VMD) on the original load sequence to obtain a subsequence with better regularity;
s2: the VMD decomposition can be used to decompose the fluctuating signal into K eigenmode function sub-signals of different frequency bands, and the specific process is as follows:
when the VMD is used for K-order decomposition, it can be regarded as the following constraint variation problem, as shown in formula (1):
where f (t) is the undigested main signal, { u { k }＝{u 1 ,…,u k And ω k }＝{ω 1 ,…,ω k Represents the set of K-order modes and the center frequency, respectively. δ (t) is a dirac distribution, which represents a convolution,
as a function of mode u k Corresponding to center frequency omega k J is an imaginary number.
Introducing an augmented Lagrange function, and solving the optimal solution of the constraint variation problem, wherein the optimal solution is shown as a formula (2):
in the formula: alpha is a secondary penalty factor used for reducing the interference of Gaussian noise; λ is the lagrange multiplier. And solving the optimal solution of the constraint variation problem and the augmented Lagrangian function by using a multiplier alternating direction method.
The final VMD update process is as follows, as shown in equations (3) to (5):
in the formula
Respectively f (t),
And λ n (t) Fourier transform; tau is an updating parameter; and n is an iteration parameter.
If the predetermined discrimination accuracy ε > 0 satisfies the following relationship, as shown in equation (6), the VMD converges and the update is stopped.
S3: respectively bringing the decomposed load subsequences into a Prophet prediction model for prediction, and finally accumulating the prediction results of each subsequence to obtain a final prediction result;
s4: and evaluating the prediction result by using two indexes of a mean absolute value percent error (MAPE) and a Root Mean Square Error (RMSE), wherein the indexes are shown in the following formula (7) and formula (8):
in the formula: x is a radical of a fluorine atom predicted As a result of load prediction, x real The load is the real value.
S5: the VMD algorithm parameters are respectively set as: initial center frequency ω is 0 and convergence criterion e is 10 -7 After repeated experiments, the secondary penalty factor and the resolution order are finally set to be alpha equal to 2000 and K equal to 3.
S6: based on an Anaconda platform, the programming language is Python, a virtual environment with a Python version of 3.7 is created, and the building of a VMD-Prophet prediction model is completed in a Spyder;
s7: the prediction of the VMD-Prophet prediction model for each load subsequence is realized in Spyder through Python programming;
s8: the effect of the VMD-Prophet predictive model on load prediction was tested in Spyder.
2. The VMD-Prophet-based short-term load prediction method according to claim 1, wherein: the VMD algorithm decomposes the original load sequence into subsequences with better regularity, and simultaneously extracts trend components or noise components which influence the prediction result and exist in the prediction process independently, so that the influence of the trend components or the noise components on the short-term power load overall prediction is reduced.
3. The VMD-Prophet-based short-term load prediction method of claim 1, wherein: the Prophet prediction model has better flexibility, can easily adapt to the seasonality of a plurality of seasons, and makes different assumptions on the trend through analysis; in addition, the measured values do not need to be distributed at equal intervals, interpolation missing values are not needed, and the fitting speed is high.
4. The VMD-Prophet-based short-term load prediction method according to claim 1, wherein: the prediction result is evaluated by the average absolute value percentage error and the root mean square error, so that the prediction effect can be better shown.
5. The VMD-Prophet-based short-term load prediction method according to claim 1, wherein: the VMD-Prophet load prediction model can be realized in a virtual environment created by an Anaconda platform through Python programming in Spyder, the decomposition and prediction of a load sequence are directly carried out, and the prediction flow is shown in FIG. 1.
The prediction process of the VMD-Prophet model can be realized in a virtual environment created by an Anaconda platform through Python programming, and can be directly used for predicting the load and improving the accuracy of load prediction.
The VMD-Prophet model introduces VMD decomposition on the basis of a Prophet prediction model, the decomposition result is shown in figure 2, the decomposed subsequences are respectively input into the Prophet prediction model for prediction, and then the prediction results are accumulated; and then evaluating the prediction result by adopting two indexes of the percentage error of the average absolute value and the root-mean-square error.
Dividing the prepared data set into a training set and a testing set, wherein the training set is used for training the model, and the testing set is used for evaluating the precision of the final model; the comparison curves between the raw data and the predicted values of the models are shown in fig. 3 and the prediction accuracy results of the models are shown in fig. 4, respectively, in comparison with other models LSTM and SARIMA for load prediction and Prophet in which VMD decomposition is not performed on the input signal.
Claims (5)
1. A short-term load prediction method based on VMD-Prophet is characterized by comprising the following steps:
s1: before the original load sequence is brought into a Prophet model for prediction, performing Variational Modal Decomposition (VMD) on the original load sequence to obtain a subsequence with better regularity;
s2: the VMD decomposition is used to decompose the fluctuating signal into K eigenmode function sub-signals of different frequency bands, and the specific process is as follows:
when the VMD is used for K-order decomposition, the problem can be regarded as the following constraint variation problem, as shown in formula (1):
wherein f (t) is the undecomposed main signal, { u k }＝{u 1 ,…,u k And { omega } and k }＝{ω 1 ,…,ω k represents the set of K-order modes and the center frequency, respectively. δ (t) is a dirac distribution, representing a convolution,
as a function of mode u k Corresponding to center frequency omega k J is an imaginary number.
Introducing an augmented Lagrange function, and solving an optimal solution of the constraint variation problem, wherein the optimal solution is shown as a formula (2):
in the formula: alpha is a secondary penalty factor used for reducing the interference of Gaussian noise; λ is the lagrange multiplier. And solving the optimal solution of the constraint variation problem and the augmented Lagrangian function by using a multiplier alternating direction method.
The final VMD update process is as follows, as shown in equations (3) to (5):
in the formula
Respectively f (t),
And λ n (t) Fourier transform; tau is an updating parameter; and n is an iteration parameter.
If the predetermined discrimination accuracy ε > 0 satisfies the following relationship, as shown in equation (6), the VMD converges and the update is stopped.
S3: respectively bringing the decomposed load subsequences into a Prophet prediction model for prediction, and finally accumulating the prediction results of each subsequence to obtain a final prediction result;
s4: and (3) evaluating the prediction result by using two indexes of a mean absolute value percent error (MAPE) and a Root Mean Square Error (RMSE), wherein the indexes are specifically shown in the following formula (7) and formula (8):
in the formula: x is the number of predicted As a result of load prediction, x real The load is the real value.
S5: the VMD algorithm parameters are respectively set as: initial center frequency ω is 0 and convergence criterion e is 10 -7 After repeated experiments, the secondary penalty factor and the resolution order are finally set to be alpha equal to 2000 and K equal to 3.
S6: based on an Anaconda platform, the programming language is Python, a virtual environment with a Python version of 3.7 is created, and the building of a VMD-Prophet prediction model is completed in a Spyder;
s7: the prediction of the VMD-Prophet prediction model for each load subsequence is realized in Spyder through Python programming;
s8: the effect of the VMD-Prophet predictive model on load prediction was tested in Spyder.
2. The VMD-Prophet-based short-term load prediction method according to claim 1, wherein: the VMD algorithm decomposes the original load sequence into subsequences with better regularity, and simultaneously extracts trend components or noise components which influence the prediction result and exist in the prediction process independently, so that the influence of the trend components or the noise components on the short-term power load overall prediction is reduced.
3. The VMD-Prophet-based short-term load prediction method according to claim 1, wherein: the Prophet prediction model has better flexibility, can easily adapt to the seasonality of a plurality of seasons, and makes different assumptions on the trend through analysis; in addition, the measured values do not need to be distributed at equal intervals, interpolation missing values are not needed, and the fitting speed is high.
4. The VMD-Prophet-based short-term load prediction method according to claim 1, wherein: the prediction result is evaluated by the average absolute value percentage error and the root mean square error, so that the prediction effect can be better shown.
5. The VMD-Prophet-based short-term load prediction method according to claim 1, wherein: the VMD-Prophet load prediction model can be realized in a virtual environment created by an Anaconda platform through Python programming in a Spyder, and the decomposition and prediction of a load sequence are directly carried out.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210392592.0A CN115099448A (en) | 2022-04-14 | 2022-04-14 | Short-term load prediction method based on VMD-Prophet |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210392592.0A CN115099448A (en) | 2022-04-14 | 2022-04-14 | Short-term load prediction method based on VMD-Prophet |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115099448A true CN115099448A (en) | 2022-09-23 |
Family
ID=83287123
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210392592.0A Pending CN115099448A (en) | 2022-04-14 | 2022-04-14 | Short-term load prediction method based on VMD-Prophet |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115099448A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117829352A (en) * | 2023-12-19 | 2024-04-05 | 浙江大学 | Industrial industry energy consumption prediction method and system based on clustering algorithm and machine learning |
-
2022
- 2022-04-14 CN CN202210392592.0A patent/CN115099448A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117829352A (en) * | 2023-12-19 | 2024-04-05 | 浙江大学 | Industrial industry energy consumption prediction method and system based on clustering algorithm and machine learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111695731B (en) | Load prediction method, system and equipment based on multi-source data and hybrid neural network | |
| CN102208028B (en) | Fault predicting and diagnosing method suitable for dynamic complex system | |
| CN111193256A (en) | Power load prediction method based on variational modal decomposition and gated cyclic unit | |
| CN112434848B (en) | Nonlinear weighted combination wind power prediction method based on deep belief network | |
| CN111832825B (en) | Wind power prediction method and system integrating long-term memory network and extreme learning machine | |
| CN114091766B (en) | CEEMDAN-LSTM-based space load prediction method | |
| CN109886464A (en) | The low information loss short-term wind speed forecasting method of feature set is generated based on optimization singular value decomposition | |
| CN113988477A (en) | Photovoltaic power short-term prediction method and device based on machine learning and storage medium | |
| CN115293326A (en) | Training method and device of power load prediction model and power load prediction method | |
| CN111210049A (en) | LSTM-based method for predicting degradation trend of lead-acid valve-controlled storage battery of transformer substation | |
| CN112821383A (en) | Power system natural frequency characteristic coefficient interval prediction method based on deep learning | |
| CN115099448A (en) | Short-term load prediction method based on VMD-Prophet | |
| Sun et al. | Short-term power load prediction based on VMD-SG-LSTM | |
| Xu et al. | Interval prediction method for wind power based on VMD-ELM/ARIMA-ADKDE | |
| Pan et al. | Study on short-term load forecasting of distributed power system based on wavelet theory | |
| CN113343470A (en) | Public steel structure building micro-strain prediction method and system | |
| CN117578440A (en) | Power grid load prediction method based on neural network | |
| CN117410959A (en) | EEMD-GWO-LSTM network and MC error correction-based power grid load ultra-short-term prediction method | |
| CN115809725A (en) | Multi-factor short-term electric quantity prediction method and device | |
| CN116070768A (en) | Short-term wind power prediction method based on data reconstruction and TCN-BiLSTM | |
| Zhu et al. | Prediction of air quality index based on wavelet transform combination model | |
| CN116245223A (en) | Airport flow short-term prediction method based on quadratic decomposition integration | |
| CN116432510A (en) | Flexible load prediction method based on ensemble learning-longhorn beetle whisker optimization algorithm | |
| Zheng et al. | Short-term load forecasting of BP network based on EMD | |
| CN105654208B (en) | Empirical mode decomposition method for determining maximum value of cellular load in space load prediction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |