CN111598303A - Summer short-term load prediction method based on meteorological component decomposition - Google Patents
Summer short-term load prediction method based on meteorological component decomposition Download PDFInfo
- Publication number
- CN111598303A CN111598303A CN202010313390.3A CN202010313390A CN111598303A CN 111598303 A CN111598303 A CN 111598303A CN 202010313390 A CN202010313390 A CN 202010313390A CN 111598303 A CN111598303 A CN 111598303A
- Authority
- CN
- China
- Prior art keywords
- load
- component
- historical
- daily
- predicted
- 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
- 238000000354 decomposition reaction Methods 0.000 title claims abstract description 40
- 238000000034 method Methods 0.000 title claims abstract description 26
- 230000000737 periodic effect Effects 0.000 claims abstract description 19
- 238000012549 training Methods 0.000 claims description 46
- 238000012795 verification Methods 0.000 claims description 26
- 238000004590 computer program Methods 0.000 claims description 16
- 238000012360 testing method Methods 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 9
- 238000005516 engineering process Methods 0.000 claims description 7
- 238000013277 forecasting method Methods 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 6
- 230000003442 weekly effect Effects 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 3
- 238000012706 support-vector machine Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000010200 validation analysis 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- 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)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a summer short-term load prediction method based on meteorological component decomposition, which comprises the following steps: decomposing the historical load time sequence data to obtain a historical load daily cycle component, a historical load low-frequency component and a historical load high-frequency component; decomposing the historical temperature time series data to obtain a historical temperature periodic component and a historical temperature fluctuation component; calculating to obtain a daily temperature fluctuation component to be predicted according to the daily weather prediction sequence data to be predicted and the historical temperature cycle component; inputting the daily temperature fluctuation component to be predicted into a weather sensitive load prediction model as an input parameter, and outputting a daily load low-frequency component to be predicted; calculating to obtain a predicted daily load time sequence according to the historical load daily cycle component, the historical load periodic cycle component, the historical load high-frequency component and the daily load low-frequency component to be predicted; the invention can combine meteorological temperature factors in power load prediction to improve the prediction accuracy of the power load.
Description
Technical Field
The invention relates to the technical field of electric power, in particular to a summer short-term load prediction method based on meteorological component decomposition.
Background
In recent years, with the continuous deepening of the reform of the electric power market in China, the short-term load prediction of the electric power system is used as an important basis for the bidding of market members, the clearing of the market and the market settlement, the accuracy of the prediction result is significant for the ordered operation of the electric power market, and the accurate load prediction is also a precondition for ensuring the safe and reliable operation of a power grid. The summer load is greatly influenced by meteorological factors such as temperature and the like, and the characteristics of strong randomness and large fluctuation are shown, so that great difficulty is brought to summer load prediction work.
In order to improve the summer load prediction accuracy, researchers propose a method for decomposing a load curve by using frequency domain analysis. Since the power load is a time sequence with periodicity, the time sequence p (t) of the load in a group of designated time domains D can be subjected to discrete fourier decomposition to obtain different angular frequencies wiOn a component basis, p (t) is reconstructed by appropriate combination into the following equation:
P(t)＝a0+D(t)+W(t)+L(t)+H(t)
in the formula, a0+ D (t) is the daily period component, W (t) is the weekly period component, L (t) is the low frequency component, and H (t) is the high frequency component. The daily period component and the weekly period component are load components which change according to a fixed period, are generally determined by daily production and life laws of people, and have strong regularity and inertia; the low-frequency component is load oscillation caused by the influence of accidental factors in the power grid, and is usually caused by meteorological change, and the load is more sensitive to the meteorological change, so the low-frequency component is also called as a meteorological sensitive load; the high frequency components are typically some high frequency noise in the load curve,reflects the random fluctuation of the power load and belongs to an unpredictable component.
Through load component decomposition, the corresponding relation between different components in the short-term load curve and the actual physical meaning can be strengthened. However, in the conventional research, researchers often focus only on the decomposition of short-term load cycle components and ignore the periodicity of meteorological factors such as temperature.
Disclosure of Invention
The invention provides a summer short-term load forecasting method based on meteorological component decomposition, which combines meteorological temperature factors in power load forecasting, increases the relevance between each component of a load and a meteorological factor component, and improves the forecasting accuracy of the power load.
In order to solve the above technical problem, an embodiment of the present invention provides a summer short-term load prediction method based on meteorological component decomposition, including:
acquiring historical load time sequence data and historical temperature time sequence data, and acquiring solar weather prediction sequence data to be predicted;
decomposing the historical load time sequence data to obtain a historical load daily cycle component, a historical load low-frequency component and a historical load high-frequency component;
decomposing the historical temperature time series data to obtain a historical temperature periodic component and a historical temperature fluctuation component;
calculating to obtain a daily temperature fluctuation component to be predicted according to the daily weather prediction sequence data to be predicted and the historical temperature cycle component;
inputting the daily temperature fluctuation component to be predicted into a weather sensitive load prediction model as an input parameter so that the weather sensitive load prediction model outputs a daily load low-frequency component to be predicted; wherein the weather-sensitive load prediction model is a prediction model for outputting a low-frequency component of a load according to an input temperature fluctuation component;
and calculating to obtain a predicted daily load time sequence according to the historical load daily cycle component, the historical load periodic cycle component, the historical load high-frequency component and the daily load low-frequency component to be predicted.
As a preferred scheme, the construction process of the weather sensitive load prediction model comprises the following steps:
acquiring a historical load low-frequency component and a historical temperature fluctuation component, and taking the historical load low-frequency component and the historical temperature fluctuation component as training data;
and establishing an SVM model, inputting the training data serving as input parameters into the SVM model for training optimization, and obtaining a weather sensitive load prediction model.
As a preferred scheme, the step of establishing an SVM model, inputting the training data as an input parameter to the SVM model for training optimization to obtain a weather sensitive load prediction model specifically comprises:
copying the training data to obtain training set data, verification set data and test set data;
inputting the training set data into the established SVM model for training, and finishing training the SVM model when a preset training condition is reached to obtain a training model;
inputting the verification set data into the training model for verification, and completing verification of the training model when preset verification conditions are met to obtain a verification model;
and inputting the test set data into the verification model for testing, and completing the test of the verification model when preset test conditions are met to obtain a weather sensitive load prediction model.
As a preferred scheme, the step of obtaining the time sequence of the predicted daily load by calculation according to the historical load daily cycle component, the historical load periodic cycle component, the historical load high-frequency component and the daily load low-frequency component to be predicted specifically comprises the following steps:
carrying out weighted average processing on the historical load high-frequency components to obtain daily load high-frequency components to be predicted;
and adding and summing the historical load daily cycle component, the historical load periodic cycle component, the daily load high-frequency component to be predicted and the daily load low-frequency component to be predicted to obtain a predicted daily load time sequence.
Preferably, the step of performing decomposition processing on the historical load time-series data includes: and decomposing the historical load time-series data by a Fourier decomposition technology.
Preferably, the step of performing decomposition processing on the historical temperature time-series data includes: and decomposing the historical temperature time-series data by a Fourier decomposition technology.
Preferably, the historical load time-series data is historical load data of 14 days before the day to be predicted.
Preferably, the historical temperature time-series data is historical temperature data of 14 days before the day to be predicted.
An embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program; wherein the computer program when executed controls the apparatus in which the computer readable storage medium is located to perform a summer short-term load prediction method based on meteorological component decomposition as defined in any one of the preceding claims.
An embodiment of the present invention further provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements the summer short-term load prediction method based on weather component decomposition according to any one of the above items.
Compared with the prior art, the embodiment of the invention has the following beneficial effects:
according to the technical scheme, the weather sensitive load forecasting model is built, the low-frequency component of the daily load to be forecasted is obtained according to the daily temperature fluctuation component to be forecasted, the time sequence of the forecast daily load is generated, the weather temperature factors are combined in the power load forecasting, the relevance between each component of the load and the weather factor component is increased, and the forecasting accuracy of the power load is improved.
Drawings
FIG. 1: the invention provides a flow diagram of one embodiment of a summer short-term load forecasting method based on meteorological component decomposition;
FIG. 2: the technical principle schematic diagram of the summer short-term load forecasting method based on meteorological component decomposition is provided;
FIG. 3: the invention provides a schematic structural diagram of an embodiment of a terminal device.
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.
Example 1
Referring to fig. 1, it is a schematic flow chart of an embodiment of a summer short-term load prediction method based on meteorological component decomposition according to the present invention, the method includes steps 101 to 106, and each step is as follows:
In this embodiment, the historical load time-series data is historical load data 14 days before the day to be predicted. In this embodiment, the historical temperature time-series data is historical temperature data of 14 days before the day to be predicted.
Specifically, the electrical load is typically sampled at 96 points per day, so there are 1344 points in the 14 day load time series. In the same manner as the power load decomposition, a temperature time series of 14 consecutive days before the prediction day is sampled, and a weather prediction series T' (T) of 96 points of the day to be predicted is also prepared.
And 102, decomposing the historical load time sequence data to obtain a historical load daily cycle component, a historical load low-frequency component and a historical load high-frequency component. In this embodiment, the following are specifically mentioned: and decomposing the historical load time-series data by a Fourier decomposition technology.
In particular, in order to determine the daily periodic component a0The angular frequency w in + D (t), the periodic component W (t), the low frequency component L (t) and the high frequency component H (t)iComposition, all angular frequencies w obtained by Fourier decomposition according to a certain ruleiRecombination was performed according to different pools. For ease of analysis, a remainder operation is introduced: the remainder of m divided by n is represented by mod (m, n), which means that m can be divided by n when mod (m, n) is 0.
The period of D (t) is 96, which includes the angular frequency set omegaday＝{w0}∪{wi|mod(96,2π/wi) The frequency index i of the daily periodic component thus takes the set { i | mod (i,14) ═ 0, i ═ 0,1, …, N-1} ∪ {0}, where angular frequency 0 corresponds to the dc component.
W (t) has a period of 7 × 96, which includes the angular frequency set Ωweek＝{wi|mod(7×96,2π/wi) 0 and mod (96,2 pi/w)i) Not equal to 0 }. Therefore, the set of all possible values of the frequency index i of the periodic component w (t) is: { i | mod (i,2) ≠ 0 and mod (i,14) ≠ 0, i ═ 0,1, …, N-1 }.
Taking a 24h period as the boundary of the low frequency component and the high frequency component, the angular frequency sets included by the low frequency component L (t) and the high frequency component H (t) are respectively omegalow＝{wi|2π/wiNot less than 96 and
and Ωhigh＝{wi|2π/wiLess than or equal to 96 and
therefore, the frequency index i of l (t) and w (t) has a set of all possible values, { i | mod (i,2) ≠ 0, i ═ 1, …,14 } and { i | mod (i,2) ≠ 0, respectively>14，i<N}。
And 103, decomposing the historical temperature time-series data to obtain a historical temperature periodic component and a historical temperature fluctuation component. In this embodiment, the following are specifically mentioned: and decomposing the historical temperature time-series data by a Fourier decomposition technology.
Specifically, a temperature time series t (t) of 14 consecutive days before the predicted day is decomposed to obtain a period component and a fluctuation component of the air temperature:
T(t)＝a0+TD(t)+ΔT(t)
TD (t) has a period of 96, which includes an angular frequency set Ωday＝{w0}∪{wi|mod(96,2π/wi) The frequency index i of the periodic component is set to { i | mod (i,14) ═ 0, i ═ 0,1, …, N-1} ∪ {0}, where angular frequency 0 corresponds to the dc component.
And 104, calculating to obtain a daily temperature fluctuation component to be predicted according to the daily weather prediction sequence data to be predicted and the historical temperature cycle component.
The daily temperature fluctuation component Δ T ' (T), Δ T ' (T) ═ T ' (T) -td (T) to be predicted is shown.
Specifically, Δ T '(T) is used as an input feature and is input into a meteorological sensitive load prediction model based on a support vector machine, so as to obtain an output value L' (T), which is a meteorological sensitive component prediction value.
And 106, calculating to obtain a predicted daily load time sequence according to the historical load daily cycle component, the historical load periodic cycle component, the historical load high-frequency component and the daily load low-frequency component to be predicted.
In this embodiment, the step 106 specifically includes: step 1061, performing weighted average processing on the historical load high-frequency components to obtain daily load high-frequency components to be predicted; and step 1062, adding and summing the historical load daily cycle component, the historical load weekly cycle component, the daily load high-frequency component to be predicted and the daily load low-frequency component to be predicted to obtain a predicted daily load time sequence.
Specifically, the weighted average processing is performed on the high-frequency component H (t) to obtain H' (t), which is a high-frequency component predicted value; then, the daily cycle component a is divided0And (d), (t), the periodic component w (t), the weather sensitive component predicted value L '(t) and the high-frequency component predicted value H' (t) are added to obtain a final predicted value.
Please refer to fig. 2, which is a schematic diagram of the technical principle of the summer short-term load prediction method based on meteorological component decomposition according to the present invention; the invention provides a summer short-term load prediction technology based on meteorological component decomposition, which decomposes a historical load sequence and a numerical meteorological sequence by adopting fast Fourier transform, decomposes the historical load sequence into a daily period component, a periodic period component, a meteorological sensitive component and a high-frequency component, and decomposes the numerical meteorological sequence into a periodic component and a fluctuation component, thereby improving the relevance between each component of the load and a meteorological factor component and ensuring the prediction precision.
Example 2
In another embodiment, the construction process of the weather-sensitive load prediction model includes steps 201 to 202, and each step specifically includes the following steps:
step 201, obtaining a historical load low-frequency component and a historical temperature fluctuation component, and using the historical load low-frequency component and the historical temperature fluctuation component as training data.
Step 202, establishing an SVM model, inputting the training data serving as input parameters into the SVM model for training optimization, and obtaining a weather sensitive load prediction model.
In this embodiment, step 202 specifically includes:
step 2021, the training data is copied to obtain training set data, verification set data and test set data.
And 2022, inputting the training set data into the established SVM model for training, and finishing training the SVM model when a preset training condition is reached to obtain a training model.
And 2023, inputting the verification set data into the training model for verification, and when a preset verification condition is reached, completing verification of the training model to obtain a verification model.
And 2024, inputting the test set data into the verification model for testing, and completing the testing of the verification model when preset test conditions are met to obtain a weather sensitive load prediction model.
In particular, a Support Vector Machine algorithm (SVM) was proposed by cornna cortex and Vapnik in 1995, and based on VC dimension theory and the principle of minimum structural risk, it is a Machine learning algorithm that can seek the best compromise between the complexity of a model and learning ability according to a limited sample to obtain the best generalization ability.
The support vector machine has high learning speed and few parameters needing parameter adjustment, and can obtain better results than other intelligent learning algorithms such as a neural network on a small sample training data set. The invention selects the load low-frequency component and the meteorological fluctuation component after decomposing the load and temperature data 14 days before the forecast day as a training set, belongs to a small sample data set, and therefore, adopts an SVM algorithm as a forecast algorithm. The algorithm comprises the following steps:
1) initializing algorithm parameters C and gamma;
2) dividing training data into 3 subsets which are respectively a training set, a verification set and a test set;
3) taking meteorological fluctuation components in the training set as input features, and taking load low-frequency components as target values to carry out model training to generate a model;
4) and C and gamma are subjected to parameter optimization by adopting a GridSearch method. The specific process is that the classification accuracy of each group of C and gamma calculation models on a verification set is calculated, and a group of parameters with the highest classification accuracy is selected as the optimal parameters of the models. Cross-validation may be used in the validation.
Through the process, the mapping relation between the weather fluctuation component and the weather sensitive load is established.
Example 3
An embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program; wherein the computer program when executed controls the device on which the computer readable storage medium is located to execute the summer short-term load prediction method based on meteorological component decomposition according to any one of the above embodiments.
Example 4
Referring to fig. 3, a schematic structural diagram of an embodiment of a terminal device according to an embodiment of the present invention is shown, where the terminal device includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and the processor, when executing the computer program, implements the summer short-term load prediction method based on weather component decomposition according to any of the above embodiments.
Preferably, the computer program may be divided into one or more modules/units (e.g., computer program) that are stored in the memory and executed by the processor to implement the invention. The one or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used for describing the execution process of the computer program in the terminal device.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, a discrete hardware component, etc., the general purpose Processor may be a microprocessor, or the Processor may be any conventional Processor, the Processor is a control center of the terminal device, and various interfaces and lines are used to connect various parts of the terminal device.
The memory mainly includes a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function, and the like, and the data storage area may store related data and the like. In addition, the memory may be a high speed random access memory, may also be a non-volatile memory, such as a plug-in hard disk, a Smart Memory Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, or may also be other volatile solid state memory devices.
It should be noted that the terminal device may include, but is not limited to, a processor and a memory, and those skilled in the art will understand that the terminal device is only an example and does not constitute a limitation of the terminal device, and may include more or less components, or combine some components, or different components.
The above-mentioned embodiments are provided to further explain the objects, technical solutions and advantages of the present invention in detail, and it should be understood that the above-mentioned embodiments are only examples of the present invention and are not intended to limit the scope of the present invention. It should be understood that any modifications, equivalents, improvements and the like, which come within the spirit and principle of the invention, may occur to those skilled in the art and are intended to be included within the scope of the invention.
Claims (10)
1. A summer short-term load prediction method based on meteorological component decomposition is characterized by comprising the following steps:
acquiring historical load time sequence data and historical temperature time sequence data, and acquiring solar weather prediction sequence data to be predicted;
decomposing the historical load time sequence data to obtain a historical load daily cycle component, a historical load low-frequency component and a historical load high-frequency component;
decomposing the historical temperature time series data to obtain a historical temperature periodic component and a historical temperature fluctuation component;
calculating to obtain a daily temperature fluctuation component to be predicted according to the daily weather prediction sequence data to be predicted and the historical temperature cycle component;
inputting the daily temperature fluctuation component to be predicted into a weather sensitive load prediction model as an input parameter so that the weather sensitive load prediction model outputs a daily load low-frequency component to be predicted; wherein the weather-sensitive load prediction model is a prediction model for outputting a low-frequency component of a load according to an input temperature fluctuation component;
and calculating to obtain a predicted daily load time sequence according to the historical load daily cycle component, the historical load periodic cycle component, the historical load high-frequency component and the daily load low-frequency component to be predicted.
2. The weather component decomposition-based summer short-term load prediction method as claimed in claim 1, wherein the weather sensitive load prediction model is constructed by:
acquiring a historical load low-frequency component and a historical temperature fluctuation component, and taking the historical load low-frequency component and the historical temperature fluctuation component as training data;
and establishing an SVM model, inputting the training data serving as input parameters into the SVM model for training optimization, and obtaining a weather sensitive load prediction model.
3. The summer short-term load forecasting method based on meteorological component decomposition according to claim 2, wherein the step of establishing an SVM model, inputting the training data as input parameters into the SVM model for training optimization to obtain a meteorological sensitive load forecasting model comprises the following steps:
copying the training data to obtain training set data, verification set data and test set data;
inputting the training set data into the established SVM model for training, and finishing training the SVM model when a preset training condition is reached to obtain a training model;
inputting the verification set data into the training model for verification, and completing verification of the training model when preset verification conditions are met to obtain a verification model;
and inputting the test set data into the verification model for testing, and completing the test of the verification model when preset test conditions are met to obtain a weather sensitive load prediction model.
4. The method for predicting the short-term load in summer based on the meteorological component decomposition as claimed in claim 1, wherein the step of calculating the time series of the predicted daily load according to the historical load daily cycle component, the historical load weekly cycle component, the historical load high frequency component and the daily load low frequency component to be predicted specifically comprises:
carrying out weighted average processing on the historical load high-frequency components to obtain daily load high-frequency components to be predicted;
and adding and summing the historical load daily cycle component, the historical load periodic cycle component, the daily load high-frequency component to be predicted and the daily load low-frequency component to be predicted to obtain a predicted daily load time sequence.
5. The summer short-term load forecasting method based on meteorological component decomposition according to claim 1, wherein the step of performing decomposition processing on the historical load time-series data comprises: and decomposing the historical load time-series data by a Fourier decomposition technology.
6. The summer short-term load prediction method based on meteorological component decomposition according to claim 1, wherein the step of performing decomposition processing on the historical temperature time-series data includes: and decomposing the historical temperature time-series data by a Fourier decomposition technology.
7. The weather-composition-decomposition-based summer short-term load prediction method as claimed in claim 1, wherein the historical load time-series data is historical load data 14 days before the day to be predicted.
8. The summer short-term load forecasting method based on meteorological component decomposition according to claim 1, wherein the historical temperature time-series data are historical temperature data 14 days before the day to be forecasted.
9. A computer-readable storage medium, characterized in that the computer-readable storage medium comprises a stored computer program; wherein the computer program when executed controls an apparatus in which the computer readable storage medium is located to perform a summer short-term load prediction method based on meteorological composition decomposition according to any one of claims 1 to 8.
10. A terminal device comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, the processor when executing the computer program implementing a summer short-term load prediction method based on weather component decomposition according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010313390.3A CN111598303B (en) | 2020-04-20 | 2020-04-20 | Summer short-term load prediction method based on meteorological component decomposition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010313390.3A CN111598303B (en) | 2020-04-20 | 2020-04-20 | Summer short-term load prediction method based on meteorological component decomposition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111598303A true CN111598303A (en) | 2020-08-28 |
| CN111598303B CN111598303B (en) | 2024-07-02 |
Family
ID=72181537
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010313390.3A Active CN111598303B (en) | 2020-04-20 | 2020-04-20 | Summer short-term load prediction method based on meteorological component decomposition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111598303B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112101681A (en) * | 2020-09-25 | 2020-12-18 | 北京师范大学 | Method for monitoring winter wheat dry and hot wind disasters based on remote sensing NDPI time sequence |
| CN112365280A (en) * | 2020-10-20 | 2021-02-12 | 国网冀北电力有限公司计量中心 | Power demand prediction method and device |
| CN114742263A (en) * | 2022-03-02 | 2022-07-12 | 北京百度网讯科技有限公司 | Load prediction method, load prediction device, electronic device, and storage medium |
| CN114925940A (en) * | 2022-07-20 | 2022-08-19 | 广东电网有限责任公司佛山供电局 | Holiday load prediction method and system based on load decomposition |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1080062A (en) * | 1996-09-05 | 1998-03-24 | Fuji Electric Co Ltd | Method for predicting daily load curve |
| CN102930356A (en) * | 2012-11-16 | 2013-02-13 | 广东电网公司电力调度控制中心 | Short-term load forecast method based on meteorological factor sensitivity |
| CN104318332A (en) * | 2014-10-29 | 2015-01-28 | 国家电网公司 | Power load predicting method and device |
| CN105320995A (en) * | 2014-08-19 | 2016-02-10 | 上海交通大学 | Frequency domain decomposition based wind power generation short-term load prediction method and apparatus |
| CN106779129A (en) * | 2015-11-19 | 2017-05-31 | 华北电力大学（保定） | A kind of Short-Term Load Forecasting Method for considering meteorologic factor |
| CN107423836A (en) * | 2017-04-07 | 2017-12-01 | 山东大学 | Short-term load forecasting method based on sendible temperature |
| CN108229754A (en) * | 2018-01-31 | 2018-06-29 | 杭州电子科技大学 | Short-term load forecasting method based on similar day segmentation and LM-BP networks |
| CN109359786A (en) * | 2018-12-05 | 2019-02-19 | 国网江苏省电力有限公司扬州供电分公司 | A kind of power station area short-term load forecasting method |
| CN109583629A (en) * | 2018-11-09 | 2019-04-05 | 广东电网有限责任公司电力调度控制中心 | Improved similar historical day short-term load forecasting method and device based on deviation self-correcting |
| CN109934418A (en) * | 2018-10-17 | 2019-06-25 | 安徽大学 | Short-term load forecasting method based on frequency domain decomposition and intelligent algorithm |
| CN110688620A (en) * | 2019-09-11 | 2020-01-14 | 新奥数能科技有限公司 | Short-term load prediction method and device |
-
2020
- 2020-04-20 CN CN202010313390.3A patent/CN111598303B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1080062A (en) * | 1996-09-05 | 1998-03-24 | Fuji Electric Co Ltd | Method for predicting daily load curve |
| CN102930356A (en) * | 2012-11-16 | 2013-02-13 | 广东电网公司电力调度控制中心 | Short-term load forecast method based on meteorological factor sensitivity |
| CN105320995A (en) * | 2014-08-19 | 2016-02-10 | 上海交通大学 | Frequency domain decomposition based wind power generation short-term load prediction method and apparatus |
| CN104318332A (en) * | 2014-10-29 | 2015-01-28 | 国家电网公司 | Power load predicting method and device |
| CN106779129A (en) * | 2015-11-19 | 2017-05-31 | 华北电力大学（保定） | A kind of Short-Term Load Forecasting Method for considering meteorologic factor |
| CN107423836A (en) * | 2017-04-07 | 2017-12-01 | 山东大学 | Short-term load forecasting method based on sendible temperature |
| CN108229754A (en) * | 2018-01-31 | 2018-06-29 | 杭州电子科技大学 | Short-term load forecasting method based on similar day segmentation and LM-BP networks |
| CN109934418A (en) * | 2018-10-17 | 2019-06-25 | 安徽大学 | Short-term load forecasting method based on frequency domain decomposition and intelligent algorithm |
| CN109583629A (en) * | 2018-11-09 | 2019-04-05 | 广东电网有限责任公司电力调度控制中心 | Improved similar historical day short-term load forecasting method and device based on deviation self-correcting |
| CN109359786A (en) * | 2018-12-05 | 2019-02-19 | 国网江苏省电力有限公司扬州供电分公司 | A kind of power station area short-term load forecasting method |
| CN110688620A (en) * | 2019-09-11 | 2020-01-14 | 新奥数能科技有限公司 | Short-term load prediction method and device |
Non-Patent Citations (1)
| Title |
|---|
| 庞松岭;穆钢;王修权;金鹏;马俊国;: "基于负荷规律性分析的支持向量机短期负荷预测方法", 东北电力大学学报, no. 04, pages 1 - 6 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112101681A (en) * | 2020-09-25 | 2020-12-18 | 北京师范大学 | Method for monitoring winter wheat dry and hot wind disasters based on remote sensing NDPI time sequence |
| CN112101681B (en) * | 2020-09-25 | 2023-04-28 | 北京师范大学 | Method for monitoring winter wheat dry hot air disasters based on remote sensing NDPI time sequence |
| CN112365280A (en) * | 2020-10-20 | 2021-02-12 | 国网冀北电力有限公司计量中心 | Power demand prediction method and device |
| CN112365280B (en) * | 2020-10-20 | 2024-04-19 | 国网冀北电力有限公司计量中心 | Electric power demand prediction method and device |
| CN114742263A (en) * | 2022-03-02 | 2022-07-12 | 北京百度网讯科技有限公司 | Load prediction method, load prediction device, electronic device, and storage medium |
| CN114742263B (en) * | 2022-03-02 | 2024-03-01 | 北京百度网讯科技有限公司 | Load prediction method, device, electronic equipment and storage medium |
| CN114925940A (en) * | 2022-07-20 | 2022-08-19 | 广东电网有限责任公司佛山供电局 | Holiday load prediction method and system based on load decomposition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111598303B (en) | 2024-07-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | Smart wind speed forecasting approach using various boosting algorithms, big multi-step forecasting strategy | |
| CN111598303A (en) | Summer short-term load prediction method based on meteorological component decomposition | |
| Li et al. | Short-term load-forecasting method based on wavelet decomposition with second-order gray neural network model combined with ADF test | |
| Sun | Hybrid model with secondary decomposition, randomforest algorithm, clustering analysis and long short memory network principal computing for short-term wind power forecasting on multiple scales | |
| Zhang et al. | A novel hybrid model for wind speed prediction based on VMD and neural network considering atmospheric uncertainties | |
| Zhu et al. | Wind power forecasting based on new hybrid model with TCN residual modification | |
| CN113657661A (en) | Enterprise carbon emission prediction method and device, computer equipment and storage medium | |
| CN116861201B (en) | Power supply system based on artificial intelligence | |
| CN116502692A (en) | Model training method, photovoltaic power generation power prediction method and device | |
| CN116306798A (en) | Ultra-short time wind speed prediction method and system | |
| Yan et al. | Noise-tolerant zeroing neural network for solving non-stationary Lyapunov equation | |
| Li et al. | Similarity grouping-guided neural network modeling for maritime time series prediction | |
| Zou et al. | A hybrid model based on multi-stage principal component extraction, GRU network and KELM for multi-step short-term wind speed forecasting | |
| CN112396225A (en) | Short-term electricity price prediction method based on long-term and short-term memory network | |
| Sun et al. | Short-term power load prediction based on VMD-SG-LSTM | |
| Nasiri Soloklo et al. | Model order reduction based on moment matching using legendre wavelet and harmony search algorithm | |
| Liu et al. | A data-driven method for online constructing linear power flow model | |
| CN117613905A (en) | Power demand mid-term prediction method and system based on multidimensional component decomposition | |
| CN116885711A (en) | Wind power prediction method, device, equipment and readable storage medium | |
| Li et al. | Adaptive Weighted Combination Approach for Wind Power Forecast Based on Deep Deterministic Policy Gradient Method | |
| Zhao et al. | Multi-Step Short-Term Wind Power Prediction Model Based on CEEMD and Improved Snake Optimization Algorithm | |
| CN116937560A (en) | New energy output prediction method, device, equipment and readable storage medium | |
| Chen et al. | The interpolation of missing wind speed data based on optimized LSSVM model | |
| Xiao-lan et al. | Short-term wind speed forecast of wind farm based on V-system and LSSVM | |
| CN110659442A (en) | System, short-term data prediction method and device thereof, and storage medium |
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 |