CN111049139A - Reactive power prediction method, system, equipment and storage medium - Google Patents
Reactive power prediction method, system, equipment and storage medium Download PDFInfo
- Publication number
- CN111049139A CN111049139A CN201911415304.3A CN201911415304A CN111049139A CN 111049139 A CN111049139 A CN 111049139A CN 201911415304 A CN201911415304 A CN 201911415304A CN 111049139 A CN111049139 A CN 111049139A
- Authority
- CN
- China
- Prior art keywords
- reactive power
- reactive
- power prediction
- prediction model
- load data
- 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
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/18—Arrangements for adjusting, eliminating or compensating reactive power in networks
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/30—Reactive power compensation
Abstract
The embodiment of the invention discloses a reactive power prediction method, a system, equipment and a storage medium. Firstly, acquiring reactive load data in power grid load data; and carrying out power prediction on the reactive load data through a preset reactive power prediction model to obtain reactive power information. Therefore, the reactive power prediction method and the device can predict the reactive power value at a certain future moment based on the reactive load data, so that the reactive power prediction behavior is achieved.
Description
Technical Field
The invention relates to the technical field of power systems, in particular to a reactive power prediction method, a reactive power prediction system, reactive power prediction equipment and a storage medium.
Background
With the continuous development of renewable energy power generation and distributed micro-grids, the prediction behavior of the power grid power becomes more and more important.
This is because, by reliably predicting the power of the power grid, the dispatching center of the power grid can know the impending change of the power grid in advance after several hours in the future, and adjust the dispatching plan of the power in time. The measure can effectively reduce the operation cost of the power grid, avoid the possible fluctuation of the quality of the electric energy and improve the operation reliability of the power system.
However, the focus of the conventional power scheduling is mainly on active power, and the prediction of reactive power is not much involved, and is in a blank stage.
Therefore, a reactive power prediction method is needed.
Disclosure of Invention
In order to solve the above problems, embodiments of the present invention provide a reactive power prediction method, system, device, and storage medium.
In a first aspect, an embodiment of the present invention provides a reactive power prediction method, including:
obtaining reactive load data in the power grid load data;
and carrying out power prediction on the reactive load data through a preset reactive power prediction model to obtain reactive power information.
Preferably, the power prediction of the reactive load data is performed through a preset reactive power prediction model to obtain reactive power information, and the method specifically includes:
and carrying out power prediction on the reactive load data through a preset reactive power prediction model based on a support vector machine to obtain reactive power information.
Preferably, the power prediction of the reactive load data is performed through a preset reactive power prediction model based on a support vector machine to obtain reactive power information, and the method specifically includes:
acquiring a current target function, a current weight vector and a current deviation in a preset reactive power prediction model based on a support vector machine;
and nonlinearly mapping the reactive load data into a high-dimensional space through the current objective function, and performing power prediction in the high-dimensional space through the current weight vector and the current deviation to obtain reactive power information.
Preferably, after the power prediction is performed on the reactive load data through a preset reactive power prediction model to obtain reactive power information, the reactive power prediction method further includes:
generating corresponding reactive power compensation operation according to the value of the reactive power information;
and compensating the reactive power according to the reactive power compensation operation.
Preferably, before obtaining the reactive load data in the grid load data, the reactive power prediction method further includes:
obtaining a reactive load sample in a power grid load sample;
establishing a training sample set according to the reactive load sample;
training a prediction model through the training sample set to obtain a reactive power prediction model to be tested;
carrying out power prediction on the reactive load sample through the reactive power prediction model to be tested to obtain a reactive power sample;
matching the reactive power sample with the current reactive power in the reactive load sample;
and when the matching is successful, taking the reactive power prediction model to be tested as a preset reactive power prediction model.
Preferably, after the matching the reactive power sample with the current reactive power in the reactive load sample, the reactive power prediction method further includes:
and returning to the step of executing the training of the prediction model through the training sample set to obtain a reactive power prediction model to be tested when the matching fails, and taking the reactive power prediction model to be tested as a preset reactive power prediction model when the matching succeeds.
Preferably, the training of the prediction model through the training sample set to obtain the reactive power prediction model to be tested specifically includes:
and nonlinearly mapping the training sample set to a high-dimensional space through a preset objective function to perform linear regression operation, and performing prediction model training through the linear regression operation to obtain a reactive power prediction model to be tested.
In a second aspect, an embodiment of the present invention provides a reactive power prediction system, including:
the power grid acquisition module is used for acquiring reactive load data in the power grid load data;
and the power prediction module is used for performing power prediction on the reactive load data through a preset reactive power prediction model so as to obtain reactive power information.
In a third aspect, an embodiment of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the steps of the reactive power prediction method provided in the first aspect of the present invention when executing the program.
In a fourth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of a reactive power prediction method provided in the first aspect of the present invention.
According to the reactive power prediction method, the system, the equipment and the storage medium provided by the embodiment of the invention, the reactive load data in the power grid load data are firstly obtained; and carrying out power prediction on the reactive load data through a preset reactive power prediction model to obtain reactive power information. Therefore, the reactive power prediction method and the device can predict the reactive power value at a certain future moment based on the reactive load data, so that the reactive power prediction behavior is achieved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
Fig. 1 is a flowchart of a reactive power prediction method according to an embodiment of the present invention;
fig. 2 is a flowchart of a reactive power prediction method according to another embodiment of the present invention;
fig. 3 is a flowchart of a reactive power prediction method according to still another embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating a comparison between a predicted value and an actual value according to yet another embodiment of the present invention;
FIG. 5 is a schematic diagram illustrating a difference between a predicted value and an actual value according to yet another embodiment of the present invention;
fig. 6 is a schematic structural diagram of a reactive power prediction system according to an embodiment of the present invention;
fig. 7 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, 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 some, but not all, embodiments of the present invention. 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.
Fig. 1 is a flowchart of a reactive power prediction method according to an embodiment of the present invention, as shown in fig. 1, the method includes:
and S1, obtaining reactive load data in the power grid load data.
First, an Energy Management System (EMS) in the power grid may be used to obtain real-time load data of the power grid, that is, power grid load data.
The power grid load data comprises reactive load data; the grid load data may also include current, voltage, and active load data.
In particular, the reactive load data may be the reactive power of a certain plant in a certain line of the power grid.
And S2, performing power prediction on the reactive load data through a preset reactive power prediction model to obtain reactive power information.
And then, power prediction can be carried out through a preset reactive power prediction model according to the reactive load data, and the reactive power information is a predicted value of the reactive power.
The reactive power information may be a value of reactive power at a future time, for example, a value of reactive power in the next day, or a value of reactive power after 3 hours, and the embodiment of the present invention is not limited herein.
Certainly, after the reactive power information is obtained, corresponding power grid scheduling operation can be performed based on the reactive power information, and initiative and refinement of power grid regulation and control are facilitated.
The reactive power prediction method provided by the embodiment of the invention comprises the steps of firstly obtaining reactive load data in power grid load data; and carrying out power prediction on the reactive load data through a preset reactive power prediction model to obtain reactive power information. Therefore, the reactive power prediction method and the device can predict the reactive power value at a certain future moment based on the reactive load data, so that the reactive power prediction behavior is achieved.
Fig. 2 is a flowchart of a reactive power prediction method according to another embodiment of the present invention, where the another embodiment of the present invention is based on the embodiment shown in fig. 1.
In this embodiment, the S2 specifically includes:
s201, performing power prediction on the reactive load data through a preset reactive power prediction model based on a support vector machine to obtain reactive power information.
As for the preset reactive power prediction model for performing the reactive power prediction behavior, a Support Vector Machine (SVM) based reactive power prediction model may be used as the preset reactive power prediction model.
The SVM is used as a learning model in the field of machine learning, and is mainly used in the aspects of regression analysis, pattern recognition, data prediction and the like.
According to the reactive power prediction method provided by the embodiment of the invention, the change rule of the reactive power can be excavated by applying the preset reactive power prediction model based on the SVM, so that the reactive power can be reliably predicted, and the accuracy is improved.
On the basis of the foregoing embodiment, preferably, the performing power prediction on the reactive load data through a preset reactive power prediction model based on a support vector machine to obtain reactive power information specifically includes:
acquiring a current target function, a current weight vector and a current deviation in a preset reactive power prediction model based on a support vector machine;
and nonlinearly mapping the reactive load data into a high-dimensional space through the current objective function, and performing power prediction in the high-dimensional space through the current weight vector and the current deviation to obtain reactive power information.
It is understood that, in the using process of the preset reactive power prediction model based on the support vector machine, since the current objective function and the model parameters are involved in the model, the model parameters are involved in the weight values and the deviation values, the reactive power prediction model can be applied based on the predetermined data types.
Specifically, the current objective function may be denoted as f (x), y ═ f (x), and f (x) may be the optimal objective function. By determining the optimal objective function f (x), the risk of the loss function can be minimized under certain constraint conditions, so that the corresponding y value can be predicted by f (x) under the condition that x is known.
Wherein, the function formula of the optimal objective function is as follows,
y＝f(x)＝wφ(x)+b，
wherein y represents the predicted reactive power at a certain future time, x represents the input reactive load data, phi (x) represents a nonlinear mapping mode for mapping the reactive load data to a high-dimensional space, w represents a weight vector, and b represents a deviation.
And performing power prediction by the optimal objective function in cooperation with the current weight vector and the current deviation in the model structure to obtain reactive power information.
On the basis of the foregoing embodiment, preferably, after the power prediction is performed on the reactive load data through a preset reactive power prediction model to obtain reactive power information, the reactive power prediction method further includes:
generating corresponding reactive power compensation operation according to the value of the reactive power information;
and compensating the reactive power according to the reactive power compensation operation.
It is understood that when the value of the reactive power at a future time is predicted, a corresponding grid dispatching operation may be performed based on the reactive power.
If the reactive power exceeds the boundary condition, the voltage of the power grid is too high or too low, the active output of the generator is reduced, and the electric energy loss is increased.
Therefore, if the predicted value of the reactive power is to be in a continuously rising state or in a continuously falling state, the reactive power compensation unit in the tunable power grid compensates the reactive power. After reactive compensation, the effects of stabilizing voltage and avoiding power grid fluctuation can be achieved.
Therefore, the embodiment of the invention can integrally improve the power grid dispatching level by reliably predicting the reactive power in advance and carrying out corresponding reactive power optimization operation based on the specific value of the reactive power, so that the power grid dispatching is more refined.
Fig. 3 is a flowchart of a reactive power prediction method according to another embodiment of the present invention, which is based on the embodiment shown in fig. 1.
In this embodiment, before S1, the reactive power prediction method further includes:
and S01, obtaining reactive load samples in the power grid load samples.
For convenience of understanding, the embodiment shown in fig. 1 and fig. 2 may be understood as a model using stage, and the embodiment of the present invention shown in fig. 3 is a model training link to train a prediction model with high prediction accuracy.
In addition, the reactive load samples and the reactive load data are of the same data type, and different names are only used for distinguishing different use conditions.
Specifically, in a model training link, a power grid load sample can be preprocessed to remove error data in the power grid load sample; then, reactive load samples are extracted therefrom for model training.
And S02, establishing a training sample set according to the reactive load sample.
As the reactive load sample records the reactive power value of the plant, a training sample set can be established for training.
The training sample set may be established based on a prediction period, for example, every 7-day reactive load sample may be used as a training sample set, and the model input amount during model training is 7-day reactive load sample once.
And S03, training a prediction model through the training sample set to obtain a reactive power prediction model to be tested.
Specifically, an SVM initial model may exist, and the training sample set may be trained as an input quantity of the SVM initial model, and the output quantity is the predicted reactive power.
In view of the fact that the SVM model can search the dependency relationship between the input and the output of data according to a limited number of sample data, the rules which cannot be obtained through principle analysis are mined, and good prediction and judgment effects are achieved on unknown data and new phenomena which cannot be observed.
Therefore, the SVM model is relatively fit with the power characteristics of the power grid, and relatively reliable prediction behaviors can be carried out on the power grid with the power having volatility and randomness.
S04, carrying out power prediction on the reactive load sample through the reactive power prediction model to be tested to obtain a reactive power sample;
the SVM initial model after model parameter training can be recorded as a reactive power prediction model to be tested, and then the reactive power prediction model can be tested.
And the reactive power sample is a predicted reactive power value at a certain future time. For example, if the reactive load sample input into the reactive power prediction model to be tested is the reactive power of the 1 st to 7 th days, the output reactive power sample may be the predicted reactive power of the 8 th day.
The reactive load sample used in the test may also be a certain training sample set.
S05, matching the reactive power sample with the current reactive power in the reactive load sample.
The reactive load samples are historical power grid data, and the current reactive power is the actual reactive power of the 8 th day.
Matching the predicted reactive power of the 8 th day with the actual reactive power of the 8 th day, and if the difference value between the predicted reactive power of the 8 th day and the actual reactive power of the 8 th day is within a preset difference value range, considering that the matching is successful, and understanding that the difference is small; if the difference between the two is not within the preset difference range, the matching is considered to be failed, and the difference is understood to be large, and the prediction is unreliable.
And S06, when the matching is successful, taking the reactive power prediction model to be tested as a preset reactive power prediction model.
If the matching is successful, the reactive power prediction model at the moment can be used as a preset reactive power prediction model for the direct use of the model in the use stage.
The reactive power prediction method provided by the embodiment of the invention can be used for training the prediction model in advance so as to be directly used in the use stage of the model.
On the basis of the foregoing embodiment, preferably, after S05, the reactive power prediction method further includes:
and when the matching fails, returning to execute S03 until the reactive power prediction model to be tested is used as a preset reactive power prediction model when the matching is successful.
It can be understood that if the difference between the two is not within the preset difference range, the matching is considered to be failed, the prediction is unreliable, and the modeling can be carried out again.
For example, a reactive power prediction model to be tested obtained at this time may be first recorded as a model a 1; then, the prediction model may be trained again through the training sample set, at which time the data content of the training sample set may be changed, and the new reactive power prediction model to be tested obtained at this time is denoted as model a 2. Then, a reactive power test can be carried out through the model A2, and if matching is successful, the model training is finished; if the matching fails, the cycle training is continued to obtain model A3, and so on.
In addition, fig. 4 is a schematic diagram illustrating a comparison between a predicted value and an actual value, so as to check whether the model has a good prediction effect.
In addition, fig. 5 is a schematic diagram of a difference between the predicted value and the actual value, and it can be clearly seen that the difference is small, and when the difference is small, the predicted value can be used as a power grid scheduling credential to enter the next power grid scheduling operation, so as to optimize the performance of the reactive power.
Therefore, the embodiment of the invention can obtain a model with higher prediction accuracy for actual prediction by circularly adjusting and testing the model.
On the basis of the foregoing embodiment, preferably, the training of the prediction model through the training sample set to obtain the reactive power prediction model to be tested specifically includes:
and nonlinearly mapping the training sample set to a high-dimensional space through a preset objective function to perform linear regression operation, and performing prediction model training through the linear regression operation to obtain a reactive power prediction model to be tested.
For a specific training mode of model training, see the following, but not limited to this training mode.
Specifically, there may be an SVM initial model, where the predetermined objective function may be denoted as f (x), y ═ f (x), and f (x) may be an optimal objective function. By determining the optimal objective function f (x), the risk of the loss function can be minimized under certain constraint conditions, so that the corresponding y value can be predicted by f (x) under the condition that x is known.
Wherein, the function formula of the optimal objective function is as follows,
y＝f(x)＝wφ(x)+b，
wherein y represents the predicted reactive power at a certain time in the future, x represents the input training sample set, phi (x) represents a nonlinear mapping mode for mapping the training sample set to a high-dimensional space, w represents a weight vector, and b represents a deviation.
Through the optimal objective function, linear regression can be carried out in a high-dimensional space to excavate the mathematical relationship between the training sample set and the reactive power, so that the determination of model parameters in the reactive power prediction model is completed, and the reactive power prediction model to be tested is successfully constructed.
More specifically, a global optimal solution can be found out through an algorithm of a convex quadratic optimization problem. Wherein, the algorithm of the convex quadratic optimization problem is as follows,
wherein x is input as an input quantity into a training sample set, ai、
All lagrange multipliers, and b is deviation; k (x, x)i) Representing a kernel function, x, converting a training sample set from a low-dimensional space to a high-dimensional feature spaceiRepresenting a vector in the data set of the training sample set, x being an argument to be operated on with all xi in the data set, i being a sequence number, l being a positive integer.
Furthermore, the kernel Function may be embodied as a Radial Basis Function (RBF), as follows,
wherein, σ is a free parameter for controlling the radial acting range of the function, and other parameters are referred to above and are not described herein.
Therefore, the embodiment of the invention can seek a prediction model with better prediction performance by applying the optimal objective function.
Fig. 6 is a schematic structural diagram of a reactive power prediction system according to an embodiment of the present invention, and as shown in fig. 6, the system includes: a power grid acquisition module 301 and a power prediction module 302;
the power grid acquisition module 301 is configured to acquire reactive load data in power grid load data;
and the power prediction module 302 is configured to perform power prediction on the reactive load data through a preset reactive power prediction model to obtain reactive power information.
The reactive power prediction system provided by the embodiment of the invention firstly obtains the reactive load data in the load data of the power grid; and carrying out power prediction on the reactive load data through a preset reactive power prediction model to obtain reactive power information. Therefore, the reactive power prediction method and the device can predict the reactive power value at a certain future moment based on the reactive load data, so that the reactive power prediction behavior is achieved.
The system embodiment provided in the embodiments of the present invention is for implementing the above method embodiments, and for details of the process and the details, reference is made to the above method embodiments, which are not described herein again.
Fig. 7 is a schematic entity structure diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 7, the electronic device may include: a processor (processor)401, a communication Interface (communication Interface)402, a memory (memory)403 and a bus 404, wherein the processor 401, the communication Interface 402 and the memory 403 complete communication with each other through the bus 404. The communication interface 402 may be used for information transfer of an electronic device. Processor 401 may call logic instructions in memory 403 to perform a method comprising:
obtaining reactive load data in the power grid load data;
and carrying out power prediction on the reactive load data through a preset reactive power prediction model to obtain reactive power information.
In addition, the logic instructions in the memory 403 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the above-described method embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented by a processor to perform the method provided by the foregoing embodiments, for example, including:
obtaining reactive load data in the power grid load data;
and carrying out power prediction on the reactive load data through a preset reactive power prediction model to obtain reactive power information.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A reactive power prediction method, comprising:
obtaining reactive load data in the power grid load data;
and carrying out power prediction on the reactive load data through a preset reactive power prediction model to obtain reactive power information.
2. The reactive power prediction method according to claim 1, wherein the power prediction of the reactive load data is performed through a preset reactive power prediction model to obtain reactive power information, and specifically includes:
and carrying out power prediction on the reactive load data through a preset reactive power prediction model based on a support vector machine to obtain reactive power information.
3. The reactive power prediction method according to claim 2, wherein the performing power prediction on the reactive load data through a preset reactive power prediction model based on a support vector machine to obtain reactive power information specifically comprises:
acquiring a current target function, a current weight vector and a current deviation in a preset reactive power prediction model based on a support vector machine;
and nonlinearly mapping the reactive load data into a high-dimensional space through the current objective function, and performing power prediction in the high-dimensional space through the current weight vector and the current deviation to obtain reactive power information.
4. The reactive power prediction method of claim 1, wherein after the power prediction of the reactive load data is performed through a preset reactive power prediction model to obtain the reactive power information, the reactive power prediction method further comprises:
generating corresponding reactive power compensation operation according to the value of the reactive power information;
and compensating the reactive power according to the reactive power compensation operation.
5. The reactive power prediction method according to any one of claims 1 to 4, wherein before the obtaining of the reactive load data in the grid load data, the reactive power prediction method further comprises:
obtaining a reactive load sample in a power grid load sample;
establishing a training sample set according to the reactive load sample;
training a prediction model through the training sample set to obtain a reactive power prediction model to be tested;
carrying out power prediction on the reactive load sample through the reactive power prediction model to be tested to obtain a reactive power sample;
matching the reactive power sample with the current reactive power in the reactive load sample;
and when the matching is successful, taking the reactive power prediction model to be tested as a preset reactive power prediction model.
6. The reactive power prediction method of claim 5, wherein after matching the reactive power sample to the current reactive power in the reactive load sample, the reactive power prediction method further comprises:
and returning to the step of executing the training of the prediction model through the training sample set to obtain a reactive power prediction model to be tested when the matching fails, and taking the reactive power prediction model to be tested as a preset reactive power prediction model when the matching succeeds.
7. The reactive power prediction method according to claim 5, wherein the training of the prediction model through the training sample set to obtain the reactive power prediction model to be tested specifically comprises:
and nonlinearly mapping the training sample set to a high-dimensional space through a preset objective function to perform linear regression operation, and performing prediction model training through the linear regression operation to obtain a reactive power prediction model to be tested.
8. A reactive power prediction system, comprising:
the power grid acquisition module is used for acquiring reactive load data in the power grid load data;
and the power prediction module is used for performing power prediction on the reactive load data through a preset reactive power prediction model so as to obtain reactive power information.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor, when executing the program, implements the steps of the reactive power prediction method according to any of claims 1 to 7.
10. A non-transitory computer readable storage medium, having stored thereon a computer program, wherein the computer program, when being executed by a processor, is adapted to carry out the steps of the reactive power prediction method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911415304.3A CN111049139A (en) | 2019-12-31 | 2019-12-31 | Reactive power prediction method, system, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911415304.3A CN111049139A (en) | 2019-12-31 | 2019-12-31 | Reactive power prediction method, system, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111049139A true CN111049139A (en) | 2020-04-21 |
Family
ID=70242617
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911415304.3A Pending CN111049139A (en) | 2019-12-31 | 2019-12-31 | Reactive power prediction method, system, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111049139A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105160444A (en) * | 2015-10-22 | 2015-12-16 | 广东电网有限责任公司电力调度控制中心 | Electrical equipment failure rate determining method and system |
| US20180048154A1 (en) * | 2016-08-15 | 2018-02-15 | Nec Laboratories America, Inc. | Two-level predictive based reactive power coordination and voltage restoration for microgrids |
| CN108304976A (en) * | 2018-03-06 | 2018-07-20 | 西安交通大学 | A kind of electric system fining load prediction and analysis method |
| CN109871622A (en) * | 2019-02-25 | 2019-06-11 | 燕山大学 | A kind of low-voltage platform area line loss calculation method and system based on deep learning |
| US10325150B2 (en) * | 2012-08-29 | 2019-06-18 | Eaton Intelligent Power Limited | System and method for electric load identification and classification employing support vector machine |
-
2019
- 2019-12-31 CN CN201911415304.3A patent/CN111049139A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10325150B2 (en) * | 2012-08-29 | 2019-06-18 | Eaton Intelligent Power Limited | System and method for electric load identification and classification employing support vector machine |
| CN105160444A (en) * | 2015-10-22 | 2015-12-16 | 广东电网有限责任公司电力调度控制中心 | Electrical equipment failure rate determining method and system |
| US20180048154A1 (en) * | 2016-08-15 | 2018-02-15 | Nec Laboratories America, Inc. | Two-level predictive based reactive power coordination and voltage restoration for microgrids |
| CN108304976A (en) * | 2018-03-06 | 2018-07-20 | 西安交通大学 | A kind of electric system fining load prediction and analysis method |
| CN109871622A (en) * | 2019-02-25 | 2019-06-11 | 燕山大学 | A kind of low-voltage platform area line loss calculation method and system based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20200327205A1 (en) | Systems and methods for enhanced sequential power system model parameter estimation | |
| CN108089135B (en) | Extreme learning model-based battery state prediction system and implementation method thereof | |
| WO2018189279A1 (en) | Black-box optimization using neural networks | |
| CN112052890B (en) | Method and device for predicting vibration of water supply pump | |
| CN114066333A (en) | Data processing method and device | |
| CN111563077B (en) | Power grid voltage data missing filling method, system, terminal and storage medium | |
| WO2020197533A1 (en) | Surrogate of a simulation engine for power system model calibration | |
| WO2021051035A1 (en) | Spatio-temporal probabilistic forecasting of wind power output | |
| CN114705990A (en) | Battery cluster state of charge estimation method and system, electronic equipment and storage medium | |
| CN112821420B (en) | XGboost-based prediction method and system for dynamic damping factor and multidimensional frequency index in ASFR model | |
| US11907865B2 (en) | Determination of security-constrained optimal power flow | |
| Razmi et al. | Neural network based on a genetic algorithm for power system loading margin estimation | |
| CN111049139A (en) | Reactive power prediction method, system, equipment and storage medium | |
| JP2019088150A (en) | Confidence coefficient monitoring system, confidence coefficient evaluation method, and program | |
| CN116540546A (en) | Recommendation method, system, equipment and medium for control parameters of process control system | |
| CN108805323B (en) | Data prediction method and device | |
| CN114065460A (en) | Model processing method, storage medium and electronic device in thermal power generation system | |
| CN112559012A (en) | System upgrading and testing method and device, computer equipment and readable storage medium | |
| CN116526515B (en) | Power grid frequency regulation and control method and controller | |
| CN114355224B (en) | Battery health state prediction method and device, electronic device and readable storage medium | |
| He et al. | Gradient Reweighting: Towards Imbalanced Class-Incremental Learning | |
| CN110224441B (en) | Power plant unit recovery sequence optimization method and device | |
| CN116955176A (en) | Test method and device | |
| CN112989581A (en) | Frequency dynamic simulation method and device, electronic equipment and storage medium | |
| Sarkar et al. | LSTM based deep neural network model of power system stabilizer for power oscillation damping in multimachine system |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200421 |
|
| RJ01 | Rejection of invention patent application after publication |