CN111355246A - Prediction method, system and storage medium for reactive compensation of phase modulator - Google Patents
Prediction method, system and storage medium for reactive compensation of phase modulator Download PDFInfo
- Publication number
- CN111355246A CN111355246A CN202010143591.3A CN202010143591A CN111355246A CN 111355246 A CN111355246 A CN 111355246A CN 202010143591 A CN202010143591 A CN 202010143591A CN 111355246 A CN111355246 A CN 111355246A
- Authority
- CN
- China
- Prior art keywords
- prediction
- neural network
- data
- reactive power
- result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000012549 training Methods 0.000 claims abstract description 49
- 238000013528 artificial neural network Methods 0.000 claims abstract description 36
- 238000012360 testing method Methods 0.000 claims abstract description 34
- 230000002441 reversible effect Effects 0.000 claims abstract description 3
- 238000010606 normalization Methods 0.000 claims description 20
- 238000005457 optimization Methods 0.000 abstract description 2
- 238000013135 deep learning Methods 0.000 description 7
- 238000013139 quantization Methods 0.000 description 7
- 230000001360 synchronised effect Effects 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 4
- 239000003607 modifier Substances 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000008094 contradictory effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
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
- H02J3/18—Arrangements for adjusting, eliminating or compensating reactive power in networks
- H02J3/1885—Arrangements for adjusting, eliminating or compensating reactive power in networks using rotating means, e.g. synchronous generators
-
- 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
- H02J3/12—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network load
- H02J3/16—Circuit arrangements for ac mains or ac distribution networks for adjusting voltage in ac networks by changing a characteristic of the network load by adjustment of reactive power
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention provides a method and a system for predicting reactive compensation of a phase modulator and a storage medium, belonging to the technical field of optimization of the phase modulator. The prediction method comprises the following steps: acquiring historical reactive power data of a phase modulator; determining a training set and a testing set according to historical reactive power data; performing a quantitative grading operation on the training set and the test set; training an initial neural network by adopting a training set to obtain a corresponding prediction result; comparing the predicted result with the standard result in the training set to calculate a corresponding error; judging whether the error is larger than a preset threshold value or not; updating parameters of the neural network by adopting a reverse gradient method under the condition that the judgment error is larger than the threshold value; under the condition that the judgment error is smaller than or equal to the threshold value, adopting a test set to test the neural network so as to judge whether the neural network meets the preset prediction precision; under the condition that the neural network meets the prediction precision, outputting the neural network; and predicting reactive compensation by adopting a neural network.
Description
Technical Field
The invention relates to the technical field of optimization of phase modulators, in particular to a method and a system for predicting reactive compensation of a phase modulator and a storage medium.
Background
The synchronous phase modifier is a synchronous motor in a special operation state, and when the synchronous phase modifier is applied to a power system, the reactive output can be automatically increased when the voltage of a power grid is reduced according to the requirement of the system; when the voltage of the power grid rises, reactive power is absorbed to maintain the voltage, the stability of the power system is improved, and the power supply quality of the system is improved. Synchronous machines, also known as synchronous compensators, which operate in motoring mode, without mechanical loads and without prime movers, and which only supply or absorb reactive power to the power system, are used to improve the grid power factor and maintain the grid voltage level.
Due to the characteristics of the power grid, the voltage of the power grid rises and falls without relevance. In the case of frequent voltage rise and drop changes, the reactive power of the phase modulator will also vary greatly, which may cause the phase modulator to malfunction relatively flat. Therefore, when planning maintenance resources of the phase modulation machine, how to predict the change of the reactive power and reasonably make a maintenance scheme according to the change become a very important ring in the maintenance work of the phase modulation machine.
Disclosure of Invention
The invention aims to provide a prediction method, a system and a storage medium for reactive compensation of a phase modulator. The prediction method, the prediction system and the storage medium can accurately predict the change of the reactive power of the phase modulator when the phase modulator executes reactive compensation operation in the future, so that the maintenance efficiency of the phase modulator is improved.
In order to achieve the above object, an embodiment of the present invention provides a prediction method for reactive compensation of a phase modulator, the prediction method including:
acquiring historical reactive power data of the phase modulator for executing the reactive compensation operation;
determining a training set and a testing set according to the historical reactive power data;
performing a quantitative hierarchical operation on the training set and the test set;
training an initial neural network by using the training set to obtain a corresponding prediction result;
comparing the predicted result with a standard result in the training set to calculate a corresponding error;
judging whether the error is larger than a preset threshold value or not;
under the condition that the error is judged to be larger than the threshold value, updating parameters of the neural network by adopting a reverse gradient method, training the initial neural network by adopting the training set again to obtain a corresponding prediction result, and executing corresponding steps of the method until the error is judged to be smaller than or equal to the threshold value;
under the condition that the error is judged to be less than or equal to the threshold value, testing the neural network by adopting the test set to judge whether the neural network meets the preset prediction precision;
under the condition that the neural network is judged to meet the prediction precision, outputting the neural network;
and predicting the reactive compensation by adopting the neural network.
Optionally, determining a training set and a test set according to the historical reactive power data specifically includes:
dividing the historical reactive power data into a plurality of data blocks according to a preset time interval;
randomly selecting one data block from the plurality of data blocks as a prediction source;
determining a source time interval corresponding to the prediction source;
determining a target time interval corresponding to a prediction result according to the source time interval;
selecting a data block corresponding to the target time interval from the plurality of data blocks as a target data block, wherein the target data block is a standard result corresponding to the prediction source;
combining said prediction source and said target data block into a prediction data;
judging whether the quantity of the predicted data is greater than or equal to a preset value or not;
under the condition that the quantity of the predicted data is judged to be smaller than the preset value, randomly selecting one data block from the plurality of data blocks again to serve as a prediction source, and executing corresponding steps of the prediction method until the quantity of the predicted data is judged to be larger than or equal to the preset value;
and combining the prediction data into the training set or the test set under the condition that the number of the prediction data is judged to be greater than or equal to the preset value.
Optionally, the performing a quantization scaling operation on the training set and the test set specifically includes:
performing a normalization operation on the average value of the reactive power in each preset time period in the time interval;
and converting the result of the normalization operation into a corresponding parameter index according to a preset numerical value interval.
Optionally, the performing a normalization operation on the average value of the reactive power in each predetermined time period in the time interval comprises:
the normalization operation is performed according to equation (1),
wherein ,for the normalized value of the i-th time period after the normalization operation,for normalizing the reactive power in the i-th time period before operation, xmaxIs the maximum value, x, of the reactive power in the current time intervalminIs the minimum value of the reactive power in the current time interval.
Optionally, converting the result of the normalization operation into a corresponding parameter index according to a preset value interval includes:
calculating the parameter index according to equation (2),
wherein ,to perform the normalization operation on the normalized value for the ith time period,is the parameter index.
Optionally, comparing the predicted result with the standard result in the training set to calculate a corresponding error specifically includes:
the error is calculated according to equation (3),
wherein Δ x is the error, n is the number of time periods comprised by the time interval,a predicted value for the ith said time period of said prediction result,a normalized value for the ith said time period of said normalized result.
In another aspect, the present invention also provides a prediction system for reactive compensation of a phase modulator, the prediction system comprising a processor configured to perform the prediction method as described in any one of the above.
In yet another aspect, the present invention also provides a storage medium storing instructions for reading by a machine to cause the machine to perform a prediction method as described in any one of the above.
According to the technical scheme, the prediction method, the system and the storage medium for the reactive power compensation of the phase modulator divide historical reactive power data of reactive power compensation operation executed by the phase modulator into a training set and a testing set, then carry out quantization grading operation on the training set and the testing set respectively, then carry out deep learning by adopting the testing set and the training set, and finally predict the reactive power of the reactive power compensation of the phase modulator by adopting a neural network obtained by the deep learning, so that the accurate prediction of the reactive power is realized. In addition, the test set and the training set are subjected to quantization operation before deep learning, so that the complexity of the algorithm is greatly reduced, and the training speed of the neural network is improved.
Additional features and advantages of embodiments of the invention will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the embodiments of the invention without limiting the embodiments of the invention. In the drawings:
fig. 1 is a flow chart of a prediction method for reactive compensation of a phase modulator according to an embodiment of the present invention;
FIG. 2 is a flow diagram of a method of generating a training set or a test set according to one embodiment of the invention;
fig. 3 is a flow diagram of a quantization scaling operation according to an embodiment of the present invention.
Detailed Description
The following detailed description of embodiments of the invention refers to the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating embodiments of the invention, are given by way of illustration and explanation only, not limitation.
In the embodiments of the present invention, unless otherwise specified, the use of directional terms such as "upper, lower, top, and bottom" is generally used with respect to the orientation shown in the drawings or the positional relationship of the components with respect to each other in the vertical, or gravitational direction.
In addition, if there is a description of "first", "second", etc. in the embodiments of the present invention, the description of "first", "second", etc. is for descriptive purposes only and is not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In addition, technical solutions between the various embodiments can be combined with each other, but must be realized by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be considered to be absent and not be within the protection scope of the present invention.
Fig. 1 is a flowchart illustrating a prediction method for reactive compensation of a phase modulator according to an embodiment of the present invention. In fig. 1, the prediction method may include:
in step S10, historical reactive power data of the phase modifier performing reactive compensation operation is acquired.
In step S11, a training set and a test set are determined from the historical reactive power data. Specifically, the process of determining the training set and the test set may be, for example, as shown in fig. 2, and in fig. 2, the process may include:
in step S20, the historical reactive power data is divided into a plurality of data blocks according to a predetermined time interval. Wherein, for the time interval, it can be, but not limited to, a day, a month or a year. Taking the time interval as one month as an example, each data block corresponds to the variation value of the reactive power in the month.
In step S21, randomly selecting a data block from a plurality of data blocks as a prediction source;
in step S22, a source time interval corresponding to the predicted source is determined;
in step S23, a target time interval corresponding to the prediction result is determined from the source time interval. Specifically, the target time interval may be determined, for example, according to the source time interval with a predetermined time length (e.g., 6 months or 12 months). More specifically, taking the time length as 12 months and the source time interval as 2012 and 1 month as an example, the target time interval may be 2013 and 1 month.
In step S24, a data block corresponding to the target time interval is selected from the plurality of data blocks as a target data block. Wherein, the target data block is a standard result corresponding to the prediction source;
combining the prediction source and target data blocks into one prediction data in step S25;
in step S26, it is determined whether the number of prediction data is greater than or equal to a preset value. Wherein, the preset value can be determined by combining the size of the data set required by the actual deep learning (training neural network) by the person in the art;
under the condition that the quantity of the predicted data is judged to be smaller than the preset value, randomly selecting one data block from the plurality of data blocks as a prediction source again (returning to the step of 21), and executing the corresponding step of the prediction method until the quantity of the predicted data is judged to be larger than or equal to the preset value;
in step S27, in the case where the number of prediction data is judged to be greater than or equal to the preset value, the prediction data is combined into a training set or a test set.
In step S12, a quantitative ranking operation is performed on the training set and the test set. In particular, the quantization scaling operation may be, for example, the method shown in fig. 3. In fig. 3, the method may include:
in step S40, a normalization operation is performed for the average value of the reactive power in each predetermined time period in the time interval. The time period may be a time period of a preset time length within the time interval. Taking the time interval as 1 month as an example, the time period may be 1 day, for example. In this embodiment, the normalization operation may be known to those skilled in the art. In one example of the invention, however, to avoid that the difference of the overall value of the reactive power in different time intervals has an effect on the change of the whole training set or test set, the normalization operation can be performed by using formula (1),
wherein ,for the normalized value of the i-th time period after the normalization operation,for normalizing the reactive power in the i-th time period before operation, xmaxIs the maximum value of reactive power, x, in the current time intervalminIs the minimum value of the reactive power in the current time interval.
In step S41, the result of the normalization operation is converted into a corresponding parameter index according to a preset value interval. Specifically, the step S41 may be, for example, calculating the parameter index according to formula (2),
wherein ,to perform the normalization operation on the normalized value for the ith time period,is a parameter index.
In step S13, training the initial neural network using the training set to obtain a corresponding prediction result;
in step S14, the predicted result is compared with the standard result in the training set to calculate the corresponding error. Wherein the error can be calculated in a number of ways known to those skilled in the art. In one example of the invention, this way may be to calculate the error, for example according to equation (3),
where Δ x is the error, n is the number of time periods included in the time interval,the predicted value for the ith time period of the predicted result,the standard value of the ith time period of the standard result.
In step S15, it is determined whether the error is greater than a preset threshold;
in step S16, in case that the determination error is greater than the threshold, updating parameters of the neural network by using an inverse gradient method, training the initial neural network again by using the training set to obtain a corresponding prediction result (i.e. returning to perform step S13) and performing the corresponding steps of the method until the determination error is less than or equal to the threshold;
in step S17, in the case that the determination error is smaller than or equal to the threshold, testing the neural network using the test set to determine whether the neural network satisfies the preset prediction accuracy;
in step S18, in the case where it is determined that the neural network satisfies the prediction accuracy, outputting the neural network;
in step S19, reactive compensation is predicted using a neural network.
In another aspect, the present invention also provides a prediction system for reactive compensation of a phase modulator, which may comprise a processor operable to perform the prediction method as described in any one of the above.
In yet another aspect, the present invention also provides a storage medium which may store instructions which are readable by a machine to cause the machine to perform any of the prediction methods described above.
According to the technical scheme, the prediction method, the system and the storage medium for the reactive power compensation of the phase modulator divide historical reactive power data of reactive power compensation operation executed by the phase modulator into a training set and a testing set, then carry out quantization grading operation on the training set and the testing set respectively, then carry out deep learning by adopting the testing set and the training set, and finally predict the reactive power of the reactive power compensation of the phase modulator by adopting a neural network obtained by the deep learning, so that the accurate prediction of the reactive power is realized. In addition, the test set and the training set are subjected to quantization operation before deep learning, so that the complexity of the algorithm is greatly reduced, and the training speed of the neural network is improved.
Although the embodiments of the present invention have been described in detail with reference to the accompanying drawings, the embodiments of the present invention are not limited to the details of the above embodiments, and various simple modifications can be made to the technical solution of the embodiments of the present invention within the technical idea of the embodiments of the present invention, and the simple modifications all belong to the protection scope of the embodiments of the present invention.
It should be noted that the various features described in the above embodiments may be combined in any suitable manner without departing from the scope of the invention. In order to avoid unnecessary repetition, the embodiments of the present invention will not be described separately for the various possible combinations.
Those skilled in the art can understand that all or part of the steps in the method for implementing the above embodiments may be implemented by a program to instruct related hardware, where the program is stored in a storage medium and includes several instructions to enable a (may be a single chip, a chip, etc.) or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present application. 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 addition, various different embodiments of the present invention may be arbitrarily combined with each other, and the embodiments of the present invention should be considered as disclosed in the disclosure of the embodiments of the present invention as long as the embodiments do not depart from the spirit of the embodiments of the present invention.
Claims (8)
1. A prediction method for reactive compensation of a phase modulator, the prediction method comprising:
acquiring historical reactive power data of the phase modulator for executing the reactive compensation operation;
determining a training set and a testing set according to the historical reactive power data;
performing a quantitative hierarchical operation on the training set and the test set;
training an initial neural network by using the training set to obtain a corresponding prediction result;
comparing the predicted result with a standard result in the training set to calculate a corresponding error;
judging whether the error is larger than a preset threshold value or not;
under the condition that the error is judged to be larger than the threshold value, updating parameters of the neural network by adopting a reverse gradient method, training the initial neural network by adopting the training set again to obtain a corresponding prediction result, and executing corresponding steps of the method until the error is judged to be smaller than or equal to the threshold value;
under the condition that the error is judged to be less than or equal to the threshold value, testing the neural network by adopting the test set to judge whether the neural network meets the preset prediction precision;
under the condition that the neural network is judged to meet the prediction precision, outputting the neural network;
and predicting the reactive compensation by adopting the neural network.
2. The prediction method of claim 1, wherein determining a training set and a test set from the historical reactive power data specifically comprises:
dividing the historical reactive power data into a plurality of data blocks according to a preset time interval;
randomly selecting one data block from the plurality of data blocks as a prediction source;
determining a source time interval corresponding to the prediction source;
determining a target time interval corresponding to a prediction result according to the source time interval;
selecting a data block corresponding to the target time interval from the plurality of data blocks as a target data block, wherein the target data block is a standard result corresponding to the prediction source;
combining said prediction source and said target data block into a prediction data;
judging whether the quantity of the predicted data is greater than or equal to a preset value or not;
under the condition that the quantity of the predicted data is judged to be smaller than the preset value, randomly selecting one data block from the plurality of data blocks again to serve as a prediction source, and executing corresponding steps of the prediction method until the quantity of the predicted data is judged to be larger than or equal to the preset value;
and combining the prediction data into the training set or the test set under the condition that the number of the prediction data is judged to be greater than or equal to the preset value.
3. The prediction method according to claim 1, wherein performing a quantitative ranking operation on the training set and the test set specifically comprises:
performing a normalization operation on the average value of the reactive power in each preset time period in the time interval;
and converting the result of the normalization operation into a corresponding parameter index according to a preset numerical value interval.
4. The prediction method according to claim 3, wherein performing a normalization operation on the average value of the reactive power in each predetermined time period in the time interval comprises:
the normalization operation is performed according to equation (1),
wherein ,for the normalized value of the i-th time period after the normalization operation,for normalizing the reactive power in the i-th time period before operation, xmaxIs the maximum value, x, of the reactive power in the current time intervalminIs the minimum value of the reactive power in the current time interval.
5. The prediction method of claim 3, wherein converting the result of the normalization operation into a corresponding parameter index according to a preset value interval comprises:
calculating the parameter index according to equation (2),
6. The prediction method of claim 3, wherein comparing the predicted result with the standard result in the training set to calculate the corresponding error specifically comprises:
the error is calculated according to equation (3),
7. A prediction system for reactive compensation of a phase modulator, characterized in that the prediction system comprises a processor for performing the prediction method according to any one of claims 1 to 6.
8. A storage medium storing instructions for reading by a machine to cause the machine to perform a prediction method according to any one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010143591.3A CN111355246B (en) | 2020-03-04 | 2020-03-04 | Prediction method, system and storage medium for reactive compensation of camera |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010143591.3A CN111355246B (en) | 2020-03-04 | 2020-03-04 | Prediction method, system and storage medium for reactive compensation of camera |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111355246A true CN111355246A (en) | 2020-06-30 |
CN111355246B CN111355246B (en) | 2023-08-18 |
Family
ID=71197345
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010143591.3A Active CN111355246B (en) | 2020-03-04 | 2020-03-04 | Prediction method, system and storage medium for reactive compensation of camera |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111355246B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112799298A (en) * | 2020-12-24 | 2021-05-14 | 哈尔滨理工大学 | Control method of synchronous phase modulator excitation system based on fuzzy neural network PID control |
CN113300379A (en) * | 2021-05-08 | 2021-08-24 | 武汉大学 | Electric power system reactive voltage control method and system based on deep learning |
CN115459299A (en) * | 2022-10-11 | 2022-12-09 | 南方电网数字电网研究院有限公司 | Low-voltage distribution reactive power regulation method and device, computer equipment and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0937466A (en) * | 1995-07-20 | 1997-02-07 | Meidensha Corp | Reactive power compensator |
CN208076675U (en) * | 2018-04-02 | 2018-11-09 | 国网湖南省电力有限公司 | A kind of trouble-shooter for large-scale phase modifier |
CN208226574U (en) * | 2018-03-28 | 2018-12-11 | 上海电气电站设备有限公司 | Synchronous capacitor group |
CN110334879A (en) * | 2019-07-11 | 2019-10-15 | 华北电力大学 | Power grid bus reactive load forecasting method and device |
-
2020
- 2020-03-04 CN CN202010143591.3A patent/CN111355246B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0937466A (en) * | 1995-07-20 | 1997-02-07 | Meidensha Corp | Reactive power compensator |
CN208226574U (en) * | 2018-03-28 | 2018-12-11 | 上海电气电站设备有限公司 | Synchronous capacitor group |
CN208076675U (en) * | 2018-04-02 | 2018-11-09 | 国网湖南省电力有限公司 | A kind of trouble-shooter for large-scale phase modifier |
CN110334879A (en) * | 2019-07-11 | 2019-10-15 | 华北电力大学 | Power grid bus reactive load forecasting method and device |
Non-Patent Citations (1)
Title |
---|
吴跨宇等: "大型调相机励磁与无功电压协调控制策略探讨" * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112799298A (en) * | 2020-12-24 | 2021-05-14 | 哈尔滨理工大学 | Control method of synchronous phase modulator excitation system based on fuzzy neural network PID control |
CN113300379A (en) * | 2021-05-08 | 2021-08-24 | 武汉大学 | Electric power system reactive voltage control method and system based on deep learning |
CN115459299A (en) * | 2022-10-11 | 2022-12-09 | 南方电网数字电网研究院有限公司 | Low-voltage distribution reactive power regulation method and device, computer equipment and storage medium |
CN115459299B (en) * | 2022-10-11 | 2024-06-25 | 南方电网数字电网研究院有限公司 | Low-voltage distribution reactive power regulation method, device, computer equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN111355246B (en) | 2023-08-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111355246A (en) | Prediction method, system and storage medium for reactive compensation of phase modulator | |
CN109885469B (en) | Capacity expansion method, prediction model creation method, device, equipment and medium | |
CN110209560B (en) | Data anomaly detection method and detection device | |
EP3089034A1 (en) | System and method for optimizing energy consumption by processors | |
CN106549772A (en) | Resource prediction method, system and capacity management device | |
CN1809823A (en) | Method and apparatus to establish, report and adjust system memory usage | |
CN112217207B (en) | Transient voltage stability margin prediction method and device | |
CN111327655A (en) | Multi-tenant container resource quota prediction method and device and electronic equipment | |
JP2015192502A (en) | Power consumption prediction method, power consumption prediction program and power consumption prediction device | |
CN112926636A (en) | Method and device for detecting abnormal temperature of traction converter cabinet body | |
CN111832693B (en) | Neural network layer operation and model training method, device and equipment | |
CN113191432B (en) | Outlier factor-based virtual machine cluster abnormality detection method, device and medium | |
CN112308337A (en) | Prediction method, prediction device and processor for probabilistic short-term load of power system | |
CN117593464A (en) | Construction method and system of electric power digital twin model library | |
CN116414662B (en) | Storage space expansion prompting method and device, electronic equipment and storage medium | |
CN115856694B (en) | Battery life prediction method, device, computer equipment and storage medium | |
CN116414663A (en) | Capacity expansion prompting method, device and storage medium based on capacity use prediction | |
CN114417022A (en) | Model training method, data processing method and device | |
JP2009086848A (en) | Semiconductor device, method for controlling semiconductor device, and method for creating control information of semiconductor device | |
CN110543549B (en) | Semantic equivalence judgment method and device | |
CN111476347B (en) | Maintenance method, system and storage medium of phase modulator based on multiple factors | |
CN112418484A (en) | Data processing method and device | |
CN113123765A (en) | Method, device and equipment for controlling operation of beam-pumping unit and storage medium | |
CN113892220A (en) | Method, apparatus and computer program product for monitoring energy consumption in an electric vehicle charging network | |
CN112084665B (en) | Modeling method and system for transformer substation 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 | ||
CB02 | Change of applicant information |
Address after: No. 397, Tongcheng South Road, Baohe District, Hefei City, Anhui Province 230061 Applicant after: Super high voltage branch of State Grid Anhui Electric Power Co.,Ltd. Applicant after: STATE GRID CORPORATION OF CHINA Address before: No. 397, Tongcheng South Road, Baohe District, Hefei City, Anhui Province 230061 Applicant before: STATE GRID ANHUI POWER SUPPLY COMPANY OVERHAUL BRANCH Applicant before: STATE GRID CORPORATION OF CHINA |
|
CB02 | Change of applicant information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |