CN113300371B - Method and device for determining real-time voltage of power distribution room - Google Patents
Method and device for determining real-time voltage of power distribution room Download PDFInfo
- Publication number
- CN113300371B CN113300371B CN202110602089.9A CN202110602089A CN113300371B CN 113300371 B CN113300371 B CN 113300371B CN 202110602089 A CN202110602089 A CN 202110602089A CN 113300371 B CN113300371 B CN 113300371B
- Authority
- CN
- China
- Prior art keywords
- voltage
- historical
- value
- power distribution
- distribution room
- 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.)
- Active
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
- 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
-
- 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
- H02J3/04—Circuit arrangements for ac mains or ac distribution networks for connecting networks of the same frequency but supplied from different sources
- H02J3/06—Controlling transfer of power between connected networks; Controlling sharing of load between connected 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
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/10—Power transmission or distribution systems management focussing at grid-level, e.g. load flow analysis, node profile computation, meshed network optimisation, active network management or spinning reserve management
-
- 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
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a method and a device for determining real-time voltage of a power distribution room, wherein the method comprises the following steps: acquiring a measuring point of target equipment on a preset path of a power distribution room through network topology; acquiring historical switch states and historical voltage values of the measuring points at the moment corresponding to the historical voltages of the power distribution room from historical data of the measuring points; training the prediction network model by taking a historical switch state and a historical voltage of a measuring point at a moment corresponding to the historical voltage of the power distribution room as training samples to obtain a target prediction network model; when a real-time data refreshing request is received, inputting the on-off state and the voltage value of the measurement point collected in a preset period to a target prediction network model to obtain a voltage prediction value; carrying out load flow calculation on the voltage of the power distribution room to obtain a load flow calculation value; and determining the real-time voltage of the power distribution room based on the voltage predicted value and the power flow calculation value. The real-time voltage of the power distribution room is determined through two modes of neural network prediction and load flow calculation, so that the availability of the distribution network AVC is improved.
Description
Technical Field
The invention relates to the technical field of power system automation, in particular to a method and a device for determining real-time voltage of a power distribution room.
Background
With the increasing importance of the development of the power distribution network in the countries in recent years, the project construction of the power distribution network is more and more, and the distribution network system in the power distribution room needs to face more complex power working conditions and higher operation level. The distribution network AVC is an important technical measure for voltage support, and can play a great role in the aspects of regulating voltage, improving system stability, stabilizing impact load influence and the like. If complex power working conditions possibly existing at the present stage need to be solved through distribution network AVC, the running level of a distribution network system is improved, and the improvement of the instantaneity of voltage data acquisition of a distribution network power distribution room is of great importance.
At present, voltage data of a distribution room on a distribution network side is transmitted to a distribution network system through a metering system, and a data acquisition period is generally 15 minutes, so that the AVC of the distribution network is poor in real-time performance and the availability cannot be guaranteed.
Therefore, the voltage stability of the distribution network side distribution room bus is maintained to the maximum extent, the development of science and technology and the improvement of the living standard of people are realized, and the important significance is achieved under the background that the problem of the voltage quality of the distribution room is more and more prominent.
Disclosure of Invention
The invention provides a method and a device for determining real-time voltage of a power distribution room, which are used for determining the real-time voltage of the power distribution room through two modes of neural network prediction and load flow calculation, so that the availability of the AVC of a distribution network is improved.
In a first aspect, the present invention provides a method for determining a real-time voltage of a power distribution room, including:
acquiring a measuring point of target equipment on a preset path of a power distribution room through network topology;
acquiring historical switch states and historical voltage values of the measuring points at the moment corresponding to the historical voltages of the power distribution room from historical data of the measuring points by taking bus refreshing intervals of the power distribution room as an acquisition cycle;
constructing an initialized prediction network model, and training the prediction network model by taking the historical on-off state and the historical voltage of the measuring point at the moment corresponding to the historical voltage of the power distribution room as training samples to obtain a target prediction network model;
when a real-time data refreshing request is received, inputting the switch state and the voltage value of the measuring point collected in a preset period to the target prediction network model to obtain a voltage prediction value;
carrying out load flow calculation on the voltage of the power distribution room to obtain a load flow calculation value;
and judging the rationality of the voltage predicted value, and determining the real-time voltage of the power distribution room based on the voltage predicted value and the power flow calculation value according to the rationality of the voltage predicted value.
Optionally, after obtaining the historical voltage and the historical switch state from the historical data of the measurement point by using a bus refreshing interval of the power distribution room as an acquisition cycle, the method further includes:
and determining a missing measurement from the historical voltage and the historical switch state, and performing supplementary processing on the missing measurement.
Optionally, the determining the real-time voltage of the power distribution room based on the voltage predicted value and the power flow calculation value according to the rationality of the voltage predicted value includes:
acquiring a historical average voltage value, and calculating the average value of the voltage values of the measuring points acquired in a preset period;
determining the difference ratio between the historical average voltage value and the average value based on the historical average voltage value and the average value by combining a preset difference ratio evaluation formula;
judging whether the difference ratio is in a reasonable range corresponding to the difference ratio evaluation formula; if so, determining that the predicted voltage value is reasonable; and if not, determining that the predicted value of the voltage is unreasonable.
Optionally, the determining the real-time voltage of the power distribution room according to the rationality of the voltage predicted value and based on the voltage predicted value and the power flow calculation value further includes:
under the condition that the voltage predicted value is reasonable, determining the real-time voltage of the power distribution room based on the size relation between the voltage predicted value and the power flow calculation value;
and under the condition that the voltage predicted value is unreasonable, taking the power flow calculated value as the real-time voltage of the power distribution room.
Optionally, constructing an initialized prediction network model, training the prediction network model by using the historical on-off state and the historical voltage of the measurement point at the time corresponding to the historical voltage of the power distribution room as training samples, and obtaining a target prediction network model, where the method includes:
inputting the historical switch state into the prediction network model to generate a corresponding voltage test value;
determining the training error according to the voltage test value and the historical voltage;
and adjusting the prediction network model based on the training error to obtain the optimal network parameter, and generating a target prediction network model by adopting the optimal network parameter.
In a second aspect, the present invention further provides a device for determining a real-time voltage of a power distribution room, including:
the first acquisition module is used for acquiring a measuring point of the target equipment on a preset path of the power distribution room through network topology;
the second acquisition module is used for acquiring the historical switch state and the historical voltage value of the measuring point at the moment corresponding to the historical voltage of the power distribution room from the historical data of the measuring point by taking a bus refreshing interval of the power distribution room as an acquisition cycle;
the training module is used for constructing an initialized prediction network model, and training the prediction network model by taking the historical switch state and the historical voltage of the measuring point at the moment corresponding to the historical voltage of the power distribution room as training samples to obtain a target prediction network model;
the prediction module is used for inputting the on-off state and the voltage value of the measuring point collected in a preset period to the target prediction network model when a real-time data refreshing request is received, and obtaining a voltage prediction value;
the calculation module is used for carrying out load flow calculation on the voltage of the power distribution room to obtain a load flow calculation value;
and the rationality judgment module is used for judging the rationality of the voltage predicted value and determining the real-time voltage of the power distribution room based on the voltage predicted value and the power flow calculation value according to the rationality of the voltage predicted value.
Optionally, the apparatus further comprises:
and the supplement module is used for determining the missing measurement from the historical voltage and the historical switch state and performing supplement processing on the missing measurement.
Optionally, the rationality determining module comprises:
the acquisition submodule is used for acquiring a historical average voltage value and calculating the average value of the voltage values of the measurement points acquired in a preset period;
the difference ratio determining submodule is used for determining the difference ratio between the historical average voltage value and the average value based on the historical average voltage value and the average value by combining a preset difference ratio evaluation formula;
the judgment submodule is used for judging whether the difference ratio is in a reasonable range corresponding to the difference ratio evaluation formula or not; if so, determining that the predicted voltage value is reasonable; and if not, determining that the predicted value of the voltage is unreasonable.
Optionally, the rationality determining module further comprises:
the first determining submodule is used for determining the real-time voltage of the power distribution room based on the magnitude relation between the voltage predicted value and the power flow calculated value under the condition that the voltage predicted value is reasonable;
and the second determining submodule is used for taking the power flow calculation value as the real-time voltage of the power distribution room under the condition that the voltage prediction value is unreasonable.
Optionally, the training module comprises:
the input submodule is used for inputting the historical switch state into the prediction network model and generating a corresponding voltage test value;
the training error determining submodule is used for determining the training error according to the voltage test value and the historical voltage;
and the target prediction network model generation submodule is used for adjusting the prediction network model based on the training error to obtain the optimal network parameter and generating the target prediction network model by adopting the optimal network parameter.
According to the technical scheme, the invention has the following advantages:
the method comprises the steps of obtaining measuring points of target equipment on a preset path of a power distribution room through network topology; acquiring historical switch states and historical voltage values of the measuring points at the moment corresponding to the historical voltages of the power distribution room from historical data of the measuring points by taking bus refreshing intervals of the power distribution room as an acquisition cycle; constructing an initialized prediction network model, and training the prediction network model by taking the historical on-off state and the historical voltage of the measuring point at the moment corresponding to the historical voltage of the power distribution room as training samples to obtain a target prediction network model; when a real-time data refreshing request is received, inputting the switch state and the voltage value of the measuring point collected in a preset period to the target prediction network model to obtain a voltage prediction value; carrying out load flow calculation on the voltage of the power distribution room to obtain a load flow calculation value; and judging the rationality of the voltage predicted value, and determining the real-time voltage of the power distribution room based on the voltage predicted value and the power flow calculation value according to the rationality of the voltage predicted value. The real-time voltage of the power distribution room is determined through two modes of neural network prediction and load flow calculation, so that the availability of the distribution network AVC is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts;
fig. 1 is a flowchart illustrating steps of a first method for determining a real-time voltage of a power distribution room according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating steps of a second embodiment of determining a real-time voltage of a power distribution room according to the present invention;
FIG. 3 is a schematic diagram of the connection between a measurement point and a power distribution room obtained through a network topology according to the present invention;
fig. 4 is a block diagram of an embodiment of a device for determining a real-time voltage of a power distribution room according to the present invention.
Detailed Description
The embodiment of the invention provides a method and a device for determining the real-time voltage of a power distribution room, wherein the real-time voltage of the power distribution room is determined through two modes of neural network prediction and load flow calculation, so that the availability of the distribution network AVC is improved.
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the embodiments described below 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.
Referring to fig. 1, fig. 1 is a flowchart illustrating a first step of a method for determining a real-time voltage of a power distribution room according to a first embodiment of the present invention, which may specifically include the following steps:
step S101, acquiring a measuring point of target equipment on a preset path of a power distribution room through network topology;
step S102, by taking a bus refreshing interval of a power distribution room as an acquisition cycle, acquiring a historical switch state and a historical voltage value of a measuring point at a moment corresponding to historical voltage of the power distribution room from historical data of the measuring point;
step S103, constructing an initialized prediction network model, and training the prediction network model by taking the historical switch state and the historical voltage of the measuring point at the moment corresponding to the historical voltage of the power distribution room as training samples to obtain a target prediction network model;
step S104, inputting the switch state and the voltage value of the measuring point collected in a preset period to the target prediction network model when a real-time data refreshing request is received, and obtaining a voltage prediction value;
step S105, carrying out load flow calculation on the voltage of the power distribution room to obtain a load flow calculation value;
step S106, judging the rationality of the predicted voltage value; and determining the real-time voltage of the power distribution room based on the voltage predicted value and the power flow calculation value according to the rationality of the voltage predicted value.
In the embodiment of the invention, measuring points of target equipment are acquired on a preset path of a power distribution room through network topology; acquiring historical switch states and historical voltage values of the measuring points at the moment corresponding to the historical voltages of the power distribution room from historical data of the measuring points by taking bus refreshing intervals of the power distribution room as an acquisition cycle; establishing an initialized prediction network model, and training the prediction network model by taking the historical switch state and the historical voltage of the measuring point at the moment corresponding to the historical voltage of the power distribution room as training samples to obtain a target prediction network model; when a real-time data refreshing request is received, inputting the switch state and the voltage value of the measuring point collected in a preset period to the target prediction network model to obtain a voltage prediction value; carrying out load flow calculation on the voltage of the power distribution room to obtain a load flow calculation value; and judging the rationality of the voltage predicted value, and determining the real-time voltage of the power distribution room based on the voltage predicted value and the power flow calculation value according to the rationality of the voltage predicted value. The real-time voltage of the power distribution room is determined through two modes of neural network prediction and load flow calculation, so that the availability of the distribution network AVC is improved.
Referring to fig. 2, a flowchart of a second embodiment of the method for determining a real-time voltage of a power distribution room of the present invention includes:
step S201, acquiring a measuring point of target equipment on a preset path of a power distribution room through network topology;
referring to fig. 3, fig. 3 is a schematic diagram illustrating connection between measurement points and a distribution room obtained through a network topology according to the present invention, in an embodiment of the present invention, three automatic switches, i.e., measurement points, G01, 601, and 602 of a heating distribution system of an I38 public distribution station are identified through the network topology, and then basic measurements are obtained on the three automatic switches.
In a specific implementation, the set of prediction network models input to step S204 as training data acquired at the measurement points is generally: [ G01-Uab, G01-Iab,
G01-switchstate，601-Uab，601-Iab，
601-switchstate，602-Uab，602-Iab，
602-switchstate，G02-switchstate，G03-switchstate，g05-switchstate), wherein the last three pieces of data of the set are states of load switches of the I38 utility substation, and the output item of the predictive network model of step S204 is a voltage prediction value of the I38 substation, which may correspond to a plurality of bus voltages of a same level circuit.
Step S202, by taking a bus refreshing interval of a power distribution room as an acquisition cycle, acquiring a historical switch state and a historical voltage value of a measuring point at a moment corresponding to the historical voltage of the power distribution room from historical data of the measuring point;
step S203, determining a missing measurement from the historical voltage and the historical switch state, and performing supplementary processing on the missing measurement;
in the embodiment of the invention, a bus refreshing interval of a power distribution room is taken as an acquisition cycle, and each cycle acquires the values and the switch states of the measurement points of all the devices searched by the topology and carries out preprocessing, namely, related historical data of the measurement points, including historical switch states and historical voltage values, are inquired and recorded from a historical library according to the acquisition cycle.
Meanwhile, each sample record is listed, and then the missing measurement is subjected to supplementary processing. The supplement method comprises the following steps: supplementing according to actual operation experience, such as supplementing the missing measurement as an average value or reasonable data deduced according to experience; for example, missing data in the third row of the table below, which is empirically inferred to be 10.164; the lost data of the fifth row has no voltage due to the disconnection of the switch, and the voltage of an automatic switch 1 of the branch is deducted to be a complementary bit 0 according to experience; the switch quantity of the sixth row of switches 1 is lost, and the collected voltage on the automatic switch 1 is 0, so that the switch is judged to be switched off according to experience.
In addition, the measured value and the rated value are compared, an abnormal proportion is calculated, the abnormal proportion is the difference between the calculated measured data and the rated data divided by the rated value, and records that the abnormal proportion exceeds a set threshold value are discarded until all missing measurement is supplemented, so that data preprocessing is completed.
Step S204, constructing an initialized prediction network model, and training the prediction network model by taking the historical switch state and the historical voltage of the measuring point at the moment corresponding to the historical voltage of the power distribution room as training samples to obtain a target prediction network model;
in an optional embodiment, constructing an initialized prediction network model, taking a historical on-off state and a historical voltage of the measurement point at a time corresponding to the historical voltage of the power distribution room as training samples, and training the prediction network model to obtain a target prediction network model, includes:
inputting the historical switch state into the prediction network model to generate a corresponding voltage test value;
determining the training error according to the voltage test value and the historical voltage;
and adjusting the prediction network model based on the training error to obtain the optimal network parameter, and generating a target prediction network model by adopting the optimal network parameter.
In the embodiment of the invention, the prediction network model determines the training error according to the voltage test value and the historical voltage, and then adjusts parameters such as width, depth, learning rate and the like of the prediction network model according to the training error to obtain the optimal network parameter, thereby obtaining the target prediction network model.
In addition, the prediction network model of the embodiment of the invention also adds a dropout layer and sets a termination condition for the model in advance to slow down the degree of overfitting.
In addition, after the target prediction network model is online, in order to ensure the effectiveness and the adaptability of the target prediction network model, data are organized regularly to carry out incremental training on the model.
Step S205, when a real-time data refreshing request is received, inputting the switch state and the voltage value of the measuring point collected in a preset period to the target prediction network model to obtain a voltage prediction value;
step S206, carrying out load flow calculation on the voltage of the power distribution room to obtain a load flow calculation value;
step S207, acquiring a historical average voltage value, and calculating the average value of the voltage values of the measurement points acquired in a preset period;
step S208, based on the historical average voltage value and the average value, determining the difference ratio between the historical average voltage value and the average value by combining a preset difference ratio evaluation formula;
in the embodiment of the present invention, after the predicted voltage value is determined by the target prediction network model, the voltage value of the measurement point is calculated by weighting all the effective voltage values participating in the operation, that is, the voltage values of the measurement points in the preset period are weighted to obtain an average value, and then the average value and the historical average voltage value are calculated according to a difference ratio evaluation formula to obtain a difference ratio, where the difference ratio evaluation formula specifically is:
wherein R isdiffIs a difference ratio, UhaveFor historical average voltage values, UaveAre averages.
Step S209, judging whether the difference ratio is in a reasonable range corresponding to the difference ratio evaluation formula; if so, determining that the predicted voltage value is reasonable; if not, determining that the predicted value of the voltage is unreasonable;
in the embodiment of the invention, if the difference proportion is greater than 10%, the voltage predicted value is not reasonable, and if the difference proportion is less than or equal to 10%, the voltage predicted value is reasonable.
Step S210, determining real-time voltage of the power distribution room based on the voltage predicted value and the power flow calculation value according to the rationality of the voltage predicted value, specifically:
under the condition that the voltage predicted value is reasonable, determining the real-time voltage of the power distribution room based on the magnitude relation between the voltage predicted value and the power flow calculation value;
and under the condition that the voltage predicted value is unreasonable, taking the power flow calculated value as the real-time voltage of the power distribution room.
In the embodiment of the invention, when the automatic voltage control system of the distribution network needs to obtain AVC real-time data, a difference ratio can be obtained according to the relation between the average value of the current sample and the historical average voltage value, when the difference ratio exceeds 10%, the current calculation value is independently adopted, otherwise, the current calculation value and the neural network prediction value are adopted, and a weighted residual error method is combined to obtain a comprehensive processing value as the real-time voltage of the distribution room. Therefore, the method can effectively avoid inaccurate voltage prediction caused by the extreme condition that the voltage is too large or too small.
The method for determining the real-time voltage of the power distribution room, provided by the embodiment of the invention, comprises the steps of obtaining a measuring point of target equipment on a preset path of the power distribution room through network topology; acquiring historical switch states and historical voltage values of the measuring points at the moment corresponding to the historical voltages of the power distribution room from historical data of the measuring points by taking bus refreshing intervals of the power distribution room as an acquisition cycle; establishing an initialized prediction network model, and training the prediction network model by taking the historical switch state and the historical voltage of the measuring point at the moment corresponding to the historical voltage of the power distribution room as training samples to obtain a target prediction network model; when a real-time data refreshing request is received, inputting the switch state and the voltage value of the measuring point collected in a preset period to the target prediction network model to obtain a voltage prediction value; carrying out load flow calculation on the voltage of the power distribution room to obtain a load flow calculation value; and judging the rationality of the voltage predicted value, and determining the real-time voltage of the power distribution room based on the voltage predicted value and the power flow calculation value according to the rationality of the voltage predicted value. The real-time voltage of the power distribution room is determined through two modes of neural network prediction and load flow calculation, so that the availability of the distribution network AVC is improved.
Referring to fig. 4, a block diagram of an embodiment of a device for determining a real-time voltage of a power distribution room is shown, which includes the following modules:
a first obtaining module 401, configured to obtain a measurement point of a target device on a preset path of a power distribution room through a network topology;
a second obtaining module 402, configured to obtain, from historical data of the measurement point, a historical on-off state and a historical voltage value of the measurement point at a time corresponding to a historical voltage of the power distribution room, with a bus refreshing interval of the power distribution room as an acquisition cycle;
the training module 403 is configured to construct an initialized prediction network model, and train the prediction network model by using a historical on-off state and a historical voltage of the measurement point at a time corresponding to the historical voltage of the power distribution room as training samples to obtain a target prediction network model;
the prediction module 404 is configured to, when a real-time data refresh request is received, input the on-off state and the voltage value of the measurement point acquired in a preset period to the target prediction network model to obtain a voltage prediction value;
the calculation module 405 is configured to perform load flow calculation on the voltage of the power distribution room to obtain a load flow calculation value;
and the rationality judgment module 406 is used for judging the rationality of the voltage predicted value and determining the real-time voltage of the power distribution room based on the voltage predicted value and the power flow calculation value according to the rationality of the voltage predicted value.
In an optional embodiment, the apparatus further comprises:
and the supplement module is used for determining the missing measurement from the historical voltage and the historical switch state and performing supplement processing on the missing measurement.
In an alternative embodiment, the rationality determining module 406 includes:
the acquisition submodule is used for acquiring a historical average voltage value and calculating the average value of the voltage values of the measurement points acquired in a preset period;
the difference ratio determining submodule is used for determining the difference ratio between the historical average voltage value and the average value based on the historical average voltage value and the average value by combining a preset difference ratio evaluation formula;
the judgment submodule is used for judging whether the difference ratio is in a reasonable range corresponding to the difference ratio evaluation formula or not; if so, determining that the predicted voltage value is reasonable; and if not, determining that the predicted value of the voltage is unreasonable.
In an alternative embodiment, the rationality determining module 406 further comprises:
the first determining submodule is used for determining the real-time voltage of the power distribution room based on the magnitude relation between the voltage predicted value and the power flow calculated value under the condition that the voltage predicted value is reasonable;
and the second determination submodule is used for taking the power flow calculation value as the real-time voltage of the power distribution room under the condition that the voltage prediction value is unreasonable.
In an alternative embodiment, the training module 403 includes:
the input submodule is used for inputting the historical switch state into the prediction network model and generating a corresponding voltage test value;
the training error determining submodule is used for determining the training error according to the voltage test value and the historical voltage;
and the target prediction network model generation submodule is used for adjusting the prediction network model based on the training error to obtain the optimal network parameter and generating the target prediction network model by adopting the optimal network parameter.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working process of the apparatus described above may refer to the corresponding process in the foregoing method embodiment, and is not described herein again.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
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 units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. 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 method according to the 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 various media capable of storing program codes.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it should 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 (6)
1. A method for determining real-time voltage of a power distribution room is characterized by comprising the following steps:
acquiring a measuring point of target equipment on a preset path of a power distribution room through network topology;
acquiring historical switch states and historical voltage values of the measuring points at the moment corresponding to the historical voltages of the power distribution room from historical data of the measuring points by taking bus refreshing intervals of the power distribution room as an acquisition cycle;
establishing an initialized prediction network model, and training the prediction network model by taking the historical switch state and the historical voltage of the measuring point at the moment corresponding to the historical voltage of the power distribution room as training samples to obtain a target prediction network model;
when a real-time data refreshing request is received, inputting the switch state and the voltage value of the measuring point collected in a preset period to the target prediction network model to obtain a voltage prediction value;
carrying out load flow calculation on the voltage of the power distribution room to obtain a load flow calculation value;
judging the rationality of the voltage predicted value, and determining the real-time voltage of the power distribution room based on the voltage predicted value and the power flow calculation value according to the rationality of the voltage predicted value;
the rationality judgment is carried out on the voltage predicted value, and the real-time voltage of the power distribution room is determined based on the voltage predicted value and the power flow calculation value according to the rationality of the voltage predicted value, and the method comprises the following steps:
acquiring a historical average voltage value, and calculating the average value of the voltage values of the measuring points acquired in a preset period;
determining the difference ratio between the historical average voltage value and the average value based on the historical average voltage value and the average value by combining a preset difference ratio evaluation formula;
judging whether the difference ratio is in a reasonable range corresponding to the difference ratio evaluation formula; if so, determining that the predicted voltage value is reasonable; if not, determining that the predicted value of the voltage is unreasonable;
under the condition that the voltage predicted value is reasonable, determining the real-time voltage of the power distribution room based on the magnitude relation between the voltage predicted value and the power flow calculation value, namely determining the real-time voltage of the power distribution room by adopting the power flow calculation value and the voltage predicted value and combining a weighted residual error method;
and under the condition that the voltage predicted value is unreasonable, taking the power flow calculated value as the real-time voltage of the power distribution room.
2. The method for determining the real-time voltage of the power distribution room according to claim 1, wherein after obtaining the historical voltage and the historical switch state from the historical data of the measurement point by taking a bus bar refresh interval of the power distribution room as a collection period, the method further comprises:
and determining a missing measurement from the historical voltage and the historical switch state, and performing supplementary processing on the missing measurement.
3. The method for determining the real-time voltage of the power distribution room according to claim 1, wherein an initialized prediction network model is constructed, and the target prediction network model is obtained by training the prediction network model with a historical on-off state and a historical voltage of the measurement point at a time corresponding to the historical voltage of the power distribution room as training samples, and comprises the following steps:
inputting the historical switch state into the prediction network model to generate a corresponding voltage test value;
determining a training error according to the voltage test value and the historical voltage;
and adjusting the prediction network model based on the training error to obtain an optimal network parameter, and generating a target prediction network model by adopting the optimal network parameter.
4. A device for determining real-time voltage of a power distribution room, comprising:
the first acquisition module is used for acquiring a measuring point of the target equipment on a preset path of the power distribution room through network topology;
the second acquisition module is used for acquiring the historical switch state and the historical voltage value of the measuring point at the moment corresponding to the historical voltage of the power distribution room from the historical data of the measuring point by taking a bus refreshing interval of the power distribution room as an acquisition cycle;
the training module is used for constructing an initialized prediction network model, and training the prediction network model by taking the historical switch state and the historical voltage of the measuring point at the moment corresponding to the historical voltage of the power distribution room as training samples to obtain a target prediction network model;
the prediction module is used for inputting the on-off state and the voltage value of the measurement point collected in a preset period to the target prediction network model when a real-time data refreshing request is received, and obtaining a voltage prediction value;
the calculation module is used for carrying out load flow calculation on the voltage of the power distribution room to obtain a load flow calculation value;
the rationality judgment module is used for judging the rationality of the voltage predicted value and determining the real-time voltage of the power distribution room based on the voltage predicted value and the power flow calculation value according to the rationality of the voltage predicted value;
the rationality judging module includes:
the acquisition submodule is used for acquiring a historical average voltage value and calculating the average value of the voltage values of the measuring points acquired in a preset period;
the difference ratio determining submodule is used for determining the difference ratio between the historical average voltage value and the average value by combining a preset difference ratio evaluation formula based on the historical average voltage value and the average value;
the judgment sub-module is used for judging whether the difference proportion is in a reasonable range corresponding to the difference proportion evaluation formula; if so, determining that the predicted voltage value is reasonable; if not, determining that the predicted value of the voltage is unreasonable;
the rationality judgment module further includes:
the first determining submodule is used for determining the real-time voltage of the power distribution room based on the magnitude relation between the voltage predicted value and the power flow calculated value under the condition that the voltage predicted value is reasonable, namely the power flow calculated value and the voltage predicted value are adopted, and the real-time voltage of the power distribution room is determined by combining a weighted residual error method;
and the second determining submodule is used for taking the power flow calculation value as the real-time voltage of the power distribution room under the condition that the voltage prediction value is unreasonable.
5. The apparatus for determining real-time voltage of a power distribution room of claim 4, wherein the apparatus further comprises:
and the supplement module is used for determining the missing measurement from the historical voltage and the historical switch state and performing supplement processing on the missing measurement.
6. The apparatus for determining real-time voltage of a power distribution room according to claim 4, wherein the training module comprises:
the input submodule is used for inputting the historical switch state into the prediction network model and generating a corresponding voltage test value;
the training error determining submodule is used for determining the training error according to the voltage test value and the historical voltage;
and the target prediction network model generation submodule is used for adjusting the prediction network model based on the training error to obtain an optimal network parameter and generating the target prediction network model by adopting the optimal network parameter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110602089.9A CN113300371B (en) | 2021-05-31 | 2021-05-31 | Method and device for determining real-time voltage of power distribution room |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110602089.9A CN113300371B (en) | 2021-05-31 | 2021-05-31 | Method and device for determining real-time voltage of power distribution room |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113300371A CN113300371A (en) | 2021-08-24 |
| CN113300371B true CN113300371B (en) | 2022-07-12 |
Family
ID=77326382
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110602089.9A Active CN113300371B (en) | 2021-05-31 | 2021-05-31 | Method and device for determining real-time voltage of power distribution room |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113300371B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115051912B (en) * | 2022-06-20 | 2023-11-03 | 广东电网有限责任公司 | Power failure user positioning method, device, equipment and medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111414999A (en) * | 2020-04-27 | 2020-07-14 | 新智数字科技有限公司 | Method and device for monitoring running state of equipment |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103972985B (en) * | 2014-05-26 | 2015-12-02 | 湖南大学 | A kind of safety on line early warning of power distribution network and prevention and control method |
| US9971371B2 (en) * | 2015-03-17 | 2018-05-15 | Mitsubishi Electric Research Laboratories, Inc. | Method for predicting a voltage collapse in a micro-grid connected to a power distribution network |
| CN104836227B (en) * | 2015-04-17 | 2017-03-15 | 天津大学 | The power distribution network active voltage control method of case-based reasioning |
| CN107634516A (en) * | 2017-09-11 | 2018-01-26 | 三峡大学 | A kind of distribution method for estimating state based on Grey Markov Chain |
| CN108173263B (en) * | 2017-12-29 | 2022-02-22 | 国网天津市电力公司电力科学研究院 | Distribution network topology error identification algorithm based on AMI measurement information |
| CN111756031B (en) * | 2019-03-29 | 2023-11-03 | 中国电力科学研究院有限公司 | Power grid operation trend estimation method and system |
| CN112819373A (en) * | 2021-02-25 | 2021-05-18 | 云南电网有限责任公司电力科学研究院 | Distribution network voltage abnormal data detection method and device |
-
2021
- 2021-05-31 CN CN202110602089.9A patent/CN113300371B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111414999A (en) * | 2020-04-27 | 2020-07-14 | 新智数字科技有限公司 | Method and device for monitoring running state of equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113300371A (en) | 2021-08-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110082699B (en) | Low-voltage transformer area intelligent electric energy meter operation error calculation method and system | |
| CN113300371B (en) | Method and device for determining real-time voltage of power distribution room | |
| CN112288303A (en) | Method and device for determining line loss rate | |
| CN109494757B (en) | Voltage reactive power operation early warning method and system | |
| CN111856309A (en) | Quantitative judgment method for health state of battery | |
| CN114528951A (en) | Distribution network line single line diagram abnormity diagnosis and analysis method, system and device | |
| CN115882456A (en) | Power control method and system based on large-scale power grid tide | |
| CN113422978B (en) | Training method and device of dormancy early warning model and dormancy early warning method and device | |
| CN110533247A (en) | A kind of monthly electricity demand forecasting method compensated using temperature record abnormal point | |
| CN110417834A (en) | A kind of multi-Substation band time scale measurement data section transmission method and system | |
| CN115561699B (en) | Operation error estimation method and device | |
| CN116484554A (en) | Topology identification method, device, equipment and medium for power distribution network | |
| CN116777264A (en) | Novel power distribution network toughness index determination method and evaluation system considering energy storage | |
| CN115545434A (en) | Building energy and carbon emission auditing method and system | |
| CN111796143B (en) | Energy-saving metering method for energy-saving equipment of power distribution and utilization system | |
| CN107565555A (en) | The appraisal procedure and assessment system of long transmission line multi-branched power supply area quality of voltage | |
| CN109327026B (en) | Low-voltage distribution network interval state estimation method | |
| CN112488426A (en) | Bottom-to-top differential power demand prediction method and system | |
| CN111339664A (en) | Layer-by-layer load modeling method and system based on edge calculation | |
| CN111709612A (en) | Power distribution network state estimation method considering collected historical data | |
| CN107634531B (en) | Automatic power generation control method for high-capacity battery energy storage access | |
| CN112417654B (en) | Comprehensive analysis method and system for micro synchronous phasor measurement | |
| Yang et al. | An ICSI-based PMU Data Recovering Method | |
| CN117499817B (en) | Distributed ammeter acquisition system and acquisition method | |
| CN116523547B (en) | Digital marketing service management platform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |