CN114925621A - Intelligent fixed value checking method - Google Patents
Intelligent fixed value checking method Download PDFInfo
- Publication number
- CN114925621A CN114925621A CN202210715074.8A CN202210715074A CN114925621A CN 114925621 A CN114925621 A CN 114925621A CN 202210715074 A CN202210715074 A CN 202210715074A CN 114925621 A CN114925621 A CN 114925621A
- Authority
- CN
- China
- Prior art keywords
- fixed value
- distribution network
- training
- checking
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/04—Power grid distribution networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
-
- 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)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention provides an intelligent fixed value checking method, which comprises the following steps: s101, acquiring single line diagram data of the power distribution network, generating an equipment topological relation diagram according to the single line diagram data of the power distribution network, and analyzing the position of distribution network equipment according to the equipment topological relation diagram; s102, judging whether the fixed value check is carried out for the first time, if the fixed value check is carried out for the first time, executing a step S103, and if not, executing a step S104; s103, acquiring power distribution network operation data, extracting power distribution network operation mode information, inputting the power distribution network operation mode information and the positions of the power distribution network equipment into a class I machine learning model, acquiring corresponding checking principles and fixed value data, and automatically performing fixed value checking on the protection equipment according to the checking principles and the fixed value data; and S104, automatically screening upper and lower level protection according to the position of the distribution network equipment, acquiring corresponding historical fixed value data according to the screened upper and lower level protection, and automatically performing fixed value checking according to the historical fixed value data. The method and the device can improve the efficiency of fixed value checking and find unreasonable fixed values in time to eliminate potential safety hazards.
Description
Technical Field
The invention relates to the technical field of power distribution network operation management, in particular to an intelligent fixed value checking method.
Background
The distribution network is a power network which receives electric energy from a transmission network or a regional power plant, distributes the electric energy on site through distribution facilities or distributes the electric energy to various users step by step according to voltage, and according to different functions, the contained distribution equipment is also different and generally comprises distribution equipment such as overhead lines, towers, cables, distribution transformers, switch equipment, reactive compensation capacitors and the like and auxiliary facilities thereof. The fixed value checking refers to verifying whether protection can reliably act or not by using the fault amount when the system in an off-line state operates in a minimum mode, and whether the protection has enough sensitivity or not. When the situation occurs, the fixed value of the power grid needs to be set again, the conventional relay protection fixed value online checking system is often developed for relay protection personnel, more manpower needs to be invested during fixed value calibration, the consumed time is long, and the requirement of operation of a power system is difficult to meet.
Disclosure of Invention
Accordingly, the present invention is directed to an intelligent method for checking a constant value, which overcomes or at least partially solves the above-mentioned problems of the prior art.
In order to achieve the above object, the present invention provides an intelligent constant value checking method, which comprises the following steps:
s101, acquiring single line diagram data of the power distribution network, generating an equipment topological relation diagram according to the single line diagram data of the power distribution network, and analyzing the position of distribution network equipment according to the equipment topological relation diagram;
s102, judging whether the constant value check is carried out for the first time, if so, executing a step S103, otherwise, executing a step S104;
s103, acquiring power distribution network operation data, extracting power distribution network operation mode information, inputting the power distribution network operation mode information and the positions of the power distribution network equipment into a class-I machine learning model, acquiring corresponding checking principles and fixed value data, and automatically performing fixed value checking on the protection equipment according to the checking principles and the fixed value data;
s104, automatically screening upper and lower level protection according to the position of the distribution network equipment, acquiring corresponding historical constant value data according to the screened upper and lower level protection, and automatically performing constant value checking according to the historical constant value data.
Further, step S103 includes the following steps:
s201, establishing a machine learning model comprising a first algorithm model and a second algorithm model based on a machine learning algorithm, wherein the first algorithm model aims at outputting corresponding checking principles and fixed value data according to input power distribution network operation mode information and distribution network equipment positions, and the second algorithm model aims at outputting possible power distribution network operation mode information and distribution network equipment positions according to input checking principles and fixed value data;
s202, pre-training a first algorithm model and a second algorithm model respectively through a complete fixed value checking training data set, wherein the complete fixed value checking training data set comprises power distribution network operation mode information, distribution network equipment position information, corresponding checking principles and fixed value data;
s203, performing iterative optimization training on the machine learning models of the same type through a condition training data set and a result training data set, wherein the condition training data set comprises power distribution network operation mode information and power distribution network equipment position information, and the result training data set comprises a checking principle and fixed value data.
Further, the iterative optimization training of the class of machine learning models specifically includes: selecting training data corresponding to the condition training data set and the result training data set when training is started, inputting the training data into the first algorithm model and the second algorithm model respectively to obtain two groups of corresponding output data, updating the complete fixed value checking training data set based on the output data, training the first algorithm model and the second algorithm model by using the updated training data in subsequent iterative training, wherein the training data used in each training is the training data updated after the last iterative training.
Further, in step S103, after the protection device is calibrated according to the calibration principle and the fixed value data, the fixed value data of this calibration is stored as historical fixed value data.
Further, when the power distribution network equipment has a fault, fault information is acquired and input into the class II machine learning model, fixed value abnormal problem information is acquired, upper and lower fixed values are calculated again according to the fixed value abnormal problem information, the upper and lower protection cooperation conditions of the fault equipment are automatically analyzed according to the recalculated fixed values, abnormal fixed values are searched, alarm information is sent out, and meanwhile historical fixed value data are modified according to the recalculated fixed values.
Further, before inputting the fault information into the class two machine learning models, the method specifically comprises the following steps:
s301, establishing a second type of machine learning model comprising a third algorithm model and a fourth algorithm model based on a machine learning algorithm, wherein the third algorithm model aims at outputting fixed value abnormal problem information according to input fault information, and the second algorithm model aims at outputting possible fault information according to the input fixed value abnormal problem;
s302, pre-training a third algorithm model and a fourth algorithm model respectively through a fault diagnosis training data set, wherein the fault diagnosis training data set comprises fault information and corresponding fixed value abnormal problem information;
and S303, performing iterative optimization training on the class II machine learning model through the fault information training data set and the fixed value abnormal problem training data set.
Further, the iterative optimization training of the two types of machine learning models specifically includes: selecting training data corresponding to the fault diagnosis training data set and the training data set with the abnormal fixed value problem when training is started, inputting the training data into the third algorithm model and the fourth algorithm model respectively to obtain two groups of corresponding output data, updating the fault diagnosis training data set based on the output data, training the third algorithm model and the fourth algorithm model by using the updated training data in subsequent iterative training, wherein the training data used in each training is the training data updated after the last iterative training.
Further, when the fixed value check is carried out, the priority of the distribution network equipment is analyzed according to the equipment topological relation graph and the distribution network operation data, and the fixed value check sequence of the upper and lower level protection corresponding to each distribution network equipment is determined according to the priority of the distribution network equipment.
Further, the distribution network equipment priority is analyzed according to the equipment topological relation graph and the power distribution network operation data, specifically, the vulnerability index, the state unbalance index and the comprehensive importance index of the line where the distribution network equipment is located are determined based on the equipment topological relation graph and the power distribution network operation data, and the distribution network equipment priority is calculated according to the vulnerability index, the state unbalance index and the comprehensive importance index.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides an intelligent fixed value checking method, which analyzes the position of distribution network equipment through distribution network single line diagram data, inputs distribution network operation mode information and the position of the distribution network equipment into a class-I machine learning model during primary checking to obtain corresponding checking principles and fixed value data, automatically checks the fixed value of protection equipment according to the checking principles and the fixed value data, automatically screens upper and lower level protection according to the position of the distribution network equipment if the initial checking is not performed, acquires corresponding historical fixed value data according to the screened upper and lower level protection, and automatically checks the fixed value according to the historical fixed value data, so that the fixed value checking efficiency can be improved, and unreasonable fixed values can be found in time to eliminate potential safety hazards.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is apparent that the drawings in the following description are only preferred embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained based on these drawings without inventive efforts.
Fig. 1 is a schematic overall flow chart of an intelligent setting value checking method according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a class of iterative training process of a machine learning model according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of an iterative training process of a class two machine learning model according to an embodiment of the present invention.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth to illustrate the invention and are not intended to limit the scope of the invention.
Referring to fig. 1, the present embodiment provides an intelligent fixed value checking method, including the following steps:
s101, acquiring single line diagram data of the power distribution network, generating an equipment topological relation diagram according to the single line diagram data of the power distribution network, wherein the equipment topological relation diagram is a simplified diagram concerning the connection relation of the distribution network equipment, and analyzing the position of the distribution network equipment according to the equipment topological relation diagram, wherein the position of the distribution network equipment reflects the connection line relation between the distribution network equipment concerned by a checker and other distribution network equipment including protection equipment.
And S102, judging whether the fixed value check is carried out for the first time, if so, executing the step S103, otherwise, executing the step S104.
S103, acquiring power distribution network operation data, extracting power distribution network operation mode information, inputting the power distribution network operation mode information and the positions of the power distribution network equipment into a class-I machine learning model, acquiring corresponding checking principles and fixed value data, and automatically performing fixed value checking on the protection equipment according to the checking principles and the fixed value data. The operation data of the power distribution network comprises basic parameter data management of equipment such as an in-station distribution network line, a transformer, a bus coupler, a circuit breaker, a motor, a reactor, a capacitor, a grounding transformer, an out-station transformer, a section switch outside the station, a tie switch, a boundary circuit breaker, a distribution transformer, a power distribution network automatic terminal and the like, and parameter data management corresponding to equipment models, wherein the operation mode of the power distribution network comprises a maximum mode and a minimum mode.
S104, automatically screening upper and lower level protection according to the position of the distribution network equipment, acquiring corresponding historical constant value data according to the screened upper and lower level protection, and automatically performing constant value checking according to the historical constant value data. The system can automatically screen the upper and lower-level coordination protection according to the positions of the distribution network equipment, such as an incoming switch, an outgoing switch, a bus coupler switch and the like.
Referring to fig. 2, before inputting the operation mode information of the power distribution network and the position of the distribution network device into the class-one machine learning model, the class-one machine learning model needs to be trained, which specifically includes the following steps:
s201, a machine learning model of the same type including a first algorithm model and a second algorithm model is created based on a machine learning algorithm, the first algorithm model aims to output corresponding checking principles and fixed value data according to input power distribution network operation mode information and distribution network equipment positions, and the second algorithm model aims to output possible power distribution network operation mode information and distribution network equipment positions according to input checking principles and fixed value data.
S202, pre-training the first algorithm model and the second algorithm model respectively through a complete fixed value checking training data set, wherein the complete fixed value checking training data set comprises power distribution network operation mode information, distribution network equipment position information, corresponding checking principles and fixed value data, namely the complete fixed value checking training data set, and each power distribution network operation mode information and each distribution network equipment position information has the corresponding checking principle and the corresponding fixed value data which can be calculated and deduced.
S203, performing iterative optimization training on the machine learning models of the same type through a condition training data set and a result training data set, wherein the condition training data set comprises power distribution network operation mode information and power distribution network equipment position information, and the result training data set comprises a checking principle and fixed value data.
Specifically, the iterative optimization training of the machine learning model of one type comprises the following steps: selecting training data corresponding to a condition training data set and a result training data set when training is started, inputting the training data into a first algorithm model and a second algorithm model respectively, specifically, inputting the data in the condition training data set into the first algorithm model, inputting the data in the result training data set into the second algorithm model, obtaining two groups of corresponding output data from the first algorithm model and the second algorithm model, updating a complete fixed value checking training data set based on the output data, training the first algorithm model and the second algorithm model by using the updated training data in subsequent iterative training, wherein the training data used in each training is the training data updated after the last iterative training, and more high-quality training data can be created through the interactive iteration of the first algorithm model and the second algorithm model, thereby improving the training quality of a class of machine learning models, the method can output more accurate checking principle and fixed value data according to the input power distribution network operation mode information and the distribution network equipment position information.
As a preferable example, in step S103, after the protection device is subjected to the fixed value check according to the check principle and the fixed value data, the fixed value data of this fixed value check is stored as the historical fixed value data. The stored historical fixed value data is used for automatically pushing when the same protection device is subjected to fixed value checking next time, the fixed value does not need to be determined again, checking efficiency is improved, comparison of new and old fixed values is supported, the fixed values are stored in a template standardization mode, intelligent matching of fixed value templates can be achieved, and template editing is supported.
As a preferred example, when a power distribution network device fails, fault information is acquired and input into a class ii machine learning model, fixed value abnormal problem information is acquired, upper and lower fixed values are recalculated according to the fixed value abnormal problem information, the upper and lower protection coordination conditions of the failed device are automatically analyzed according to the recalculated fixed value, the abnormal fixed value is searched and alarm information is sent, and meanwhile, historical fixed value data is modified according to the recalculated fixed value. The fault information comprises information such as switch positions, open circuit positions and fault types; the fixed value abnormal problem information comprises problem information such as improper fixed value matching, grade crossing matching, out-of-limit matching and the like.
Referring to fig. 3, before inputting the fault information into the class ii machine learning model, the class ii machine learning model needs to be trained, which specifically includes the following steps:
s301, creating a second class of machine learning models comprising a third algorithm model and a fourth algorithm model based on a machine learning algorithm, wherein the third algorithm model aims to output fixed value abnormal problem information according to input fault information, and the second algorithm model aims to output possible fault information according to the input fixed value abnormal problem.
S302, pre-training the third algorithm model and the fourth algorithm model respectively through a fault diagnosis training data set, wherein the fault diagnosis training data set comprises fault information and corresponding fixed value abnormal problem information.
And S303, performing iterative optimization training on the class II machine learning model through the fault information training data set and the fixed value abnormal problem training data set.
Specifically, the iterative optimization training of the two-class machine learning model comprises the following steps: selecting training data corresponding to the fault diagnosis training data set and the fixed value abnormal problem training data set when training is started, inputting the training data into a third algorithm model and a fourth algorithm model respectively to obtain two groups of corresponding output data, specifically, inputting the data in the fault diagnosis training data set into the third algorithm model, inputting the data in the fixed value abnormal problem training data set into the fourth algorithm model, updating the fault diagnosis training data set based on the output data, training the third algorithm model and the fourth algorithm model by using the updated training data in subsequent iterative training, wherein the training data used in each training is the training data updated after the previous iterative training.
As a preferred example, when performing the constant value check, analyzing the priority of the distribution network device according to the device topology relationship diagram and the distribution network operation data, and determining the constant value check order of the upper and lower level protection corresponding to each distribution network device according to the priority of the distribution network device. In a large-scale power distribution network, the number of protection devices to be checked is large, it is difficult to perform fixed value checking on all protection devices in a short time, and different protection devices have different influence degrees on the power distribution network.
Analyzing the priority of the distribution network equipment according to the equipment topological relation graph and the power distribution network operation data, specifically determining a vulnerability index, a state unbalance index and a comprehensive importance index of a line where the distribution network equipment is located based on the equipment topological relation graph and the power distribution network operation data, and calculating the priority of the distribution network equipment according to the vulnerability index, the state unbalance index and the comprehensive importance index. The vulnerability index shows whether the line where the distribution network equipment is located is easy to damage; the state unbalance index is used for measuring whether the distribution network equipment is in a stage of developing to an unbalance state; the comprehensive importance index is used for reflecting the influence degree of distribution network equipment on the integral stable operation of the power distribution network, and different index weights are different when the priority of the distribution network equipment is analyzed.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and should not be taken as limiting the scope of the present invention, which is intended to cover any modifications, equivalents, improvements, etc. within the spirit and scope of the present invention.
Claims (9)
1. An intelligent fixed value checking method is characterized by comprising the following steps:
s101, acquiring single line diagram data of the power distribution network, generating an equipment topological relation diagram according to the single line diagram data of the power distribution network, and analyzing the position of distribution network equipment according to the equipment topological relation diagram;
s102, judging whether the fixed value check is carried out for the first time, if the fixed value check is carried out for the first time, executing a step S103, and if not, executing a step S104;
s103, acquiring power distribution network operation data, extracting power distribution network operation mode information, inputting the power distribution network operation mode information and the positions of the power distribution network equipment into a class I machine learning model, acquiring corresponding checking principles and fixed value data, and automatically performing fixed value checking on the protection equipment according to the checking principles and the fixed value data;
s104, automatically screening upper and lower level protection according to the position of the distribution network equipment, acquiring corresponding historical constant value data according to the screened upper and lower level protection, and automatically performing constant value checking according to the historical constant value data.
2. The intelligent fixed value checking method according to claim 1, wherein step S103 further comprises the following steps:
s201, establishing a machine learning model comprising a first algorithm model and a second algorithm model based on a machine learning algorithm, wherein the first algorithm model aims at outputting corresponding checking principles and fixed value data according to input power distribution network operation mode information and distribution network equipment positions, and the second algorithm model aims at outputting possible power distribution network operation mode information and distribution network equipment positions according to input checking principles and fixed value data;
s202, pre-training a first algorithm model and a second algorithm model respectively through a complete fixed value checking training data set, wherein the complete fixed value checking training data set comprises power distribution network operation mode information, distribution network equipment position information, corresponding checking principles and fixed value data;
s203, performing iterative optimization training on the machine learning models of the same type through a condition training data set and a result training data set, wherein the condition training data set comprises power distribution network operation mode information and distribution network equipment position information, and the result training data set comprises a checking principle and fixed value data.
3. The intelligent fixed value checking method according to claim 2, wherein the iterative optimization training of a class of machine learning models specifically comprises: selecting training data corresponding to the condition training data set and the result training data set when training is started, inputting the training data into the first algorithm model and the second algorithm model respectively to obtain two groups of corresponding output data, updating the complete fixed value checking training data set based on the output data, training the first algorithm model and the second algorithm model by using the updated training data in subsequent iterative training, wherein the training data used in each training is the training data updated after the last iterative training.
4. The intelligent fixed-value checking method according to claim 1, wherein in step S103, after the fixed-value checking of the protection device is performed according to the checking principle and the fixed-value data, the fixed-value data of the current fixed-value checking is stored as historical fixed-value data.
5. The intelligent fixed value checking method according to claim 1, wherein when the distribution network equipment has a fault, fault information is acquired and input into a class II machine learning model to acquire fixed value abnormal problem information, upper and lower fixed values are recalculated according to the fixed value abnormal problem information, the upper and lower protection coordination conditions of the fault equipment are automatically analyzed according to the recalculated fixed value, an abnormal fixed value is searched and alarm information is sent, and meanwhile, historical fixed value data are modified according to the recalculated fixed value.
6. The intelligent fixed value checking method according to claim 5, wherein before inputting the fault information into the class II machine learning model, the method specifically comprises the following steps:
s301, establishing a second type of machine learning model comprising a third algorithm model and a fourth algorithm model based on a machine learning algorithm, wherein the third algorithm model aims at outputting fixed value abnormal problem information according to input fault information, and the second algorithm model aims at outputting possible fault information according to the input fixed value abnormal problem;
s302, pre-training a third algorithm model and a fourth algorithm model respectively through a fault diagnosis training data set, wherein the fault diagnosis training data set comprises fault information and corresponding fixed value abnormal problem information;
and S303, performing iterative optimization training on the class II machine learning model through the fault information training data set and the fixed value abnormal problem training data set.
7. The intelligent fixed value checking method according to claim 6, wherein the iterative optimization training of the class II machine learning model specifically comprises: selecting training data corresponding to the fault diagnosis training data set and the training data set with the abnormal fixed value problem when training is started, inputting the training data into the third algorithm model and the fourth algorithm model respectively to obtain two groups of corresponding output data, updating the fault diagnosis training data set based on the output data, training the third algorithm model and the fourth algorithm model by using the updated training data in subsequent iterative training, wherein the training data used in each training is the training data updated after the last iterative training.
8. The intelligent fixed value checking method according to claim 1, wherein during fixed value checking, the priorities of the distribution network devices are analyzed according to the device topological relation diagram and the distribution network operation data, and the fixed value checking order of the upper and lower level protection corresponding to each distribution network device is determined according to the priorities of the distribution network devices.
9. The intelligent fixed value checking method according to claim 8, wherein the distribution network equipment priority is analyzed according to the equipment topological relation graph and the distribution network operation data, specifically, the vulnerability index, the state unbalance index and the comprehensive importance index of the line where the distribution network equipment is located are determined based on the equipment topological relation graph and the distribution network operation data, and the distribution network equipment priority is calculated according to the vulnerability index, the state unbalance index and the comprehensive importance index.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210715074.8A CN114925621A (en) | 2022-06-23 | 2022-06-23 | Intelligent fixed value checking method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210715074.8A CN114925621A (en) | 2022-06-23 | 2022-06-23 | Intelligent fixed value checking method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114925621A true CN114925621A (en) | 2022-08-19 |
Family
ID=82814614
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210715074.8A Pending CN114925621A (en) | 2022-06-23 | 2022-06-23 | Intelligent fixed value checking method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114925621A (en) |
-
2022
- 2022-06-23 CN CN202210715074.8A patent/CN114925621A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Papic et al. | Survey of tools for risk assessment of cascading outages | |
| EP2930634A2 (en) | System and method for automated substation design and configuration | |
| CN107330159B (en) | System for intelligent computation of power system | |
| Thurner | Structural Optimizations in Strategic Medium Voltage Power System Planning | |
| CN112766783B (en) | Method and system for evaluating operation quality of power equipment, terminal equipment and medium | |
| CN104836626A (en) | Digital transformer station distributed test system | |
| CN114925621A (en) | Intelligent fixed value checking method | |
| CN110310098B (en) | Automatic construction method and device for distribution network planning problem library | |
| CN113780598B (en) | Intelligent substation virtual terminal checking method | |
| CN115563550A (en) | Distribution network scheduling operation ticket error keyword identification method based on K nearest neighbor | |
| CN109102170A (en) | Device model title modification method, device and storage medium based on OMS | |
| CN114266427A (en) | Topology analysis-based new equipment commissioning starting scheme generation method | |
| CN114201481A (en) | Distribution network fault management system based on distribution transformer reliability | |
| CN113659549A (en) | Relay protection setting value checking method based on digital dynamic simulation technology | |
| CN112949271A (en) | Maintenance safety measure analysis method and system | |
| CN111460612A (en) | Real-time simulation operation method and system for primary equipment and secondary equipment of transformer substation | |
| Han et al. | An online calculation method of theoretical power losses for high-voltage distribution system based on rapid modeling and data quality analysis | |
| CN110807607A (en) | Low-voltage transformer area checking method based on big data platform and related device | |
| CN110457856A (en) | A kind of distribution voltage problem base construction method and device | |
| CN104158290A (en) | Grid safety accident hidden danger analyzer | |
| CN108269198A (en) | Intelligent substation reorganization and expansion configuration file automatic reconfiguration method based on SED files | |
| CN115021199A (en) | Fixed value checking and evaluating system for power distribution network | |
| CN112350380B (en) | Method and system for constructing scheduling side operation model of power grid safety and stability control system | |
| CN112784382B (en) | Simulink simulation-based power distribution network three-level protection setting calculation method | |
| CN112491019B (en) | Intelligent analysis method for relay protection action of power distribution network |
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 |