KR20240084739A - Protection system of power distribution system and dentifying method of fault using the same - Google Patents

Abstract

A protection system for a distribution system according to an embodiment of the present invention includes at least one relay that controls the operation of a circuit breaker (CB) in the distribution system and performs a protection function for the distribution system based on a fault determination model; And an energy management system (EMS) that receives failure waveform data when a high-resistance accident occurs from a relay and builds a failure determination model that determines failure due to a high-resistance accident based on the failure waveform data.

Description

Distribution system protection system and accident detection method {PROTECTION SYSTEM OF POWER DISTRIBUTION SYSTEM AND DENTIFYING METHOD OF FAULT USING THE SAME}

The present invention relates to a protection system for a distribution system and a method for determining an accident accordingly.

High Resistance Fault (HRF) in the distribution system is an accident that occurs when the distribution line comes into contact with materials with high resistance such as gravel, sand, or trees for some reason, and short-line ground faults account for more than 70% of distribution system accidents. do. Accordingly, high-resistance accidents require reliable detection and elimination like other accidents. However, in high-resistance accidents, the increase in fault current is not large compared to the load current and shows similar characteristics to arc loads, making accident determination difficult.

In other words, it is difficult to detect high-resistance faults using existing general overcurrent relays, and techniques that utilize the nonlinear and time-varying characteristics of high-resistance faults for detection are being studied. In this way, the application of distributed power to the distribution network is increasing. When a failure occurs in a distribution system with distributed power, the pattern of the fault current, such as the direction of the current, changes depending on the relationship between the location of the fault and the location of the distributed power. In particular, failures in distribution system feeders must be accurately and quickly detected and eliminated to prevent the spread of failures.

Additionally, as distribution systems have become more complex due to the installation of distributed power sources or loop configurations, the pattern of fault currents in the event of an accident has also become more complex. Therefore, the basic protection system of the distribution system based on a simple algorithm has the problem of being difficult to determine in the case of accidents with small fault currents, such as high-resistance accidents.

In this regard, as IT technology has recently developed, neural networks, support vector machine genetic algorithms, expert systems, fuzzy theory, etc. are being applied to wiring system accident protection techniques.

However, because these techniques are methods of applying artificial intelligence algorithms through offline data, there are limitations in that the waveforms of the actual system are not reflected or that offline learning must be performed again to apply the actual waveforms.

Republic of Korea Patent Publication No. 10-2022-0059058 (Title of invention: Protection device and artificial intelligence device for closed-loop distribution system)

In order to solve the above-mentioned problems, the present invention improves the machine learning model by using the fault waveform stored in the digital relay when an accident occurs, and utilizes the energy management system (EMS) of the distribution system to determine the fault waveform. The purpose is to provide a protection system for the distribution system that builds a database and a method to identify accidents accordingly.

However, the technical challenge that this embodiment aims to achieve is not limited to the technical challenges described above, and other technical challenges may exist.

As a technical means for achieving the above-described technical problem, the protection system for the distribution system according to an embodiment of the present invention regulates the operation of the circuit breaker (CB) of the distribution system and provides protection for the distribution system based on a fault determination model. At least one relay that performs; And an energy management system (EMS) that receives failure waveform data when a high-resistance accident occurs from a relay and builds a failure determination model that determines failure due to a high-resistance accident based on the failure waveform data.

In addition, the fault determination method performed by the protection system of the distribution system according to another embodiment of the present invention is (a) at least one relay controls the operation of the circuit breaker (CB) of the distribution system, and based on the fault determination model performing a protection function for the distribution system; And (b) the energy management system (EMS) receives failure waveform data when a high-resistance accident occurs from the relay, and includes a step of constructing a failure determination model that determines failure due to a high-resistance accident based on the failure waveform data. do.

According to the problem-solving means of the present invention described above, high-resistance faults that are difficult to determine with the protection algorithm of existing relays can be determined based on a fault determination model built through machine learning.

In addition, by using the current waveform generated in the actual distribution system, the accuracy of the fault determination model built through machine learning can be increased, and the distribution system protection system can be updated automatically.

Figure 1 is a diagram showing the configuration of a protection system for a distribution system according to an embodiment of the present invention.
Figure 2 is a configuration diagram for explaining detailed modules of a protection system for a distribution system according to an embodiment of the present invention.
Figure 3 is a diagram for explaining the operation process of the protection system of the distribution system according to an embodiment of the present invention.
Figure 4 is a flowchart illustrating a method for determining an accident through a protection system in a distribution system according to another embodiment of the present invention.

Below, with reference to the attached drawings, embodiments of the present invention will be described in detail so that those skilled in the art can easily implement the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. In order to clearly explain the present invention in the drawings, parts unrelated to the description are omitted, and similar parts are given similar reference numerals throughout the specification.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case where it is "directly connected," but also the case where it is "electrically connected" with another element in between. . In addition, when a part is said to "include" a certain component, this means that it does not exclude other components, but may further include other components, unless specifically stated to the contrary, and one or more other features. It should be understood that it does not exclude in advance the presence or addition of numbers, steps, operations, components, parts, or combinations thereof.

The following examples are detailed descriptions to aid understanding of the present invention and do not limit the scope of the present invention. Accordingly, inventions of the same scope and performing the same function as the present invention will also fall within the scope of rights of the present invention.

Hereinafter, an embodiment of the present invention will be described in detail with reference to the attached drawings.

Figure 1 is a diagram showing the configuration of a protection system for a distribution system according to an embodiment of the present invention, and Figure 2 is a configuration diagram for explaining detailed modules of a protection system for a distribution system according to an embodiment of the present invention.

Referring to FIG. 1, the distribution system protection system 10 of the present invention includes at least one relay 210 and an EMS 220 for managing the distribution system.

Hereinafter, the configuration of the EMS 220 will be described in detail with reference to FIG. 2.

For example, the EMS 220 receives failure waveform data when a high-resistance accident occurs from the relay 210, and builds a failure determination model 222 that determines failure due to a high-resistance accident based on the failure waveform data. You can.

As an example, the failure determination model 222 is built using time series data of voltage or current for the failure waveform as learning data, and can be learned to classify high-resistance accidents.

Specifically, the EMS 220 includes a communication module 110, memory 120, processor 130, and database 140.

As an example, the communication module 110 may provide a communication interface capable of transmitting and receiving time series data of voltage and current measured from the relay 210 to the energy management system 220 in conjunction with a communication network. Here, the communication module 110 may be a device that includes hardware and software necessary to transmit and receive signals such as control signals or data signals through wired or wireless connections with other network devices.

The memory 120 records a program that determines whether a high-resistance accident has occurred. Additionally, it performs a function of temporarily or permanently storing data processed by the processor 130. Here, the memory 120 may include volatile storage media or non-volatile storage media, but the scope of the present invention is not limited thereto.

A program for determining whether a high-resistance accident has occurred is stored in the memory 120. This memory 120 stores various types of data generated during the execution of an operating system for driving the energy management system 220 or a program that determines whether a high-resistance accident has occurred.

The processor 130 executes the program stored in the memory 120 and performs the following processing according to the execution of the program that determines whether a high resistance accident has occurred.

The program receives failure waveform data determined to have occurred in a high-resistance accident based on the failure determination model 222 from the relay 210, and adds the received failure waveform data to the database 140 to create the failure determination model 222. It can be renewed.

Here, the processor 130 may include all types of devices capable of processing data. For example, it may refer to a data processing device built into hardware that has a physically structured circuit to perform a function expressed by code or instructions included in a program. Examples of data processing devices built into hardware include a microprocessor, central processing unit (CPU), processor core, multiprocessor, and application-specific (ASIC). It may encompass processing devices such as integrated circuits and FPGAs (field programmable gate arrays), but the scope of the present invention is not limited thereto.

The database 140 may be a medium that organically combines and stores data commonly required to perform an accident determination method through the energy management system 220. For example, the database 140 may include a separate fault waveform DB 221 in which voltage or current waveform data resulting from a high-resistance fault is stored. The database 140 may be included as a separate component from the memory 120 or may be built in a partial area of the memory 120.

Hereinafter, the configuration of the relay 210 will be described in detail with reference to FIG. 2. Among the configurations of the energy management system 220 shown in FIG. 1 described above, descriptions of configurations that perform the same function as those of the relay 210 will be omitted.

By way of example, each relay 210 may include a communication module, a failure determination algorithm 212, and a waveform DB 211. At this time, the communication module may provide a communication interface that can transmit and receive the failure determination model 222 constructed from the energy management system 220 to the relay 210 in conjunction with the communication network.

As an example, the failure determination algorithm 212 may include an existing general protection algorithm such as a protection relay or an overcurrent relay. In addition, the failure determination algorithm 212 can perform a protection function for the distribution system by transmitting the failure determination model 222, which is learned in real time by the energy management system 220.

For example, the relay 210 may monitor a failure in the electrical system of the distribution system and adjust the operation of the circuit breaker (CB) of the distribution system when a failure is detected through the transmitted failure determination model 222.

Additionally, the relay 210 may infer whether a high-resistance accident has occurred based on the transmitted failure determination model 222 and transmit the detected failure waveform data to the energy management system 220 when it is determined that an accident has occurred.

Additionally, the waveform DB 211 may store voltage or current waveform data resulting from a high-resistance accident.

For example, the EMS 220 performs power system monitoring and control functions, which are general functions, and may include a fault waveform DB 221 and a fault determination model 222 built based on the fault waveform data. That is, the EMS 220 uses the failure waveform data received from the relay 210 as learning data for the failure determination model 222, and when the failure waveform data is newly received, the failure determination model 222 is created using the data. It can be renewed. Such EMS 220 can transmit the built or updated failure determination model 222 to each relay 210.

In an additional embodiment, the EMS 220 integrates and manages the fault waveform data collected from each relay 210 and builds a deep learning learning model to determine high resistance faults for each relay 210, The constructed failure determination model 222 can also be transmitted.

Figure 3 is a diagram for explaining the operation process of the protection system of the distribution system according to an embodiment of the present invention.

Referring to FIG. 3, if an accident occurs in a distribution system in which a protection system is installed (S310), the relay 210 may operate (S320). At this time, the relay 210 can transmit the fault waveform to the EMS 220 when an accident occurs. Next, the EMS 220 may receive the failure waveform and store it in the failure waveform DB 221 (S330). That is, the failure waveform DB 221 of the EMS 220 may be updated. Next, the EMS 220 may learn the failure determination model 222 based on the failure waveform data (S340). That is, the present invention can update the failure waveform model 222 by reflecting actual accident data as learning data. Afterwards, the algorithm of the relay 210 can be updated in real time by transmitting the updated fault waveform model 222 (S350). Accordingly, the relay 210 can apply the fault determination algorithm 212, which reflects the characteristics of the distribution system and the actual accident waveform, to the system protection system.

Hereinafter, descriptions will be omitted for components that perform the same function among the components shown in FIGS. 1 to 3 described above.

Figure 4 is a flowchart illustrating a method for determining an accident through a protection system in a distribution system according to another embodiment of the present invention.

Referring to FIG. 4, the fault determination method performed by the protection system of the distribution system of the present invention involves at least one relay 210 controlling the operation of the circuit breaker (CB) of the distribution system and based on the fault determination model 222. The step of performing a protection function for the distribution system (S410) and the energy management system (EMS, 220) receive fault waveform data when a high-resistance accident occurs from the relay 210, and detect the high-resistance accident based on the fault waveform data. It includes a step (S420) of constructing a failure determination model 222 that performs failure determination by .

Step S410 includes the step of the relay 210 inferring whether a high-resistance accident has occurred based on the failure determination model 222 and transmitting the detected fault waveform data to the energy management system 220 when it is determined that the accident has occurred. can do.

Step S420 may include the energy management system 220 updating the failure determination model 222 by adding the failure waveform data determined to have occurred to the database. Here, the failure determination model 222 is constructed using waveform data of voltage or current when a high-resistance accident occurs as learning data, and may be learned to classify whether or not a high-resistance accident occurs.

If the input voltage or current waveform data is determined to be a high-resistance fault based on the fault determination model 222 in step S410, the relay 210 may operate the circuit breaker of the distribution system.

The method according to the embodiment of the present invention described above can also be implemented in the form of a recording medium containing instructions executable by a computer, such as a program module executed by a computer. Such recording media includes computer-readable media, which can be any available media that can be accessed by a computer and includes both volatile and non-volatile media, removable and non-removable media. Computer-readable media also includes computer storage media, both volatile and non-volatile implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules, or other data. , includes both removable and non-removable media.

The description of the present invention described above is for illustrative purposes, and those skilled in the art will understand that the present invention can be easily modified into other specific forms without changing the technical idea or essential features of the present invention. will be. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive. For example, each component described as single may be implemented in a distributed manner, and similarly, components described as distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the claims described below rather than the detailed description above, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention. do.

10: Protection system
110: communication module 120: memory
130: processor 140: database
210: Relay 220: Energy management system, EMS

Claims (8)

In the protection system of the distribution system,
At least one relay that controls the operation of a circuit breaker (CB) in the distribution system and performs a protection function for the distribution system based on a fault determination model; and
Distribution, including an energy management system (EMS) that receives failure waveform data when a high-resistance accident occurs from the relay and builds the failure determination model to determine failure due to a high-resistance accident based on the failure waveform data. System protection system.
According to claim 1,
The relay infers whether a high-resistance accident has occurred based on the failure determination model, and transmits the detected fault waveform data to the energy management system when it is determined that an accident has occurred.
According to claim 2,
The energy management system includes a memory storing a program for determining whether a high-resistance accident has occurred and a processor executing the program,
The program updates the failure determination model by adding the failure waveform data determined to have occurred in the accident to the database,
The fault determination model is constructed using waveform data of voltage or current when a high-resistance accident occurs as learning data, and is learned to classify whether or not a high-resistance accident occurs.
According to claim 1,
A protection system for a distribution system, wherein the relay operates a circuit breaker in the distribution system when the input voltage or current waveform data is determined to be a high-resistance fault based on the fault determination model.
In the accident determination method performed by the protection system of the distribution system,
(a) at least one relay controlling the operation of a circuit breaker (CB) in the distribution system and performing a protection function for the distribution system based on a fault determination model; and
(b) the energy management system (EMS) receives failure waveform data when a high-resistance accident occurs from the relay, and constructs the failure determination model to determine failure due to a high-resistance accident based on the failure waveform data. Inclusive, accident determination method.
According to claim 5,
The step (a) is
The relay infers whether a high-resistance accident has occurred based on the failure determination model, and transmitting the detected failure waveform data to the energy management system when it is determined that an accident has occurred.
According to claim 6,
The step (b) is
The energy management system includes the step of updating the failure determination model by adding the failure waveform data determined to have occurred in the accident to a database,
The fault determination model is constructed using waveform data of voltage or current when a high-resistance accident occurs as learning data, and is learned to classify whether or not a high-resistance accident occurs.
According to claim 5,
In step (a) above,
If the voltage or current waveform data input based on the fault determination model is determined to be a high-resistance fault, the relay operates a circuit breaker in the distribution system.

Images