KR102601686B1 - Server, method and computer program for managing power quality of data center - Google Patents

Abstract

The server that manages the power quality of the data center includes a voltage data acquisition unit that acquires a plurality of voltage data from a plurality of voltage sensors installed near the power system, power supply device, and power distribution device that constitute the power system, and the plurality of voltage data Among them, a harmonic generation determination unit that determines whether harmonics are generated through a first power quality prediction engine based on the first voltage data measured at the input terminal of the power supply device, and a harmonic generation determination unit that determines whether harmonics are generated based on the first voltage data measured at the output terminal of the power supply device. a voltage fluctuation detection unit that detects the degree of voltage fluctuation through a second power quality prediction engine based on the third voltage data measured at the output terminal of the power distribution device and a third power quality prediction engine that detects the degree of voltage drop. It includes a voltage drop detection unit, a simulation unit that simulates power quality based on whether the harmonics occur, the degree of voltage fluctuation, and the degree of voltage drop, and a device that diagnoses whether an abnormality in the power quality occurs based on the results of the simulation. It includes a diagnostic unit, and the simulation unit functions as an environment of the deep reinforcement learning model, and the diagnostic unit functions as an agent of the deep reinforcement learning model.

Description

Server, method, and computer program for managing power quality of a data center {SERVER, METHOD AND COMPUTER PROGRAM FOR MANAGING POWER QUALITY OF DATA CENTER}

The present invention relates to a server, method, and computer program for managing power quality in a data center.

Data Center refers to a facility that integrates and manages the equipment needed to provide IT services, such as servers, networks, and storage, in one building. A data center consists of servers, storage, and network devices to provide computing services, as well as generators, uninterruptible power supplies (UPS), thermostats, backup systems, and security systems necessary to maintain these devices.

These data centers require large-scale power as a core infrastructure for storing and distributing big data, and in relation to technology for supplying power to data centers, the prior art, Korea Patent Publication No. 2021-0076340, is a data center power supply system and A power supply method for a data center power supply system is being disclosed.

In the case of data centers, if there is a power outage in the electrical system or an unexpected breakdown of network equipment, it becomes difficult to provide stable and continuous IT services. Below, the cause of power quality deterioration when power is supplied to a data center will be briefly explained through FIG. 1.

FIG. 1 is a diagram illustrating the causes of deterioration in power quality that occurs in a conventional power system. Referring to FIG. 1, a conventional power system 1 consists of a power system 100 and a UPS system 110 including a power supply device 111 (UPS) and a power distribution device 112 (PDU).

The conventional power system 1 is a power supply device 111 directly connected to the power system 100 and the computer room, as well as harmonic currents generated from other power supply devices connected to other computer rooms, resulting in harmonic waves 120. ) had the problem of increasing its capacity.

In addition, in the conventional power system 1, the power supplied in three phases by the power supply device 111 varies depending on the characteristics of the CPU that is used in one phase (single phase), so the voltage value for each single phase is different. There was a problem in that the voltage fluctuated 130 and occurred.

In addition, the conventional power system 1 has a problem in that a voltage drop 140 occurs due to insulation, leakage current, etc. due to a decrease in equipment efficiency of the distribution board 113 in the UPS system 110, so that aged power equipment Retrofit of the distribution board (113) to be replaced with new equipment was required.

When trying to detect whether an abnormality in power quality has occurred using the conventional power system 1, as the regulations of the power system 100 are applied to the UPS system 110, the regulations for use of electrical equipment for distribution It was determined that the voltage fluctuation of 207V to 233V was within the normal range. As a result, it becomes impossible to diagnose the safety status of voltage values measured in real time in the power system 100 and the UPS system 110, making it impossible to diagnose the occurrence of abnormal signs such as voltage fluctuations, voltage drops, and power outages. There is a problem that it cannot be done.

The present invention seeks to provide a server, method, and computer program for acquiring a plurality of voltage data from a plurality of voltage sensors installed near the power system, power supply device, and power distribution device that constitute the power system.

Among the plurality of voltage data, whether harmonics are generated is determined through a first power quality prediction engine based on the first voltage data measured at the input terminal of the power supply device, and based on the second voltage data measured at the output terminal of the power supply device. A server, method, and computer program for detecting the degree of voltage fluctuation through a second power quality prediction engine and detecting the degree of voltage drop through a third power quality prediction engine based on third voltage data measured at the output terminal of the power distribution device. We would like to provide.

We intend to provide a server, method, and program that diagnoses abnormalities in power quality based on simulation results.

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

As a means to achieve the above-described technical problem, an embodiment of the present invention provides a voltage data for obtaining a plurality of voltage data from a plurality of voltage sensors installed near the power system, power supply device, and power distribution device constituting the power system. A data acquisition unit, a harmonic generation determination unit that determines whether harmonics are generated through a first power quality prediction engine based on the first voltage data measured at the input terminal of the power supply device among the plurality of voltage data, and a harmonic generation determination unit of the power supply device. A voltage change detection unit that detects the degree of voltage change through a second power quality prediction engine based on the second voltage data measured at the output terminal and a third power quality prediction based on the third voltage data measured at the output terminal of the power distribution device. A voltage drop detection unit that detects the degree of voltage drop through an engine, a simulation unit that simulates power quality based on whether or not the harmonics occur, the degree of voltage change, and the degree of voltage drop, and the power based on the results of the simulation. Power quality includes a diagnostic unit that diagnoses whether an abnormality in quality occurs, the simulation unit functions as an environment of the deep reinforcement learning model, and the diagnostic unit functions as an agent of the deep reinforcement learning model. A management server can be provided.

Another embodiment of the present invention includes obtaining a plurality of voltage data from a plurality of voltage sensors installed near the power system, power supply device, and power distribution device constituting the power system by a voltage data acquisition unit, and obtaining a plurality of voltage data by the simulation unit. Determining whether harmonics are generated through a first power quality prediction engine based on first voltage data measured at the input terminal of the power supply device among the plurality of voltage data, at the output terminal of the power supply device by the simulation unit Detecting the degree of voltage variation through a second power quality prediction engine based on the measured second voltage data, third power quality based on the third voltage data measured at the output terminal of the power distribution device by the simulation unit Detecting the degree of voltage drop through a prediction engine, simulating power quality based on whether or not the harmonic occurs, the degree of voltage change, and the degree of voltage drop by the simulation unit, and determining the results of the simulation by the diagnosis unit. Based on this, it includes diagnosing whether an abnormality in the power quality occurs, wherein the simulation unit functions as an environment of the deep reinforcement learning model, and the diagnosis unit functions as an agent of the deep reinforcement learning model. A power quality management method can be provided.

In another embodiment of the present invention, when executed by a computing device, the computer program generates a plurality of voltage data from a plurality of voltage sensors installed near the power system, power supply device, and power distribution device constituting the power system by the voltage data acquisition unit. Obtain voltage data, determine whether harmonics occur through a first power quality prediction engine based on the first voltage data measured at the input terminal of the power supply device among the plurality of voltage data by the simulation unit, and determine whether harmonics are generated by the power supply. Detecting the degree of voltage fluctuation through a second power quality prediction engine based on the second voltage data measured at the output terminal of the device, and a third power quality prediction engine based on the third voltage data measured at the output terminal of the power distribution device Detects the degree of voltage drop, simulates the power quality based on whether the harmonics occur, the degree of voltage fluctuation, and the degree of the voltage drop, and generates an abnormality in the power quality based on the results of the simulation by the diagnostic unit. The simulation unit functions as an environment of the deep reinforcement learning model, and the diagnosis unit runs a computer program stored in a medium containing a sequence of instructions to function as an agent of the deep reinforcement learning model. can be provided.

The above-described means for solving the problem are merely illustrative and should not be construed as limiting the present invention. In addition to the exemplary embodiments described above, there may be additional embodiments described in the drawings and detailed description of the invention.

According to one of the means for solving the problems of the present invention described above, voltage data related to power quality within the power system is collected in real time, and the voltage data collected in real time is used to determine whether harmonics occur, voltage change information, and voltage drop information. Based on this, a server, method, and computer program for managing power quality that diagnose power quality in real time can be provided.

Server, method, and computer program for predicting power quality according to load changes of IT network equipment based on whether harmonics occur, degree of voltage change, and degree of voltage drop, and optimizing power quality based on voltage waves and harmonics according to load change can be provided.

In order to manage the power quality of the data center in real time, based on voltage data measurement and data analysis, it detects in real time where an abnormality occurs in the power load (IT network equipment), preventing downtime in the computer room due to electrical disasters. Servers, methods, and computer programs that can minimize downtime can be provided.

By generating management indicators of the UPS system for electrical safety, servers, methods, and computer programs can be provided to provide stable and continuous data center services.

FIG. 1 is a diagram illustrating the causes of deterioration in power quality that occurs in a conventional power system.
Figure 2 is a configuration diagram of a power system according to an embodiment of the present invention.
Figure 3 is a configuration diagram of a power quality management server according to an embodiment of the present invention.
Figure 4 is an exemplary diagram showing historical data and prediction data output through a deep reinforcement learning model according to an embodiment of the present invention.
FIG. 5 is an exemplary diagram illustrating a process for diagnosing whether an abnormality in power quality has occurred according to an embodiment of the present invention.
Figure 6 is a flowchart of a method for managing power quality of a data center in a power quality management server according to an 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 that are not related 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 does not mean excluding other components unless specifically stated to the contrary, but may further include other components, 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.

In this specification, 'part' includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Additionally, one unit may be realized using two or more pieces of hardware, and two or more units may be realized using one piece of hardware.

In this specification, some of the operations or functions described as being performed by a terminal or device may instead be performed on a server connected to the terminal or device. Likewise, some of the operations or functions described as being performed by the server may also be performed on a terminal or device connected to the server.

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

Figure 2 is a configuration diagram of a power system according to an embodiment of the present invention. Referring to FIG. 2 , the power system 2 may include a power system 200, a UPS system 210, and a power quality management server 220. Here, the UPS system 210 may include a power supply device 211 and a power distribution device 212.

The power system 200, the UPS system 210, and the power quality management server 220 are exemplary illustrations of components that can be controlled by the power system 2.

Each component of the power system 2 in FIG. 2 is generally connected through a network. For example, as shown in FIG. 2, the power quality management server 220 may be connected to the power system 200 or the UPS system 210 simultaneously or at time intervals.

Network refers to a connection structure that allows information exchange between nodes such as terminals and servers, including Local Area Network (LAN), Wide Area Network (WAN), and World Wide Area Network (WWW). Wide Web), wired and wireless data communication networks, telephone networks, wired and wireless television communication networks, etc. Examples of wireless data communication networks include 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), Wi-Fi, Bluetooth communication, infrared communication, and ultrasound. This includes, but is not limited to, communication, Visible Light Communication (VLC), LiFi, etc.

The power system 200 may receive power and perform primary transformation 202 on the supplied power. For example, the power system 200 can transform a voltage of 154kV or 22.9Kv to 6.6kV. Thereafter, the power system 200 may perform secondary transformation 203 on the power to be supplied to the UPS system 210 starting from the distribution board. For example, the power system 200 can transform a voltage of 6.6 kV to 380 V.

The power system 200 may include a harmonic reduction device 201.

The harmonic reduction device 201 is a filter consisting of a series circuit of an inductor and a capacitor with a low impedance value for the relevant frequency to prevent a specific frequency from entering the facility or system in order to remove one or multiple harmonic currents and voltages. It can be.

When receiving a harmonic control signal from the power quality management server 220, the harmonic reduction device 201 may reduce harmonics based on the harmonic control value included in the received harmonic control signal.

The UPS system 210 may include a power supply device (211, Uninterrupted Power Supply (UPS)) and a power distribution unit (212, PDU).

The power supply device 211 may refer to a device that supplies power from a battery for a certain period of time during a power outage, and then replenishes power to the battery in a standby state when power is supplied.

The power supply device 211 may receive power from the power system 200. Here, the voltage used in the power supply device 211 may be 380V.

Power distribution device 212 may be responsible for providing local and remote power management for the IT rack.

The power distribution device 212 may receive power from the power supply device 211. Here, the voltage used in the power distribution device 212 may be 220V.

The power quality management server 220 acquires a plurality of voltage data from a plurality of voltage sensors installed near the power system 200, the power supply device 211, and the power distribution device 212 that constitute the power system 2. You can. For example, the power quality management server 220 may obtain a plurality of voltage data from a plurality of sensors installed near the input and output terminals of the power system 200, the power supply device 211, and the power distribution device 212. .

The power quality management server 220 may determine whether harmonics are generated through the first power quality prediction engine based on the first voltage data measured at the input terminal of the power supply device 211 among the plurality of voltage data. At this time, the power quality management server 220 may input the first voltage data into the first power quality prediction engine to derive a first management index value predicting whether harmonics will occur.

The power quality management server 220 may detect the degree of voltage variation through a second power quality prediction engine based on the second voltage data measured at the output terminal of the power supply device 211. At this time, the power quality management server 220 may input the second voltage data into the second power quality prediction engine to derive a second management index value in which the degree of voltage change is predicted.

The power quality management server 220 may detect the degree of voltage drop through a third power quality prediction engine based on the third voltage data measured at the output terminal of the power distribution device 212. At this time, the power quality management server 220 may input the third voltage data into the third power quality prediction engine to derive a third management index value in which the degree of voltage drop is predicted.

The power quality management server 220 may simulate power quality based on whether harmonics occur, the degree of voltage fluctuation, and the degree of voltage drop.

The power quality management server 220 may diagnose whether an abnormality in power quality has occurred based on the results of the simulation.

Here, the power quality management server 220 includes the functions of the environment and agent of the deep reinforcement learning model, and uses the agent to set the first management index value, the second management index value, and the third management index value. State information is given, and the agent can take action to detect whether an abnormality in power quality occurs based on the state information to satisfy a preset reward function.

The power quality management server 220 may control at least one of the voltage or harmonics of the power system 2 based on at least one of the first management index value, the second management index value, and the third management index value.

For example, the power quality management server 220 calculates a harmonic control value for the harmonic reduction device 201 included in the power system 200 based on the first management index value, and includes the calculated harmonic control value. The harmonic control signal can be transmitted to the harmonic reduction device 201.

For another example, the power quality management server 220 calculates a voltage control value for the power supply device 211 based on the second management index value, and supplies power with a voltage control signal including the calculated voltage control value. It can be transmitted to device 211.

This power quality management server 220 is equipped with a power quality stabilization solution to operate the data center at optimal power quality, and monitors power quality in real time to determine whether an abnormality has occurred in the power system 2 based on DX (digital transformation). Diagnosis can be performed with

Figure 3 is a configuration diagram of a power quality management server according to an embodiment of the present invention. Referring to FIG. 3, the power quality management server 220 may include a voltage data acquisition unit 300, a simulation unit 310, a diagnosis unit 320, and a control unit 330.

The voltage data acquisition unit 300 acquires a plurality of voltage data from a plurality of voltage sensors installed near the power system 200, the power supply device 211, and the power distribution device 212 that constitute the power system 2. You can. For example, the voltage data acquisition unit 300 may acquire a plurality of voltage data on a distribution board basis from a plurality of sensors in order to remotely control all distribution boards of the power system 2 within the data center in real time.

The simulation unit 310 may include a harmonic generation determination unit 311, a voltage change detection unit 312, and a voltage drop detection unit 313.

The harmonic generation determination unit 311 may determine whether harmonics are generated through the first power quality prediction engine based on the first voltage data measured at the input terminal of the power supply device 211 among the plurality of voltage data. To this end, the harmonic generation determination unit 311 can predict whether harmonics will occur in real time to diagnose the volatility of harmonics generated from the UPS system 210 and flowing into the power system 200.

The harmonic generation determination unit 311 may input the first voltage data into the first power quality prediction engine and derive a first management index value predicting whether harmonics will occur.

The voltage change detector 312 may detect the degree of voltage change through the second power quality prediction engine based on the second voltage data measured at the output terminal of the power supply device 211. To this end, the voltage change detector 312 performs real-time measurement on all distribution boards within the UPS system 210 in order to manage the power quality of the input terminal (IN)/output terminal (OUT) of the power supply device 211 used at 380V. Based on this, the degree of voltage fluctuation can be predicted based on 380V.

The voltage change detection unit 312 may input the second voltage data into the second power quality prediction engine and derive a second management index value in which the degree of voltage change is predicted.

The voltage drop detection unit 313 may detect the degree of voltage drop through a third power quality prediction engine based on the third voltage data measured at the output terminal of the power distribution device 212. To this end, the voltage change detection unit 312 performs real-time measurement on all distribution boards within the UPS system 210 in order to manage the power quality of the input terminal (IN)/output terminal (OUT) of the power distribution device 212 used at 220V. Based on this, the degree of voltage drop can be predicted based on 220V.

The voltage drop detection unit 313 may input the third voltage data into the third power quality prediction engine and derive a third management index value in which the degree of voltage drop is predicted.

The simulation unit 310 may simulate power quality based on whether harmonics occur, the degree of voltage change, and the degree of voltage drop. This simulation unit 310 can function as an environment for a deep reinforcement learning model.

The diagnostic unit 320 may diagnose whether an abnormality in power quality has occurred based on the results of the simulation. The process of diagnosing whether an abnormality in power quality occurs based on the results of the simulation will be described in detail with reference to FIGS. 4 and 5.

Figure 4 is an exemplary diagram showing historical data and prediction data output through a deep reinforcement learning model according to an embodiment of the present invention. Referring to FIG. 4, the simulation unit 310 functions as the environment 401 of the deep reinforcement learning model 400, and the diagnosis unit 320 functions as the agent 402 of the deep reinforcement learning model 400. there is.

Here, state 403 information including the first management index value, the second management index value, and the third management index value is given to the agent 402, and the agent 402 satisfies the preset reward 404 function. Based on the status information, an action (405, Action) can be taken to detect whether an abnormality in power quality has occurred. At this time, the agent 402 can directly learn the action probability through the deep reinforcement learning model 400 and explore a policy for what action to take. When the agent 402 learns the probability of action, the stability of learning can be increased by using the value function 406 (Value).

The simulation unit 310 collects current power quality measurement data and past power quality, such as transformer power factor, harmonics, IT equipment load factor, and primary/secondary voltages of the input and output terminals of the power supply device 211, measured for power quality management. Diagnostic data can be used to simulate power quality.

The simulation unit 310 can simulate power quality based on whether harmonics occur, the degree of voltage fluctuation, and the degree of voltage drop using the deep reinforcement learning model 410.

Here, the deep reinforcement learning model 410 may include an Actor network and a Critic network. The Actor network determines the action of the agent 402 when given a state, and the Critic network can evaluate the value of the state. Through this process, the simulation unit 310 can output the π(s, a) value derived through the Actor network and the V(s) value derived through the Critic network as the simulation result 413. Here, V(s) refers to the value function, and π(s, a) may refer to the probability of taking a specific action in a certain state.

Through this process, the simulation unit 310 can output past data 420 and predicted data 421 using the current power quality measurement value 411 and the past power quality diagnosis value 412. Here, the prediction data 421 may represent at least one of a first management index value in which harmonic generation is predicted, a second management index value in which the degree of voltage change is predicted, and a third management index value in which the degree of voltage drop is predicted. .

Afterwards, the simulation unit 310 refers to the difference between the real-time current power quality measurement value 411 and the past power quality diagnosis value 412, and generates the first to third management index values that are the results predicted through deep reinforcement learning. A condition evaluation can be performed. To this end, the simulation unit 310 performs a state evaluation on load fluctuations and power quality fluctuation values that change in real time through deep reinforcement learning, and uses the corrected real-time prediction data 421 as a basis for determining whether an abnormality has occurred and It can be set as a management target value for power quality. At this time, the deep reinforcement learning model 400 can evaluate the state of the prediction result by referring to the difference between the setting of the rule set and the past state.

FIG. 5 is an exemplary diagram illustrating a process for diagnosing whether an abnormality in power quality has occurred according to an embodiment of the present invention. Referring to FIG. 5 , the diagnosis unit 320 may diagnose whether an abnormality 510 in power quality has occurred based on the results of the simulation. For example, a reference point for the occurrence of a power quality abnormality may be created based on a judgment basis for the occurrence of a power quality abnormality and a power quality management target value. At this time, it is possible to diagnose whether an abnormality in power quality (510) has occurred using the measurement data (501) and prediction data (500) rather than the rule set.

In the past, power quality was inspected once a year by using a rule set method, which was limited to a formal periodic inspection. However, the present invention determines abnormalities related to harmonics and voltage in real time, thereby interoperating with the harmonic reduction device 201. It is possible to prevent facility damage in advance and predict major items of power quality deterioration of the power supply device 211.

In the past, as the regulations of the power system 100 were applied to the UPS system 110 for diagnosis, it was difficult to diagnose whether an abnormality occurred in real time with respect to the voltage measured in the UPS system 110, and the distribution of the power system 100 was difficult. Although the fluctuation of 207V to 233V was considered a normal range according to the regulations for the use of dedicated electrical equipment, the present invention uses predicted data to diagnose power quality abnormalities in order to establish power quality standards suitable for the UPS system 210. can do.

In other words, the present invention applies the regulations of the power system 100, which is a problem of the prior art, while diagnosing whether an abnormality in power quality has occurred by using the data predicted through the solution of the power quality management server 220, and further New indicators for control can be created. Through this, the present invention diagnoses the power supply device 211 and the distribution board within the UPS system 210 in real time, where problems related to voltage and harmonics are expected to occur, and uses the predicted data to indicate abnormalities in power quality. New indicators can be created for diagnosis.

Returning to FIG. 3, the control unit 330 may control at least one of the voltage or harmonics of the power system 2 based on at least one of the first management index value, the second management index value, and the third management index value. there is. At this time, when building a control model, the control unit 330 applies a time-specific hunting prevention processor to calculate the optimal control predicted operating point value to prevent overcontrol of the harmonic reduction device 201 and the power supply device 211. And, it is possible to finally control the harmonic reduction device 201 or the power control device 211 of the power system 2 based on the calculated optimal control predicted operating point value. Here, the optimal control predicted operating point value may be calculated based on the first to third management index values and the control history.

For example, the control unit 330 calculates a harmonic control value for the harmonic reduction device 201 included in the power system 200 based on the first management index value, and performs harmonic control including the calculated harmonic control value. The signal can be transmitted to the harmonic reduction device 201.

For another example, the control unit 330 may calculate a voltage control value for the power supply device 211 based on the second management index value. For example, the control unit 330 calculates the voltage control value for the power supply 211 to be 2.2V based on 220V for voltage boosting of 1%, and 220V for voltage boosting of 2%. The voltage control value for the power supply device 211 is calculated as 4.4V, and for a voltage boost of 3%, the voltage control value for the power supply device 211 is calculated as 6.6V based on 220V, and 4. For a voltage step-up of %, the voltage control value for the power supply 211 is calculated to be 8.8 V based on 220 V, and for a voltage step-up of 5%, the voltage for the power supply 211 is calculated based on 220 V. The control value can be calculated as 11V.

The control unit 330 may transmit a voltage control signal including the calculated voltage control value to the power supply device 211.

The control unit 330 can perform real-time control within a prediction range to respond to momentary OFF and load rate changes of IT equipment. Here, if a power quality problem occurs and the corresponding state value is outside the predicted control range, control may not be performed even if power quality stabilization through control is necessary. This is to minimize breakdowns and electrical hunting by causing switching elements of power conversion devices to excessively repeat ON/OFF operations due to temporary changes in power quality.

Figure 6 is a flowchart of a method for managing power quality of a data center in a power quality management server according to an embodiment of the present invention. The method of managing the power quality of a data center in the power quality management server 220 shown in FIG. 6 includes steps processed in time series by the power system 2 according to the embodiment shown in FIGS. 2 to 5. do. Therefore, even if the content is omitted below, it also applies to the method of managing the power quality of the data center in the power quality management server 220 according to the embodiment shown in FIGS. 2 to 5.

In step S610, the power quality management server 220 is installed near the power system 200, the power supply device 211, and the power distribution device 212 constituting the power system 2 by the voltage data acquisition unit 300. A plurality of voltage data can be obtained from a plurality of voltage sensors 220 to 223.

In step S620, the power quality management server 220 calculates the harmonic signal through the first power quality prediction engine based on the first voltage data measured at the input terminal of the power supply device 211 among the plurality of voltage data by the simulation unit 310. You can determine whether it has occurred or not.

In step S630, the power quality management server 220 detects the degree of voltage variation through a second power quality prediction engine based on the second voltage data measured at the output terminal of the power supply device 211 by the simulation unit 310. You can.

In step S640, the power quality management server 220 detects the degree of voltage drop through a third power quality prediction engine based on the third voltage data measured at the output terminal of the power distribution device 212 by the simulation unit 310. You can.

In step S650, the power quality management server 220 may simulate power quality based on whether harmonics are generated, the degree of voltage change, and the degree of voltage drop by the simulation unit 310. Here, the simulation unit 310 may function as an environment for a deep reinforcement learning model.

In step S660, the power quality management server 220 may diagnose whether an abnormality in power quality has occurred based on the results of the simulation by the diagnosis unit 320. Here, the diagnosis unit 320 may function as an agent of a deep reinforcement learning model.

In the above description, steps S610 to S660 may be further divided into additional steps or combined into fewer steps, depending on the implementation of the present invention. Additionally, some steps may be omitted or the order between steps may be switched as needed.

The method of managing the power quality of a data center in the power quality management server described with reference to FIGS. 2 to 6 may be in the form of a computer program stored on a medium executed by a computer or a recording medium containing instructions executable by a computer. It can be implemented. Additionally, the method of managing the power quality of a data center in the power quality management server described with reference to FIGS. 2 to 6 may also be implemented in the form of a computer program stored in a medium executed by a computer.

Computer-readable media 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. Additionally, computer-readable media may include computer storage media. Computer storage media includes both volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data.

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 unitary 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.

200: Power system
201: Harmonic reduction device
210: UPS system
211: power supply
212: Power distribution device
220: Power quality management server
300: Voltage data acquisition unit
310: Simulation unit
311: Harmonic generation determination unit
312: Voltage change detection unit
313: Voltage drop detection unit
320: Diagnostic unit
330: control unit

Claims (17)

In a server that manages power quality in a data center,
A voltage data acquisition unit that acquires a plurality of voltage data from a plurality of voltage sensors installed near the power system, power supply device, and power distribution device that constitute the power system;
Among the plurality of voltage data, a harmonic generation determination unit that determines whether harmonics are generated through a first power quality prediction engine based on the first voltage data measured at the input terminal of the power supply device, and a harmonic generation determination unit that determines whether harmonics occur at the output terminal of the power supply device. A voltage change detection unit that detects the degree of voltage change through a second power quality prediction engine based on second voltage data, and a voltage change detector that detects the degree of voltage change through a third power quality prediction engine based on third voltage data measured at the output terminal of the power distribution device. a simulation unit including a voltage drop detection unit that detects the degree of drop, and predicting power quality based on whether harmonics occur, the degree of voltage change, and the degree of voltage drop; and
Diagnosis unit that diagnoses whether an abnormality in the power quality occurs based on the prediction result
Including,
The simulation unit functions as an environment for the deep reinforcement learning model,
The diagnostic unit functions as an agent of the deep reinforcement learning model,
State information including power quality prediction data predicted through the deep reinforcement learning model is given to the agent, and the agent determines the power quality based on the state information to satisfy a preset reward function. A power quality management server that takes action to detect whether an abnormality has occurred.
According to claim 1,
The harmonic generation determination unit inputs the first voltage data into the first power quality prediction engine to derive a first management index value predicting whether the harmonic generation will occur.
According to claim 2,
The voltage change detection unit inputs the second voltage data into the second power quality prediction engine to derive a second management index value in which the degree of voltage change is predicted.
According to claim 3,
The voltage drop detection unit inputs the third voltage data into the third power quality prediction engine to derive a third management index value in which the degree of voltage drop is predicted.
According to claim 4,
The state information includes the first management index value, the second management index value, and the third management index value.
According to claim 5,
Power quality management further comprising a control unit that controls at least one of the voltage or harmonics of the power system based on at least one of the first management index value, the second management index value, and the third management index value. server.
According to claim 6,
The control unit calculates a harmonic control value for the harmonic reduction device included in the power system based on the first management index value,
A power quality management server that transmits a harmonic control signal including the calculated harmonic control value to the harmonic reduction device.
According to claim 6,
The control unit calculates a voltage control value for the power supply device based on the second management index value,
A power quality management server that transmits a voltage control signal including the calculated voltage control value to the power supply device.
In a method of managing power quality of a data center in a power quality management server,
Obtaining a plurality of voltage data from a plurality of voltage sensors installed near the power system, power supply device, and power distribution device constituting the power system by a voltage data acquisition unit;
determining whether harmonics are generated through a first power quality prediction engine based on first voltage data measured at the input terminal of the power supply device among the plurality of voltage data by a simulation unit;
detecting the degree of voltage variation through a second power quality prediction engine based on second voltage data measured at the output terminal of the power supply device by the simulation unit;
detecting the degree of voltage drop through a third power quality prediction engine based on third voltage data measured at the output terminal of the power distribution device by the simulation unit;
Predicting power quality by the simulation unit based on whether or not the harmonics occur, the degree of voltage change, and the degree of voltage drop; and
Diagnosing whether an abnormality in the power quality occurs based on the prediction result by a diagnostic unit
Including,
The simulation unit functions as an environment for the deep reinforcement learning model,
The diagnostic unit functions as an agent of the deep reinforcement learning model,
State information including power quality prediction data predicted through the deep reinforcement learning model is given to the agent, and the agent determines the power quality based on the state information to satisfy a preset reward function. A power quality management method that takes action to detect whether an abnormality has occurred.
According to clause 9,
The power quality management method further includes the step of inputting the first voltage data into the first power quality prediction engine to derive a first management index value predicting whether or not the harmonics will occur.
According to claim 10,
The power quality management method further includes the step of inputting the second voltage data into the second power quality prediction engine to derive a second management index value in which the degree of voltage change is predicted.
According to claim 11,
The power quality management method further includes the step of inputting the third voltage data into the third power quality prediction engine to derive a third management index value in which the degree of voltage drop is predicted.
According to claim 12,
The power quality management method wherein the status information includes the first management index value, the second management index value, and the third management index value.
According to claim 13,
Power quality management further comprising controlling at least one of the voltage or harmonics of the power system based on at least one of the first management index value, the second management index value, and the third management index value. method.
According to claim 14,
The controlling step is,
calculating a harmonic control value for a harmonic reduction device included in the power system based on the first management index value; and
A power quality management method comprising transmitting a harmonic control signal including the calculated harmonic control value to the harmonic reduction device.
According to claim 15,
The controlling step is,
calculating a voltage control value for the power supply device based on the second management index value; and
A power quality management method comprising transmitting a voltage control signal including the calculated voltage control value to the power supply device.
A computer program stored on a medium containing a sequence of instructions for managing power quality of a data center, comprising:
When the computer program is executed by a computing device,
A voltage data acquisition unit acquires a plurality of voltage data from a plurality of voltage sensors installed near the power system, power supply device, and power distribution device constituting the power system,
The simulation unit determines whether harmonics are generated through a first power quality prediction engine based on the first voltage data measured at the input terminal of the power supply device among the plurality of voltage data, and the voltage measured at the output terminal of the power supply device is determined by the simulation unit. The degree of voltage fluctuation is detected through a second power quality prediction engine based on the second voltage data, and the degree of voltage drop is detected through a third power quality prediction engine based on the third voltage data measured at the output terminal of the power distribution device. Detect and predict power quality based on whether harmonics occur, the degree of voltage fluctuation, and the degree of voltage drop,
A diagnostic unit diagnoses whether an abnormality in the power quality occurs based on the prediction result,
The simulation unit functions as an environment for the deep reinforcement learning model,
The diagnostic unit functions as an agent of the deep reinforcement learning model,
State information including power quality prediction data predicted through the deep reinforcement learning model is given to the agent, and the agent determines the power quality based on the state information to satisfy a preset reward function. A computer program stored on a medium that includes a sequence of instructions to take action to detect whether an abnormality has occurred.

Images