System for analyzing demand for power generation amount, and determining and dealing with failure of electric vehicle charging station facility

Abstract

The present invention provides a system for analyzing a demand for a power generation amount, and determining and dealing with a failure of an electric vehicle charging station facility, comprising: a data collection control unit that receives, in real time, data related to a renewable energy power generation facility and an ESS facility, receives a control signal through an operation data collection unit, and controls operations of the renewable energy power generation facility and the ESS facility; a facility failure prediction unit that performs, in real time, failure diagnosis on the renewable energy generation facility and the ESS facility, predicts the occurrence of failures in the renewable energy generation facility and the ESS facility, and transmits failure diagnosis result data and failure occurrence prediction data to the operation data collection unit; and the operation data collection unit that stores therein data obtained from the data collection control unit and the facility failure prediction unit, and provides data requested by a manager to a smart device of the manager.

Description

Power generation demand analysis, fault detection, and response system for electric vehicle charging station facilities

[0001] The present invention relates to a power generation demand analysis, fault detection, and response system, and more specifically, to a power generation demand analysis, fault detection, and response system for electric vehicle charging station facilities.

[0002] The problem with the prior art related to the present invention lies in the lack of a system to effectively detect various failures and respond quickly during the operation of electric vehicle charging station facilities. In particular, charging infrastructure that includes renewable energy-based power facilities and ESS (Energy Storage System) facilities faces the problem that it is difficult to respond urgently because the cause of the problem cannot be detected early when a failure occurs. This not only limits the ability to guarantee safety and reliability to users but also poses a significant risk of degrading the overall efficiency of the system as failures persist.

[0003] First, the power supply systems of existing electric vehicle (EV) charging stations often detect problems only after a failure occurs, making it difficult to immediately reroute power or replace faulty equipment. This limitation leads to disruptions because failures are not detected immediately, despite the fact that uninterrupted power supply is essential for the operation of EV charging stations.

[0004] Second, there is a lack of a system to predict and prepare for failures in renewable energy generation facilities and ESS facilities. Currently, most charging station facilities are equipped with real-time data collection and fault detection capabilities, but they lack data analysis functions for failure prediction. Consequently, failures that may occur over time cannot be predicted and prepared for in advance, resulting in a failure to carry out essential maintenance and preventive measures. This causes a decline in the lifespan and stability of the facilities in the long term.

[0005] Third, conventional charging station systems have limited data collection capabilities regarding the analysis of failure causes. Most facilities merely monitor the operational status of the equipment and do not collect data on the causes that led to the failure. Consequently, it becomes difficult to accurately identify the cause of a failure, increasing the likelihood of the same problem recurring. Particularly in the case of communication equipment, there is insufficient data-based system to analyze the cause or respond when communication failures occur, making it difficult to take appropriate measures to prevent recurrence.

[0006] Fourth, conventional technology lacks a system to provide rapid notifications when a situation arises requiring direct intervention by an administrator. Although some systems are equipped with the capability to transmit data to the administrator's device, urgent notifications are not properly delivered in the event of a failure, making rapid response difficult. If immediate notification is delayed in the event of a failure, it may cause problems with the continuity of electric vehicle charging services and negatively impact user trust.

[0007] Fifth, since renewable energy generation facilities are affected by external factors such as weather and pollution levels, a function is required to inspect their condition and diagnose the causes of reduced power generation. However, existing technologies have limitations in that they cannot specifically analyze the impact of these factors on low power output or provide immediate countermeasures when a problem is identified. This results in a failure to identify the cause when power generation is lower than predicted, leading to decreased operational efficiency.

[0008] Sixth, existing charging station facilities lack a system for rapidly analyzing and diagnosing the cause of network failures. For example, there is no system to differentiate between physical network issues and software problems when a communication equipment failure occurs. Due to these structural issues, identifying the cause of the failure is delayed, and there is a risk that charging services will be interrupted for an extended period as the failure persists.

[0009] Finally, there is a lack of response capabilities in the event of a failure in ESS facilities. It is essential to identify battery-related issues or abnormal connection conditions and to take measures such as restarting the battery connections if necessary, but existing systems have limited capabilities for these functions. In particular, since ESS facilities pose a risk of fire or explosion if a failure occurs, rapid diagnosis and response are crucial, but existing technologies fail to adequately address this.

[0010] In conclusion, conventional electric vehicle charging station facilities have various limitations in terms of fault detection, prediction, and rapid response, which impede the stability and operational efficiency of charging stations. These issues must be resolved to ensure the continuity and reliability of electric vehicle charging services. The present invention aims to solve these problems of conventional technology by providing a system that monitors the status of renewable energy generation facilities and ESS facilities in real time, predicts failures early, and responds quickly. Through this, the present invention enables the stable operation of electric vehicle charging station facilities and aims to provide users with safe and reliable electric vehicle charging services.

[0011] The objective of the present invention is to provide a system for analyzing power generation demand, determining faults, and responding to electric vehicle charging station facilities, which can build an infrastructure for providing electric vehicle charging services that meets local power requirements, electrical design regulations, electrical design technical standards, and local environmental conditions in various countries around the world, build an AI EMS linked to the local power grid, rapidly detect and respond to failures in electric vehicle charging service provision facilities, solar power generation facilities, and ESS facilities based on AI EMS based on demonstration site operation data, and predict the occurrence of failures in electric vehicle charging service provision facilities, solar power generation facilities, and ESS facilities based on fault detection data to prevent or respond to failures before they occur.

[0012] A system for power generation demand analysis, fault determination, and response to an electric vehicle charging station facility according to one aspect of the present invention for achieving the above purpose is a system for monitoring and controlling a grid power network comprising a configuration in which power is produced through a renewable energy generation facility, stored in an ESS facility, and then provided to an electric vehicle charging station, wherein the system comprises: a data collection control unit that receives data related to the renewable energy generation facility and the ESS facility in real time through the grid power network, monitors the flow of power provided through the grid power network, transmits the data received in real time and the monitoring data to an operation data collection unit, and receives control signals through the operation data collection unit to control the operation of the renewable energy generation facility and the ESS facility; and an facility fault prediction unit that performs real-time fault diagnosis regarding the renewable energy generation facility and the ESS facility based on data acquired through the data collection control unit, predicts the occurrence of a fault regarding the renewable energy generation facility and the ESS facility based on data stored in the operation data collection unit, and transmits fault diagnosis result data and fault occurrence prediction data to the operation data collection unit. The configuration may include an operation data collection unit that internally stores data acquired from the data collection control unit and the equipment failure prediction unit, wirelessly links with the manager's smart device to receive control signals related to renewable energy generation facilities and ESS facilities from the manager and transmits them to the data collection control unit, and provides data requested by the manager to the manager's smart device.

[0013] In one embodiment of the present invention, the data collection control unit comprises: a power generation facility monitoring unit that checks real-time weather conditions and the contamination status of renewable energy power generation facilities when power generation within a preset range is not reached within a preset time range, and transmits data related to the failure status of the renewable energy power generation facilities to the operation data collection unit so that it is output to an administrator's smart device through the operation data collection unit if the weather conditions or the contamination status are not the cause of the low power generation problem; and a communication facility monitoring unit that determines whether the socket server is operating normally when the communication status is poor, and if the socket server stops, determines that physical network damage is the primary cause and switches to a standby state for a preset time until normalization, and if there is no abnormality in the socket server, determines that the processing capability of the AI ​​EMS server is the primary cause and transmits inspection request data by the administrator to the operation data collection unit so that it is output to an administrator's smart device through the operation data collection unit to check the session memory and check for external network attacks. The configuration may include an ESS monitoring unit that determines whether the battery is connected to the facility when an abnormality occurs in the BMS installed in the ESS, controls the battery to restart the facility connection state as a response to the ESS abnormality, and if there is a physical abnormality in the ESS facility, disconnects the battery facility connection state and then transmits the inspection request data by the manager to the operation data collection unit so that it is output to the manager's smart device through the operation data collection unit.

[0014] In one embodiment of the present invention, the equipment failure prediction unit may comprise: a data receiving unit that receives data acquired through the data collection control unit; a guide data storage unit that stores data related to the normal state range for each of the multiple data of the renewable energy generation facility and the ESS facility, and modifies the data related to the normal state range by a control signal transmitted from a manager's smart device; a failure determination unit that determines whether each data received through the data receiving unit meets the criteria for the data related to the normal state range stored in the guide data storage unit, and if it does not meet the criteria, determines that a failure has occurred in the facility related to the data and transmits the related data to an operation data collection unit; and a prediction determination unit that compares the data acquired in real time from the operation data collection unit with a power generation prediction model, and if the data acquired in real time exceeds a preset range from the power generation prediction model and a difference occurs, transmits a warning signal indicating that there is a high probability of a failure in the facility and related data to the operation data collection unit so that they are output to the manager's smart device.

[0015] In one embodiment of the present invention, the operation data collection unit may comprise: a system diagram output unit that provides a system diagram processed to allow visual recognition of the current power flow of the grid based on data acquired from the data collection control unit and the equipment failure prediction unit, and provides a map image processed to allow visual recognition of the location where renewable energy generation facilities and ESS facilities are installed to the manager's smart device; an operation status output unit that provides a data table and graph processed to allow visual recognition of the current power generation, transmission, charging, discharging, and utilization status of the grid based on data acquired from the data collection control unit and the equipment failure prediction unit to the manager's smart device; and a management history output unit that provides a data table and graph processed to allow visual recognition of the equipment control history data, equipment failure history data, and equipment response history data of the renewable energy generation facilities and ESS facilities based on data acquired from the data collection control unit and the equipment failure prediction unit to the manager's smart device.

[0016] In one embodiment of the present invention, the operation data collection unit may be configured to include: a fault notification output unit that provides fault-related information and a warning alarm to a manager's smart device when a fault occurs in the power flow, generation, predetermined, charging, discharging, or usage status of the current power grid based on data acquired from the data collection control unit and the equipment fault prediction unit; and a communication failure output unit that determines whether there is a communication failure by determining whether there is a data response during the process of receiving data by continuously communicating with the data collection control unit and the equipment fault prediction unit, and when a communication failure occurs, provides data related to the equipment where the communication failure occurred to the manager's smart device and simultaneously provides an alarm.

[0017] As explained above, according to the power generation demand analysis, fault determination, and response system for electric vehicle charging station facilities of the present invention, by providing a data collection control unit, an equipment fault prediction unit, and an operation data collection unit that perform specific roles, it is possible to build an electric vehicle charging service provision infrastructure that meets local power requirements, electrical design regulations, electrical design technical standards, and local environmental conditions of various countries around the world, and to build an AI EMS linked to the local power grid, and to rapidly detect and respond to faults in electric vehicle charging service provision facilities, solar power generation facilities, and ESS facilities by means of an AI EMS based on demonstration site operation data, and to predict the occurrence of faults in electric vehicle charging service provision facilities, solar power generation facilities, and ESS facilities based on fault detection data, thereby preventing or responding in advance to the occurrence of faults.

[0018] FIG. 1 is a schematic diagram showing the configuration of a power generation demand analysis, fault determination, and response system for an electric vehicle charging station facility according to one embodiment of the present invention.

[0019] FIG. 2 is a block diagram showing a power generation demand analysis, fault determination, and response system for an electric vehicle charging station facility according to one embodiment of the present invention.

[0020] FIG. 3 is an example of a system for local grid connection of an AI EMS applied to a power generation demand analysis, fault judgment, and response system of an electric vehicle charging station facility according to one embodiment of the present invention.

[0021] Figure 4 is a table showing examples of operation data items based on the PV inverter protocol.

[0022] Figure 5 is a table showing examples of operation data items based on PCS and BMS protocols.

[0023] Figure 6 is a table showing examples of operation data items based on PCS and BMS protocols.

[0024] Figure 7 is a flowchart showing an example of a basic operation algorithm for ESS facility operation control.

[0025] Figure 8 is a flowchart showing an example of an algorithm for determining and dealing with abnormal low power generation conditions in existing construction.

[0026] Figure 9 is a flowchart showing an example of an algorithm for determining and dealing with abnormal low power generation conditions in existing construction.

[0027] Figure 10 is a flowchart showing an example of an algorithm for determining and dealing with communication abnormalities in existing facilities.

[0028] Figure 11 is a flowchart showing an example of an algorithm for determining and dealing with communication abnormalities in existing facilities.

[0029] Figure 12 is a flowchart showing an example of an algorithm for determining and responding to abnormalities in existing BMS facilities.

[0030] Figure 13 is a flowchart showing an example of an algorithm for determining and responding to abnormalities in existing BMS facilities.

[0031] Figure 14 is a schematic diagram showing an example of a configuration of an equipment anomaly detection model using AI.

[0032] Figure 15 is a figure showing the screen of the AI ​​prediction and diagnosis service for existing solar ESS equipment data.

[0033] Preferred embodiments of the present invention will be described in detail below with reference to the drawings. Prior to this, terms and words used in this specification and claims should not be interpreted as being limited to their ordinary or dictionary meanings, but should be interpreted in a meaning and concept consistent with the technical spirit of the present invention.

[0034] Throughout this specification, when it is stated that one component is located "on" another component, this includes not only cases where one component is in contact with another component, but also cases where another component exists between the two components. Throughout this specification, when it is stated that a part "includes" a component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components.

[0035] FIG. 1 shows a schematic diagram illustrating the configuration of a power generation demand analysis, fault detection, and response system for an electric vehicle charging station facility according to one embodiment of the present invention, FIG. 2 shows a block diagram illustrating a power generation demand analysis, fault detection, and response system for an electric vehicle charging station facility according to one embodiment of the present invention, and FIG. 3 shows an example of a system for an AI EMS for local grid connection applied to a power generation demand analysis, fault detection, and response system for an electric vehicle charging station facility according to one embodiment of the present invention.

[0036] Referring to these drawings, the power generation demand analysis, fault determination, and response system (100) of an electric vehicle charging station facility according to the present embodiment is equipped with a data collection control unit (110), an equipment failure prediction unit (120), and an operation data collection unit (130) that perform specific roles, thereby enabling the construction of an electric vehicle charging service provision infrastructure that meets local power requirements, electrical design regulations, electrical design technical standards, and local environmental conditions of various countries around the world, and the construction of an AI EMS linked to the local power grid. It can also rapidly detect and respond to failures in electric vehicle charging service provision facilities, solar power generation facilities, and ESS facilities by means of an AI EMS based on demonstration site operation data, and predict the occurrence of failures in electric vehicle charging service provision facilities, solar power generation facilities, and ESS facilities based on failure detection data, thereby enabling prevention or response in advance before failure occurs.

[0037] Hereinafter, with reference to the drawings, each component constituting the power generation demand analysis, fault judgment, and response system (100) of the electric vehicle charging station facility according to the present embodiment will be described in detail.

[0038] The data collection control unit (110) is a core element of the present invention and plays an essential role in maintaining a stable power supply by collecting, controlling, and monitoring data from the renewable energy generation facility and ESS facility of the electric vehicle charging station. This control unit is composed of several detailed components for real-time monitoring of power flow, data collection for fault prediction, and smooth communication with the manager, thereby enhancing the stability and efficiency of the system. The role of each detailed component is described in detail below.

[0039] (1) Power generation facility monitoring unit (111)

[0040] The power generation facility monitoring unit plays the role of analyzing the cause and transmitting the data to the manager's smart device when the electricity produced by renewable energy generation facilities fails to reach the set generation range. For example, if power generation falls short within a specific timeframe, it checks weather conditions or the contamination status of the facility; if external environmental factors or contamination are not the cause, it suspects an internal malfunction and notifies the manager of the relevant data, thereby enabling prompt inspection and action. This allows for the continuous monitoring of the power generation facility's status and efficient management.

[0041] (2) Communication equipment monitoring unit (112)

[0042] The communication facility monitoring unit is a component that monitors the communication status of the charging station and supports taking appropriate measures in the event of a problem. In the event of a communication failure, it first checks whether the socket server is operating normally; if the socket server is not operating normally, it determines the possibility of physical network damage and switches the system to a standby state. On the other hand, if the socket server is operating normally, it checks the processing capability of the AI ​​EMS server and provides data to the administrator so that a review of session memory and external network attacks can be requested, thereby helping to maintain the stability of the communication status.

[0043] (3) ESS monitoring unit (113)

[0044] The ESS monitoring unit checks the battery connection status and takes appropriate action when an abnormality occurs in the Battery Management System (BMS) installed in the ESS. For example, if an abnormality occurs in the ESS, it ensures the safety of the system by restarting the battery facility connection status or disconnecting it in the event of a physical abnormality. In addition, when such a situation occurs, it maintains the reliability of the ESS system by transmitting inspection request data to the manager's smart device so that immediate action can be taken.

[0045] (4) Real-time data collection function

[0046] The data collection and control unit performs the function of collecting data generated from renewable energy generation facilities and ESS facilities in real time. This enables real-time monitoring of the operating status, power generation, and stored power of the power facilities, allowing for verification of smooth power supply and immediate response in the event of problems. By rapidly reacting to changing conditions through real-time data collection, it contributes to enhancing the operational stability of charging stations.

[0047] (5) Control signal reception and control function

[0048] The data collection and control unit can receive control signals from the manager's smart device to coordinate the operation of power generation facilities and ESS facilities. Through this, the manager can remotely control the facilities depending on the situation and perform various measures as needed, such as adjusting power generation and changing charging / discharging settings. This function plays an important role in efficiently managing the operation of charging stations and, in particular, enables a rapid response in the event of a system failure.

[0049] (6) Operational data transfer function

[0050] The data collection control unit transmits collected data to the operational data collection unit, enabling its use for fault prediction and statistical analysis. Through this data transmission function, operational data is managed centrally, contributing to the establishment of integrated fault prediction and response plans. This plays an essential role in maintaining consistency in overall system operations and ensuring the stable operation of facilities in the long term.

[0051] (7) Power flow monitoring function

[0052] The data collection and control unit continuously monitors the power flow of renewable energy generation facilities and ESS facilities to check whether the power flow is proceeding smoothly based on real-time and monitoring data. Through this, it identifies the generation and storage status according to power demand at a specific point in time and can quickly notify the manager in the event of an anomaly, thereby enabling the continuous operation of the charging station.

[0053] In this way, the data collection control unit (110) detects the operating status and potential for failure of the electric vehicle charging station in real time and performs appropriate control when necessary, thereby increasing the safety and efficiency of the system and supporting the stable operation of the charging station equipment through failure prevention and rapid response.

[0054]

[0055] The data collection control unit (110) plays an important role in receiving data related to renewable energy generation facilities and ESS (Energy Storage System) facilities in real time through the grid power system. This process is key to the efficient operation of the power grid and energy management, enabling real-time monitoring of the facility status and optimal control through the collected data. A method for implementing this is described in detail.

[0056] (1) Connection with the power grid

[0057] The data collection control unit (110) collects real-time data through a continuous connection with the power grid. The power grid is a core network that manages the energy flow between power sources and consumers, and transmits power data from renewable energy generation facilities and ESS facilities in real time. The data collection control unit is connected to this network and can receive data generated from the generation facilities and ESS facilities in real time. Through this connection, the control unit collects important information in real time, such as the output of the generation facilities, the charging status of the ESS, and the power flow of the power grid.

[0058] (2) Real-time data collection

[0059] The data collection control unit collects various data provided by the power grid in real time. For example, in the case of solar power generation facilities, various parameters such as power generation, conversion efficiency, voltage, and frequency are collected. In ESS facilities, the charge and discharge status of batteries, as well as surplus power, are monitored in real time. All of this data is collected in real time and transmitted to the processing system of the control unit. Collecting data in real time is essential for accurately understanding the status of the power grid and optimizing the operation of the facilities.

[0060] (3) Data formats and protocols

[0061] During the process of collecting real-time data, the data is transmitted through a standardized format and protocol. Standardized communication protocols are used between the power grid and the data collection control unit to ensure stable and efficient data transmission. For example, real-time data can be transmitted via communication protocols such as MODBUS, OPC-UA, and MQTT. The data is converted into digitized signals for collection, enabling the control unit to process this data in real time. The use of the correct protocol for data collection is a critical factor in enhancing the stability and efficiency of the system.

[0062] (4) Data filtering and cleansing

[0063] Since collected real-time data is transmitted from various sensors and equipment, it undergoes filtering and refinement processes. The data collection control unit filters out unnecessary or error-containing data and selects and processes only critical information. For example, if there is an anomaly in power flow, this data is filtered in real-time to secure accurate status information. This allows for the elimination of inaccurate or duplicate data, enabling the rapid processing of accurate data necessary for actual operation. The data refinement process enhances the reliability and accuracy of the system.

[0064] (5) Data transmission and processing

[0065] The refined data is transmitted to the built-in system of the data collection control unit for processing. This data is analyzed in real time to evaluate the status of power generation facilities and ESS facilities, and is used to generate control signals. Based on the real-time data, the control unit generates necessary control commands, enabling real-time control of, for example, the charging status of the ESS or the output adjustment of the power generation facilities. This maintains an energy flow optimized for the power grid and supports efficient energy management. The collected data is also transmitted to the operational data collection unit, providing real-time status information to the manager and enabling a rapid response in the event of a failure.

[0066] In this way, the data collection control unit (110) receives data related to renewable energy generation facilities and ESS facilities in real time through the grid power system. This process plays an important role in maintaining the stability and efficiency of the power grid through real-time data collection, filtering and refinement, and the generation of appropriate control signals.

[0067] The equipment failure prediction unit (120) is an important component that predicts and diagnoses failures in the renewable energy generation equipment and ESS (Energy Storage System) equipment of an electric vehicle charging station in real time. Based on collected data, this unit detects signs that the equipment is out of normal range and predicts the possibility of a failure, and performs the function of warning the manager. Through the predicted failure information, preventive measures can be taken before a failure occurs, thereby preventing equipment failures in advance and maintaining stable electric vehicle charging services. The equipment failure prediction unit is composed of a data receiving unit, a guide data storage unit, a failure judgment unit, a prediction judgment unit, etc., and each component works closely together to increase the accuracy of failure prediction.

[0068] (1) Data receiving unit (121)

[0069] The data receiving unit (121) plays the role of collecting data in real time from renewable energy generation facilities and ESS facilities. This data includes various operational indicators such as voltage, current, temperature, and power production of each facility, and through this data, the current status of the facilities can be continuously monitored. This unit collects real-time operational data of the facilities and provides basic data necessary for the subsequent stages of fault judgment and prediction. The collected data is analyzed in real time and used for fault prediction, and provides information necessary for the manager.

[0070] (2) Guide data storage unit (122)

[0071] The guide data storage unit (122) is a unit that stores data related to the normal operating range of renewable energy generation facilities and ESS facilities. This data includes the range in which the facilities operate normally (voltage, temperature, power consumption, etc.), and through this, the possibility of failure can be predicted based on data generated during actual operation. This stored data is used to monitor the operating status of the facilities and to determine whether a failure has occurred by comparing collected data with the standard. In addition, the normal range can be modified or updated to meet conditions set by the manager.

[0072] (3) Fault detection unit (123)

[0073] The fault determination unit (123) determines whether a fault has occurred by comparing the collected data with the normal range. This unit evaluates whether a fault has occurred by comparing the data collected in real time with the normal range data stored in the guide data storage unit. If data outside the normal range is detected, it determines that a fault has occurred in the equipment and transmits the relevant fault information to the operation data collection unit (130) so that the manager can take appropriate measures. This allows for the rapid identification and response to the occurrence of a fault.

[0074] (4) Prediction judgment unit (124)

[0075] The prediction judgment unit (124) is an important unit that predicts the likelihood of a failure and predicts whether there is a possibility of a failure by comparing collected data with a power generation prediction model. If the real-time data exceeds the set range of the power generation prediction model, it determines that there is a high probability of a failure and warns the manager. The prediction judgment unit sends a warning signal to allow for preventive measures to be taken before a failure occurs, and contributes to failure prevention by notifying the manager of the likelihood of a failure in real time.

[0076] (5) Fault cause analysis function

[0077] The equipment failure prediction unit analyzes data with a high probability of failure and provides the function to identify its causes. For example, by analyzing various causes such as temperature or voltage anomalies and equipment malfunctions, it identifies the root cause of failures and assists managers in taking appropriate action. This analysis of failure causes provides crucial information for the continuous operation of equipment and supports the prevention of similar failures in the future.

[0078] (6) Pattern recognition and learning functions

[0079] The equipment failure prediction unit is also equipped with the capability to learn failure patterns by analyzing past failure data. This function analyzes the causes and timing of past failures and helps predict new ones based on this analysis. For example, it improves the accuracy of failure prediction by identifying specific recurring patterns and incorporating them into the model. This learning capability enhances prediction accuracy over time and proves more effective in preventing failures.

[0080] (7) Failure prevention and response system

[0081] The equipment failure prediction unit provides a system for preventing failures in advance and sends notifications so that managers can take immediate action when a potential failure is detected. This system enhances equipment efficiency and minimizes emergency situations by providing the capability to take preventive measures before a failure occurs. Furthermore, it provides data to facilitate a rapid response when a failure occurs, enabling managers to make quick and accurate decisions based on this data. This ensures the operational stability of the equipment and prevents interruptions to electric vehicle charging services.

[0082] The normal state range related data and criteria stored in the above-mentioned guide data storage unit (122) will be explained in detail.

[0083] The guide data storage unit (122) serves to store various data that defines the normal state of the system. Information related to various normal state ranges is stored here, which helps monitor the performance of the system and enables the prediction model to operate efficiently. Seven examples of 'data related to normal state ranges' are described in detail below.

[0084] (1) Normal range data of power generation

[0085] Normal power generation range data defines the normal range of power generation for power generation facilities (e.g., solar, wind, etc.) used in electric vehicle charging stations. This data establishes the expected range of power generation based on specific time periods or weather conditions, allowing for comparison with actual power generation. For example, a solar power plant can expect a consistent amount of power generation on sunny days, and if the generation falls within this normal range, the system determines that it is operating normally.

[0086] (2) Equipment temperature normal range data

[0087] Equipment temperature normal range data defines the temperature range in which power generation equipment can operate normally. If the equipment temperature falls outside this range, problems such as overheating or cooling may occur, so it is monitored to ensure operation within the normal range. For example, the normal temperature range for a solar inverter is typically between 20 and 40 degrees, and if it falls outside this range, the equipment may become overloaded or performance may degrade.

[0088] (3) Voltage normal range data (Voltage normal range data is data that defines whether the voltage supplied to the electric vehicle charging station is within a normal range. Since large fluctuations in voltage can reduce charging efficiency or damage equipment, the voltage must be maintained within a certain range. For example, in a typical electric vehicle charging system, the voltage must be maintained within the range of 220V ± 10%, and if it deviates from this range, charging instability or equipment failure may occur.

[0089] (4) Charging current normal range data

[0090] Charging current normal range data defines the normal range of current flowing during electric vehicle charging. If the current flows excessively, it can damage the charger or the electric vehicle battery, while if it flows too little, the charging speed becomes very slow. For example, the normal current range for a fast charger may be between 20A and 80A, and if it falls outside this range, charging efficiency may decrease or a malfunction may occur.

[0091] (5) Charging station device status normal range data

[0092] Charging station device status normal range data defines the normal operating range of each device in an electric vehicle charging station (e.g., charging ports, power converters, control systems, etc.). Since each device operates properly only under specific conditions, there is a possibility of failure if it falls outside this range. For example, when the charging station's port status is normal, the connection status is displayed as 'Normal,' and this status can be used to determine whether there is a system error.

[0093] (6) Data on power generation range according to weather conditions

[0094] Data on power generation ranges based on weather conditions is used to determine whether power generation falls within a normal range based on weather data (e.g., temperature, humidity, solar radiation, etc.). For instance, power generation is expected to decrease on days with poor weather conditions (rain, cloudy conditions), and if it remains within this range, it is considered to be in a normal state. Power generation ranges related to weather data can be predefined and utilized for prediction and fault diagnosis.

[0095] (7) Battery capacity normal range data

[0096] Battery capacity normal range data includes normal range data related to the battery capacity of an Energy Storage System (ESS). If the battery capacity is within the normal range, the charging station can supply or store energy as expected; however, if it falls outside this range, charging performance deteriorates or there is a risk of battery damage. For example, the normal capacity range of a battery may be between 80% and 100%, and a capacity outside this range reduces battery efficiency and increases the likelihood of failure in the long term.

[0097] In this way, the guide data storage unit (122) stores various normal range data necessary for the system to operate normally. This enables the system to detect abnormal conditions early and take appropriate action.

[0098]

[0099] The power generation prediction model of the prediction judgment unit (124) mentioned above will be explained in more detail.

[0100] The power generation prediction model of the prediction judgment unit (124) performs an important function of analyzing real-time data of the power generation facility and predicting future power generation based on the data to warn of the possibility of failure. Through this prediction model, the operator of the electric vehicle charging station can play an important role in increasing the efficiency of the power generation facility and preventing failures. Below are three feasible examples of the power generation prediction model and a detailed explanation of each example.

[0101] Example 1: Power generation prediction model based on weather data

[0102] Models that predict power generation based on weather data are widely used in renewable energy systems, such as solar power plants. Since weather conditions have a significant impact on power generation, this method involves collecting weather data in real time and predicting output based on it. By predicting potential fluctuations in power generation at solar power plants, these models facilitate efficient energy management and fault prediction.

[0103] (1) Weather data collection

[0104] To predict power generation based on weather data, the model collects information on weather conditions in real time. Data such as temperature, humidity, solar radiation, cloud cover, and temperature change rate have a significant impact on solar power generation. The prediction judgment unit (124) collects this weather data and analyzes past data to derive a correlation with power generation.

[0105] (2) Analysis of the correlation between weather data and power generation

[0106] To understand the impact of weather conditions on power generation, prediction models utilize collected weather data to analyze correlations with past power generation patterns. For example, they identify changes in power generation at specific temperatures and track trends of decreasing generation under specific cloud cover. Through this process, the model can mathematically express the relationship between weather conditions and power generation.

[0107] (3) Weather-based power generation forecast

[0108] Power generation forecasting models based on weather data use prediction algorithms to forecast power generation based on future weather conditions. For example, weather forecasts can be used to predict the amount of power generated by a solar power plant over the next few hours or days. This forecast plays a crucial role in supplying the power required for electric vehicle charging stations.

[0109] (4) Fault prediction and early warning

[0110] The power generation forecasting model warns of the possibility of system failure if expected power generation is low or exhibits abnormal patterns due to weather conditions. For example, solar power generation can drop sharply on cloudy or rainy days. This model analyzes weather conditions in real time and immediately alerts managers if power generation is lower than expected.

[0111] (5) Interconnection with energy management systems

[0112] The weather-based power generation forecasting model operates in conjunction with the Energy Management System (EMS) of the electric vehicle charging station. The EMS adjusts the energy consumption of the charging station by reflecting fluctuations in power generation due to weather conditions. For example, if the predicted power generation is insufficient, it efficiently manages power usage by supplying additional power from the Energy Storage System (ESS) or adjusting the charging speed.

[0113] (6) Improvement of model accuracy and continuous updates

[0114] Weather-based prediction models can improve their accuracy over time. By comparing and analyzing the difference between weather forecasts and actual power generation and incorporating this into the model, prediction accuracy is gradually increased. Through continuous data, the model can make increasingly precise predictions, and the accuracy of fault prediction also improves.

[0115] (7) Operational optimization

[0116] Weather-based power generation forecasting contributes to the operational optimization of electric vehicle charging stations. By regulating the power supply and demand of charging stations based on weather data, energy efficiency can be maximized. The forecasting model assists managers by suggesting optimal charging times or by calculating solar power shortfalls in advance, enabling appropriate responses.

[0117] Example 2: Regression analysis model based on historical power generation data

[0118] A power generation prediction model based on regression analysis is a method that forecasts future power generation based on historical data. This model analyzes the past performance of power facilities and predicts power generation trends based on this analysis, enabling the early detection of failures.

[0119] (1) Collection and analysis of past data

[0120] The regression analysis model analyzes power generation trends based on historical data collected from power generation facilities at electric vehicle charging stations. It collects power generation data from each facility (solar, wind, etc.) by time period and analyzes the correlation between each time period and the amount of power generated. For example, it can identify patterns where a constant amount of power is consistently generated during specific time periods.

[0121] (2) Application of regression analysis algorithm

[0122] Regression analysis models train a prediction model based on historical data. Through this process, a mathematical model is constructed to predict power generation. For example, linear or polynomial regression analysis can be used to predict trends in power generation based on historical data. This model predicts future power generation by learning the increasing or decreasing trends over time.

[0123] (3) Prediction of future power generation

[0124] Regression analysis models use learned algorithms to predict future power generation. For example, based on data from the past 30 days, they can predict power generation for the next hour or day. This prediction provides important information for meeting the power demand required by electric vehicle charging stations.

[0125] (4) Prediction of failure probability

[0126] Regression analysis models predict the likelihood of failure when outliers or sudden changes occur by comparing power generation trends with past data. For example, if a specific piece of equipment generates less power than predicted, it can be determined that there is a high probability of failure. This model warns managers of such occurrences and helps them take corrective action before a failure takes place.

[0127] (5) Improvement of equipment performance

[0128] Regression analysis models also help improve equipment performance. By analyzing the difference between predicted and actual power generation, performance issues can be detected and addressed early. For example, identifying the cause of low power generation during specific time periods and resolving equipment issues during those times can increase the efficiency of the entire system.

[0129] (6) Continuous learning of the model

[0130] Regression analysis models continuously collect data and learn from it to improve prediction accuracy. They retrain the model based on new data and continuously improve it by comparing prediction results. Through this process, prediction accuracy increases over time, and the reliability of failure prediction can be strengthened.

[0131] (7) Improvement of operational efficiency

[0132] Predicting power generation through regression analysis models can significantly improve operational efficiency. Based on the predicted power generation, it is possible to optimize operations, such as optimizing the energy supply and demand of electric vehicle charging stations or supplementing power shortages through ESS. This can reduce energy waste and minimize the operating costs of charging stations.

[0133] Example 3: Machine learning-based power generation prediction model

[0134] Machine learning-based power generation prediction models are advanced methods that forecast power generation based on historical data and various variables. By utilizing machine learning algorithms, they can improve the accuracy of power generation prediction and perform precise fault prediction.

[0135] (1) Data preprocessing

[0136] Machine learning-based power generation prediction models perform forecasts by utilizing various input data. To this end, data preprocessing is essential. For example, weather data, equipment status, and time-of-day information that affect solar power generation are used as input data. This data is organized so that the machine learning model can learn, and unnecessary data is removed or missing values ​​are processed.

[0137] (2) Feature extraction and selection

[0138] Machine learning models select key features for prediction. They identify the most critical variables (features) for power generation forecasting and input them into the model. For example, weather variables or the real-time status of facilities can play a significant role in power generation forecasting. In this process, unnecessary variables are eliminated, and the key variables necessary to improve prediction accuracy are incorporated into the model.

[0139] (3) Application of machine learning algorithms

[0140] A prediction model is trained using machine learning algorithms. Various machine learning algorithms, such as regression analysis, decision trees, random forests, and neural networks, can be used. For example, the random forest algorithm can improve the accuracy of power generation prediction by combining multiple decision trees. The model learns based on historical data to predict future power generation.

[0141] (4) Prediction and evaluation

[0142] Machine learning models predict future power generation based on learned data. For example, they can predict power generation one day or one week in advance. The predicted results are evaluated by comparing them with actual power generation. During this process, the model's predictive performance is verified, and if necessary, the model is retrained to improve prediction accuracy.

[0143] (5) Fault prediction and warning system

[0144] Machine learning models are also used to predict failures. If power generation falls short of forecasts, the model warns of a potential failure. For example, if power generation drops sharply, the system identifies this as a sign of failure and sends out a warning signal. This warning system helps enable countermeasures before a failure occurs.

[0145] (6) Continuous updates of the model

[0146] Machine learning models are continuously trained and updated to adapt to new data and situations. This is used to refine model predictions based on actual data generated during operation and to improve model accuracy. Through this process, the model becomes capable of making increasingly accurate predictions.

[0147] (7) Operational optimization and efficiency improvement

[0148] Machine learning-based power generation prediction models contribute to improving operational efficiency. Based on predicted power generation, energy demand at charging stations can be optimized, or power shortages can be compensated for through ESS. This reduces energy waste and minimizes operating costs for charging stations.

[0149] The operational data collection unit (130) is a component that plays an important role in managing the data flow of the electric vehicle charging station and monitoring equipment failure prediction and operational status in real time. This unit receives all data collected from the data collection control unit (110) and the equipment failure prediction unit (120) and provides it to the manager in a form required by the manager. In addition, it visualizes the data so that the manager can intuitively recognize it and performs the function of managing the overall operational status of the system. The operational data collection unit performs a key role in ensuring the smooth operation of the electric vehicle charging station by providing various data in real time, such as failure warnings, equipment status, power generation, and transmission status.

[0150] (1) System diagram output section (131)

[0151] The system diagram output unit (131) generates a system diagram that allows for the visual recognition of the current power flow of the power grid based on collected data, and provides this to the manager's smart device. This unit visualizes and displays the power flow in real time, which transmits power generated at the power plant to the charging station through the transmission network. Through this, the manager can intuitively understand the flow and status of the power and take immediate action if any abnormal signs are detected. The system diagram output unit supports the efficient operation of the power grid and provides the function of monitoring changes in the power flow in real time.

[0152] (2) Operation status output section (132)

[0153] The operation status output unit (132) monitors the power generation, transmission, charging, discharging, and usage status of the electric vehicle charging station in real time and provides processed data tables and graphs to the manager's smart device so that they can be visually recognized. This unit displays the status of each facility and power flow in real time, allowing the manager to grasp the operation status of the entire system at a glance. By visually representing the operation status of each facility through graphs and tables, it helps the operator immediately identify and respond to areas where problems have occurred.

[0154] (3) Management history output unit (133)

[0155] The management history output unit (133) is a unit that provides data on the control history, failure history, and response history of renewable energy generation facilities and ESS facilities to a manager's smart device in a visually recognizable form. This unit manages records of control and maintenance work performed by each facility and supports tracking the history in the event of a failure. The management history output unit increases the reliability of the system and provides useful data for future management or maintenance work, thereby extending the lifespan of the facilities and helping with efficient operation.

[0156] (4) Disaster notification output unit (134)

[0157] The fault notification output unit (134) functions to provide faults or warnings that occur in the system to the manager's smart device in real time. When a fault occurs in the power flow or equipment status, this unit immediately sends a notification to the manager to help quickly recognize the problem. The fault notification can occur in any situation, including failures in the power system, charging station, or equipment, and the manager can take appropriate measures through it. This unit helps increase the reliability of electric vehicle charging station operations and enables a rapid response in the event of a fault.

[0158] (5) Communication failure output unit (135)

[0159] The communication failure output unit (135) monitors the communication status between the data collection control unit (110) and the equipment failure prediction unit (120) and notifies the manager if a communication failure occurs. When a problem occurs with data transmission, this unit checks the communication status of the relevant equipment or system and transmits information about the faulty part to the manager. The communication failure output unit ensures the normal operation of the system, prevents data loss due to communication failures, and helps the manager quickly resolve the problem.

[0160] (6) Data analysis and reporting functions

[0161] The operational data collection unit (130) goes beyond simply collecting data to provide the function of analyzing the collected data and generating reports based on it. This unit performs an integrated analysis based on power flow, equipment status, and failure prediction data, and reports the results to the manager. These reports are provided on a daily, weekly, and monthly basis and are used as basic data for improving operational status. The data analysis function plays an important role in optimizing system operations and supports the manager in making better decisions.

[0162] (7) Real-time monitoring and notification system

[0163] The operational data collection unit (130) provides the function of monitoring data in real time and immediately sending notifications regarding important matters to the manager. This system checks the status of power, the operating status of equipment, and whether there is a malfunction in real time, and sends a notification to the manager quickly if abnormal signs are detected. This unit is an essential element for maintaining the safe and efficient operation of the electric vehicle charging station, and helps the manager check the status of the system in real time and take necessary measures.

[0164] As explained above, the power generation demand analysis, fault determination, and response system (100) of an electric vehicle charging station effectively solves various problems that occurred in the prior art. In the operation of existing charging stations, problems such as power flow, equipment status, and fault diagnosis were often handled manually or could not be monitored in real time. As a result, it was difficult to respond immediately when a fault occurred, and the reliability of the operation was often reduced due to a lack of preventive measures. To solve these problems, the present invention provides a system that can detect faults early and respond automatically based on real-time data collection and monitoring.

[0165] First, the present invention provides a function to detect and predict failures of all equipment related to an electric vehicle charging station in real time. In existing systems, in order to detect equipment failures, problems had to be recognized after a certain period of time had passed or manual inspections had to be performed. However, the present invention analyzes real-time data through an equipment failure prediction unit (120) and predicts failures before they occur, allowing the manager to respond early. Through this, service downtime due to failures can be minimized and operational efficiency can be increased.

[0166] Secondly, the present invention can monitor the interaction between the power grid, renewable energy generation facilities, and ESS facilities in real time. In existing systems, there is often a lack of real-time information regarding power flow, making it difficult to respond efficiently in situations of power shortage or excess. The present invention visualizes power flow in real time through a data collection control unit (110) and a grid diagram output unit (131), thereby helping a manager immediately identify the status of the power and respond quickly when necessary. Providing such real-time information contributes significantly to increasing the operational efficiency of electric vehicle charging stations.

[0167] Thirdly, the present invention enhances fault diagnosis and prediction functions to provide the ability to prevent failures before they occur. In conventional technology, failures were often discovered only after they occurred, which resulted in delays in repair or response. The equipment failure prediction unit (120) of the present invention analyzes real-time data to predict equipment that is likely to fail in advance and provides a warning signal to the manager. This allows for the prevention of failures in advance or rapid response, thereby increasing the equipment utilization rate and reducing operating costs.

[0168] Fourth, the present invention provides a user-friendly system that helps managers intuitively understand complex data and take quick action. Existing systems made it difficult for operators to grasp the situation in real time due to the difficulty of data analysis and interpretation. However, the present invention visually provides the power generation amount, transmission status, charging status, etc., through the operation status output unit (132) and system diagram output unit (131) of the operation data collection unit (130), thereby enabling managers to easily monitor the status of the system and take appropriate action. This reduces the workload of managers and significantly improves the stability of the system.

[0169] Finally, the present invention provides a function capable of effectively responding even after a failure occurs. In conventional systems, response was only provided after a failure had occurred, often resulting in prolonged system recovery times. The present invention establishes a system capable of automatically responding to failures, thereby rapidly resolving issues and ensuring the continuous provision of electric vehicle charging services. This enhances the user experience and maximizes the operational efficiency of charging station operators.

[0170] The above detailed description of the present invention describes only specific embodiments thereof. However, it should be understood that the present invention is not limited to the specific forms mentioned in the detailed description, but rather should be understood to include all variations, equivalents, and substitutions within the spirit and scope of the invention as defined by the appended claims.

[0171] In other words, the present invention is not limited to the specific embodiments and descriptions described above, and any person skilled in the art to which the present invention pertains can make various modifications without departing from the essence of the invention as claimed in the claims, and such modifications fall within the scope of protection of the present invention.

[0172] The modes for carrying out the invention are described together in the best mode for carrying out the invention above.

[0173] The present invention relates to a system for analyzing power generation demand, determining faults, and responding to electric vehicle charging station facilities. It can establish an infrastructure for providing electric vehicle charging services that meets local power requirements, electrical design regulations, electrical design technical standards, and local environmental conditions in various countries around the world, and can establish an AI EMS linked to the local power grid. It can also rapidly detect and respond to faults in electric vehicle charging service facilities, solar power generation facilities, and ESS facilities through the AI ​​EMS based on demonstration site operation data. Furthermore, it can predict the occurrence of faults in electric vehicle charging service facilities, solar power generation facilities, and ESS facilities based on fault detection data, thereby preventing or responding to faults in advance, thus having industrial applicability.

Claims

A system for monitoring and controlling a grid power system that includes a configuration for producing electricity through renewable energy generation facilities, storing it in ESS facilities, and then supplying it to electric vehicle charging stations, A data collection control unit (110) that receives data related to renewable energy generation facilities and ESS facilities in real time through the above-mentioned grid power network, monitors the flow of power provided through the grid power network, transmits the data received in real time and the monitoring data to the operation data collection unit (130), and receives control signals through the operation data collection unit (130) to control the operation of renewable energy generation facilities and ESS facilities; A facility fault prediction unit (120) that performs real-time fault diagnosis regarding renewable energy generation facilities and ESS facilities based on data acquired through the data collection control unit (110), predicts the occurrence of a fault regarding renewable energy generation facilities and ESS facilities based on data stored in the operation data collection unit (130), and transmits fault diagnosis result data and fault occurrence prediction data to the operation data collection unit (130); and An operation data collection unit (130) that internally stores data acquired from the data collection control unit (110) and the equipment failure prediction unit (120), wirelessly links with the manager's smart device to receive control signals related to renewable energy generation equipment and ESS equipment from the manager and transmits them to the data collection control unit (110), and provides data requested by the manager to the manager's smart device; A power generation demand analysis, fault determination, and response system for electric vehicle charging station facilities, characterized by including In paragraph 1, The above data collection control unit (110) is, If the amount of power generated within a preset time range is not reached, the power generation monitoring unit (111) checks the real-time weather conditions and the contamination status of the renewable energy power generation facility, and if the weather conditions or contamination status is not the cause of the low power generation problem, transmits data related to the failure status of the renewable energy power generation facility to the operation data collection unit (130) so that it is output to the manager's smart device through the operation data collection unit (130); A communication equipment monitoring unit (112) that determines whether the socket server is operating normally when the communication status is poor, and if the socket server has stopped, determines that physical network damage is the biggest cause and switches to a waiting state for a preset time until normalization, and if there is no problem with the socket server, determines that the processing capability of the AI ​​EMS server is the biggest cause and transmits inspection request data by the administrator to the operation data collection unit (130) so that it is output to the administrator's smart device through the operation data collection unit (130) to check the session memory and check for external network attacks; and An ESS monitoring unit (113) determines whether the battery is connected to the equipment when an abnormality occurs in the BMS installed in the ESS, controls the battery to restart the equipment connection state as a response to the ESS abnormality, and if there is a physical abnormality in the ESS equipment, disconnects the battery equipment connection state and then transmits the inspection request data by the manager to the operation data collection unit (130) so that it is output to the manager's smart device through the operation data collection unit (130); A power generation demand analysis, fault determination, and response system for electric vehicle charging station facilities, characterized by including In paragraph 2, The above equipment failure prediction unit (120) is, A data receiving unit (121) that receives data obtained through the data collection control unit (110); A guide data storage unit (122) that stores data related to the normal state range for each of the multiple data of renewable energy generation facilities and ESS facilities, and modifies the data related to the normal state range by a control signal transmitted from a manager's smart device; A fault determination unit (123) that determines whether each data received through the data receiving unit (121) meets the criteria for normal state range related data stored in the guide data storage unit (122), and if it does not meet the criteria, determines that a fault has occurred in the equipment related to the data and transmits the related data to the operation data collection unit (130); and A prediction judgment unit (124) compares real-time data acquired from an operation data collection unit (130) with a power generation prediction model, and if the real-time data acquired exceeds a preset range from the power generation prediction model and a difference occurs, transmits a warning signal indicating a high probability of failure in the equipment and related data to the operation data collection unit (130) so that they are output to the manager's smart device; A power generation demand analysis, fault determination, and response system for electric vehicle charging station facilities, characterized by including In paragraph 3, The above operation data collection unit (130) is, Based on the data acquired from the above data collection control unit (110) and equipment failure prediction unit (120), a system diagram output unit (131) provides a system diagram processed to allow visual recognition of the current power flow of the power grid to the manager's smart device, and provides a map image processed to allow visual recognition of the locations where renewable energy generation facilities and ESS facilities are installed to the manager's smart device; An operation status output unit (132) that provides a data table and graph processed to allow visual recognition of the current power grid generation, transmission, charging, discharging, and utilization status based on data obtained from the above data collection control unit (110) and equipment failure prediction unit (120) to a manager's smart device; and A management history output unit (133) that provides a data table and graph processed to allow visual recognition of equipment control history data, equipment failure history data, and equipment response history data of renewable energy generation equipment and ESS equipment based on data obtained from the above data collection control unit (110) and equipment failure prediction unit (120) to a manager's smart device; A power generation demand analysis, fault determination, and response system for electric vehicle charging station facilities, characterized by including In paragraph 4, The above operation data collection unit (130) is, Based on the data obtained from the above data collection control unit (110) and equipment failure prediction unit (120), if a failure occurs in the current power grid power flow, generation, predetermined, charging, discharging, or usage status, a failure notification output unit (134) provides failure-related information and a warning alarm to the manager's smart device; and A communication failure output unit (135) that determines whether there is a communication failure by checking whether there is a data response during the process of receiving data by continuously communicating with the data collection control unit (110) and the equipment failure prediction unit (120), and provides data related to the equipment where the communication failure occurred to the manager's smart device and simultaneously provides an alarm when a communication failure occurs; A power generation demand analysis, fault determination, and response system for electric vehicle charging station facilities, characterized by including

Images