WO2020125984A1 - System and method for power outage prediction - Google Patents

System and method for power outage prediction Download PDF

Info

Publication number
WO2020125984A1
WO2020125984A1 PCT/EP2018/086079 EP2018086079W WO2020125984A1 WO 2020125984 A1 WO2020125984 A1 WO 2020125984A1 EP 2018086079 W EP2018086079 W EP 2018086079W WO 2020125984 A1 WO2020125984 A1 WO 2020125984A1
Authority
WO
WIPO (PCT)
Prior art keywords
black
brown
electrical grid
events
data
Prior art date
Application number
PCT/EP2018/086079
Other languages
French (fr)
Inventor
Jitendra Solanki
Kevin Tom
Original Assignee
Robert Bosch Gmbh
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Robert Bosch Gmbh filed Critical Robert Bosch Gmbh
Priority to PCT/EP2018/086079 priority Critical patent/WO2020125984A1/en
Publication of WO2020125984A1 publication Critical patent/WO2020125984A1/en

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring
    • G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
    • G05B23/0224—Process history based detection method, e.g. whereby history implies the availability of large amounts of data
    • G05B23/024—Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring
    • G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
    • G05B23/0283—Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
    • H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/001—Methods to deal with contingencies, e.g. abnormalities, faults or failures
    • H02J3/0012—Contingency detection
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/20—Pc systems
    • G05B2219/26—Pc applications
    • G05B2219/2639—Energy management, use maximum of cheap power, keep peak load low
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
    • H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
    • Y02B90/20—Smart grids as enabling technology in buildings sector
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/30—State monitoring, e.g. fault, temperature monitoring, insulator monitoring, corona discharge
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S20/00—Management or operation of end-user stationary applications or the last stages of power distribution; Controlling, monitoring or operating thereof
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S40/00—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them
    • Y04S40/20—Information technology specific aspects, e.g. CAD, simulation, modelling, system security

Definitions

  • the present disclosure relates to power irregularity prediction in power systems, and more specifically, to a system and method for predicting black-out and/or brown-out events in power systems.
  • a method may be provided for power irregularity prediction.
  • the power irregularity may include black-out and/or brown-out events in an electrical grid.
  • the method may be computer-implemented.
  • the method may include receiving, by a computing device, an input data, which may include a historical data of black-out events in the electrical grid.
  • the method may further include determining, by the computing device, patterns of black-out events in the electrical grid using one or more machine learning models based on the input data.
  • the method may include, predicting, by the computing device, a future, e.g., a next, black-out event in the electrical grid based at least in part on the patterns of the black-out events.
  • Prediction data of the future black out event in the electrical grid may then be outputted by a computing device.
  • the method may further include, outputting, by the computing device, prediction data of the future black-out event in the electrical grid.
  • the input data may include historical data of brown-out events.
  • the method may further include determining, by the computing device, patterns of brown-out events in the electrical grid based on the input data.
  • the method may include, predicting, by the computing device, a future brown out event in the electrical grid based on the patterns of the brown-out events.
  • a system may be provided.
  • the system may include a non-transitory memory device for storing computer-readable program code, and a processor in communication with the memory device.
  • the processor may be operative with the computer-readable program code to perform operations.
  • the system may be implemented as one or more computer systems.
  • the operations may include receiving an input data, which may include a historical data of black-out events in an electrical grid.
  • the operations may further include determining, using one or more machine learning models, patterns of black-out events in the electrical grid based on the input data.
  • the operations may further include predicting a future black-out event in the electrical grid based on the patterns of the black-out events.
  • the operations may further include outputting prediction data of the future black-out event in the electrical grid.
  • the input data may include historical data of brown-out events.
  • the operations may further include determining patterns of brown-out events in the electrical grid based on the input data.
  • the operations may include predicting a future brown-out event in the electrical grid based on the patterns of the brown-out events.
  • FIG.1 is a block diagram illustrating an exemplary environment
  • FIG. 2 shows an exemplary architecture of a plant control system
  • Fig. 3 shows an exemplary process for predicting one or more future black-out and/or brown-out events.
  • a framework for controlling or managing power supply in a microgrid is described herein.
  • a microgrid may be set-up to manage and provide electricity to a residential, commercial, and/or industrial customers.
  • the framework predicts power irregularity in a power system or electrical grid.
  • the power irregularity may include one or more future black-out and/or brown-out events (events may also be named occurrences) in the electrical grid.
  • the one or more future black-out and/or brown-out events may be the next black-out and/or brown-out events.
  • the electrical grid may be connected to the microgrid.
  • the electrical grid for example, may be one of the input or sources of power of the microgrid.
  • a black-out (also named as power outage, grid failure, power cut, power black-out, or power failure), for example, may be a short-term or a long-term loss of the electric power to a particular area.
  • a brown-out (also named grid voltage reduction), for example, may be an intentional or unintentional drop in voltage in an electrical grid. For example, intentional brown-outs may be used for load reduction in an emergency. The reduction lasts for minutes or hours, as opposed to short-term voltage sag (or dip).
  • the framework receives input data, which include historical data of black-out and/or brown-out events which have occurred in the electrical grid. For example, the framework receives the historical data of black-out and brown-out events over a predefined time interval.
  • the framework may include machine learning models or algorithms to determine patterns of the black-out and/or brown-out events in the electrical grid based on the historical data.
  • the framework may predict one or more next black-out and/or brown-out occurrences in the electrical grid based on the patterns of the black out and/or brown-out events which patterns are determined from the historical data.
  • the framework may output prediction data of one or more black-out and/or brown-out occurrences in the electrical grid. Real-time or new data of black-out and brown-out events may be continuously captured to train the machine learning models and improve accuracy of the machine learning models.
  • the framework may receive grid parameters of the electrical grid as well as weather parameters that include weather information and seasonal information. Additionally, the framework may receive occasion information such as festivals and other special events occurring in the vicinity of the electrical grid or area encompassed by the electrical grid. In one embodiment, the framework may predict one or more next black-out and/or brown-out events based on the grid parameters, weather information, seasonal information and/or occasion information using the machine learning models. In some embodiments, the framework may predict one or more next black-out and/or brown-out events based on the historical data of black-out and/or brown-out events, the grid parameters as well as using weather information, seasonal information and occasion information. In some cases, the framework may receive user input of information regarding scheduled maintenance at the grid.
  • the input data may include historical data of the black-out events.
  • patterns of black-out events in the electrical grid may be determined by a computing device using one or more machine learning models based at least in part on the historical data of the black-out events, and may further include other data, for example, historical data of the brown-out events.
  • the input data may include historical data of the brown-out events.
  • patterns of brown-out events in the electrical grid may be determined by a computing device using one or more machine learning models based at least in part on the historical data of the brown-out events, and may further include other data, for example, historical data of the black-out events.
  • the input data may include grid parameters of the electrical grid.
  • patterns of the black-out events and/or brown-out events in the electrical grid may be determined by the computing device using one or more machine learning models based on the grid parameters.
  • patterns of the black-out events and/or brown-out events in the electrical grid may be determined by the computing device using one or more machine learning models based on the historical data of the black-out and/or brown-out events and the grid parameters.
  • the input data may include weather and seasonal information.
  • patterns of the black-out events and/or brown-out events in the electrical grid may be determined by the computing device using one or more machine learning models based on the weather and seasonal information.
  • patterns of the black-out events and/or brown-out events in the electrical grid may be determined by a computing device using one or more machine learning models based on the grid parameters and the weather and seasonal information.
  • patterns of the black-out events and/or brown-out events in the electrical grid may be determined by the computing device using one or more machine learning models based on the historical data of the black-out and/or brown-out events and the grid parameters, weather and seasonal information.
  • the computing device receives user input, which includes information of a scheduled maintenance of a grid infrastructure. Patterns of the black out events and/or brown-out events in the electrical grid may be further determined based on the user input.
  • a prediction output data may be employed to control and manage efficient operation of power sources and loads in the microgrid which is connected to the electrical grid. For example, output data of the prediction of the next black-out and brown-out events may be used to efficiently operate and control power sources and storage devices as well as manage demand response by residential, commercial and/or industrial customers.
  • the framework advantageously facilitates controlling and managing power supply in the microgrid. This allows for resilient and reliable power supply in the microgrid.
  • FIG. 1 shows a simplified diagram of an exemplary environment or architecture 100.
  • Environment 100 may have a distributed architecture.
  • the environment in one embodiment, may include a microgrid and a power system or electrical grid 130.
  • the environment 100 facilitates power irregularity prediction.
  • the environment facilitates predicting one or more next black-out and/or brown-out occurrences in the electrical grid.
  • the environment includes a communication network 105.
  • the communication network may be, for example, the internet. Other types of communication networks or combination of networks may also be useful.
  • the environment includes a plurality of servers and one or more client or user devices 1 10a-b coupled to the communication network.
  • a server may include one or more computers.
  • a computer includes a memory and a processor.
  • Various types of computers may be employed for the server.
  • the computer may be a mainframe, a workstation as well as other types of processing devices.
  • the memory of a computer may include any memory or database module.
  • the memory may be volatile or non-volatile types of non-transitory computer-readable media such as magnetic media, optical media, random access memory (RAM), read-only memory (ROM), removable media, or any other suitable local or remote memory component.
  • the server includes more than one computer, they are connected through the communication network such as an internet, intranet, local area network (LAN), wide area network (WAN), internet or a combination thereof.
  • the servers may be part of the same private network.
  • the servers may be located in single or multiple locations. Other configurations of servers may also be useful.
  • the servers may form a cloud.
  • a computing device for example, includes a local memory and a processor.
  • the computing device may further include a display.
  • the display may serve as an input and output component of the user device.
  • the memory may be volatile or non-volatile types of non-transitory computer-readable media such as magnetic media, optical media, RAM, ROM, removable media, or any other suitable memory component.
  • processing devices may serve as user devices.
  • the user devices may include a personal computer, or a mobile client device such as a smart phone. Other types of user devices, such as laptops or tablets may also be useful.
  • a user may connect to a server using a user device.
  • the user device may be referred to as the client side while the server may be referred to as the server side.
  • a user may access the server by logging in the user’s respective account with, for example, a password using a user device.
  • a user may communicate with the server via a user interface (Ul) on the user device.
  • Ul user interface
  • the environment may include a plant control system (or controller) 120.
  • the plant control system may reside on a server.
  • the plant control system may reside on a plurality of servers.
  • the server or plurality of servers may reside in a cloud.
  • the plant control system may manage or control power supply(ies) in the microgrid.
  • the plant control system may facilitate supply of power to the microgrid in the event of black-out or brown out in the electrical grid.
  • the plant control system 120 may be in communication with the electrical grid 130 and the microgrid.
  • the electrical grid may include generating stations that produce electrical power, high voltage transmission lines that carry power from distant sources to demand centers and distribution lines that connect individual customers.
  • the electrical grid may encompass a network of areas.
  • the microgrid it may be connected to the electrical grid.
  • the electrical grid may be one of the sources of power to the microgrid.
  • the microgrid encompasses a defined area.
  • the microgrid may include one or more power sources 140a-b, one or more storage devices 150 and a plurality of loads 160a-c.
  • the power sources 140a-b may include engine-generators such as diesel generators, and renewable energy sources such as solar photo-voltaic modules, wind turbines and fuel cells.
  • the storage devices may include batteries.
  • the plurality of loads may include electrical demand by various equipments or components at the premises of commercial, industrial and/or residential customers. Other types of power sources, storage devices and loads in the microgrid may also be useful.
  • the environment may include a data source 170.
  • the data source in some embodiments, may be a repository containing information acquired from the electrical grid. For example, historical data including previous black-out and brown out events which have occurred in the electrical grid may be retrieved and stored in the data source.
  • information of the electrical grid such as grid parameters, time, weather information, seasonal information, and occasion information related to the electrical grid may be retrieved and stored in the data source.
  • the grid parameters, time, weather information, seasonal information, and occasion information may be stored to draw inferences and correlations of patterns of black-out and/or brown out events occurring in the electrical grid.
  • Fig. 2 shows an exemplary architecture 200 of an embodiment of the controller 120.
  • the controller includes a data acquisition module 210, a preprocessor 220, a database 230, a machine learning module 240, a distributed generation module 250 and a demand response module 260.
  • Providing the controller with other components may also be useful.
  • the various components may reside on one or more servers. For example, the components may reside on different servers or on the same server. Other configurations of the components may also be useful.
  • the data acquisition module 210 receives input data.
  • the input data in one embodiment, includes historical data of black-out and/or brown-out events 270 which have occurred in the electrical grid.
  • the previous black out and brown-out events may occur in a plurality of areas encompassed by the electrical grid.
  • black-out and brown-out events may have occurred, for example, at generating stations, voltage transmission lines, and distribution lines.
  • the data acquisition module may obtain the historical data of the black-out and brown-out events over a predefined time interval.
  • the time interval may be predefined by a user.
  • the data acquisition module may continuously obtain the historical data of the previous black-out and brown-out events over a time period of two years. In other implementations, the time interval may be four months. Other time intervals for continuously obtaining the historical data of black-out and brown-out events occurring in the power system may also be useful.
  • the historical data of the previous black-out and brown-out events includes information such as, for example, a unique identifier identifying each black-out or brown out event, duration of the black-out and/or brown-out events, day of occurrence, start time and end time, location of occurrence, geographical area (e.g., extent of black-out or brown-out), planned or unplanned (e.g., intentional shut down of station), demand or load at the affected area, weather information, seasonal information, as well as occasion information related to the area where the black-out and/or brown-out events occurred, cause of black-out and/or brown-out events (e.g., utility failure to component failures within power infrastructure, weather, natural disasters, installation design issues).
  • a unique identifier identifying each black-out or brown out event
  • duration of the black-out and/or brown-out events day of occurrence, start time and end time, location of occurrence
  • geographical area e.g., extent of black-out or brown-out
  • planned or unplanned e.
  • the input data additionally may include real time data of black-out and/or brown-out events 272 in the electrical grid.
  • real-time data of one or more black-out and/or brown-out events occurring in the electrical grid may be obtained by the acquisition module.
  • the real-time data of one or more black-out and/or brown-out events may be used for training and continuous learning by machine learning models in the controller 120.
  • the input data may include grid parameters of the electrical grid 274 and weather parameters 276.
  • the grid parameters of the electrical grid may include voltage amplitude, phase and/or frequency of the voltage, time of the day on which the grid parameters are obtained or recorded.
  • the weather parameters it may include weather information (e.g., temperature, wind speed, precipitation) and seasonal information related to the electrical grid, for example, at the time the black-out and/or brown-out events occur at the electrical grid.
  • the data acquisition module may receive the input data from an external data source such as data source 170 as described with respect to Fig. 1 .
  • the data acquisition module may directly monitor and acquire the input data such as the historical data of black-out and/or brown-out events in the electrical grid as it occurs over the predefined time interval.
  • the data acquisition module may continuously acquire the grid and weather parameters as well as real-time data of one or more black- out and/or brown-out events in the electrical grid as it occurs.
  • the input data for example, may be collected using sensor devices and data loggers or micro-processors connected to sensors.
  • the input data may be collected using sensor devices such as one or more of voltage sensors, current sensors, power and phasor measurement sensors, temperature sensors, humidity sensors and wind speed sensors and weather stations.
  • the sensor devices may be positioned at various locations of the electrical grid such as the generating stations, transmission lines and distribution lines. Other configurations for obtaining the input data may also be useful.
  • the preprocessor preprocess the input data and stores data entries (or records) in the database. For example, the preprocessor preprocesses the historical data of the black-out and/or brown-out events. For example, each data entry represents an occurrence or instance of a black-out event or brown-out event in the electrical grid.
  • the preprocessor preprocesses the input data to categorize the data. For example, the preprocessor preprocesses the input data collected using the various sensor devices such as a voltage sensor, current sensor, power and phasor measurement sensor, temperature sensor, humidity sensor and wind speed sensor and/or weather station.
  • the input data may be stored in an array format with respect to time and prepossessed to eliminate noise.
  • data normalization may be performed.
  • input data such as seasonal information and occasion information may be stored. For example, occasions such as festivals and other special events may lead to increase in load on the electrical grid.
  • a black-out event may be determined based on the voltage characteristics such as a voltage drop to zero or near zero.
  • a brown-out event for example, may be determined based on a voltage reduction of more than 10%.
  • frequency-deviations may be recorded and stored in the database.
  • the database may be a repository which contains the historical data of the black-out and/or brown-out events in the electrical grid.
  • the database stores the historical data of the previous black-out and brown-out events received by the data acquisition module.
  • the historical data for example, is stored in the database for processing by the machine learning module.
  • the database may store the real-time data of black-out and brown-out events in the electrical grid.
  • the database may store the grid and weather parameters for processing by the machine learning module.
  • the input data may be directly retrieved from the external data source for processing by the machine learning module.
  • the machine learning module may directly receive input data such as the historical data, real-time data, and/or grid and weather parameters as well as occasion information from the external data source.
  • the database may contain one or more machine learning models or algorithms.
  • the machine learning models may be used by the machine learning module to determine patterns of black-out and brown-out events in the electrical grid based on the historical data of the black-out and brown-out events.
  • the machine learning models may be semi-supervised learning models. Exemplary models include, but are not limited to, artificial neural networks, genetic algorithms, random forests, other stochastic methods, or a combination thereof. Other types of models may also be useful.
  • a semi-supervised learning model may be trained using supervised learning techniques.
  • the machine learning module may determine patterns of black-out and brown-out events in the electrical grid based on the historical data of the black-out and brown-out events.
  • the machine learning module may use one or more of the machine learning models to determine patterns of previous black out and brown-out events in the electrical grid.
  • the machine learning module uses a long short term memory method to determine the patterns of previous black-out and brown-out events.
  • the long short term memory method may be augmented with a rule-based approach to improve the accuracy of the prediction.
  • the machine learning module predicts one or more next black-out and/or brown-out events in the electrical grid based on the patterns of previous black-out and brown-out events. Rule-based methods add additional information about events for which specific pattern does not exist in historical/training data.
  • the machine learning module may use the machine learning models to determine patterns of previous black-out and brown-out events in the electrical grid based on the historical data of the black-out and/or brown-out events.
  • the black-out and/or brown-out events include information such as the duration of the black-out and/or brown-out events, day of occurrence, start time and end time, location of occurrence, geographical area (e.g., extent of black-out or brown-out), planned or unplanned (e.g., intentional shut down of station), demand or load at the affected area, weather information related to the area where the black-out or brown-out event occurred, cause of black-out or brown-out (e.g., utility failure to component failures within power infrastructure, weather conditions, natural disasters, overloading of substation assets/components, high peak loading of the overall grid, scheduled and unscheduled maintenance).
  • substation operators may intentionally shut down power due to weather conditions in order to avoid accidents and failures.
  • some areas may be shut down to reduce overall load.
  • power of different areas is shut down at different times of the day/week in a regular pattern.
  • the machine learning module uses such information to determine patterns of the previous black-out and brown-out events in the electrical grid. For example, the machine learning module further determines a pattern of power shut down at different areas at different times (e.g., of the day or week).
  • the machine learning module may evaluate the historical data of the black-out and brown-out events in the electrical grid based on time periods such as months, days, and hours to determine patterns for the occurrences of the black-out and brown-out events.
  • the machine learning module may output prediction data 280 of the prediction of one or more next black-out and/or brown-out events in the electrical grid.
  • the prediction output data may include information of the one or more possible next black-out and/or brown-out events.
  • the prediction output data may include black-out or brown-event, day, time and duration for the next black-out or brown-out event, likelihood, probability, or confidence interval of the occurrence, location, affected area, historical frequency.
  • the prediction output data may be used to continuously train the machine learning models and improve the accuracy of the machine learning models for determining patterns of the power outage as well as predicting a next power outage event.
  • the machine learning module may receive the real-time data of one or more black-out and brown-out events occurring in the electrical grid and may compare the real-time data to the prediction output data. For example, the machine learning module may use the real-time data of the black-out and brown-out events and the prediction output data of the prediction of one or more next black-out and/or brown-out events as training data to continuously train the machine learning models. For example, the output data of a prediction of the one or more next black-out and/or brown-out events may be compared with real-time data of black-out and/or brown out events to determine whether the prediction is correct or accurate. The determination is used to train the machine learning models in the database.
  • the machine learning models or algorithms may be configured such that in a continuous process, new data may be recorded and used to improve the accuracy of the algorithm. This enables continuous learning by the machine learning models, further improving subsequent predictions of black-out and brown-out events in the electrical grid.
  • the machine learning module may use the grid parameters to predict one or more next black-out and brown-out events.
  • the machine learning module receives the grid parameters from the external data source.
  • the machine learning module may monitor the grid parameters of the electrical grid.
  • the machine learning module further determines the patterns of black-out and/or brown-out events in the electrical grid based on the the grid parameters of the electrical grid.
  • the machine learning module determines deviation in the grid parameters of the power system.
  • the deviation in the grid parameters for example, may include voltage and frequency deviations. The voltage and frequency deviations may be used to predict failures in the electrical grid.
  • the machine learning module may use the weather parameters and occasion information to predict the next black-out and/or brown-out events in the electrical grid.
  • the weather parameters may include weather and seasonal information at areas encompassed by the electrical grid. For example, severe weather pattern (e.g., heavy wind, rain) affects the overhead transmission and distribution lines in an electrical grid.
  • severe weather pattern e.g., heavy wind, rain
  • substation operators may resort to turning off the power of an affected area to protect the system from short circuit (e.g., due to heavy wind overhead transmission/distribution lines (wires) may mechanically touch each other).
  • substation operators may also turns off the power as a safety precaution in severe weather conditions (e.g., due to poor infrastructure severe weather conditions may lead to damage (breakage) of the electricity poles and distribution lines).
  • the machine learning module further determines the patterns of black-out and/or brown-out events in the electrical grid based on the weather information, seasonal information and/or occasion information.
  • the machine learning module may receive user input 278 and may incorporate the user input in the prediction of the one or more next black-out and/or brown-out events.
  • the user input may include information such as scheduled maintenance of a grid infrastructure.
  • a user interface at the user device may enable the user to enter the relevant information regarding the scheduled maintenance of the grid infrastructure.
  • the information regarding the scheduled maintenance of the grid infrastructure for example, provides the controller with information of a planned power cut in an area encompassed by the electrical grid.
  • the user input may be provided by a user using a user device.
  • the machine learning module may incorporate the information regarding the scheduled maintenance to improve the accuracy of prediction of the one or more next black-out and/or brown-out event.
  • the machine learning module further determines the patterns of black-out and/or brown-out events in the electrical grid based on user input of a planned power cut.
  • the machine learning module may determine patterns of black-out and/or brown-out events based on inferences and correlations using the grid parameters, weather information, time, seasonal information, and occasion information.
  • the prediction output data may be displayed on one or more user devices for analysis by a user. Since the electrical grid is one of the source for the microgrid, a black-out event or brown-out event in the electrical grid affects operation of the microgrid. Accordingly, prediction of black-out and/or brown-out events may be used to manage the operations of the microgrid. In some embodiments, the controller may use the prediction output data to manage the microgrid. For example, the plant control system uses the prediction of the next black-out and/or brown-out events to control one or more of the power sources such as one or more diesel generators and solar photo voltaic modules and one or more storage devices in order to handle one or more of the next black-out and brown-out events.
  • the power sources such as one or more diesel generators and solar photo voltaic modules and one or more storage devices
  • the distributed generation module 250 controls power supply to one or more loads in the microgrid using the diesel generators and solar photo-voltaic modules based on the prediction of one or more next black-out and brown-out events.
  • the demand response module 260 may use the prediction output data to manage demand response for power supply to the loads in the in the microgrid.
  • Fig. 3 shows an exemplary process 300 for predicting one or more future black out and/or brown-out events.
  • the controller 120 as described in Figs. 1 -2 predicts one or more black-out and/or brown-out events in the electrical grid 120.
  • the controller receives input data.
  • the input data includes historical data of black-out events in the electrical grid.
  • the input data includes historical data of brown-out events in the electrical grid.
  • the input data includes grid parameters of the electrical grid, weather information, seasonal information and/or occasion information.
  • the input data includes user input.
  • the user input includes information of a scheduled maintenance of a grid infrastructure.
  • the controller determines, using one or more machine learning models, patterns of black-out events in the electrical grid based at least in part on the historical data of the black-out events. Additionally or alternatively, the controller determines patterns of brown-out events in the electrical grid based at least in part on the historical data of the brown-out events. According to some embodiments, the controller determines patterns of black-out events and/or brown-out events in the electrical grid based on the grid parameters, weather information, seasonal information, occasion information and/or the user input.
  • the controller determines patterns of black-out events and/or brown-out events in the electrical grid based on the historical data of the black-out/brown-out events, grid parameters, weather information, seasonal information, occasion information and/or the user input.
  • the one or more machine learning models may include a long short term memory method which is used to determine the patterns of previous black-out and brown-out events.
  • the long short term memory method may be augmented with a rule-based approach to improve the accuracy of the prediction.
  • the controller predicts a future black-out event in the electrical grid based at least in part on the patterns of the black-out events. Additionally or alternatively, the controller predicts a future brown-out event in the electrical grid based at least in part on the patterns of the brown-out events.
  • the controller outputs prediction data of a future black-out event in the electrical grid. Additionally or alternatively, the controller outputs prediction data of a future brown-out event in the electrical grid.
  • the output prediction data of one or more of the future black-out events and/or brown-out events may be used to control a microgrid.
  • the electrical grid may be connected to the microgrid.
  • the controller may control one or more power sources, one or more storage devices and/or demand response of the microgrid based on the prediction data. According to some embodiments, the controller may train the one or more machine learning models using the prediction data.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Automation & Control Theory (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Power Engineering (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Quality & Reliability (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • Operations Research (AREA)
  • Supply And Distribution Of Alternating Current (AREA)

Abstract

Described herein is a method and a system for power irregularity prediction. The power irregularity may include black-out and/or brown out events in an electrical grid. In accordance with one aspect, an input data which includes a historical data of black-out and/or brown-out events in the electrical grid is received. Patterns of black-out and/or brown-out events in the electrical grid is determined using one or more machine learning models based at least in part on the historical data of the black-out and/or brown-out events. A future black-out event and/or brown-out event in the electrical grid is predicted based on the patterns of the black-out and/or brown-out events. Prediction data of the future black-out and/or brown-out event in the electrical grid is then outputted by a computing device.

Description

SYSTEM AND METHOD FOR POWER OUTAGE PREDICTION
TECHNICAL FIELD
[0001] The present disclosure relates to power irregularity prediction in power systems, and more specifically, to a system and method for predicting black-out and/or brown-out events in power systems.
BACKGROUND
[0002] Electricity grid failure (or black-outs) and grid voltage reduction (or brown-outs) are rampant in parts of the developing countries. In some countries, black-out happens many times a day with variable durations. In some instances, power failures last only a few hours, while in other cases some black-outs can last days or even weeks, completely shutting down production at companies and critical infrastructures such as telecommunication networks, financial services, water supplies and hospitals. Furthermore, particularly in the developing countries, black-outs and brown-outs occur on a frequent basis in some areas, resulting in serious implications to the operations and economic loss in those areas.
[0003] There are many causes of power failures in an electricity network. For example, frequent black-outs and brown-outs occur in emerging economies with underinvested energy infrastructures, and which are also prone to serious weather and natural hazards. Other examples include faults at power stations, damage to electric transmission lines, substations or other parts of the distribution system, a short circuit, or the overloading of electricity mains. In addition, as power grids become more interconnected, a black-out in one region can trigger a cascading effect that could result in black-outs of a larger section of the electrical network. This may range from a building, to a block, to an entire city, to an entire electrical grid.
[0004] Therefore, there is a need to provide for a solution to manage and control the occurrences of black-out and/or brown-out events in an electrical grid. SUMMARY
[0005] In accordance with one aspect, a method may be provided for power irregularity prediction. The power irregularity may include black-out and/or brown-out events in an electrical grid. The method may be computer-implemented. The method may include receiving, by a computing device, an input data, which may include a historical data of black-out events in the electrical grid. The method may further include determining, by the computing device, patterns of black-out events in the electrical grid using one or more machine learning models based on the input data. The method may include, predicting, by the computing device, a future, e.g., a next, black-out event in the electrical grid based at least in part on the patterns of the black-out events. Prediction data of the future black out event in the electrical grid may then be outputted by a computing device. Thus, the method may further include, outputting, by the computing device, prediction data of the future black-out event in the electrical grid. In some embodiments, the input data may include historical data of brown-out events. The method may further include determining, by the computing device, patterns of brown-out events in the electrical grid based on the input data. The method may include, predicting, by the computing device, a future brown out event in the electrical grid based on the patterns of the brown-out events.
[0006] In accordance with another aspect, a system may be provided. The system may include a non-transitory memory device for storing computer-readable program code, and a processor in communication with the memory device. The processor may be operative with the computer-readable program code to perform operations. For example, the system may be implemented as one or more computer systems. The operations may include receiving an input data, which may include a historical data of black-out events in an electrical grid. The operations may further include determining, using one or more machine learning models, patterns of black-out events in the electrical grid based on the input data. The operations may further include predicting a future black-out event in the electrical grid based on the patterns of the black-out events. The operations may further include outputting prediction data of the future black-out event in the electrical grid. In some embodiments, the input data may include historical data of brown-out events. The operations may further include determining patterns of brown-out events in the electrical grid based on the input data. The operations may include predicting a future brown-out event in the electrical grid based on the patterns of the brown-out events. [0007] With these and other advantages and features that will become hereinafter apparent, further information may be obtained by reference to the following detailed description and appended claims, and to the figures attached hereto.
BRIEF DESCRIPTION OF THE DRAWINGS
[0008] In the following description, various embodiments of the present disclosure are described with reference to the following drawings, in which:
[0009] Fig .1 is a block diagram illustrating an exemplary environment;
[0010] Fig. 2 shows an exemplary architecture of a plant control system; and
[0011] Fig. 3 shows an exemplary process for predicting one or more future black-out and/or brown-out events.
DETAILED DESCRIPTION
[0012] In the following description, for purposes of explanation, specific numbers, materials and configurations are set forth in order to provide a thorough understanding of the present frameworks. However, it will be apparent to one skilled in the art that the present frameworks may be practiced without the specific exemplary details. In other instances, well-known features are omitted or simplified to clarify the description of the exemplary implementations of the present framework and methods, and to thereby better explain the present framework and methods. Furthermore, for ease of understanding, certain method steps are delineated as separate steps; however, these separately delineated steps should not be construed as necessarily order dependent in their performance.
[0013] As used herein, the term“and/or” includes any and all combinations of one or more of the associated listed items.
[0014] A framework for controlling or managing power supply in a microgrid is described herein. A microgrid, for example, may be set-up to manage and provide electricity to a residential, commercial, and/or industrial customers. In accordance with one aspect, the framework predicts power irregularity in a power system or electrical grid. The power irregularity may include one or more future black-out and/or brown-out events (events may also be named occurrences) in the electrical grid. For example, the one or more future black-out and/or brown-out events may be the next black-out and/or brown-out events. The electrical grid may be connected to the microgrid. The electrical grid, for example, may be one of the input or sources of power of the microgrid. A black-out (also named as power outage, grid failure, power cut, power black-out, or power failure), for example, may be a short-term or a long-term loss of the electric power to a particular area. A brown-out (also named grid voltage reduction), for example, may be an intentional or unintentional drop in voltage in an electrical grid. For example, intentional brown-outs may be used for load reduction in an emergency. The reduction lasts for minutes or hours, as opposed to short-term voltage sag (or dip).
[0015] In one embodiment, the framework receives input data, which include historical data of black-out and/or brown-out events which have occurred in the electrical grid. For example, the framework receives the historical data of black-out and brown-out events over a predefined time interval. The framework may include machine learning models or algorithms to determine patterns of the black-out and/or brown-out events in the electrical grid based on the historical data. The framework may predict one or more next black-out and/or brown-out occurrences in the electrical grid based on the patterns of the black out and/or brown-out events which patterns are determined from the historical data. The framework may output prediction data of one or more black-out and/or brown-out occurrences in the electrical grid. Real-time or new data of black-out and brown-out events may be continuously captured to train the machine learning models and improve accuracy of the machine learning models.
[0016] In some embodiments, the framework may receive grid parameters of the electrical grid as well as weather parameters that include weather information and seasonal information. Additionally, the framework may receive occasion information such as festivals and other special events occurring in the vicinity of the electrical grid or area encompassed by the electrical grid. In one embodiment, the framework may predict one or more next black-out and/or brown-out events based on the grid parameters, weather information, seasonal information and/or occasion information using the machine learning models. In some embodiments, the framework may predict one or more next black-out and/or brown-out events based on the historical data of black-out and/or brown-out events, the grid parameters as well as using weather information, seasonal information and occasion information. In some cases, the framework may receive user input of information regarding scheduled maintenance at the grid. Such information may also be used to predict one or more next black-out and/or brown-out events in the electrical grid. [0017] As described, the input data may include historical data of the black-out events. In some embodiments, patterns of black-out events in the electrical grid may be determined by a computing device using one or more machine learning models based at least in part on the historical data of the black-out events, and may further include other data, for example, historical data of the brown-out events.
[0018] The input data may include historical data of the brown-out events. In some embodiments, patterns of brown-out events in the electrical grid may be determined by a computing device using one or more machine learning models based at least in part on the historical data of the brown-out events, and may further include other data, for example, historical data of the black-out events.
[0019] The input data may include grid parameters of the electrical grid. In some embodiments, patterns of the black-out events and/or brown-out events in the electrical grid may be determined by the computing device using one or more machine learning models based on the grid parameters. In one embodiment, patterns of the black-out events and/or brown-out events in the electrical grid may be determined by the computing device using one or more machine learning models based on the historical data of the black-out and/or brown-out events and the grid parameters.
[0020] The input data may include weather and seasonal information. In some embodiments, patterns of the black-out events and/or brown-out events in the electrical grid may be determined by the computing device using one or more machine learning models based on the weather and seasonal information. In one embodiment, patterns of the black-out events and/or brown-out events in the electrical grid may be determined by a computing device using one or more machine learning models based on the grid parameters and the weather and seasonal information. In one embodiment, patterns of the black-out events and/or brown-out events in the electrical grid may be determined by the computing device using one or more machine learning models based on the historical data of the black-out and/or brown-out events and the grid parameters, weather and seasonal information.
[0021] In some embodiments, the computing device receives user input, which includes information of a scheduled maintenance of a grid infrastructure. Patterns of the black out events and/or brown-out events in the electrical grid may be further determined based on the user input. [0022] A prediction output data may be employed to control and manage efficient operation of power sources and loads in the microgrid which is connected to the electrical grid. For example, output data of the prediction of the next black-out and brown-out events may be used to efficiently operate and control power sources and storage devices as well as manage demand response by residential, commercial and/or industrial customers. The framework advantageously facilitates controlling and managing power supply in the microgrid. This allows for resilient and reliable power supply in the microgrid.
[0023] It should be appreciated that the framework described herein may be implemented as a method, a computer-controlled apparatus, a computer process, a computing system, or as an article of manufacture such as a computer-usable medium. These and various other features and advantages will be apparent from the following description.
[0024] FIG. 1 shows a simplified diagram of an exemplary environment or architecture 100. Environment 100 may have a distributed architecture. The environment, in one embodiment, may include a microgrid and a power system or electrical grid 130. The environment 100, for example, facilitates power irregularity prediction. For example, the environment facilitates predicting one or more next black-out and/or brown-out occurrences in the electrical grid. In one embodiment, the environment includes a communication network 105. The communication network may be, for example, the internet. Other types of communication networks or combination of networks may also be useful. The environment includes a plurality of servers and one or more client or user devices 1 10a-b coupled to the communication network.
[0025] A server may include one or more computers. A computer includes a memory and a processor. Various types of computers may be employed for the server. For example, the computer may be a mainframe, a workstation as well as other types of processing devices. The memory of a computer may include any memory or database module. The memory may be volatile or non-volatile types of non-transitory computer-readable media such as magnetic media, optical media, random access memory (RAM), read-only memory (ROM), removable media, or any other suitable local or remote memory component.
[0026] In the case where the server includes more than one computer, they are connected through the communication network such as an internet, intranet, local area network (LAN), wide area network (WAN), internet or a combination thereof. The servers, for example, may be part of the same private network. The servers may be located in single or multiple locations. Other configurations of servers may also be useful. For example, the servers may form a cloud.
[0027] As for the client or user devices, they may be any computing devices. A computing device, for example, includes a local memory and a processor. The computing device may further include a display. The display may serve as an input and output component of the user device. The memory may be volatile or non-volatile types of non-transitory computer-readable media such as magnetic media, optical media, RAM, ROM, removable media, or any other suitable memory component. Various types of processing devices may serve as user devices. For example, the user devices may include a personal computer, or a mobile client device such as a smart phone. Other types of user devices, such as laptops or tablets may also be useful.
[0028] A user may connect to a server using a user device. The user device may be referred to as the client side while the server may be referred to as the server side. A user may access the server by logging in the user’s respective account with, for example, a password using a user device. A user may communicate with the server via a user interface (Ul) on the user device.
[0029] According to various embodiments, the environment may include a plant control system (or controller) 120. The plant control system, for example, may reside on a server. Alternatively, the plant control system may reside on a plurality of servers. For example, the server or plurality of servers may reside in a cloud. The plant control system may manage or control power supply(ies) in the microgrid. For example, the plant control system may facilitate supply of power to the microgrid in the event of black-out or brown out in the electrical grid.
[0030] According to various embodiments, the plant control system 120 may be in communication with the electrical grid 130 and the microgrid. The electrical grid, for example, may include generating stations that produce electrical power, high voltage transmission lines that carry power from distant sources to demand centers and distribution lines that connect individual customers. For example, the electrical grid may encompass a network of areas. As for the microgrid, it may be connected to the electrical grid. For example, the electrical grid may be one of the sources of power to the microgrid. The microgrid encompasses a defined area. According to various embodiments, the microgrid may include one or more power sources 140a-b, one or more storage devices 150 and a plurality of loads 160a-c. The power sources 140a-b, for example, may include engine-generators such as diesel generators, and renewable energy sources such as solar photo-voltaic modules, wind turbines and fuel cells. The storage devices, for example, may include batteries. The plurality of loads, for example, may include electrical demand by various equipments or components at the premises of commercial, industrial and/or residential customers. Other types of power sources, storage devices and loads in the microgrid may also be useful.
[0031] In some embodiments, the environment may include a data source 170. The data source, in some embodiments, may be a repository containing information acquired from the electrical grid. For example, historical data including previous black-out and brown out events which have occurred in the electrical grid may be retrieved and stored in the data source. In some cases, information of the electrical grid such as grid parameters, time, weather information, seasonal information, and occasion information related to the electrical grid may be retrieved and stored in the data source. For example, the grid parameters, time, weather information, seasonal information, and occasion information may be stored to draw inferences and correlations of patterns of black-out and/or brown out events occurring in the electrical grid.
[0032] Fig. 2 shows an exemplary architecture 200 of an embodiment of the controller 120. In one embodiment, the controller includes a data acquisition module 210, a preprocessor 220, a database 230, a machine learning module 240, a distributed generation module 250 and a demand response module 260. Providing the controller with other components may also be useful. The various components may reside on one or more servers. For example, the components may reside on different servers or on the same server. Other configurations of the components may also be useful.
[0033] In one embodiment, the data acquisition module 210 receives input data. The input data, in one embodiment, includes historical data of black-out and/or brown-out events 270 which have occurred in the electrical grid. For example, the previous black out and brown-out events may occur in a plurality of areas encompassed by the electrical grid. Such black-out and brown-out events may have occurred, for example, at generating stations, voltage transmission lines, and distribution lines.
[0034] The data acquisition module may obtain the historical data of the black-out and brown-out events over a predefined time interval. The time interval, for example, may be predefined by a user. For example, the data acquisition module may continuously obtain the historical data of the previous black-out and brown-out events over a time period of two years. In other implementations, the time interval may be four months. Other time intervals for continuously obtaining the historical data of black-out and brown-out events occurring in the power system may also be useful.
[0035] The historical data of the previous black-out and brown-out events includes information such as, for example, a unique identifier identifying each black-out or brown out event, duration of the black-out and/or brown-out events, day of occurrence, start time and end time, location of occurrence, geographical area (e.g., extent of black-out or brown-out), planned or unplanned (e.g., intentional shut down of station), demand or load at the affected area, weather information, seasonal information, as well as occasion information related to the area where the black-out and/or brown-out events occurred, cause of black-out and/or brown-out events (e.g., utility failure to component failures within power infrastructure, weather, natural disasters, installation design issues).
[0036] According to various embodiments, the input data additionally may include real time data of black-out and/or brown-out events 272 in the electrical grid. For example, real-time data of one or more black-out and/or brown-out events occurring in the electrical grid may be obtained by the acquisition module. The real-time data of one or more black-out and/or brown-out events may be used for training and continuous learning by machine learning models in the controller 120.
[0037] According to various embodiments, the input data may include grid parameters of the electrical grid 274 and weather parameters 276. The grid parameters of the electrical grid, for example, may include voltage amplitude, phase and/or frequency of the voltage, time of the day on which the grid parameters are obtained or recorded. As for the weather parameters, it may include weather information (e.g., temperature, wind speed, precipitation) and seasonal information related to the electrical grid, for example, at the time the black-out and/or brown-out events occur at the electrical grid.
[0038] The data acquisition module may receive the input data from an external data source such as data source 170 as described with respect to Fig. 1 . Alternatively, the data acquisition module may directly monitor and acquire the input data such as the historical data of black-out and/or brown-out events in the electrical grid as it occurs over the predefined time interval. Additionally, the data acquisition module may continuously acquire the grid and weather parameters as well as real-time data of one or more black- out and/or brown-out events in the electrical grid as it occurs. The input data, for example, may be collected using sensor devices and data loggers or micro-processors connected to sensors. For example, the input data may be collected using sensor devices such as one or more of voltage sensors, current sensors, power and phasor measurement sensors, temperature sensors, humidity sensors and wind speed sensors and weather stations. The sensor devices, for example, may be positioned at various locations of the electrical grid such as the generating stations, transmission lines and distribution lines. Other configurations for obtaining the input data may also be useful.
[0039] The preprocessor, in one embodiment, preprocess the input data and stores data entries (or records) in the database. For example, the preprocessor preprocesses the historical data of the black-out and/or brown-out events. For example, each data entry represents an occurrence or instance of a black-out event or brown-out event in the electrical grid.
[0040] In one embodiment, the preprocessor preprocesses the input data to categorize the data. For example, the preprocessor preprocesses the input data collected using the various sensor devices such as a voltage sensor, current sensor, power and phasor measurement sensor, temperature sensor, humidity sensor and wind speed sensor and/or weather station. The input data may be stored in an array format with respect to time and prepossessed to eliminate noise. In addition, data normalization may be performed. According to some embodiments, input data such as seasonal information and occasion information may be stored. For example, occasions such as festivals and other special events may lead to increase in load on the electrical grid. A black-out event may be determined based on the voltage characteristics such as a voltage drop to zero or near zero. A brown-out event, for example, may be determined based on a voltage reduction of more than 10%. Additionally, frequency-deviations may be recorded and stored in the database.
[0041] In one embodiment, the database may be a repository which contains the historical data of the black-out and/or brown-out events in the electrical grid. For example, the database stores the historical data of the previous black-out and brown-out events received by the data acquisition module. The historical data, for example, is stored in the database for processing by the machine learning module. Additionally, the database may store the real-time data of black-out and brown-out events in the electrical grid. In some embodiments, the database may store the grid and weather parameters for processing by the machine learning module. Additionally or alternatively, the input data may be directly retrieved from the external data source for processing by the machine learning module. For example, the machine learning module may directly receive input data such as the historical data, real-time data, and/or grid and weather parameters as well as occasion information from the external data source.
[0042] According to various embodiments, the database may contain one or more machine learning models or algorithms. The machine learning models may be used by the machine learning module to determine patterns of black-out and brown-out events in the electrical grid based on the historical data of the black-out and brown-out events. In some embodiments, the machine learning models may be semi-supervised learning models. Exemplary models include, but are not limited to, artificial neural networks, genetic algorithms, random forests, other stochastic methods, or a combination thereof. Other types of models may also be useful. A semi-supervised learning model may be trained using supervised learning techniques.
[0043] The machine learning module, in accordance with various embodiments, may determine patterns of black-out and brown-out events in the electrical grid based on the historical data of the black-out and brown-out events. The machine learning module may use one or more of the machine learning models to determine patterns of previous black out and brown-out events in the electrical grid. In one embodiment, the machine learning module uses a long short term memory method to determine the patterns of previous black-out and brown-out events. In addition, the long short term memory method may be augmented with a rule-based approach to improve the accuracy of the prediction. The machine learning module predicts one or more next black-out and/or brown-out events in the electrical grid based on the patterns of previous black-out and brown-out events. Rule-based methods add additional information about events for which specific pattern does not exist in historical/training data.
[0044] The machine learning module may use the machine learning models to determine patterns of previous black-out and brown-out events in the electrical grid based on the historical data of the black-out and/or brown-out events. For example, the black-out and/or brown-out events include information such as the duration of the black-out and/or brown-out events, day of occurrence, start time and end time, location of occurrence, geographical area (e.g., extent of black-out or brown-out), planned or unplanned (e.g., intentional shut down of station), demand or load at the affected area, weather information related to the area where the black-out or brown-out event occurred, cause of black-out or brown-out (e.g., utility failure to component failures within power infrastructure, weather conditions, natural disasters, overloading of substation assets/components, high peak loading of the overall grid, scheduled and unscheduled maintenance). For example, in a planned shut-down, substation operators may intentionally shut down power due to weather conditions in order to avoid accidents and failures. In the case of high peak loading of the overall grid, some areas may be shut down to reduce overall load. In such cases, power of different areas is shut down at different times of the day/week in a regular pattern. The machine learning module uses such information to determine patterns of the previous black-out and brown-out events in the electrical grid. For example, the machine learning module further determines a pattern of power shut down at different areas at different times (e.g., of the day or week).
[0045] Additionally, the machine learning module may evaluate the historical data of the black-out and brown-out events in the electrical grid based on time periods such as months, days, and hours to determine patterns for the occurrences of the black-out and brown-out events.
[0046] According to various embodiments, the machine learning module, may output prediction data 280 of the prediction of one or more next black-out and/or brown-out events in the electrical grid. The prediction output data may include information of the one or more possible next black-out and/or brown-out events. For example, the prediction output data may include black-out or brown-event, day, time and duration for the next black-out or brown-out event, likelihood, probability, or confidence interval of the occurrence, location, affected area, historical frequency.
[0047] According to various embodiments, the prediction output data may be used to continuously train the machine learning models and improve the accuracy of the machine learning models for determining patterns of the power outage as well as predicting a next power outage event.
[0048] According to various embodiments, the machine learning module may receive the real-time data of one or more black-out and brown-out events occurring in the electrical grid and may compare the real-time data to the prediction output data. For example, the machine learning module may use the real-time data of the black-out and brown-out events and the prediction output data of the prediction of one or more next black-out and/or brown-out events as training data to continuously train the machine learning models. For example, the output data of a prediction of the one or more next black-out and/or brown-out events may be compared with real-time data of black-out and/or brown out events to determine whether the prediction is correct or accurate. The determination is used to train the machine learning models in the database. For example, the machine learning models or algorithms may be configured such that in a continuous process, new data may be recorded and used to improve the accuracy of the algorithm. This enables continuous learning by the machine learning models, further improving subsequent predictions of black-out and brown-out events in the electrical grid.
[0049] According to various embodiments, the machine learning module may use the grid parameters to predict one or more next black-out and brown-out events. For example, the machine learning module receives the grid parameters from the external data source. The machine learning module may monitor the grid parameters of the electrical grid. The machine learning module further determines the patterns of black-out and/or brown-out events in the electrical grid based on the the grid parameters of the electrical grid. For example, the machine learning module determines deviation in the grid parameters of the power system. The deviation in the grid parameters, for example, may include voltage and frequency deviations. The voltage and frequency deviations may be used to predict failures in the electrical grid. For example, serious overloading of the electrical grid which leads to local reduction of voltage may be used as an indicator of a possible tripping of power as a response by a protection system to avoid damage to the infrastructure. Additionally, if overall grid is overloaded, frequency of the grid drops which leads to overall grid failure.
[0050] Additionally, the machine learning module may use the weather parameters and occasion information to predict the next black-out and/or brown-out events in the electrical grid. The weather parameters may include weather and seasonal information at areas encompassed by the electrical grid. For example, severe weather pattern (e.g., heavy wind, rain) affects the overhead transmission and distribution lines in an electrical grid. For example, substation operators may resort to turning off the power of an affected area to protect the system from short circuit (e.g., due to heavy wind overhead transmission/distribution lines (wires) may mechanically touch each other). Further, substation operators may also turns off the power as a safety precaution in severe weather conditions (e.g., due to poor infrastructure severe weather conditions may lead to damage (breakage) of the electricity poles and distribution lines). Further, due to seasons (e.g., winter) and occasions (e.g., festivals and special events), there may be an increase in load on the electrical grid. Another example of seasonal effect is during summer months where electricity demand increases whereas production from hydro electric power plants reduces which leads to shortage of power and thus black-out. Such information may be used to predict one or more next black-out and/or brown-out events in the electrical grid. For example, the machine learning module further determines the patterns of black-out and/or brown-out events in the electrical grid based on the weather information, seasonal information and/or occasion information.
[0051] According to various embodiments, the machine learning module may receive user input 278 and may incorporate the user input in the prediction of the one or more next black-out and/or brown-out events. The user input, for example, may include information such as scheduled maintenance of a grid infrastructure. For example, a user interface at the user device may enable the user to enter the relevant information regarding the scheduled maintenance of the grid infrastructure. The information regarding the scheduled maintenance of the grid infrastructure, for example, provides the controller with information of a planned power cut in an area encompassed by the electrical grid. The user input may be provided by a user using a user device. The machine learning module may incorporate the information regarding the scheduled maintenance to improve the accuracy of prediction of the one or more next black-out and/or brown-out event. For example, the machine learning module further determines the patterns of black-out and/or brown-out events in the electrical grid based on user input of a planned power cut. The machine learning module may determine patterns of black-out and/or brown-out events based on inferences and correlations using the grid parameters, weather information, time, seasonal information, and occasion information.
[0052] The prediction output data, for example, may be displayed on one or more user devices for analysis by a user. Since the electrical grid is one of the source for the microgrid, a black-out event or brown-out event in the electrical grid affects operation of the microgrid. Accordingly, prediction of black-out and/or brown-out events may be used to manage the operations of the microgrid. In some embodiments, the controller may use the prediction output data to manage the microgrid. For example, the plant control system uses the prediction of the next black-out and/or brown-out events to control one or more of the power sources such as one or more diesel generators and solar photo voltaic modules and one or more storage devices in order to handle one or more of the next black-out and brown-out events. For example, the distributed generation module 250 controls power supply to one or more loads in the microgrid using the diesel generators and solar photo-voltaic modules based on the prediction of one or more next black-out and brown-out events. Additionally, the demand response module 260 may use the prediction output data to manage demand response for power supply to the loads in the in the microgrid.
[0053] Fig. 3 shows an exemplary process 300 for predicting one or more future black out and/or brown-out events. For example, the controller 120 as described in Figs. 1 -2 predicts one or more black-out and/or brown-out events in the electrical grid 120.
[0054] At 310, the controller receives input data. The input data includes historical data of black-out events in the electrical grid. According to some embodiments, the input data includes historical data of brown-out events in the electrical grid. According to some embodiments, the input data includes grid parameters of the electrical grid, weather information, seasonal information and/or occasion information. According to some embodiments, the input data includes user input. For example, the user input includes information of a scheduled maintenance of a grid infrastructure.
[0055] At 320, the controller determines, using one or more machine learning models, patterns of black-out events in the electrical grid based at least in part on the historical data of the black-out events. Additionally or alternatively, the controller determines patterns of brown-out events in the electrical grid based at least in part on the historical data of the brown-out events. According to some embodiments, the controller determines patterns of black-out events and/or brown-out events in the electrical grid based on the grid parameters, weather information, seasonal information, occasion information and/or the user input. According to some embodiments, the controller determines patterns of black-out events and/or brown-out events in the electrical grid based on the historical data of the black-out/brown-out events, grid parameters, weather information, seasonal information, occasion information and/or the user input. In one embodiment, the one or more machine learning models may include a long short term memory method which is used to determine the patterns of previous black-out and brown-out events. In addition, the long short term memory method may be augmented with a rule-based approach to improve the accuracy of the prediction.
[0056] At 330, the controller predicts a future black-out event in the electrical grid based at least in part on the patterns of the black-out events. Additionally or alternatively, the controller predicts a future brown-out event in the electrical grid based at least in part on the patterns of the brown-out events.
[0057] At 340, the controller outputs prediction data of a future black-out event in the electrical grid. Additionally or alternatively, the controller outputs prediction data of a future brown-out event in the electrical grid. The output prediction data of one or more of the future black-out events and/or brown-out events may be used to control a microgrid. For example, the electrical grid may be connected to the microgrid. The controller may control one or more power sources, one or more storage devices and/or demand response of the microgrid based on the prediction data. According to some embodiments, the controller may train the one or more machine learning models using the prediction data.
[0058] Although the one or more above-described implementations have been described in language specific to structural features and/or methodological steps, it is to be understood that other implementations may be practiced without the specific features or steps described. Rather, the specific features and steps are disclosed as preferred forms of one or more implementations.

Claims

1. A computer-implemented method for power irregularity prediction, comprising: receiving, by a computing device, an input data comprising a historical data of black out events in an electrical grid;
determining, by the computing device using one or more machine learning models, patterns of black-out events in the electrical grid based on the input data;
predicting, by the computing device, a future black-out event in the electrical grid based at least in part on the patterns of the black-out events; and
outputting, by the computing device, prediction data of the future black-out event in the electrical grid.
2. The method of claim 1 , wherein the input data further comprises historical data of brown-out events.
3. The method of claim 2, further comprising determining, by the computing device using the one or more machine learning models, patterns of brown-out events in the electrical grid based on the input data.
4. The method of claim 3, further comprising predicting a future brown-out event in the electrical grid based on the patterns of the brown-out events.
5. The method of any of claims 1 to 4, wherein the input data further comprises grid parameters of the electrical grid.
6. The method of any of claims 1 to 5, wherein the input data further comprises weather and seasonal information.
7. The method of any of claims 1 to 6, further comprising receiving, by the computing device, user input, wherein the user input comprises information of a scheduled maintenance of a grid infrastructure.
8. The method of any of the previous claims, further comprising controlling, by the computing device, one or more power sources and one or more storage devices of a microgrid based on the prediction data.
9. The method of any of the previous claims, further comprising training the one or more machine learning models using the prediction data.
10. A computer program for power irregularity prediction, wherein the computer program is configured to carry out the steps of the method according to any one of claims 1 to 9 when run on a computer.
1 1 . A non-transitory computer-readable storage medium on which the computer program of claim 10 is stored.
12. A system, comprising:
a non-transitory memory device for storing computer-readable program code; and a processor in communication with the memory device, the processor being operative with the computer-readable program code to perform operations comprising
receiving an input data comprising a historical data of black-out events in an electrical grid,
determining, using one or more machine learning models, patterns of black-out events in the electrical grid based on the input data,
predicting a future black-out event in the electrical grid based on the patterns of the black-out events, and
outputting, by the computing device, prediction data of the future black-out event in the electrical grid.
13. The system of claim 12, wherein the input data further comprises historical data of brown-out events.
14. The system of claim 13, further comprising determining, by the computing device using the one or more machine learning models, patterns of brown-out events in the electrical grid based on the input data.
15. The system of claim 14, further comprising predicting a future brown-out event in the electrical grid based on the patterns of the brown-out events.
16. The system of any of claims 12 to 15, wherein the input data further comprises grid parameters of the electrical grid.
17. The system of any of claims 12 to 16, wherein the input data further comprises weather and seasonal information.
PCT/EP2018/086079 2018-12-20 2018-12-20 System and method for power outage prediction WO2020125984A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/EP2018/086079 WO2020125984A1 (en) 2018-12-20 2018-12-20 System and method for power outage prediction

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/EP2018/086079 WO2020125984A1 (en) 2018-12-20 2018-12-20 System and method for power outage prediction

Publications (1)

Publication Number Publication Date
WO2020125984A1 true WO2020125984A1 (en) 2020-06-25

Family

ID=64900932

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2018/086079 WO2020125984A1 (en) 2018-12-20 2018-12-20 System and method for power outage prediction

Country Status (1)

Country Link
WO (1) WO2020125984A1 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114740282A (en) * 2022-01-21 2022-07-12 国网江苏省电力有限公司常州供电分公司 Method and system for identifying power failure event of low-voltage line
GB2586435B (en) * 2019-04-05 2023-12-27 Orxa Grid Ltd Electrical grid monitoring system

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130006903A1 (en) * 2011-06-29 2013-01-03 Infosys Limited System and method for predictive analytics in an electrical grid network
US20130191052A1 (en) * 2012-01-23 2013-07-25 Steven J. Fernandez Real-time simulation of power grid disruption
WO2015145784A1 (en) * 2014-03-27 2015-10-01 Nec Corporation Energy management method and system for energy supply system
WO2016007567A1 (en) * 2014-07-11 2016-01-14 Microsoft Technology Licensing, Llc Server installation as a grid condition sensor
EP3009801A1 (en) * 2014-09-17 2016-04-20 Kabushiki Kaisha Toshiba Failure sign diagnosis system of electrical power grid and method thereof
WO2016144357A1 (en) * 2015-03-12 2016-09-15 Hewlett Packard Enterprise Development Lp Power distribution plan
US20160291067A1 (en) * 2015-03-31 2016-10-06 Enernoc, Inc. Apparatus and method for fine-grained weather normalization of energy consumption baseline data

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20130006903A1 (en) * 2011-06-29 2013-01-03 Infosys Limited System and method for predictive analytics in an electrical grid network
US20130191052A1 (en) * 2012-01-23 2013-07-25 Steven J. Fernandez Real-time simulation of power grid disruption
WO2015145784A1 (en) * 2014-03-27 2015-10-01 Nec Corporation Energy management method and system for energy supply system
WO2016007567A1 (en) * 2014-07-11 2016-01-14 Microsoft Technology Licensing, Llc Server installation as a grid condition sensor
EP3009801A1 (en) * 2014-09-17 2016-04-20 Kabushiki Kaisha Toshiba Failure sign diagnosis system of electrical power grid and method thereof
WO2016144357A1 (en) * 2015-03-12 2016-09-15 Hewlett Packard Enterprise Development Lp Power distribution plan
US20160291067A1 (en) * 2015-03-31 2016-10-06 Enernoc, Inc. Apparatus and method for fine-grained weather normalization of energy consumption baseline data

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GB2586435B (en) * 2019-04-05 2023-12-27 Orxa Grid Ltd Electrical grid monitoring system
CN114740282A (en) * 2022-01-21 2022-07-12 国网江苏省电力有限公司常州供电分公司 Method and system for identifying power failure event of low-voltage line
CN114740282B (en) * 2022-01-21 2023-10-27 国网江苏省电力有限公司常州供电分公司 Identification method and system for low-voltage line power failure event

Similar Documents

Publication Publication Date Title
JP7118282B2 (en) Systems, methods, and computer program products for configuring microgrids
US10261536B2 (en) Systems and methods for optimizing microgrid power generation and management with predictive modeling
US10437209B2 (en) Solar tracker and related methods, devices, and systems
US9225173B2 (en) Systems and methods for microgrid power generation and management
CN102902245B (en) Intelligent monitoring system of photovoltaic power station
US10169832B2 (en) Method and instrumentation for sustainable energy load flow management system performing as resilient adaptive microgrid system
Li et al. Edge-cloud computing systems for smart grid: state-of-the-art, architecture, and applications
Hatziargyriou et al. Energy management and control of island power systems with increased penetration from renewable sources
JP6069738B2 (en) Charge / discharge control system, charge / discharge control method, and charge / discharge control program
WO2020125984A1 (en) System and method for power outage prediction
Koh et al. Reliability evaluation of electric power systems with solar photovoltaic & energy storage
CN106849064B (en) Regional power grid load prediction management system based on meteorological data
CN118263983A (en) Micro-network management system and method based on intelligent park
US20210351612A1 (en) Solar inverter power output communications methods, and related computer program products
US20220284156A1 (en) Real-time update of power system models for dynamic security assessment
Borra et al. Dynamic programming for solving unit commitment and security problems in microgrid systems
US20240097446A1 (en) Severe weather-driven large-scale outage management for emergency power grid
Chiacchio et al. Performance assessment of domestic photovoltaic power plant with a storage system
Amelete et al. Maintenance optimisation using intelligent asset management in electricity distribution companies
Onaolapo Reliability study under the smart grid paradigm using computational intelligent techniques and renewable energy sources.
Popov et al. Stochastic model for microgrid load forecasting
Olsina et al. Optimization of spinning reserve in stand-alone wind-diesel power systems
Hatziargyriou et al. More Care overview
Biswas et al. Renewable Energy Integration with Existing Grid using Battery Energy Storage and Machine Learning Applications
CN110875634A (en) Island microgrid information management system

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18826651

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18826651

Country of ref document: EP

Kind code of ref document: A1