Power grid management

Abstract

The method comprises the steps of: - collecting (510) datasets from various sources, said datasets including real-time data and / or historical data and being relevant to the power grid management; - generating (540) a computer-based model that virtually represents the power grid, based on the collected datasets; - simulating (550) how the power grid operates under various conditions and / or operational scenarios using the computer-based model; - managing (560) the power grid based on simulation results; wherein the method further includes a step (516) of determining a user category among a plurality of predetermined user categories, and the computer-based model is adapted to the determined user category.

Description

Power Grid ManagementTECHNICAL FIELD

[0001] The present disclosure relates to the field of power systems, specifically to power grid management.BACKGROUND

[0002] A power grid, also known as an electrical grid, is a network of synchronized elements that deliver electricity from producers (such as power stations) to consumers like homes, businesses, and public services. The primary goal of a power grid is to generate, transmit, and distribute electricity efficiently and reliably across various geographical regions.

[0003] Components of a power grid include:- power generation stations, that are facilities where electricity is produced. They can include various types of plants such as thermal (coal, natural gas, nuclear), hydroelectric, solar, wind, and other renewable energy sources. The choice of generation type can depend on geographic, economic, and environmental factors;- high-voltage transmission lines that carry electricity over long distances from power plants to substations. These lines are an integral part of the grid because they minimize the energy lost in transmitting electricity over great distances;- substations, that are installations where the high voltage from transmission lines is stepped down to a lower voltage suitable for distribution to consumers. They play a critical role in managing the flow of electricity within the grid and ensuring that it is delivered safely and efficiently;- distribution lines, that are networks of lower voltage lines that deliver electricity from substations to consumers. Distribution lines are more ubiquitous than transmission lines and are typically seen running along streets and into homes and businesses;- transformers, that adjust voltage levels to ensure that electricity is transmitted efficiently and safely. They increase (step up) or decrease (step down) voltageas necessary to accommodate different stages of the electricity distribution process;- control systems, also called grid control centers, that monitor and control the electrical system to ensure balance between electricity production and consumption, maintaining reliability and preventing outages. They use advanced communication technology to manage grid operations in real-time;- smart meters and sensors of various types, that are used throughout the grid to collect data on electricity usage, voltage levels, current flows, and other operational metrics. This data is crucial for efficient grid management, billing, and in implementing smart grid technologies;- energy storage systems, such as battery storage facilities, that help in managing the supply and demand of electricity by storing excess electricity and releasing it when demand exceeds generation. They are especially important in grids with a high proportion of renewable energy sources, which can be intermittent.

[0004] The power grid is an essential infrastructure, and its reliability and efficiency are crucial to the functioning of modem society, supporting sectors such as industry, transportation, communication, health, and education.

[0005] Nowadays, power grids face challenges such as adapting to a higher proportion of renewable energy sources, ensuring consistent reliability and security, reducing transmission losses, and responding to environmental and regulatory changes. The complexity of managing and optimizing grid performance necessitates innovative solutions that can enhance grid resilience and enable more decentralized and participatory energy systems.

[0006] Current methods for grid management face several difficulties. The handling of large volumes of data for analytical purposes is a resourceintensive task that requires significant preprocessing, often necessitating the expertise of specialized professionals. Additionally, the need for dynamic interaction with advanced analytical platforms introduces complexities, including the need for real-time adjustment of parameters based on varyinguser inputs and the translation of complex interactions into actionable data. These challenges highlight the need for a system that can dynamically process and utilize information, adapt to user interactions, and continuously improve analytical mechanisms and customization for various stakeholders.SUMMARY

[0007] The present disclosure concerns a computer-implemented method for power grid management, said method comprising the steps of:- collecting datasets from various sources, said datasets including real-time data and / or historical data and being relevant to the power grid management;- generating a computer-based model that virtually represents the power grid, based on the collected datasets;- simulating how the power grid operates under various conditions and / or operational scenarios using the computer-based model;- managing the power grid based on simulation results; wherein the method further includes a step of determining a user category among a plurality of predetermined user categories, and the computer-based model is adapted to the determined user category.

[0008] The computer-based or digital model is adapted or specific to a given user category. Thanks to that, this model provides a dynamic and adaptable tool for power grid management to enhance the efficiency and organization of the power grid system.

[0009] In an embodiment, the method may further comprise a step of determining a grid stage from a plurality of predetermined grid stages corresponding to different development phases of the power grid, wherein the computer-based model is adapted to the determined grid stage

[0010] The computer-based or digital model can adapt not only to a specific category or type of user but also to a specific development or lifecycle stage of the power grid PWG (e.g., planning or pre-building, building, operating, and / ormaintenance stage). Thanks to that, this model provides a dynamic and adaptable tool for enhancing power grid management.

[0011] In an embodiment, the method may comprise a step of data integration based on the determined user category and / or grid stage. This step of data integration could include categorizing and prioritizing the collected datasets. Alternatively or additionally, it could include:- a first step of data adjustment that includes generating missing data points within the collected datasets; and / or- a second step of data adjustment that includes identifying datasets collected from various sources that differ in granularity of the datapoints, and aligning the data points in granularity so that they match a consistent granularity.

[0012] The first and / or second step of data adjustment could be performed with generative Al models.

[0013] In an embodiment, the step of data integration may include weighting the datasets based on one or more factors from the group including a data source reliability, the selected stage, and a proportion of generated data points within the dataset.

[0014] In an embodiment, the step of generating the computer-based model that virtually represents the power grid may include generating a metaverse environment where a plurality of users can interact with each other and / or with the virtual representation of the power grid.

[0015] For example, the step of managing the power grid could include optimizing operation of the power grid by performing at least one of the steps of:- forecasting demand and supply of power within the power grid;- detecting operational anomalies and / or faults within the power grid;- controlling power generation and distribution within the power grid;- evaluating impact of one or more external factors, such as weather conditions, availability of renewable energy sources, and load fluctuations, on the stability and / or efficiency of the power grid.

[0016] Alternatively or additionally, the step of managing the power grid could include a step of predicting a potential failure of at least one component of the power grid, and estimating an amount of time that the component is expected to function before the predicted failure, to schedule a maintenance action before expiration of said amount of time.

[0017] Alternatively or additionally, the step of managing the power grid could include adjusting operational parameters of the power grid.

[0018] Alternatively or additionally, the step of managing the power grid could include detecting vulnerabilities of the power grid.

[0019] The present disclosure also concerns:- a computer program comprising instructions which, when the program is executed by a computer, cause the computer to carry out the steps of the method previously defined; and- a system comprising means for carrying out the steps of the method previously defined.BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Other features, purposes and advantages of the disclosure will become more explicit by means of reading the detailed statement of the non-restrictive embodiments made with reference to the accompanying drawings.

[0021] FIG. 1 illustrates a flow chart diagram outlining the process for managing a power grid using a computer-based model, or digital twin system of the power grid, that virtually represents the power grid, according to an embodiment.

[0022] FIG. 2 illustrates a flow chart diagram outlining a process for data integration for generating the power grid digital twin system, according to an embodiment.

[0023] FIG. 3 illustrates a flow chart diagram representing different operations of managing a power grid system, according to an embodiment.

[0024] FIG. 4 illustrates an example of virtual representation of a power grid in a metaverse environment.DETAILED DESCRIPTION

[0025] The following detailed description describes various features and functions of the disclosed systems and methods with reference to the accompanying figures. In the figures, similar symbols identify similar components, unless context dictates otherwise. The illustrative system, device and method embodiments described herein are not meant to be limiting. It may be readily understood by those skilled in the art that certain aspects of the disclosed systems, devices and methods can be arranged and combined in a wide variety of different configurations, all of which are contemplated herein.

[0026] The present disclosure concerns a system and method designed to enhance the efficiency and organization of a power grid system, or power grid, here referred as “PWG”, through the implementation of a dynamic digital twin system implemented with a computer-based model that virtually, or digitally, represents the power grid PWG. This system utilizes real-world data, including real-time data and / or historical data, to create a comprehensive digital and virtual representation of the power grid PWG. It is dynamic and adaptable, capable of handling complex interactions and data processing demands associated with modern power grid management. In particular, it can adapt to a specific development or lifecycle stage of the power grid PWG (e.g., planning or pre-building, building, operating, and / or maintenance stage), to a specific category or type of user, and / or to a current state of the real-world power grid.

[0027] A computer-based model, in the context of the present disclosure, refers to a digital representation of a power grid system PWG that can be created and used (i.e. , manipulated, executed) by a computer. This model uses real-world data (real-time data and / or historical data), mathematical operations, and algorithms like machine learning algorithms to simulate the dynamics of power generation, transmission, distribution, and consumption within the power gridPWG. In other words, it is a computational simulation that mimics the behavior, operations, and interactions of the electrical power grid PWG under different scenarios or conditions.

[0028] In the present disclosure, the model is adapted or specific to a given user category and / or to a power grid’s development stage, as will be detailed later. This model provides a dynamic and adaptable tool for power grid management to enhance the efficiency and organization of a power grid system PWG.

[0029] FIG. 1 shows a flowchart of a computer-implemented method 500 for power grid management, according to an embodiment. The method 500 may include:- a step 510 of collecting datasets from various sources, followed by data integration at step 520,- determination of a grid stage for simulation at 515;- determination of a user category for simulation at 516;- data storage at step 530;- generating a computer-based model representing the power grid PWG at step 540,- simulating operation of the power grid PWG with the computer-based model at step 550, and- managing the power grid PWG based on simulation results at step 560.

[0030] The steps 510 to 560 may be carried out by a computing device or a computing system.

[0031] At step 510, the method 500 involves collecting datasets including data relevant to the management of the power grid PWG, such as:- electrical parameters: voltage, current, frequency, power flows, etc.- geographic information: locations of generation units, substations, transmission, and distribution lines;- operational data: real-time and historical data on power generation and consumption;- environmental data: weather conditions, which can affect generation (especially renewable sources) and demand.

[0032] The above list of data is only illustrative and non-limitative.

[0033] The collected data can include real-time data and / or historical, or past, data.

[0034] The collected data can be provided by various data sources, and include for example:- data from various components of power grid PWG system, such as power generation stations, substations, control systems, transformers, energy storage systems, etc.;- data from smart meters and / or sensors of various types of the power grid system PWG (e.g., data on electricity usage, voltage levels, current flows, and other operational metrics);- satellite data;- data (e.g., textual and / or graphical data) from information and data repositories like websites, databases, publications, etc.

[0035] The data provided by the power grid components may advantageously include real-time data and optionally historical data. The data from the control system(s) of the power grid PWG may indicate activities, behaviors, actions carried out in the power grid system PWG. This may allow to identify the reason(s) of faults in the power grid PWD for example.

[0036] The smart meter or sensor data may include real-time data and optionally historical data. This may allow to monitor various operational parameters (electricity usage, voltage levels, current flows, etc.) within the power grid PWG.

[0037] The satellite data may include digital images and / or any other type of data captured by a satellite. The satellite data may include real-time data and optionally historical data.. The use of satellite data may allow to enhance the following areas:- Environmental monitoring: satellite images help monitor vegetation near power transmission or distribution lines, predicting potential issues and reducing the risk of power outages caused by overgrown vegetation;- Infrastructure mapping: high-resolution images assist in mapping power grid infrastructure, identifying components and their conditions, and building comprehensive system models within a digital twin system;- Terrain analysis: analyzing terrain with satellite data optimizes the placement of power grid components by understanding geographical topography, improving energy distribution routes and anticipating future challenges;- Energy generation optimization: monitoring weather patterns, solar radiation, and other parameters relevant to renewable energy generation with satellite data optimizes the placement and performance of solar panels and other technologies to enhance renewable energy generation;- Natural disaster response: integrating satellite data enables the digital twin system to respond quickly to natural disasters, such as fires, earthquakes, or floods, by redirecting power flows to minimize disruptions and improve grid resilience to monitor the environment.

[0038] The data from information and data repositories may include historical data, for example about wildfires, earthquakes, solar storms, cyclones, human development, infrastructure development, deforestation, climate, temperature, that is related to a given region where a power grid system PWG is planned to be built or where an existing power grid system PWG is located. As an illustrative and non-limitative example, this type of data may include textual data retrieved from a government public report on deforestation.

[0039] The collection of datasets at step 510 allows to acquire a huge amount of data of different types for the purpose of simulating the power grid PWG. It is a step that provides the foundational information for subsequent steps in the method 500.

[0040] At step 515, the method 500 may determine a development or lifecycle stage of the power grid system PWG for which simulation is requested. Forinstance, this grid development stage could be one among several predetermined stages, which may include the grid planning (pre-building) stage, grid building stage, grid operating stage, and grid maintenance stage.. The development stage may be selected by a user through user interface means. Alternatively, it may be pre-stored in memory and accessed in step 515. This step 515 acknowledges that power grids have various stages of development. By specifying a specific development stage of the power grid lifecycle, the computer-based model can more accurately replicate or represent the current attributes or characteristics of the power grid PWG, which aids in simulating realistic operational scenarios.

[0041] At step 516, the method may determined a role of the user or operator requesting the simulation of the power grid system PWG. For example, the step 516 may include selecting a predetermined role among a plurality of predetermined user roles that may include:- Grid Operator: This role is responsible for the operation and control of the power grid. A grid operator monitors the grid’s performance and adjusts as necessary to ensure stable and efficient operation.- Maintenance Engineer: This role is responsible for the physical upkeep of the power grid infrastructure. A maintenance engineer can use the simulation to plan and schedule maintenance activities.- Regulatory Authority: This role oversees the operation of the power grid to ensure it complies with laws and regulations. A regulator authority can use the simulation to audit the grid’s operation and investigate incidents.- Power Producer: This role generates electricity to supply to the grid. A product producer can use the simulation to optimize their production schedule based on demand forecasts.- Emergency Planner: This role plans for emergency situations that might affect the power grid. An emergency planner might use the simulation to examine their emergency response plans.- Environmental Analyst: This role assesses the environmental impact of the power grid. An environmental analyst might use the simulation to study theeffects of different operational strategies on the environment.The above list is only illustrative and non-limitative.

[0042] The selection may be performed by the user or operator through user interface means. This step 516 aids in customizing or adapting the computer- based model to reflect the requirements and characteristics of different user groups or categories or roles that may interact with the power grid and / or with one another. The determination of a user category allows for a more targeted and effective simulation of the power grid's operation.

[0043] The steps 515, 516 provide necessary information to adapt the simulation to the stage of development of the power grid PWG for which simulation is requested and to the user requesting the simulation.

[0044] At 520, the method 500 may integrate the collected datasets. Data integration 520 is necessary for combining datasets from different sources to create a unified and coherent set or collection of data that can be effectively used for modeling and simulation purposes.

[0045] Figure 2 illustrates a process of data integration 520, according to an embodiment. The purpose of data integration is to ensure that data is accurate, consistent and usable for simulations of the power grid system PWG. The data integration may be adapted or specific to the user category and / or the power grid development stage determined in steps 515, 516.

[0046] FIG. 2 shows a flowchart of the process 520 for data integration in the context of power grid management, according an embodiment. The process 520 includes steps of:- data organization 521 ,- missing data generation 522,- data alignment 523,- weighting data 524, and- generating a reliability report 525.

[0047] In an embodiment, the steps of data integration 521 -525 may be performed using generative Al models. These steps may be carried out using LLM (Large Language Model) agents. The LLM agents may perform the different tasks or steps 521 -525 independently

[0048] This process 520 serves as a component of the overall process for managing the power grid, ensuring that the data used for simulation and decision-making is accurate, comprehensive, and appropriately processed.

[0049] At step 521 , the method 520 may organize the collected datasets by categorizing and prioritizing the data. This step 521 involves organizing the datasets into categories and hierarchically based on their relevance and importance to the power grid management tasks in the context of the grid development stage and the user role determined in the steps 515, 516. For example, the categorization may be based on the type of data, while prioritization may depend on the impact of the data on grid's performance, stability and / or any other operational parameters relevant to the selected grid development stage and / or user role. As an illustrative and non-limitative example, if a user wants to simulate the power grid PWG at a planning or prebuilding stage, a high priority may be attributed to historical data of wildfires, earthquakes, solar storms, cyclones, human development, infrastructure development, deforestation, climate, temperature, related to a given area where the power grid PWG is planned to be built.

[0050] Optionally, the step 521 of organizing data may further include analyzing the collected data to determine attributes that may include data type and data granularity or time frame. These attributes can be used for data adjustment in the steps 522, 523. The term granularity refers to the level of detail or precision at which data is captured, stored, and / or analyzed. It determines how fine or coarse the data points are within a dataset. Granularity can be described along a spectrum, from very fine (high granularity) to very coarse (low granularity). It can concern various data attributes or data features such as time and location (e.g., the granularity of sensor data can be a time interval between sensed datapoints or sensing frequency). Thus, the granularity refers to the degree of detail represented in the data, impacting the depth and specificity of the information available for analysis.

[0051] At step 522, the process 520 may identify and generate missing data points or values within the collected datasets. This data adjustment step 522 aids in maintaining the integrity of the datasets, as the process 520 fills in gaps that could otherwise lead to inaccuracies in the simulation and management of the power grid PWG.

[0052] At step 523, the process 520 identifies datasets collected from various sources that differ in granularity of the datapoints and aligns these data points in granularity so that they match a consistent granularity. This data adjustment step ensures that datasets collected from various sources with different granularities (e.g., different time intervals between data points) are standardized to match a consistent granularity (e.g., a consistent time frame). The final granularity can depend on the user category and / or on the grid development stage determined in steps 515, 516. This alignment facilitates accurate modeling and simulation of the power grid PWG.

[0053] For misaligned and / or missing data, generative Al (Artificial Intelligence) model(s) can be used to predict missing values or data points. For instance, let’s consider that the system has collected environmental data like humidity recorded hourly, and temperature and wind recorded every minute. Depending on the power grid's development stage, the data needs to be in hourly intervals for a certain range. Generative Al can aggregate the data with an appropriate aggregation function, and predict any missing data for the required range to support further simulation processes.

[0054] At step 524, the method 520 weights the datasets, possibly adjusted. This step involves assigning different levels of importance to the datasets based on factors such as data source reliability, the stage of power grid development, the user’s category, and the proportion of generated data points within the dataset. For example, let’s consider a data set including data aboutdeforestation from two different sources. The deforestation data set may include a set of government data based on a government public report and a set of proprietary data based on satellite images over years in a specific region. Additionally, the government data was relatively complete with no missing values, but the proprietary data had some missing values (for example, cloudy days caused data loss on satellite images). For the purpose of simulation of the power grid PWG at a planning or pre-building stage, the method 520 may attribute different weights to the set of government data and the set of proprietary data depending on the data source reliability, the stage of power grid development, and / or the proportion of generated data points within the dataset. Weighting the data helps to refine the simulation and management processes by emphasizing more reliable and relevant information.

[0055] Optionally, at step 525, the method 520 may generate a reliability report. This report includes information on the adjustments performed on the datasets. For example, it may include:- Data Adjustments: Detailed records of any adjustments or transformations applied to the datasets. This could include normalization, handling of missing values, outlier detection and inconsistencies, and summarizing these findings in the report.- Data Quality Metrics: Statistics that quantify the quality of the data, such as completeness (percentage of missing values), uniqueness (duplicate records), timeliness (delays in data collection or processing), consistency (contradictions within or between datasets), etc.

[0056] This report will provide valuable insights into the reliability of the simulation and its results, and can support decision-making and continuous improvement in the operation of the power grid system. It ensures that the simulation is as accurate and useful as possible. Also, by preparing this report we can increase confidence in the simulation results and make more informed decisions based on those results. It also provides a record of the steps taken, which can be useful for troubleshooting, auditing, or future improvements. Thereliability report can be used to assess the quality of the data and the expected accuracy of the simulation results, and to perform monitoring on the later steps.

[0057] At step 530, the method 500 stores the integrated data. Data storage ensures that the integrated datasets are securely saved and readily accessible for further processing.

[0058] At step 540, the method 500 generates a computer-based or digital model that virtually represents or replicates the power grid system PWG based on the data stored in step 530, as illustrated in figure 4. This step 540 involves creating a digital twin, or digital representation, of the power grid PWG that can be used to simulate the operation and performance of the power grid PWG under various conditions and scenarios. The generated model is adapted to the user category determined in the step 516. Advantageously, the generated model is adapted not only to the user category but also to the grid development phase determined in the step 515. As a result, the generated digital twin of the power grid is specific to the user category and advantageously to the grid's current development stage. In other words, the method 500 creates an adaptive digital twin of the power grid PWG that can be both user-specific and reflective of the grid's current (or specified) development stage. The present method allows to tailor the computer-based model to specific user needs and / or the current state of the power grid's development.

[0059] In an embodiment, the generation of the model includes generating a metaverse environment where a plurality of users can interact with each other and / or with the virtual representation of the power grid PWG.

[0060] Components of the generated model may include for example:- generation units: models of power plants (e.g., coal, gas, nuclear, renewable sources) and their operational characteristics;- transmission lines: simulation of high-voltage power lines that transport electricity over long distances;- distribution networks: detailed replication of lower-voltage networks that distribute electricity to end users;- substations: nodes where voltage levels are transformed and distributed; and / or- loads: representation of consumer demand, including residential, commercial, and industrial usage.

[0061] Functionalities of the generated model when used or executed by a computer may include for example:- simulation of operations: mimicking day-to-day operations, including power dispatch, load balancing, and fault management;- scenario analysis: evaluating the impact of different scenarios or conditions, such as equipment failures, demand spikes, and integration of new power sources;- optimization: identifying the most efficient ways to generate, transmit, and distribute electricity;- reliability and stability analysis: assessing the grid's ability to withstand and recover from disruptions.

[0062] In an embodiment, the digital twin system implemented with the computer-based model may be updated based on new data inputs. These new data inputs may include current or live or real-time data from different sources. They may comprise for example electrical parameters, geographic information, operational data, and / or environmental data, as previously described. For updating the model, the steps of collecting data 510, data integration 520, data storage 530 and computer-based model generation 540 may be executed again. The update can be performed regularly. Alternatively, or additionally, it may be performed upon instruction for the user. This allows to dynamically adapt the computer-based model to a current state of the power grid PWG. In this way, the generated model dynamically mimics, replicates a current state of the power grid PWG.

[0063] The resulting model serves as a foundation for simulating the power grid's behavior and for making informed management decisions.

[0064] At step 550, the method 500 simulates the operation of the power grid PWG using the computer-based model. This simulation step 550 allows for the analysis of the power grid's behavior under different operational scenarios and conditions, which helps in effective grid management.

[0065] At step 560, the method 500 manages the power grid PWG based on results obtained from the simulation. This step 560 involves making informed decisions to optimize the operation and management of the power grid PWG, ensuring the stability and efficiency of the power grid PWG.

[0066] For example, applications of the power grid simulation can include:- planning and development: assisting in the design and expansion of the power grid infrastructure;- operational management: supporting real-time decision-making for grid operators;- training and education: providing a virtual environment for training engineers and operators;- research and innovation: facilitating studies on new technologies and methods for grid optimization and sustainability.

[0067] As shown in figure 3, the step 560 of managing the power grid PWG may include optimizing operation of the power grid by performing at least one of the steps of:- forecasting demand and supply of power within the power grid (561 );- detecting operational anomalies and / or faults within the power grid (562);- controlling power generation and distribution within the power grid (563);- evaluating impact of one or more external factors, such as weather conditions, availability of renewable energy sources, and load fluctuations, on the stability and / or efficiency of the power grid (564).

[0068] Additionally, or alternatively, the step 560 of managing the power grid PWG may include predicting a potential failure of at least one component of the power grid PWG, and estimating an amount of time that the component isexpected to function before the predicted failure, to schedule a maintenance action before expiration of said amount of time (565).

[0069] Additionally, or alternatively, the step 560 of managing the power grid PWG may include adjusting operational parameters of the power grid PWG (566).

[0070] Additionally, or alternatively, the step 560 of managing the power grid PWG may include detecting vulnerabilities of the power grid PWG (567).

[0071] Method 500 may include one or more operations, functions, or actions as illustrated by one or more of blocks 510-560. Although the blocks are illustrated in a sequential order, these blocks may in some instances be performed in parallel, and / or in a different order than those described herein. Also, the various blocks may be combined into fewer blocks, divided into additional blocks, and / or removed based upon the desired implementation.

[0072] In addition, for the method 500 and other processes and methods disclosed herein, the flowchart shows functionality and operation of one possible implementation of present embodiments. In this regard, each block may represent a module, a segment, a portion of a manufacturing or operation process, or a portion of program code, which includes one or more instructions executable by a processor for implementing specific logical functions or steps in the process. The program code may be stored on any type of computer readable medium, for example, such as a storage device including a disk or hard drive. The computer readable medium may include non-transitory computer readable medium, for example, such as computer-readable media that stores data for short periods of time like register memory, processor cache and Random Access Memory (RAM). The computer readable medium may also include non-transitory media, such as secondary or persistent long term storage, like read only memory (ROM), optical or magnetic disks, compact-disc read only memory (CD-ROM), for example. The computer readable media may also be any other volatile or non-volatile storage systems. The computerreadable medium may be considered a computer readable storage medium, for example, or a tangible storage device.

[0073] The present disclosure also concerns a computing device or system that comprises means for performing one or more or all steps of the method previously described. The means may include at least one processor and at least one memory storing instructions that, when executed by the at least one processor, cause the device or system to perform one or more or all steps of the method. The means may include circuitry (e.g. processing circuitry) to perform one or more or all steps of a method according to the first aspect. The computing device or system further includes user interface means.

[0074] The present disclosure further concerns:- a computer program comprises instructions that, when executed by a computer, cause the computer to perform at least to perform one or more or all steps of the method previously described;- a non-transitory computer readable medium comprises program instructions stored thereon for causing a computer to perform one or more or all steps of a method previously described.

[0075] FINAL CONSIDERATIONS

[0076] Although an overview of the inventive subject matter has been described with reference to specific example embodiments, various modifications and changes may be made to these embodiments without departing from the broader spirit and scope of embodiments of the present invention. For example, various embodiments of features thereof may be mixed and matched or made optional by a person of ordinary skill in the art. Therefore, the Detailed Description is not to be taken in a limiting sense, and the scope of various embodiments is defined only by the appended claims, along with the full range of equivalents to which such claims are entitled.

Claims

CLAIMS1. A computer-implemented method for power grid management, said method comprising the steps of:- collecting (510) datasets from various sources, said datasets including realtime data and / or historical data and being relevant to the power grid management;- generating (540) a computer-based model that virtually represents the power grid, based on the collected datasets;- simulating (550) how the power grid operates under various conditions and / or operational scenarios using the computer-based model;- managing (560) the power grid based on simulation results; wherein the method further includes a step (516) of determining a user category among a plurality of predetermined user categories, and the computer-based model is adapted to the determined user category.

2. The method according to claim 1 , comprising a step (515) of determining a grid stage from a plurality of predetermined grid stages corresponding to different development phases of the power grid, wherein the computer-based model is adapted to the determined grid stage.

3. The method according to claim 2, comprising a step (520) of data integration based on the determined user category and / or grid stage.

4. The method according to claim 3, wherein the step (520) of data integration includes categorizing and prioritizing (521 ) the collected datasets.

5. The method according to claim 3 or 4, wherein the step of data integration (520) includes a first step of data adjustment (522) that includes generating missing data points within the collected datasets.

6. The method according to any of claims 3 to 5, wherein the step of data integration (520) includes a second step of data adjustment (523) that includes identifying datasets collected from various sources that differ in granularity ofthe datapoints, and aligning the data points in granularity so that they match a consistent granularity.

7. The method according to claim 5 or 6, wherein the first and / or second step of data adjustment (522, 523) are performed with generative Al models.

8. The method according to any of claims 5 to 7, wherein the step of data integration (520) includes weighting (524) the datasets based on one or more factors from the group including a data source reliability, the selected stage, and a proportion of generated data points within the dataset.

9. The method according to any of claims 1 to 8, wherein the step (540) of generating the computer-based model that virtually represents the power grid includes generating a metaverse environment where a plurality of users can interact with each other and / or with the virtual representation of the power grid.

10. The method according to any of claims 1 to 9, wherein the step (560) of managing the power grid includes optimizing operation of the power grid by performing at least one of the steps of:- forecasting demand and supply of power within the power grid (561 );- detecting operational anomalies and / or faults within the power grid (562);- controlling power generation and distribution within the power grid (563);- evaluating impact of one or more external factors, such as weather conditions, availability of renewable energy sources, and load fluctuations, on the stability and / or efficiency of the power grid (564).11 . The method according to any of claims 1 to 11 , wherein the step of managing the power grid includes a step (565) of predicting a potential failure of at least one component of the power grid, and estimating an amount of time that the component is expected to function before the predicted failure, to schedule a maintenance action before expiration of said amount of time.

12. The method according to any of claims 1 to 12, wherein the step of managing the power grid includes adjusting (566) operational parameters of the power grid.

13. The method according to any of claims 1 to 13, wherein the step of managing the power grid includes detecting vulnerabilities of the power grid (567).

14. Computer program comprising instructions which, when the program is executed by a computer, cause the computer to carry out the steps of the method according to any of the claims 1 to 13.

15. A system comprising means for carrying out the steps of the method according to any of the claims 1 to 13.

Images