KR20230011196A - Method and apparatus for managing a renewable energy based on an artificial intelligence - Google Patents

Abstract

The present invention relates to a renewable energy management device and method using a plurality of renewable energy power generation facilities that produce electricity through renewable energy generation and provide real-time power generation information and facility-related information. To this end, the renewable energy management device based on artificial intelligence comprises: a data collection server which is connected to the plurality of renewable energy power generation facilities through a network, receives and collects real-time power generation information and facility-related information, collects information on environmental factors affecting renewable energy power generation, and then uses the information to construct a database; a power generation prediction server which generates a power generation prediction model through artificial intelligence analysis of the data stored in the database, and generates power generation prediction information of the plurality of renewable energy power generation facilities using the power generation prediction model; and a management server which creates and manages a virtual power plant consisting of at least one renewable energy power generation facility based on the power generation prediction information of the plurality of renewable energy power generation facilities. The renewable energy management device can increase an efficiency of power management in renewable energy industry and revitalize the renewable energy industry.

Description

Apparatus and method for managing a renewable energy based on artificial intelligence {Method and apparatus for managing a renewable energy based on an artificial intelligence}

The present invention relates to an artificial intelligence-based renewable energy management device and method for integrated management of renewable energy generation facilities.

As the lack of support for traditional energy sources such as coal and oil accelerates, there is a global trend to strengthen economic sanctions by imposing a carbon tax if there is no RE 100, which is a certification that 100% of the electricity used by companies is from renewable energy.

As such, as restrictions and limitations on the use of traditional energy sources emerge, interest in renewable energy such as solar light, wind power, and geothermal heat is growing.

Meanwhile, in order to respond to these changes, Information announced related policies such as the Renewable Energy 3020 Policy, the Green New Deal Policy, and the 2050 Low Carbon Power Generation Electricity, increasing the share of renewable energy generation from 7% in 2016 to 20% in 2030, with a target of about 285%. is announcing a policy to increase

The traditional energy industry consists of a centralized production and sales structure, but the renewable energy industry is changing to an open and distributed production and sales structure by applying 4th industrial technologies such as artificial intelligence and blockchain. Opportunities for various new growth industries are expanding in the ecosystem.

In particular, the power distribution system is changing from a method that only transfers electricity produced in large quantities from existing coal-fired power plants or nuclear power plants to central supply, to renewable energy produced on a small scale in dispersed areas in various ways. In other words, the next-generation power grid called 'smart grid' is a combination of renewable energy such as solar and wind power and energy storage devices, and generates electricity by installing small-scale facilities and stores the remaining power in energy storage devices, It has a form that can be traded.

However, if it changes to a distributed production and sales structure, it is difficult to grasp the total power demand at a glance like in the traditional energy industry.

Korean Registered Patent No. 10-2221251 (registered on February 23, 2021)

The present invention collects real-time power generation information, facility-related information, and environmental factor information from a plurality of renewable energy power generation facilities, generates a power generation prediction model based on the collected real-time power generation information, facility-related information, and environmental factor information, After grouping a plurality of renewable energy generation facilities based on the base, by creating and managing a Virtual Power Plant (VPP) for each group, the efficiency of power management in the new renewable energy industry as well as the vitalization of the new renewable energy industry is improved. Provides an artificial intelligence-based renewable energy management device and method that can be improved.

As a technical means for achieving the above technical problem, the artificial intelligence-based renewable energy management device according to an embodiment of the present invention generates power through renewable energy generation and provides real-time power generation information and facility-related information In the new renewable energy management device using a plurality of renewable energy generation facilities, it is connected to the plurality of new and renewable energy generation facilities through a network to receive and collect real-time power generation information and facility-related information, as well as the new and renewable energy generation A data collection server that collects environmental factor information that affects and then uses it to build a database, and generates a power generation prediction model through artificial intelligence analysis of the data stored in the database, and uses the power generation prediction model to A power generation prediction server for generating power generation prediction information of a plurality of new and renewable energy power generation facilities, and a virtual power plant composed of at least one new and renewable energy power generation facility based on the power generation prediction information of the plurality of new and renewable energy power generation facilities is created and managed. It may include a management server that

According to an embodiment of the present invention, the data collection server further collects power grid configuration information, which is a connection path through which the plurality of renewable energy generation facilities supply power through power generation, to build the database, and the management server builds the database. A virtual power plant may be created based on the power generation prediction information and the power grid configuration information.

According to an embodiment of the present invention, the management server receives real-time power generation information from the plurality of renewable energy power generation facilities, and compares the received real-time power generation information with the predicted power generation amount. Renewable energy with power loss It is determined whether there is a power generation facility, and if there is, it is possible to change the renewable energy power generation facility in the virtual power plant including the renewable energy power generation facility with the power loss.

According to an embodiment of the present invention, the management server compares real-time generation amount information received from a plurality of new and renewable energy generation facilities included in the virtual power plant and power generation prediction information of the virtual power plant, so that power loss of the virtual power plant is detected. If there is power loss, it is possible to change new renewable energy generation facilities in the virtual power plant.

As a technical means for achieving the above technical problem, the artificial intelligence-based renewable energy management method according to an embodiment of the present invention generates power through renewable energy generation and provides real-time power generation information and facility-related information In the renewable energy management method using a plurality of renewable energy generation facilities, a management device is connected to the plurality of renewable energy generation facilities through a network to receive and collect real-time power generation information and facility-related information, and the new Building a database by collecting environmental factor information that affects renewable energy generation; generating a power generation prediction model through artificial intelligence analysis of data stored in the database in the management device; Generating generation prediction information of the plurality of renewable energy generation facilities using a generation prediction model, and generating at least one new renewable energy generation based on the generation prediction information of the plurality of new and renewable energy generation facilities in the management device. A step of creating and managing a virtual power plant composed of facilities may be included.

According to an embodiment of the present invention, the constructing step further collects power grid configuration information, which is a connection path through which the plurality of renewable energy generation facilities supply power through power generation, to build the database, and the managing step comprises: A virtual power plant may be generated based on the power generation prediction information and the power grid configuration information.

According to an embodiment of the present invention, the managing step includes receiving real-time power generation information from the plurality of renewable energy generation facilities, and comparing the received real-time power generation information with the predicted power generation information. The method may further include determining whether there is a renewable energy generation facility and, as a result of the determination, changing a new and renewable energy generation facility in the virtual power plant, including the new and renewable energy generation facility having power loss, if present.

According to an embodiment of the present invention, the step of managing power loss of the virtual power plant through comparison between real-time power generation amount information received from a plurality of renewable energy generation facilities included in the virtual power plant and power generation prediction information of the virtual power plant. determining whether there is a power loss, and as a result of the determination, if there is power loss, renewable energy generation facilities in the virtual power plant may be changed.

According to the above-described embodiment of the present invention, real-time power generation information, facility-related information, and environmental factor information are collected from a plurality of renewable energy generation facilities, and power generation based on the collected real-time power generation information, facility-related information, and environmental factor information. After creating a prediction model, grouping multiple new and renewable energy generation facilities based on this, and creating and managing a virtual power plant (VPP) for each group, thereby activating the new and renewable energy industry as well as renewable energy It can improve the efficiency of industrial power management.

1 is a diagram showing the overall configuration of an artificial intelligence-based renewable energy management system according to an embodiment of the present invention.
Figure 2 is a block diagram showing the detailed configuration of the renewable energy management device according to an embodiment of the present invention.
Figure 3 is a flow chart showing the operating process of the renewable energy management device according to an embodiment of the present invention.

Hereinafter, specific embodiments of the present invention will be described with reference to the drawings. The detailed descriptions that follow are provided to provide a comprehensive understanding of the methods, devices and/or systems described herein. However, this is only an example and the present invention is not limited thereto.

In describing the embodiments of the present invention, if it is determined that the detailed description of the known technology related to the present invention may unnecessarily obscure the subject matter of the present invention, the detailed description will be omitted. In addition, terms to be described later are terms defined in consideration of functions in the present invention, which may vary according to the intention or custom of a user or operator. Therefore, the definition should be made based on the contents throughout this specification. Terminology used in the detailed description is only for describing the embodiments of the present invention and should in no way be limiting. Unless expressly used otherwise, singular forms of expression include plural forms. In this description, expressions such as "comprising" or "comprising" are intended to indicate any characteristic, number, step, operation, element, portion or combination thereof, one or more other than those described. It should not be construed to exclude the existence or possibility of any other feature, number, step, operation, element, part or combination thereof.

Hereinafter, an artificial intelligence-based renewable energy management system and method according to an embodiment of the present invention will be described with reference to the accompanying drawings.

1 is a diagram showing the overall configuration of an artificial intelligence-based renewable energy management system according to an embodiment of the present invention, and FIG. 2 is a block diagram showing the detailed configuration of a renewable energy management device according to an embodiment of the present invention. It is also

As shown in FIG. 1, the artificial intelligence-based renewable energy management system according to an embodiment of the present invention includes a plurality of renewable energy generation facilities 100 and a new renewable energy management device 200 connected through a wired or wireless network. ) and the like.

The renewable energy power generation facility 100 may produce electricity through power generation using geothermal heat, solar light, wind power, ocean, and the like.

In addition, the new renewable energy power generation facility 100 according to an embodiment of the present invention checks the real-time power generation amount and generates corresponding information (hereinafter, referred to as 'real-time power generation information'), and then connects the renewable energy through a network. An information provider 110 capable of transmitting to the management device 200 may be further provided.

The information provider 110 is automatically connected to the renewable energy management device 200 based on the access information of the renewable energy management device 200 and can transmit real-time power generation information to the renewable energy management device 200. .

In addition, the information provider 110 transmits facility-related information such as operation time and stoppage, operating cost, maintenance cost, cost information such as facility unit cost, depreciation, and generation unit cost to the renewable energy management device 200. can

The new renewable energy management device 200 includes information on real-time power generation received from the renewable energy power generation facility 100 connected through a network and external environmental factors related to renewable energy generation, such as weather, temperature, wind speed, and the like. Factor information may be collected and stored in the database 212 .

In addition, the new renewable energy management device 200 analyzes the data stored in the database 212 through an artificial intelligence engine to predict the amount of power generation of each new and renewable energy power generation facility 100, and a plurality of new sources based on the predicted amount of power generation. After grouping the renewable energy generation facility 100 into a plurality of virtual power plants, an optimal power generation plan may be established based on the grouping.

To this end, the renewable energy management device 200 may include a data collection server 210, a power generation prediction server 220, and a management server 230, as shown in FIG. 2 .

The data collection server 210 is connected to a plurality of renewable energy generation facilities 100 through a network to collect information on real-time power generation, as well as power grid configuration information connected to the renewable energy generation facilities 100 and external environmental factors. etc. may be collected and stored in the database 212 .

In addition, the data collection server 210 may collect facility-related information and cost information about facility operation and performance from the plurality of renewable energy generation facilities 100 and store them in the database 212 .

In addition, the data collection server 210 provides meteorological information corresponding to external environmental factors from the external environmental information providing server (120 in FIG. 1 ) providing external environmental factors, such as wind speed, wind direction, temperature, weather, warnings and warnings, etc. The same weather information may be collected and stored in the database 212 .

In particular, the data collection server 210 according to an embodiment of the present invention may collect real-time power generation information, facility-related information, cost information, external environmental factor information, etc., classify them, and store them in the database 212 .

In addition, the data collection server 210 according to an embodiment of the present invention is power grid configuration information for each renewable energy generation facility 100 to supply power, for example, connection of the renewable energy generation facility 100 to supply power. After collecting the information, it can be stored in the database 212 by matching it with the identifier of the renewable energy generation facility 100 .

Through this, matching data in which the identifier of the renewable energy power generation facility 100 is matched with the real-time power generation amount, facility-related information, cost information required for power generation, external environmental factors, and power grid configuration information may be stored in the database 212 through this.

The power generation prediction server 220 processes the matching data stored in the database 212 as standardized data, analyzes the standardized data with an artificial intelligence engine to generate a power generation prediction model, and generates a power generation prediction model for each renewable energy source. The amount of power generated by the power generation facility 100 can be predicted.

In an embodiment of the present invention, the power generation prediction server 220 may include a data processing unit 222 for converting big data collected in the database 212, that is, unstructured data into structured structured data.

The data processor 222 may include a data conversion module 222a, a data calibration module 222b, and a data integration module 222c.

The data conversion module unit 222a may convert the type of matching data stored in the database 212 or convert it into a form that is easy to analyze.

The data correction module 222b may perform missing value conversion, outlier removal, and noise data correction.

The data integration module 222c may link and integrate the corrected data with existing or similar data so as to facilitate data analysis. As for data integration, it is essential if analysis is required with legacy systems, i.e. data from existing systems.

The data processor 222 according to an embodiment of the present invention selects at least one of the modules 222a, 222b, and 222c based on the state of the matching data stored in the database 212 and converts the data into a form that can be analyzed. can be dealt with

In addition, the generation prediction server 220 may further include a generation prediction model generation unit 224 that generates a generation prediction model through artificial intelligence analysis based on the data processed by the data processing unit 222 .

The power generation prediction model generation unit 224 is a quantitative and qualitative analysis algorithm for the data processed by the data processing unit 222, deep neural network, LSTM, SVR, random forest, Gaussian mixture A power generation prediction model may be generated using a linear analysis algorithm such as S-ARIMA, a non-linear analysis algorithm such as Prophet, a timeline analysis, an adversarial self-learning algorithm (forecast GAN), an integrated judgment algorithm (Ensemble), and the like.

The power generation prediction model generation unit 224 calculates the change in real-time power generation according to the start-up and operation information of the renewable energy power generation facility 100, which is facility-related information, and the external environmental factor information, and the facility that affects the change in real-time power generation A power generation prediction model in which weights are assigned to related information and external environmental factor information may be generated.

The generation amount prediction server 220 may further include a generation amount predictor 226 that predicts the amount of power generation of each renewable energy power generation facility 100 based on the generation amount prediction model.

The power generation prediction unit 226 predicts the power generation of each renewable energy power generation facility 100 for each temperature change cycle, season, month, day and hour based on the power generation prediction model, and stores the predicted power generation information in the database 212. can Specifically, the generation amount prediction unit 226 uses the predicted generation amount information (hereinafter referred to as 'generation amount prediction information') for each new and renewable energy generation facility 100 to identify the identifier of each new and renewable energy generation facility 100. Matching data matched with can be updated.

The management server 230 selects at least one or more of the new and renewable energy generation facilities 100 based on the generation prediction information for each new and renewable energy generation facility 100 and groups them to create a plurality of virtual power plants, An optimal power generation plan can be established based on multiple virtual power plants.

As an example, the management server 230 selects at least one or more of the renewable energy generation facilities 100 based on the power grid configuration information and the predicted generation amount of the renewable energy generation facilities 100 stored in the database 212. You can then group them to create multiple virtual power plants. Specifically, the management server 230 selects the identifier of the renewable energy generation facility 100 having the same power grid configuration information through analysis of matching data stored in the database 212, and selects the selected renewable energy generation facility 100 A virtual power plant may be created by selecting an identifier of the renewable energy power generation facility 100 as a predetermined power generation unit, for example, a unit capable of selling electricity, based on power generation prediction information matched to the identifier of .

In addition, the management server 230 determines whether or not power is lost through comparison between real-time power generation amount information received from the renewable energy power generation facility 100 and power generation prediction information, and if it is determined that power is lost, it can be supplemented. .

Here, the determination of power loss can be made through comparison between real-time power generation information and power generation prediction information, that is, the renewable energy power generation facility 100 that produces a higher real-time power generation than the predicted power generation within a preset range. It can be made through whether or not there is a renewable energy power generation facility 100 that produces less than the predicted power generation within a predetermined range or real-time power generation.

That is, the management server 230 supplements the power loss part by adding the renewable energy generation facility 100 to the virtual power plant including the renewable energy generation facility 100 determined to be power loss, or determines the power loss. A virtual power plant including the renewable energy generation facility 100 may be reset.

The management server 230 according to an embodiment of the present invention manages the minimum amount of power that can be sold, and can generate a virtual power plant using prediction information on the generation amount of the renewable energy generation facility 100 generating less than the minimum amount of power. .

In addition, the management server 230 may determine a cycle based on prediction information on generation amount of each new and renewable energy power generation facility 100 for each month, day, and hour, and may create a virtual power plant for each cycle. Specifically, the management server 230 analyzes generation prediction information of each new and renewable energy generation facility 100 by month, day, and hour to determine the time when the generation prediction information changes significantly within a preset range, and based on the time point After determining the virtual power plant creation cycle, virtual power plants may be created and managed for each virtual power plant creation cycle.

It will be described with reference to Figure 3 for the process of operating the renewable energy management apparatus having the configuration as described above.

Figure 3 is a flow chart showing the process of operating the renewable energy management device according to an embodiment of the present invention.

As shown in FIG. 3, the data collection server 210 of the renewable energy management device 200 provides equipment related information from the information provider 110 in a plurality of renewable energy generation facilities 100 connected through a network. Real-time power generation information, power grid configuration information, cost information, etc. are collected, and external environmental factor information is collected from the environmental information providing server 120 connected through the network (S300) and stored in the database 212. At this time, the data collection server 210 generates matching data by matching facility-related information, real-time power generation information, power grid configuration information, cost information, external environmental factor information, etc. to the identifier of each new and renewable energy generation facility 100 to create a database. (212).

Thereafter, the power generation prediction server 220 generates a power generation prediction model through artificial intelligence analysis on the matching data collected for a predetermined period through S300 (S302), and then generates each new and renewable energy power generation facility (100) based on the power generation prediction model. ) Generates generation prediction information for (S304), and matches the identifier of each renewable energy generation facility 100 to the generated generation prediction information and stores it in the database 212.

Then, the management server 230 is a method of grouping at least one renewable energy generation facility 100 by using power generation forecast information, predetermined reference data, and power grid configuration information of each renewable energy generation facility 100. Create at least two virtual power plants. Here, the reference data may be the minimum amount of electricity that can be sold.

For example, the management server 230 may create a virtual power plant by grouping new and renewable energy generation facilities 100 that generate less than a minimum amount of power and are connected to the same power grid (S306).

In addition, the management server 230 provides one renewable energy generation facility 100 in the case of the renewable energy generation facility 100 (hereinafter referred to as 'excess renewable energy generation facility') performing power generation in excess of the minimum amount of power. may be set as a virtual power plant for independent power generation (S308) and managed.

Thereafter, the management server 230 determines whether there is power loss through comparison between real-time power generation information of each new and renewable energy generation facility 100 in the virtual power plant and power generation prediction information of each new and renewable energy generation facility 100 ( S310). Specifically, the management server 230 may determine whether there is a power loss by checking whether the real-time power generation is lower or higher than the predicted power generation within a preset range.

As a result of the determination in S310, if there is a power loss, the management server 230 determines whether a change in the virtual power plant is required (S312). Specifically, the management server 230 may determine whether the virtual power plant needs to be changed by checking whether the sum of the real-time power generation of each new and renewable energy generation facility 100 in the virtual power plant is less than the minimum amount of power that can be sold.

As a result of the determination in S312, if the amount of power is less than the minimum, the management server 230 changes the renewable energy generation facility 100 in the virtual power plant to manage power loss (S314). Specifically, the management server 230 may change the virtual power plant by including the excess renewable energy generation facility 100 set as a virtual power plant for single power generation having the same power grid configuration information in the virtual power plant that has lost power. .

On the other hand, although omitted in the embodiment of the present invention as described above, the management server 230 according to the embodiment of the present invention is a virtual power plant based on daily, hourly, and monthly real-time power generation information of each renewable energy power generation facility 100 Generation cycles are created, and virtual power plants may be created and managed for each generated virtual power plant generation cycle.

According to the embodiment of the present invention as described above, it has been described as an example of changing the renewable energy power generation facility 100 in a virtual power plant to manage current loss when it is less than the minimum amount of power to manage power loss. When the real-time power generation is higher than the predicted power generation within a preset range, the renewable energy power generation facility 100 in virtual power generation may be changed to manage power loss.

In addition, although the power loss has been described based on the renewable energy generation facility 100, the power loss can be achieved by comparing the sum of the real-time power generation of the renewable energy power generation facility 100 included in the virtual power plant and the prediction information of the generation amount. there is. That is, the management server 230 may determine whether a power loss occurs by checking that the sum of the real-time power generation of the renewable energy generation facilities 100 included in the virtual power plant is lower or higher than the power generation prediction information within a preset range. there is.

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

The scope of the present invention is indicated by the following claims rather than the detailed description above, and all changes or modifications derived from the meaning and scope of the claims and equivalent concepts thereof should be construed as being included in the scope of the present application. .

100: new renewable energy power generation facility
110: information provider
120: environment information providing server
200: new renewable energy management device

Claims (8)

In the new renewable energy management device using a plurality of renewable energy power generation facilities that produce power through renewable energy generation and provide real-time power generation information and facility-related information,
Connected to the plurality of renewable energy generation facilities through a network to receive and collect real-time power generation information and facility-related information, collect environmental factor information affecting the generation of new and renewable energy, and build a database using it. A data collection server that
A power generation prediction server for generating a power generation prediction model through artificial intelligence analysis of data stored in the database and generating power generation prediction information of the plurality of renewable energy power generation facilities using the power generation prediction model;
An artificial intelligence-based new and renewable energy management device comprising a management server that creates and manages a virtual power plant composed of at least one new and renewable energy generation facility based on the prediction information on the generation amount of the plurality of new and renewable energy generation facilities.
According to claim 1,
The data collection server,
Building the database by further collecting power grid configuration information, which is a connection path through which the plurality of renewable energy generation facilities supply power through power generation;
The management server,
An artificial intelligence-based renewable energy management device for generating a virtual power plant based on the power generation prediction information and the power grid configuration information.
According to claim 1,
The management server,
Real-time power generation information is received from the plurality of renewable energy generation facilities, and it is determined whether there is a renewable energy generation facility with power loss through comparison between the received real-time generation amount information and the generation amount prediction information. An artificial intelligence-based renewable energy management device that changes new and renewable energy generation facilities in virtual power plants, including new and renewable energy generation facilities that are lost.
According to claim 1,
The management server,
It is determined whether there is power loss of the virtual power plant through comparison between real-time power generation information received from a plurality of renewable energy generation facilities included in the virtual power plant and power generation prediction information of the virtual power plant, and if there is power loss, the virtual power plant An artificial intelligence-based renewable energy management device that changes renewable energy generation facilities in power plants.
In the renewable energy management method using a plurality of renewable energy generation facilities that produce power through renewable energy generation and provide real-time power generation information and facility-related information,
In addition to receiving and collecting real-time power generation information and facility-related information by being connected to the plurality of renewable energy power generation facilities through a network in a management device, environmental factor information affecting the renewable energy generation is collected to build a database steps,
Generating a power generation prediction model through artificial intelligence analysis of data stored in the database in the management device;
Generating generation amount prediction information of the plurality of renewable energy power generation facilities using the generation amount prediction model in the management device;
Artificial intelligence-based renewable energy management method comprising the step of generating and managing a virtual power plant composed of at least one new renewable energy generation facility based on the prediction information of the generation amount of the plurality of renewable energy generation facilities in the management device.
According to claim 5,
The building step is
Building the database by further collecting power grid configuration information, which is a connection path through which the plurality of renewable energy generation facilities supply power through power generation;
The management step is
An artificial intelligence-based renewable energy management method for generating a virtual power plant based on the power generation prediction information and the power grid configuration information.
According to claim 5,
The management step is
Receiving real-time generation amount information from the plurality of renewable energy generation facilities;
Determining whether there is a renewable energy generation facility with power loss through comparison between the received real-time generation amount information and the generation amount prediction information;
As a result of the determination, if present, artificial intelligence-based renewable energy management method further comprising the step of changing renewable energy generation facilities in the virtual power plant, including the renewable energy generation facilities with the power loss.
According to claim 5,
The management step is
Determining whether or not there is a power loss of the virtual power plant through comparison between real-time generation amount information received from a plurality of renewable energy generation facilities included in the virtual power plant and power generation prediction information of the virtual power plant;
As a result of the determination, an artificial intelligence-based renewable energy management method for changing renewable energy generation facilities in the virtual power plant when there is a power loss.

Images