WO2017159982A1

WO2017159982A1 - Microgrid operation system and method

Info

Publication number: WO2017159982A1
Application number: PCT/KR2017/001063
Authority: WO
Inventors: 류광렬
Original assignee: 부산대학교 산학협력단
Priority date: 2016-03-14
Filing date: 2017-02-01
Publication date: 2017-09-21
Also published as: KR20170106703A; KR101793149B1

Abstract

The present invention relates to a microgrid operation system and method, the microgrid operation system of the present invention comprising: an information provision unit for receiving raw data including data on the current status of operation of diesel power generation; a prediction unit for creating prediction data of the diesel power generation by using the raw data; an operation plan optimization unit for establishing an optimal operation plan for the diesel power generation by using the prediction data; and a monitoring unit for collecting the data on the current status of operation, transmitting same to the information provision unit, and transmitting the data on the current status of operation and the optimal operation plan to a user, wherein the prediction unit comprises a learning data collection module for creating learning data by using the raw data, an algorithm provision module for providing and updating a prediction model by using the learning data, and a prediction module for creating the prediction data through the raw data and the prediction model.

Description

Microgrid Operating System and Methods

The present invention relates to microgrid operating systems and methods.

Microgrid refers to the application of smart grid, a next-generation intelligent power grid that optimizes energy efficiency by integrating information technology (IT) into the existing grid. In other words, microgrid refers to a local power supply system centered on a distributed power source independent from the existing wide area power system. Independent microgrids provide power through diesel and renewable generation. In this case, when the generation amount of the diesel generator according to the time zone is determined based on the generation amount prediction information for the renewable power, the prediction amount information on the load characteristics information of the energy storage device and the characteristics and operating state information of the diesel generator, Maintenance cost can be reduced.

The problem to be solved by the present invention is to provide a microgrid operating system that can minimize the operating cost, and prevent blackout.

Another object of the present invention is to provide a microgrid operating method that can minimize the operating cost and prevent blackout.

Problems to be solved by the present invention are not limited to the above-mentioned problems, and other problems not mentioned will be clearly understood by those skilled in the art from the following description.

The microgrid operating system according to an embodiment of the present invention for solving the above problems is an information providing unit for receiving raw data including operating status data of diesel power generation, prediction of diesel power generation using the furnace data A prediction unit for generating data, an operation plan optimization unit for establishing an optimal operation plan for diesel power generation using the prediction data, and collecting and transmitting the operation status data to the information providing unit, and the operation status data and the optimal operation. A monitoring unit for transmitting a plan to a user, wherein the prediction unit includes a training data collection module for generating training data using the raw data, an algorithm providing module for providing and updating a prediction model using the training data, and Example of generating prediction data through raw data and the prediction model A module.

The training data collection module may generate training data using raw data of a first time point, and the prediction module may generate training data using raw data of a second time point later than the first time point.

The second time point may be a current time point.

The raw data may include at least one of weather forecast data, real-time weather data, and real-time power consumption data.

The weather forecast data may include at least one of wind speed forecast data and insolation forecast data, and the real time weather data may include at least one of real time wind speed data and real time insolation data.

The operation plan optimization unit includes a population including a plurality of candidate operation plans, a genetic operator that performs generation replacement by genetically calculating the plurality of candidate operation plans, and selects an optimal operation plan. The generation change may genetically compute the plurality of candidate operating plans to add a new candidate operating plan to the population, simulate each candidate operating plan to derive an evaluation value, and according to the evaluation value, some candidate operating plans. And removing from the population, and selecting the optimal operation plan may include selecting a candidate operation plan having the highest evaluation value as the optimal operation plan.

The genetic operation may include at least one of a crossover operation and a mutation operation.

The evaluation value may be the sum of the total diesel generation cost and the power shortage loss cost in consideration of blackout.

Here, the control unit may further include a power generation unit that is controlled by the optimal operation plan and transmits operation status data to the monitoring unit.

The power generation unit may include a diesel generator, an energy storage system (ESS), and a power transmission system.

In the microgrid operating method according to some embodiments of the present invention for solving the other problem, the information providing unit receives the furnace data including the operation status data of the diesel power generation, the prediction unit using the furnace data to predict the diesel power generation Generate data, the operation plan optimizer generates a plurality of candidate operation plans of diesel power generation, the operation plan optimizer evaluates each of the plurality of candidate operation plans, derives an evaluation value, and exceeds a preset number or time limit If not, the operation plan optimizer updates the candidate operation plan according to the evaluation value, derives an updated evaluation value of the candidate operation plan, and if the preset number or time limit is exceeded, the operation plan. The optimizer uses the evaluation value to optimize the operating system among the candidate operation plans. The selection and involves the parts of the control according to the power operating plan optimization in addition to the optimal operation program.

The deriving of the evaluation value may include generating power generation amount by unit time in the candidate operation plan, determining whether blackout occurs according to the generation amount by unit time, and calculating total cost according to generation amount and blackout occurrence by unit time. It may include.

Determining whether the blackout occurs may include determining a charge / discharge state of the energy storage system.

The generating of the prediction data may include learning data collection module collecting the raw data to generate training data, an algorithm providing module providing and updating a prediction model using the training data, and the prediction module is configured to generate the raw data. It may include generating prediction data through the prediction model.

Selecting the optimal operating plan may include selecting the optimal operating plan again at predetermined intervals.

Specific details of other embodiments are included in the detailed description and the drawings.

According to embodiments of the present invention has at least the following effects.

That is, the microgrid operating system and method according to some embodiments of the present invention can accurately predict the auxiliary diesel generation amount corresponding to the fluctuation range of renewable power generation, which is the main energy source of the independent microgrid. In other words, in the case of renewable power generation, the fluctuation range of power generation is very large according to weather conditions such as weather, so if conservatively reducing the expected generation amount of renewable energy, diesel generation will be excessive and operation cost will increase, and the expectation of renewable energy If the power generation is excessively caught, it may cause a blackout phenomenon in which the power supply is cut off because the load power cannot be handled.

Accordingly, the microgrid operating system and method according to some embodiments of the present invention accurately predict the expected generation of renewable energy and precisely specify diesel generation, thereby minimizing the operating cost of the standalone microgrid while preventing blackout. can do.

The effects according to the present invention are not limited by the contents exemplified above, and more various effects are included in the present specification.

1 is a block diagram illustrating a microgrid operating system according to some embodiments of the present invention.

FIG. 2 is a block diagram illustrating in detail the predictor of FIG. 1.

3 is a block diagram illustrating in detail the operation plan optimizer of FIG. 1.

4 is a diagram illustrating a solution representation of a candidate operating plan of the microgrid operating system according to some embodiments of the present invention.

FIG. 5 is a diagram for describing repetition of selecting an optimal operation plan of a microgrid operating system according to some embodiments of the present disclosure.

6 is a flowchart illustrating a microgrid operating method according to some embodiments of the present invention.

7 is a flowchart for explaining in detail the step of evaluating the candidate operation plan of FIG.

Advantages and features of the present invention and methods for achieving them will be apparent with reference to the embodiments described below in detail with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but will be implemented in various forms, and only the present embodiments are intended to complete the disclosure of the present invention, and the general knowledge in the art to which the present invention belongs. It is provided to fully convey the scope of the invention to those skilled in the art, and the present invention is defined only by the scope of the claims. Like reference numerals refer to like elements throughout.

Although the first, second, etc. are used to describe various elements, components and / or sections, these elements, components and / or sections are of course not limited by these terms. These terms are only used to distinguish one element, component or section from another element, component or section. Therefore, the first device, the first component, or the first section mentioned below may be a second device, a second component, or a second section within the technical spirit of the present invention.

When elements or layers are referred to as "on" or "on" of another element or layer, intervening other elements or layers as well as intervening another layer or element in between. It includes everything. On the other hand, when a device is referred to as "directly on" or "directly on" indicates that no device or layer is intervened in the middle.

The spatially relative terms " below ", " beneath ", " lower ", " above ", " upper " It may be used to easily describe the correlation of a device or components with other devices or components. Spatially relative terms are to be understood as including terms in different directions of the device in use or operation in addition to the directions shown in the figures. For example, when flipping a device shown in the figure, a device described as "below or beneath" of another device may be placed "above" of another device. Thus, the exemplary term "below" can encompass both an orientation of above and below. The device may be oriented in other directions as well, in which case spatially relative terms may be interpreted according to orientation.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. In this specification, the singular also includes the plural unless specifically stated otherwise in the phrase. As used herein, “comprises” and / or “comprising” refers to the presence of one or more other components, steps, operations and / or elements. Or does not exclude additions.

Unless otherwise defined, all terms (including technical and scientific terms) used in the present specification may be used in a sense that can be commonly understood by those skilled in the art. In addition, the terms defined in the commonly used dictionaries are not ideally or excessively interpreted unless they are specifically defined clearly.

1 to 5, a microgrid operating system according to some embodiments of the present invention will be described.

FIG. 1 is a block diagram illustrating a microgrid operating system according to some embodiments of the present invention, and FIG. 2 is a block diagram illustrating in detail the predictor of FIG. 1. 3 is a block diagram illustrating in detail the operation plan optimization unit of FIG. 1, and FIG. 4 is a diagram illustrating a solution representation of a candidate operation plan of a microgrid operating system according to some embodiments of the present disclosure. FIG. 5 is a diagram for describing repetition of selecting an optimal operation plan of a microgrid operating system according to some embodiments of the present disclosure.

Referring to FIG. 1, a microgrid operating system according to some embodiments of the present invention may include an information providing unit 100, a prediction unit 200, an operation plan optimization unit 300, a power generation unit 400, and a monitoring unit 500. ).

The information provider 100 may receive raw data. The information provider 100 may receive the raw data and transmit it to the predictor 200. The raw data may include at least one of weather forecast data, real-time weather data, and real-time power consumption data. The weather forecast data may include wind speed forecast data and solar radiation forecast data. The real-time weather data may include real-time wind speed data and real-time solar radiation data.

The raw data may also include operational status data. The operation status data may be transmitted from the monitoring unit 500 to the information providing unit 100. However, it is not limited thereto. That is, the operation status data may be transmitted directly from the power generation unit 400 without passing through the monitoring unit 500.

The operation status data may include a diesel generator status data, an energy storage system (ESS) status data and a transmission status data.

The raw data may include past history data and data of the present time. That is, the raw data may include past weather change history data and past time slot power consumption history data.

The information provider 100 may process the raw data into a format required by the predictor 200 and transmit the raw data to the predictor 200. However, the present invention is not limited thereto, and the raw data may be transmitted to the predicting unit 200 as it is, and the raw data may be processed by the predicting unit 200 in a required format.

The information provider 100 may update the raw data at predetermined intervals or in real time. That is, the raw data may be updated using new data at the present time.

The prediction unit 200 may receive the raw data from the information providing unit 100. The prediction unit 200 may generate prediction data using the raw data. The prediction unit 200 may transmit the prediction data to the operation plan optimization unit 300.

The prediction data may include prediction weather data and prediction power consumption data. The prediction data may be continuously updated at predetermined intervals or in real time.

The operation plan optimizer 300 may receive the prediction data from the predictor 200. The operation plan optimizer 300 may establish an optimal operation plan of diesel power using the prediction data. The optimal operation plan may be an operation plan of the diesel generator 410, the energy storage system (ESS) 420, and the power transmission system 430. That is, the power generation unit 400 may be controlled according to the optimum operation plan.

The generator 400 may actually produce power. The generator 400 may include a diesel generator 410, an energy storage system 420, and a power transmission system 430. The generation unit 400 may generate operation status data. The operation status data of the power generation unit 400 may be operation status data of the diesel generator 410, the energy storage system 420, and the power transmission system 430, respectively. That is, the operation status data may include a diesel generator status data, energy storage system status data and transmission system status data. The operation status data may be transmitted to the monitoring unit 500. Alternatively, the operation status data may be directly transmitted to the information providing unit 100 without passing through the monitoring unit 500.

The diesel generator 410 may generate electric power using diesel. The diesel generator 410 may be used as an energy source to supplement renewable energy with a large fluctuation in a microgrid system that mainly uses renewable energy. The diesel generator 410 may transmit the diesel generator status data to the monitoring unit 500. The diesel generator 410 may be controlled by the optimum operation plan of the operation plan optimizer 300.

The energy storage system 420 may be a device for storing generated power. If the energy stored in the energy storage system 420 is less than the power consumption, the microgrid system may black out. The energy storage system 420 may transmit the energy storage system status data to the monitoring unit 500. The energy storage system 420 may be controlled by the optimal operation plan of the operation plan optimizer 300.

The power transmission system 430 may be a system for transmitting generated energy or power to a place where electric power is required. The power transmission system 430 may transmit the power transmission system status data to the monitoring unit 500. The power transmission system 430 may be controlled by the optimum operation plan of the operation plan optimizer 300.

The monitoring unit 500 may receive operation status data from the power generation unit 400. The monitoring unit 500 may provide the user 10 with the operation status data and the optimal operation plan. The monitoring unit 500 may transmit the operation status data to the information providing unit 100. The monitoring unit 500 may provide the operation status data and the optimum operation plan to the user in the form of an electronic signal. However, it is not limited thereto.

Referring to FIG. 2, the prediction unit 200 may include a data processing module 210, a learning data collection module 220, an algorithm providing module 230, a prediction module 240, and a generator emulator 250. .

The data processing module 210 may process raw data. The data processing module 210 may later process the raw data into a format required by the prediction module 240 and the algorithm providing module 230. The data processing module 210 may process data of a current time point among raw data and send the processed data to the prediction module 240. In addition, the data processing module 210 may process historical data of past time points among raw data and transmit the processed historical data to the learning data collection module 220.

The training data collection module 220 may generate training data using the raw data. The training data may be provided to the algorithm providing module 230 and used to update the prediction model of the algorithm. The learning data may be generated using past history data among raw data. The training data may be generated by selecting only data suitable for model training among raw data.

The algorithm providing module 230 may receive the training data from the training data collection module 220. The algorithm providing module 230 may apply a machine learning algorithm based on the training data to form a prediction model and update it. The machine learning algorithm may be a k-Nearest Neighbor algorithm. However, it is not limited thereto. The algorithm providing module 230 may update the prediction model and provide it to the prediction module 240.

The prediction module 240 may generate the prediction data using the processed raw data provided by the data processing module 210 and the prediction model updated and provided by the algorithm providing module 230.

The prediction data may include wind speed / insolation amount prediction data and power consumption amount prediction data. The power consumption prediction data may be transmitted to the operation plan optimizer 300.

The generator emulator 250 may be an emulator of a wind generator and a solar generator. The generator emulator 250 may generate wind / solar power generation forecast data using the wind speed / insolation amount prediction data. That is, the generator emulator 250 may predict the actual generation amount of renewable energy of the wind power generator and the solar generator using the data of the wind speed and the solar radiation amount. The generator emulator 250 may transmit the wind / solar power generation forecast data to the operation plan optimizer 300.

Referring to FIG. 3, the operation plan optimizer 300 may receive wind / solar power generation forecast data, power consumption forecast data, energy storage system status data, and diesel generator status data. The operation plan optimizer 300 may include a population 310 and a genetic operator 320.

The population 310 may include a plurality of candidate operation plans 311a and 311b therein. The candidate operation plans 311a and 311b inside the population 310 may include the amount of power generated by the diesel generator 410 per unit time.

Candidate operating plans

311a and 311b may be arbitrarily generated initially.

Genetic operator 320 may evaluate candidate

operational plans

311a and 311b in population 310. That is, the genetic operator 320 may derive evaluation values of the candidate operation plans 311a and 311b in the population 310. The evaluation value is determined in consideration of the operating cost and black out of the diesel generator 410. The said evaluation value is explained in full detail later.

The genetic operator 320 may use the evaluation value to alternate generations of candidate operation plans within the population 310 through genetic operations. The genetic operation may include at least one of crossover and mutation.

The breeding means generating new candidate operation plans 311a and 311b by intersecting the symbol strings of the two candidate operation plans 311a and 311b. However, the present invention is not limited thereto, and new candidate operation plans 311a and 311b may be generated by crossing not only two but also three or more candidate operation plans 311a and 311b. That is, it may be a method of forming a new child whose parents are the candidate candidate plans 311a and 311b. In the microgrid system according to some embodiments of the present invention, for example, a simulated binary crossover (SBX) operation may be performed. However, it is not limited thereto.

The mutation refers to a method in which at least a part of symbol strings of one

candidate operation plan

311a or 311b is changed in order or arbitrarily to generate another

candidate operation plan

311a or 311b. This mutation operation can prevent the entire

candidate operating plan

311a, 311b from falling into one regional optimal solution by crossover. In a microgrid system according to some embodiments of the present invention, for example, a PM (Polynomial Mutation) operation may be performed. However, it is not limited thereto.

The genetic operator 320 may derive an evaluation value by evaluating the newly formed candidate operation plans 311a and 311b. At this time, based on the evaluation value, the candidate operation plan 311b whose evaluation value is greater than or equal to a certain criterion is maintained in the population 310, and the candidate operation plan 311a whose evaluation value is lower than or equal to the specific criterion is removed from the population 310. can do. In this way, updating the group of candidate operation plans 311a and 311b having a high evaluation value through the genetic operation of the genetic calculator 320 is called generation replacement.

The genetic operator 320 may repeat the generation replacement several times. That is, the generation replacement can be completed when the preset number of times is met or the preset time limit is exceeded. At the end of the generation change, candidate operation plans 311a and 311b having the highest evaluation values may be selected as optimal operation plans. That is, the operation plan optimization unit 300 may select the candidate operation plans 311a and 311b having the highest evaluation values as the optimal operation plan.

Referring to FIG. 4, the candidate operation plans 311a and 311b may be represented by the solution representation of FIG. 4. The solution representation of FIG. 4 shows the power generation plan until h minutes after the diesel generator 410. Although not necessarily limited thereto, the candidate operation plans 311a and 311b may be normalized values of −1 to 1 based on the maximum allowable value per minute of the change in output per minute for each diesel generator 410.

For example, if the value of D _{t, 1} is 0.5, it means to increase 50KW when the allowable power change per minute of each diesel generator is 100KW.

Referring back to FIG. 3, after the candidate operation plans 311a and 311b of FIG. 4 are formed, the genetic operator 320 may evaluate the candidate operation plans 311a and 311b. At this time, the evaluation value may be the same as Equation 1.

Here, C is an evaluation value, and α may be an additional loss factor for preventing blackout.

In this case, C _DG is the total diesel generation cost, P _{DG, i, j} is the generation amount of the j-th unit of the i-th diesel generator over time. N is the total number of generators and H is the planning time. a, b and c are real coefficients.

At this time, LC _DG is the power shortage loss cost, and L _{DG, i, j} is the required generation amount by the j-th unit of the i-th diesel generator. N is the total number of generators and H is the planning time. L _{DG, i, j} may be a value obtained by subtracting the P _{DG, i, j} in the energy consumption prediction data.

The genetic operator 320 may derive the evaluation value C by using Equations 1 to 3 above. Accordingly, an optimal operation plan with the highest evaluation value C can be selected.

Referring to FIG. 5, the microgrid system according to some embodiments of the present invention may newly select and apply an optimum operation plan at a predetermined time (t minutes) even when an optimal operation plan is selected. That is, the operation planning period (P1 ~ P4) of diesel power generation can be newly started every t minutes. This is because it is established based on the estimated value of the power supply and demand, in order to reduce the risk of blackout or dump load of the diesel generator 410 when the difference between the actual power supply and demand is large. That is, by selecting a new optimal operation plan every predetermined time (t minutes), it is possible to cope with the unexpected imbalance of power supply and demand.

The microgrid system according to some embodiments of the present invention may use an evaluation value, such as Equation 4, which is more precise than the above-described embodiment.

Where C is an estimate, C _G (G _i ) is the cost of diesel generating per unit time, N is the present time point, α is an additional loss factor to prevent blackout, and C _P (G _i ) is the present time point. _GAVG is the average cost of diesel generation over a predetermined time period according to the existing diesel generation plan.

When the equation 4 is interpreted, the last term in equation 1,

Can be added to calculate the evaluation value C. The last term may be to add a blackout penalty in the future, unlike a blackout penalty in the current state.

For example, if the diesel power generation plan for the next four hours is established from the existing diesel power generation plan, the average diesel power generation for the four hours may be obtained as G _AVG . For example, if G _AVG is 400 KW, it may be determined whether or not the blackout is made in the future based on the diesel generating amount of 400 KW. This future time point may be viewed as, for example, 4 hours to 8 hours, and M in Equation 4 may be a time point at this time.

In order to calculate these values, naturally, the generation amount of renewable energy must be further predicted and utilized.

This allows the calculation of penalties for the prevention of blackouts in the long run, and allows for more precise microgrid operational planning.

Hereinafter, a method of operating a microgrid according to some embodiments of the present invention will be described with reference to FIGS. 1 to 7. Portions that overlap with the description of the microgrid operating system described above are briefly or omitted.

FIG. 6 is a flowchart illustrating a microgrid operating method according to some embodiments of the present invention, and FIG. 7 is a flowchart illustrating a detailed step of evaluating a candidate operation plan of FIG. 6.

3 and 6, a candidate operational development plan is generated (S100).

Candidate operating plans

311a and 311b may be arbitrarily generated initially.

Next, the candidate operation plan is evaluated (S200).

Genetic operator 320 may evaluate candidate

operational plans

311a and 311b in population 310. That is, the genetic operator 320 may derive evaluation values of the candidate operation plans 311a and 311b in the population 310. The evaluation value is determined in consideration of the operating cost and black out of the diesel generator 410.

3 and 7, the step S200 of evaluating the candidate operation plan may be described in detail.

First, the oil field calculator 320 receives the operation status data of the diesel generator / energy storage system and the power supply and demand prediction value (S210).

Subsequently, the genetic operator 320 receives candidate operation plans 311a and 311b from the population 310 (S220).

Subsequently, the oilfield calculator 320 determines the diesel generation amount, the energy storage system charge / discharge amount, and the blackout occurrence at each time point from the candidate operation plans 311a and 311b (S230).

At this time, the diesel generation amount for each time point is expressed in the candidate operation plans 311a and 311b as shown in FIG. The energy storage system charge / discharge amount is expressed as in Equation 5.

Here, P _ESS is the amount of charge / discharge of the energy storage system, and if greater than zero, the discharge from the energy storage system may be charged to the energy storage system. L is power demand, P _W is wind power generation and P _PV is solar power generation. P _DG is diesel generation.

Here, ESS _t ₊ ₁ is the energy storage system charge at the time t + 1, ESS _t is the energy storage system charge at the time t. P _ESS is the charge / discharge amount of the energy storage system.

At this time, blackout occurs when ESS _t ₊₁ is less than 0, and dump load occurs when ESS _t ₊₁ exceeds ESS _MAX .

Subsequently, an operation cost is calculated according to the amount of diesel generation and blackout occurring at each time point in the candidate operation plan (S240).

This may be calculated with reference to Equation 1 or Equation 4 above. In this case, α in Equations 1 and 4 may vary depending on whether blackout occurs.

3 and 6, it is determined whether the specified number of evaluation times or the time limit are exceeded (S300).

If the specified evaluation number or time limit is not exceeded, the candidate operation plan is updated based on the evaluation (S400).

The update may mean generation replacement according to genetic operation. That is, the genetic operator 320 may alternate generations of candidate operation plans in the population 310 through genetic calculation using the evaluation value. The genetic operation may include at least one of crossover and mutation.

If the specified evaluation number or time limit is exceeded, an optimal operation plan is selected using the evaluation value among candidate operation plans (S500).

Although the embodiments of the present invention have been described above with reference to the accompanying drawings, those skilled in the art to which the present invention pertains may be embodied in other specific forms without changing the technical spirit or essential features of the present invention. I can understand that. Therefore, it should be understood that the embodiments described above are exemplary in all respects and not restrictive.

Claims

An information provider for receiving raw data including operating status data of diesel power generation;

A prediction unit generating prediction data of diesel power generation using the furnace data;

An operation plan optimization unit for establishing an optimal operation plan of diesel power generation using the prediction data; And

Collecting the operation status data and delivering to the information providing unit, including a monitoring unit for delivering the operation status data and the optimal operation plan to the user,

The prediction unit comprises a training data collection module for generating training data using the raw data;

An algorithm providing module for providing and updating a prediction model using the training data;

And a prediction module for generating prediction data through the raw data and the prediction model.
According to claim 1,

The raw data includes at least one of weather forecast data, real-time weather data and real-time power consumption data.
The method of claim 2,

The weather forecast data includes at least one of wind speed forecast data and insolation forecast data.

The real-time weather data includes at least one of real-time wind speed data and real-time solar radiation data.
According to claim 1,

The operation plan optimization unit,

A population comprising a plurality of candidate operational plans,

Genetic operators for genetic generation of the plurality of candidate operating plans, including genetic operators (Genetic operators) for selecting the optimal operating plan,

The generation replacement genetically computes the plurality of candidate operating plans to add new candidate operating plans to the population, simulates each of the candidate operating plans to derive an evaluation value, and recalls some candidate operating plans according to the evaluation values. Including removing from the population,

Selecting the optimal operation plan includes selecting a candidate operation plan having the highest evaluation value as an optimal operation plan.
The method of claim 4, wherein

The genetic operation comprises at least one of a crossover operation and a mutation operation.
The method of claim 4, wherein

The evaluation value is a microgrid operating system derived by the following formula (1) to (3).

(1) Evaluation value = C DG + α × LC DG

(2)

(3)

Where α is an additional loss factor to prevent blackout, P DG, i, j is the generation of the jth unit of the i-th diesel generator over time, N is the total number of generators, H is the planned time point, a, b and c is a real number coefficient, and L DG, i, j is a value obtained by subtracting P DG, i, j from the real-time power consumption data.
The method of claim 4, wherein

The evaluation value is a microgrid operating system derived by the following formula (4).

(4)

Where C is the evaluation value, C G (G i ) is the diesel generating cost per unit time, N is the present point in time, α is an additional loss factor to prevent blackout, and C P (G i ) is the present point in time G AVG is the average cost of diesel generation over a predetermined period of time according to the currently established diesel generation plan, and M is the end point in the future for applying a blackout penalty.
The method of claim 7, wherein

The power generation unit is controlled by the optimum operation plan and transmits operation status data to the monitoring unit.

The power generation unit microgrid operating system including a diesel generator, an energy storage system (ESS) and a power transmission system.
The information service department receives the raw data including the operating status data of diesel power generation,

The prediction unit generates the prediction data of the diesel power generation using the furnace data,

The operation plan optimizer creates a plurality of candidate operation plans for diesel generation,

The operation plan optimizer evaluates each of the plurality of candidate operation plans to derive an evaluation value,

When not exceeding a preset number or time limit, the operation plan optimizer updates the candidate operation plan according to the evaluation value, derives an updated evaluation value of the candidate operation plan, and sets the preset number or time limit. When exceeding, the operation plan optimization unit selects an optimal operation plan of the candidate operation plan using the evaluation value,

And the operation plan optimizer controls a power generation unit according to the optimum operation plan.
The method of claim 9,

Deriving the evaluation value, microgrid operation method comprising the following formula (1) to (3).

(1) Evaluation value = C DG + α × LC DG

(2)

(3)

Where α is an additional loss factor to prevent blackout, P DG, i, j is the generation of the jth unit of the i-th diesel generator over time, N is the total number of generators, H is the planned time point, a, b and c is a real number coefficient, and L DG, i, j is a value obtained by subtracting P DG, i, j from the real-time power consumption data.
The method of claim 9,

Deriving the evaluation value micro grid operating system comprising the following formula (4).

(4)

Where C is the evaluation value, C G (G i ) is the diesel generating cost per unit time, N is the present point in time, α is an additional loss factor to prevent blackout, and C P (G i ) is the present point in time G AVG is the average cost of diesel generation over a predetermined period of time according to the currently established diesel generation plan, and M is the end point in the future for applying a blackout penalty.
The method of claim 9,

Generating the prediction data,

The training data collection module collects the raw data to generate training data.

An algorithm providing module provides and updates a prediction model using the training data,

And a prediction module generating prediction data through the raw data and the prediction model.
The method of claim 9,

Selecting the optimal operation plan,

And reselecting said optimal operating plan at predetermined intervals.