Apparatus and method for operating virtual power plant

Abstract

An apparatus for operating a virtual power plant (VPP), according to one embodiment of the present disclosure, may comprise a processor for identifying, on the basis of receiving a power supply instruction regarding output limitations of the VPP, an output amount to be distributed to a plurality of renewable energy power plants in the VPP in correspondence to the power supply instruction, limiting, on the basis of the identified output amount, the output of second power control devices that excludes at least one predefined first power control device from among a plurality of power control devices included in each renewable energy power plant, and acquiring power generation amount data from the first power control device.

Description

Operating device and operating method of a virtual power plant

[0001] The present invention relates to an operating device and operating method of a virtual power plant.

[0002] Recently, the adoption rate of renewable energy-based Distributed Energy Resources (DERs) has been increasing worldwide. With the expansion of renewable energy, there is a growing number of attempts to build Virtual Power Plants (VPPs) based on Information and Communications Technology (ICT) to integrate and operate distributed energy resources as if they were a single power plant in order to resolve issues such as the uncertainty of renewable energy output and the stability of the distribution system.

[0003] The virtual power plant operation system comprises forecasting, bidding, operation, and settlement processes. Among these, forecasting is affected by environmental factors such as weather and regional characteristics; therefore, improving forecasting accuracy is essential to contribute to grid stabilization and the operator's profitability.

[0004] In order to efficiently operate power systems connected to distributed energy and provide stable power supply services, a renewable energy generation forecasting system has been established, which forecasts the generation of renewable energy such as solar and wind power plants of 20 MW or more, submits the forecast to the Power Exchange, and sets the unit price based on the error rate with the actual generation.

[0005] Accordingly, virtual power plants participating in the wholesale electricity market may limit or reduce their output by controlling it in cases where they generate more power than the awarded amount due to their own forecasting errors, or in accordance with dispatch instructions from the system operator for various reasons (such as supply and demand balance).

[0006] When output limitations occur, the virtual power plant restricts the output that renewable energy resources can generate, resulting in power generation at a lower output than the actual potential; consequently, it becomes outlier data with a very low correlation between the weather information used for forecasting and the power generation output.

[0007] Since such outlier data must be excluded from training, it is becoming difficult to secure actual data to continuously update the power generation prediction model.

[0008] The objective of the present invention is to provide a method for obtaining power generation data for predicting renewable energy generation in an output-limited environment.

[0009] An operating device for a virtual power plant (VPP) according to one embodiment of the present invention may include a processor that, based on receiving a dispatch instruction regarding output restriction of the virtual power plant, identifies an output amount to be distributed to a plurality of renewable energy power plants within the virtual power plant in response to said dispatch instruction, restricts the output of the remaining second power control devices, excluding at least one first power control device defined among a plurality of power control devices included in each renewable energy power plant based on the identified output amount, and obtains power generation data from said first power control device.

[0010] The above processor can distribute output to each renewable energy power plant based on at least one of the capacity and output of the plurality of renewable energy power plants.

[0011] The processor can distribute output to the second power control device based on at least one of the output of the first power control device and the capacity and output of the second power control device.

[0012] The above processor can expand the power generation amount of the first power control device in proportion to the capacity of each renewable energy power plant.

[0013] The above processor can generate or update a power generation prediction model using the power generation data and weather data.

[0014] A method for operating a virtual power plant (VPP) performed by an operating device according to an embodiment of the present invention may include: a step of identifying an output amount to be distributed to a plurality of renewable energy power plants within the virtual power plant in response to a dispatch instruction based on receiving a dispatch instruction regarding output limiting of the virtual power plant; a step of limiting the output of the remaining second power control devices, excluding at least one first power control device defined among a plurality of power control devices included in each renewable energy power plant based on the identified output amount; and a step of obtaining power generation data from the first power control device.

[0015] The step of identifying the amount of output to be distributed to the plurality of renewable energy power plants may include the step of distributing output to each renewable energy power plant based on at least one of the capacity and output of the plurality of renewable energy power plants.

[0016] The step of limiting the output of the second power control device may include the step of distributing the output to the second power control device based on at least one of the output of the first power control device and the capacity and output of the second power control device.

[0017] After the step of acquiring the above power generation data, the method may further include a step of expanding the power generation of the first power control device in proportion to the capacity of each renewable energy power plant.

[0018] After the step of acquiring the above-mentioned power generation data, the method may further include a step of generating or updating a power generation prediction model using the above-mentioned power generation data and weather data.

[0019] According to one embodiment of the present invention, it is possible to ensure the acquisition of data for performance optimization of a power generation prediction model while adjusting the output according to the requirements of a power system operator. Through this, the power generation prediction model can be kept up to date and its accuracy can be continuously improved.

[0020] FIG. 1 is a schematic diagram illustrating a virtual power plant operation system according to one embodiment of the present invention.

[0021] FIG. 2 is a block diagram illustrating the configuration of a virtual power plant operation device according to an embodiment of the present invention.

[0022] FIG. 3 is a diagram illustrating the operation flowchart of a virtual power plant operating device according to one embodiment of the present invention.

[0023] FIG. 4 is a diagram illustrating the operation of a virtual power plant operating device according to the first embodiment of the present invention.

[0024] FIG. 5 is a diagram illustrating the operation of a virtual power plant operating device according to a second embodiment of the present invention.

[0025] Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the accompanying drawings. The detailed description disclosed below, together with the accompanying drawings, is intended to describe exemplary embodiments of the present invention and is not intended to represent the only embodiment in which the present invention can be practiced. In order to clearly explain the present invention in the drawings, parts unrelated to the description may be omitted, and the same reference numerals may be used for identical or similar components throughout the specification.

[0026] FIG. 1 is a schematic diagram illustrating a virtual power plant operation system according to one embodiment of the present invention.

[0027] A virtual power plant operating device (100) (hereinafter also referred to as the operating device (100)) according to one embodiment of the present invention is a device for operating a virtual power plant and can be implemented as a computer, a PLC (Programmable Logic Controller), a server, a smartphone, a tablet PC, a smart pad, a laptop, etc.

[0028] A virtual power plant (VPP) (200) is a system that connects distributed small-scale energy resources (solar, wind, energy storage systems, electric vehicles, etc.) to a digital network and operates them as one large-scale power plant.

[0029] A virtual power plant (200) may include a plurality of renewable energy power plants (1, 2, ..., n), and each renewable energy power plant may again include a plurality of power conditioning units (PCU1, PCU2, ..., PCU n). A power conditioning unit (PCU) is a device that converts and manages power generated in a power generation system to suit the power grid. The power conditioning unit can perform power conversion, voltage and frequency regulation, power generation optimization, power grid connection and protection, etc.

[0030] The operating device (100) can predict the power generation of each resource through the virtual power plant (200), coordinate power demand and supply, compensate for renewable energy variability, and increase grid stability. In addition, small-scale resources can also participate in the power market, enabling efficient and environmentally friendly energy operation. At this time, tasks such as prediction, bidding, operation, and settlement can be performed by a single operating device (100), but are not limited thereto, and separate operating devices (100) performing one or more tasks can be distributed and operated.

[0031] As power generation forecasting is required daily or hourly, the processes of data collection, data preprocessing, training (updating) the forecast model, model deployment, and monitoring are carried out repeatedly, while continuous attempts are being made to improve forecast accuracy. One such effort is the continuous updating of the forecast model, and to successfully execute this, power generation and weather data must be continuously collected.

[0032] However, as described above, with the implementation of the power generation forecasting system, power system operators (e.g., power exchanges) are restricting the power of virtual power plant operators for various reasons, such as when the current power output is higher than the amount of power awarded to each virtual power plant operator, or when the supply exceeds the demand of the power system in the higher-level system.

[0033] As such, power generation data obtained when output limitations occur is unsuitable for use as training data for power generation prediction models.

[0034] Therefore, the present invention proposes a method for generating power in accordance with weather conditions by not imposing power limits on some power control devices through power distribution. The power generation data (actual data) obtained from these power control devices will be suitable for use as training data for a power generation prediction model.

[0035] Hereinafter, the configuration and operation of an operating device (100) according to one embodiment of the present invention will be described in detail with reference to the drawings.

[0036] FIG. 2 is a block diagram illustrating the configuration of a virtual power plant operation device according to an embodiment of the present invention.

[0037] An operating device (100) according to one embodiment of the present invention includes an input unit (110), a communication unit (120), a display unit (130), a storage unit (140), and a processor (150).

[0038] The input unit (110) generates input data in response to user input of the operating device (100). For example, the user input may be a power control device that does not limit the output, a user input that sets a power control device to limit the output, a user input that sets a standard for distributing the output, and other user inputs that are necessary for the operation of the virtual power plant, which can be applied without restriction.

[0039] The input unit (110) includes at least one input means. The input unit (110) may include a keyboard, a key pad, a dome switch, a touch panel, a touch key, a mouse, a menu button, etc.

[0040] The communication unit (120) can communicate with external devices such as a data provider server, API, and power system operator server to transmit and receive power generation data, weather data, learning data, power generation prediction model, and output distributed by renewable energy power plant / power control device.

[0041] To this end, the communication unit (120) can perform wireless communication such as 5G (5th generation communication), LTE-A (long term evolution-advanced), LTE (long term evolution), Wi-Fi (wireless fidelity), Bluetooth, or wired communication such as LAN (local area network), WAN (Wide Area Network), and power line communication.

[0042] The display unit (130) displays display data according to the operation of the operating device (100). The display unit (130) may display, for example, a screen displaying received dispatch instructions, a screen displaying distributed output amounts by renewable energy power plant / power control device, a screen displaying the operation of each power control device, a screen displaying power generation prediction information output from a power generation prediction model, and other screens receiving user input.

[0043] The display unit (130) includes a liquid crystal display (LCD), a light emitting diode (LED) display, an organic light emitting diode (OLED) display, a micro electro mechanical systems (MEMS) display, and an electronic paper display. The display unit (130) can be combined with the input unit (110) to be implemented as a touch screen.

[0044] The storage unit (140) stores operation programs of the operating device (100). The storage unit (140) includes storage with non-volatile properties that can preserve data (information) regardless of whether power is provided, and memory with volatile properties in which data to be processed by the processor (150) is loaded and data cannot be preserved if power is not provided. Storage includes flash memory, hard-disc drive (HDD), solid-state drive (SSD), and ROM (Read Only Memory), and memory includes buffer and RAM (Random Access Memory).

[0045] The storage unit (140) can store power generation data, weather data, learning data, power generation prediction models, and distributed output amounts per renewable energy power plant / power control device.

[0046] The storage unit (140) can store computational programs, etc., required in the process of identifying the output amount for each renewable energy power plant / power control device, limiting the output, and obtaining power generation data.

[0047] The processor (150) can control at least one other component (e.g., hardware or software component) of the operating device (100) by executing software such as a program, and can perform various data processing or operations.

[0048] A processor (150) according to one embodiment of the present invention, based on receiving a dispatch instruction regarding output limitation of a virtual power plant, identifies an output amount to be distributed to a plurality of renewable energy power plants within the virtual power plant in response to the dispatch instruction, limits the output of the remaining second power control devices excluding at least one first power control device defined among a plurality of power control devices included in each renewable energy power plant based on the identified output amount, and can obtain power generation data from the first power control device.

[0049] Meanwhile, the processor (150) may perform at least some of the data analysis, processing, and result information generation for performing the above operations using at least one of machine learning, neural network, or deep learning algorithms as a rule-based or artificial intelligence algorithm. Examples of neural networks may include models such as CNN (Convolutional Neural Network), DNN (Deep Neural Network), and RNN (Recurrent Neural Network).

[0050] FIG. 3 is a diagram illustrating the operation flowchart of a virtual power plant operating device according to one embodiment of the present invention.

[0051] According to one embodiment of the present invention, the processor (150) can identify the amount of output to be distributed to a plurality of renewable energy power plants within the virtual power plant in response to the power supply instructions based on receiving a power supply instruction regarding the output limit of the virtual power plant (200) (S10).

[0052] A dispatch instruction regarding output limitation may be issued by a power system operator (e.g., a power exchange) when the current power output is higher than the amount of power generated by each virtual power plant operator that was awarded in the bid, or when the supply of the power system exceeds the demand of the upper system, and the reason is not limited to any one. The processor (150) may receive a dispatch instruction from the power system operator's server, etc., but the instruction reception path is also not limited to any one.

[0053] In addition, power supply instructions regarding output limits can be divided into methods of specifying the absolute output and methods of specifying the reduction amount. The method of specifying the absolute output is the commonly used method, for example, the absolute output can be set to 1000W. The method of specifying the reduction amount can be used when the output amount needs to be adjusted quickly in real-time situations, for example, the reduction output can be set to 200W.

[0054] In the event that an output limit occurs, the processor (150) may distribute output to each renewable energy power plant based on at least one of the capacity and output of the multiple renewable energy power plants. Power plant capacity refers to the maximum amount of power that a power plant can produce, and power plant output refers to the amount of power that the power plant is currently actually producing. Power plant output fluctuates over time and may be affected by demand, weather conditions, equipment status, etc.

[0055] For example, if the target output of 10 renewable energy power plants is set to 1000W, the output of each renewable energy power plant can be distributed in proportion to the capacity of each renewable energy power plant. If the capacity of each renewable energy power plant is the same, each renewable energy power plant is limited to outputting 100W. Alternatively, the output of each renewable energy power plant can be distributed in proportion to the current production output of each renewable energy power plant.

[0056] The processor (150) can command control by distributing output to each renewable energy power plant within the virtual power plant. When a command is transmitted to each power plant, it is delivered to the power control device within the power plant and limits the output according to the instructions.

[0057] According to one embodiment of the present invention, the processor (150) can limit the output of the remaining second power control devices, excluding at least one first power control device defined among the plurality of power control devices included in each renewable energy power plant, based on the identified output amount (S20).

[0058] Some (or one) of the multiple power control devices present in each power plant is configured not to perform output control, and the remaining power control devices that perform output control share and distribute the amount of output to be distributed to the power control devices that do not perform output control. Hereinafter, the power control device whose output is not limited is referred to as the first power control device, and the power control device whose output is limited is referred to as the second power control device.

[0059] The criteria for selecting the first power control unit among multiple power control units within each power plant may include placement location and capacity. For example, it may be a power control unit placed in a location with a low communication success rate due to the network structure. This is because the requirements for a communication success rate are lower compared to the second power control unit, which requires smooth output limiting. As another example, the lower the capacity, the higher the probability of being selected as the first power control unit. This is because, although the first power control unit has no restrictions on power production, the renewable energy power plant containing it is subject to power limitations; therefore, power production must be managed to the extent that it does not negatively impact these limitations.

[0060] The processor (150) can distribute output to the second power control device based on at least one of the output of the first power control device and the capacity and output of the second power control device. After considering the output of the first power control device, the processor (150) can distribute output between the second power control devices based on at least one of the capacity and output of the second power control device.

[0061] According to one embodiment of the present invention, the processor (150) can obtain power generation data from the first power control device (S30).

[0062] Power generation data may include, for example, the power generation amount of the corresponding power control device, and may also include information such as the generator type, generator ID, discharge / charge status, date, and time.

[0063] The power generation data of a power control device that has not performed output control can be used as training data for a power generation prediction model. The processor (150) can scale up the power generation of the first power control device in proportion to the capacity of each renewable energy power plant. That is, the capacity of the power control device is scaled up to the total capacity of the power plant and used as power generation data for the entire power plant. The processor (150) can create or update a power generation prediction model using the power generation data and weather data.

[0064] According to one embodiment of the present invention, power generation data without output limitations can be acquired in a situation where output limitations occur, thereby providing power generation data necessary for updating a prediction model. Through this, the power generation prediction model can be kept up to date and its accuracy can be continuously improved.

[0065] FIG. 4 is a diagram illustrating the operation of a virtual power plant operating device according to the first embodiment of the present invention.

[0066] The virtual power plant operating device (100) manages the virtual power plant (200) and manages the operation of each renewable energy power plant (210, 220, 230, ...) within the virtual power plant (200).

[0067] Each renewable energy power plant (210, 220, 230, ...) includes a first power control device (211, 221, 231, ...) that does not limit output even when receiving a dispatch instruction, and a second power control device (212, 222, 232, ...) that limits output according to the dispatch instruction.

[0068] The operating device (100) can obtain total power generation data of renewable energy power plant 1 (210) by expanding the power generation data of the first power control device (211), obtain total power generation data of renewable energy power plant 2 (220) by expanding the power generation data of the first power control device (221), and obtain total power generation data of renewable energy power plant n (230) by expanding the power generation data of the first power control device (231).

[0069] For example, when the power generation amount of the first power control device (211) is 100W and both the first power control device (211) and the second power control device (212) have the same power generation capacity, the operating device (100) can identify the power generation amount of the renewable energy power plant 1 (210) as (100*N)W.

[0070] FIG. 5 is a diagram illustrating the operation of a virtual power plant operating device according to a second embodiment of the present invention.

[0071] As described above with reference to FIG. 3, we will examine the process of updating and using a power generation prediction model using power generation data (510) obtained from the first power control device.

[0072] The operating device (100) can generate / update a power generation prediction model (530) using power generation data (510) and weather data (520). At this time, the power generation data (510) is data obtained through S30 of FIG. 3, and the weather data (520) is actual weather data at the time when the power generation data (510) is obtained.

[0073] The renewable energy generation forecasting system described above consists of a system that forecasts the amount of power generated for 24 hours from 00:00 to 24:00 on the day before the transaction (hereinafter referred to as the short-term forecasting system) and a system that forecasts the amount of power generated for the next 24 hours based on each hourly forecasting point (hereinafter referred to as the ultra-short-term forecasting system).

[0074] Currently, power system operators request generation forecast information twice a day (at 10:00 AM and 5:00 PM) on the day prior to trading for the short-term forecast system, and request hourly generation forecast information for the ultra-short-term forecast system (the number of forecasts and the timing of forecasts for the short-term and ultra-short-term forecast systems are merely examples and may change depending on policy).

[0075] The power generation prediction model (530) is trained to predict the amount of power generation corresponding to the forecast data (540) using actual measured power generation data (510) and weather data (520). The forecast data (540) is data that predicts weather changes.

[0076] Since the power generation prediction model (530) is generated and distributed for each renewable energy power plant, the training data for generating the model and the input data to be input into the model can also be generated for each model.

[0077] Weather data (520) may include, for example, temperature, precipitation, wind speed, humidity, solar radiation, snow cover, and total cloud cover in the area of ​​the power plant, and may also include information such as a set resource name, unique area name, latitude, longitude, date, and time. At this time, since solar radiation among the weather data is important information for predicting power generation, it may be collected from two or more weather centers (i.e., two or more APIs), and in addition to solar radiation, information such as azimuth angle and zenith angle may be collected.

[0078] There may be various ways to update the power generation prediction model (530). For example, the currently deployed model can be updated using newly collected power generation data (510) and weather data (520). As another example, a new model can be created using newly collected power generation data (510) and weather data (520), and the performance difference between the currently deployed model and the newly created model can be compared to update to the model with better performance.

[0079] The operating device (100) can obtain power generation prediction data (550) through a power generation prediction model (530) and bid (560) using the power generation prediction data (550).

[0080] According to one embodiment of the present invention, it is possible to ensure the acquisition of data for performance optimization of a power generation prediction model while adjusting the output according to the requirements of a power system operator.

Claims

1. In an operating device for a Virtual Power Plant (VPP), Based on receiving a dispatch instruction regarding the output limit of a virtual power plant, identify the amount of output to be distributed to a plurality of renewable energy power plants within the virtual power plant in response to the said dispatch instruction, and Based on the identified output amount, the output of the remaining second power control devices is limited, excluding at least one predefined first power control device among the plurality of power control devices included in each renewable energy power plant, and An operating device comprising a processor that acquires power generation data from the first power control device.

2. In Paragraph 1, The above processor is, An operating device that distributes output to each renewable energy power plant based on at least one of the capacity and output of the plurality of renewable energy power plants.

3. In Paragraph 1, The above processor is, An operating device that distributes output to the second power control device based on at least one of the output of the first power control device and the capacity and output of the second power control device.

4. In Paragraph 1, The above processor is, An operating device that expands the power generation amount of the first power control device in proportion to the capacity of each renewable energy power plant.

5. In Paragraph 4, The above processor is, An operating device that generates or updates a power generation prediction model using the above-mentioned power generation data and weather data.

6. A method for operating a Virtual Power Plant (VPP) performed by an operating device, A step of identifying an amount of output to be distributed to a plurality of renewable energy power plants within a virtual power plant in response to said dispatch instruction, based on receiving a dispatch instruction regarding the output limit of a virtual power plant; A step of limiting the output of the remaining second power control devices, excluding at least one predefined first power control device among a plurality of power control devices included in each renewable energy power plant based on the identified output amount; An operation method comprising the step of obtaining power generation data from the first power control device.

7. In Paragraph 6, The step of identifying the output amount to be distributed to the plurality of renewable energy power plants mentioned above is, An operation method comprising the step of distributing output to each renewable energy power plant based on at least one of the capacity and output of the plurality of renewable energy power plants.

8. In Paragraph 6, The step of limiting the output of the second power control device is, An operating method comprising the step of distributing output to the second power control device based on at least one of the output of the first power control device and the capacity and output of the second power control device.

9. In Paragraph 6, After the step of acquiring the above power generation data, An operation method further comprising the step of expanding the power generation amount of the first power control device in proportion to the capacity of each renewable energy power plant.

10. In Paragraph 9, After the step of acquiring the above power generation data, An operation method further comprising the step of creating or updating a power generation prediction model using the above power generation data and weather data.

Images