# US 2024/0202825 A1 · Method for optimizing power trading profit of a virtual power plant and a system thereof

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2024/0202825 A1
- Document ID: US20240202825A1
- Status: Published application
- Kind: A1
- Application number: 18/541,451
- Filed: 2023-12-15
- Published: 2024-06-20
- Earliest claimed: 2022-12-19
- Assignees: Hyundai Autoever Corp.
- Applicants: Hyundai Autoever Corp.
- Inventors: Dae Gun Ko; Claire Park; Kyung Hwan Park; Hae Lyong Choi
- Web page: https://patentgrep.com/patent/US20240202825A1

## CPC

- G06Q 40/04: Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
- G06Q 50/06: Energy or water supply
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

A method for optimizing power trading profits of a virtual power plant includes obtaining data on constraints of an optimal control model for optimizing power trading profits of the virtual power plant composed of renewable energy use devices including a first electric vehicle using a managed charging method (V1G), a second electric vehicle using a vehicle-to-grid charging method (V2G), an energy storage system (ESS), and a photovoltaic (PV); and inputting input data including a variable value to the optimal control model and outputting data on optimal power trading profits of the virtual power plant using an output value of the optimal control model. The variable value includes schedule data for each time zone of the first electric vehicle, schedule data for each time zone of the second electric vehicle, schedule data for each time zone of the ESS, and schedule data for each time zone of the PV.

## Claims

### Claim 1

A method for optimizing power trading profits of a virtual power plant, the method being performed by a computing system, the method comprising:
obtaining data on constraints of an optimal control model for optimizing power trading profits of the virtual power plant, wherein the virtual power plant comprises renewable energy use devices including a first electric vehicle using a managed charging method (V1G), a second electric vehicle using a vehicle-to-grid charging method (V2G), an energy storage system (ESS), and a photovoltaic (PV); and
inputting input data, including a variable value, to the optimal control model and outputting data on optimal power trading profits of the virtual power plant using an output value of the optimal control model, under the constraints,
wherein the variable value includes schedule data for each time zone of the first electric vehicle, schedule data for each time zone of the second electric vehicle, schedule data for each time zone of the ESS, and schedule data for each time zone of the PV.

### Claim 2 (depends on 1)

The method of claim 1, wherein the constraints express that it is possible to participate in a power trading market for conducting power trading using the renewable energy use devices only for a pre-designated minimum trading time or more.

### Claim 3 (depends on 1)

The method of claim 1, wherein the constraints include a condition in which the first electric vehicle or the second electric vehicle participates in a power trading market only when it is connected to a pre-designated charging device to be in a standby state.

### Claim 4 (depends on 1)

The method of claim 1, wherein the constraints consider priorities given to each power trading market of a plurality of power trading markets.

### Claim 5 (depends on 1)

The method of claim 1, wherein the input data further includes data on initial battery states of charge of the renewable energy use devices.

### Claim 6 (depends on 1)

The method of claim 1, wherein the input data further includes data on a battery charging amount when the first electric vehicle departs according to a planned schedule of the first electric vehicle or data on a battery charging amount when the second electric vehicle departs according to a planned schedule of the second electric vehicle.

### Claim 7 (depends on 1)

The method of claim 1, wherein the input data further includes a predicted solar energy power generation amount of the PV.

### Claim 8 (depends on 1)

The method of claim 1, wherein the input data further includes predicted power demand for each building included in the virtual power plant.

### Claim 9 (depends on 8)

The method of claim 8, further comprising: calculating the predicted power demand for each building by inputting a power usage amount during a past pre-designated time, weather information, and date information to a power demand prediction model and using a result value extracted from the power demand prediction model.

### Claim 10 (depends on 1)

The method of claim 1, further comprising: finding, by the optimal control model, the variable value for deriving a minimum value of a difference between a charging cost value and a profit value during a schedule creation period,
wherein the charging cost is a charging cost of the first electric vehicle, the second electric vehicle, and the ESS, and
wherein the profits are profits of the first electric vehicle, the second electric vehicle, the ESS, and the PV.

### Claim 11 (depends on 1)

The method of claim 1, wherein the constraints include a condition in which it is possible to participate in a power trading market for conducting power trading using the renewable energy use devices every 4 hours, a condition in which each of the renewable energy use devices creates only one schedule for each time zone, a condition in which only a renewable energy use device that has obtained certification in advance among the renewable energy use devices participates in the power trading market, a condition in which the first electric vehicle or the second electric vehicle participates in the power trading market only when it is on standby at an electric vehicle charger (EVC), a condition in which hourly charging and discharging amounts of the renewable energy use devices follow established standards, and a condition in which the renewable energy use devices most preferentially participate in a power trading market that has already successfully bid, and
wherein the input data includes data on initial battery states of charge of the renewable energy use devices, data on a battery charging amount when the first electric vehicle or the second electric vehicle departs according to a planned schedule of the first electric vehicle or the second electric vehicle, a predicted solar energy power generation amount of the PV, and predicted power demand for each building included in the virtual power plant.

### Claim 12 (depends on 11)

The method of claim 11, wherein the optimal control model is a mixed integer linear programming (MILP) model,
wherein the method further comprises calculating the predicted power demand for each building included in the virtual power plant and the predicted solar energy power generation amount of the PV by inputting a power usage amount during a past pre-designated time, weather information, and date information to a power demand prediction model and using a result value extracted from the power demand prediction model, and
wherein the power demand prediction model is a bidirectional long short-term memory (BLSTM) model.

### Claim 13

An operation server of a virtual power plant, comprising:
one or more processors;
a memory configured to store one or more instructions; and
a communication interface,
wherein the one or more processors are configured, by executing the stored one or more instructions, to:
perform an operation of obtaining data on constraints of an optimal control model for optimizing power trading profits of the virtual power plant, wherein the virtual power plant comprises renewable energy use devices including a first electric vehicle using a managed charging method (V1G), a second electric vehicle using a vehicle-to-grid charging method (V2G), an energy storage system (ESS), and a photovoltaic (PV); and
perform an operation of inputting input data including a variable value to the optimal control model and outputting data on optimal power trading profits of the virtual power plant using an output value of the optimal control model, under the constraints,
wherein the variable value includes schedule data for each time zone of the first electric vehicle, schedule data for each time zone of the second electric vehicle, schedule data for each time zone of the ESS, and schedule data for each time zone of the PV.

### Claim 14 (depends on 13)

The operation server of claim 13, wherein the constraints include a condition in which it is possible to participate in a power trading market for conducting power trading using the renewable energy use devices every 4 hours, a condition in which each of the renewable energy use devices creates only one schedule for each time zone, a condition in which only a renewable energy use device that has obtained certification in advance among the renewable energy use devices participates in the power trading market, a condition in which the first electric vehicle or the second electric vehicle participates in the power trading market only when it is on standby at an electric vehicle charger (EVC), a condition in which hourly charging and discharging amounts of the renewable energy use devices follow established standards, and a condition in which the renewable energy use devices most preferentially participate in a power trading market that has already successfully bid.

### Claim 15 (depends on 13)

The operation server of claim 13, wherein the input data includes data on initial battery states of charge of the renewable energy use devices, data on a battery charging amount when the first electric vehicle or the second electric vehicle departs according to a planned schedule of the first electric vehicle or the second electric vehicle, a predicted solar energy power generation amount of the PV, and predicted power demand for each building included in the virtual power plant.

### Claim 16 (depends on 15)

The operation server of claim 15, wherein the optimal control model is a mixed integer linear programming (MILP) model,
wherein the predicted power demand for each building included in the virtual power plant and the predicted solar energy power generation amount of the PV are values calculated by inputting a power usage amount during a past pre-designated time, weather information, and date information to a power demand prediction model and using a result value extracted from the power demand prediction model, and
wherein the power demand prediction model is a bidirectional long short-term memory (BLSTM) model.

### Claim 17 (depends on 13)

The operation server of claim 13, wherein the optimal control model is a model configured to find the variable value for deriving a minimum value of a difference between a charging cost value and a profit value during a schedule creation period,
wherein the charging cost is a charging cost of the first electric vehicle, the second electric vehicle, and the ESS, and
wherein the profits are profits of the first electric vehicle, the second electric vehicle, the ESS, and the PV.
