Distributed electric energy transaction method and system based on virtual power plant

Abstract

The invention provides a distributed electric energy transaction method and system based on a virtual power plant, and belongs to the technical field of energy. The method comprises the following steps of: scheduling and trading among power plants; taking electric energy prices and allocation time as comprehensive indexes in the scheduling process among the power plants; the lowest scheduling scheme of the comprehensive indexes is obtained through calculation, and the electric energy scheduling work of the virtual power plant in a period of time in the future is completed through the lowest scheduling scheme of the comprehensive indexes; the unit price of each power plant for supplying power to the corresponding user is obtained through the actual condition of each power plant in the virtual power plant, and the total transaction price between the virtual power plant and the user is obtained by combining the total consumed electric quantity of the corresponding user; according to the method, electric energy transactions of virtual power plants are divided into scheduling and transactions among the power plants and transactions between the power plants and users; therefore, the scheduling and transaction process is clearer and simpler, the scheduling algorithm is simplified, and the technical implementation cost and security are improved.

Description

Technical Field

[0001] The present invention relates to the field of energy technology, and in particular to a distributed power trading method and system based on a virtual power plant. Background Art

[0002] In the past few decades, traditional power systems have mainly relied on large centralized power plants, which usually use coal and natural gas as their main energy sources and transmit electricity to end users through long-distance power transmission networks; however, this traditional energy production and distribution model has some obvious challenges, including unstable energy supply, environmental pollution, low energy efficiency and slow response to changes in local market demand.

[0003] With the advancement of technology and the promotion of policies, distributed energy systems are gradually emerging. Distributed energy refers to small-scale power generation or energy storage near consumers or directly at the consumer end, mainly including renewable energy equipment such as solar energy, wind energy, hydropower and energy storage batteries. The advantage of these methods is that they can provide more flexible, low-carbon and efficient power supply, reducing dependence on traditional centralized power networks. However, the uneven distribution, volatility and unpredictability of distributed energy also bring management difficulties. In order to optimize the utilization of these distributed energy resources and ensure the reliability and economy of power supply, virtual power plant (VPP) technology came into being.

[0004] Virtual power plant technology uses information and communication technology (ICT) to integrate multiple distributed energy resources into a unified virtual power supplier, with the scheduling and control functions of a centralized power plant. Virtual power plants can not only optimize the power output of each distributed power generation unit, but also realize the intelligent scheduling of energy storage equipment, load balancing management, and flexible participation in the power market. The core of the virtual power plant lies in its flexible scheduling and market responsiveness of distributed resources, allowing these resources to participate in power market transactions like traditional power plants and make real-time adjustments based on changes in demand and prices, thereby improving the stability of the power grid, enhancing the intelligence level of the power system and reducing overall system costs.

[0005] In terms of electricity trading, with the development of smart grid technology and power market mechanisms, the role of virtual power plants in electricity trading is becoming increasingly important; traditional electricity trading usually relies on long-term electricity contracts and grid dispatching between large power plants, but with the emergence of distributed energy and virtual power plants, electricity trading has become more complex and dynamic; the distributed electricity trading method of virtual power plants utilizes highly automated control systems, through real-time data transmission, market demand response and optimized scheduling, so that these distributed energy can be flexibly bought and sold in the electricity market, further improving the utilization efficiency of power resources and promoting the access and consumption of renewable energy.

[0006] As the proportion of renewable energy gradually increases, the power system will rely more on flexible, intelligent and efficient power trading systems; the distributed power trading method based on virtual power plants is not only a technical supplement and innovation to the traditional power system, but also provides important technical support for building a low-carbon, efficient and intelligent energy Internet; its promotion and application will help achieve a broader energy transformation, promote the popularization of green and low-carbon technologies and the realization of sustainable development goals.

[0007] However, there are still many problems in the scheduling and trading of virtual power plants, such as overly complex scheduling algorithms, increased costs of technical implementation, and safety issues. Therefore, what technology can be used to improve and solve these problems is the main research direction of virtual power plant technology. Summary of the Invention

[0008] The purpose of the present invention is to overcome the above problems existing in the prior art and to greatly improve its technical effect on the basis of the original technology. The present invention provides a distributed power trading method based on a virtual power plant, which includes:

[0009] S1, scheduling and trading between power plants: the power plants refer to a plurality of distributed energy resources distributed in different locations that make up a virtual power plant; the steps of scheduling and trading between power plants are as follows: S11, predicting the power generation of each power plant and the power required by the users of the corresponding power plants in the future through a neural network algorithm, calculating the difference between the power generation of each power plant and the power required by the users of the corresponding power plants, and judging whether the power generation of the corresponding power plant is in excess or insufficient capacity; the future period refers to the time set according to the number and status of power plants in the virtual power plant; S12, the power plants with excess capacity obtained by scheduling S11 supply power to the power plants with insufficient capacity, and the scheduling uses electricity price and dispatch time as comprehensive indicators; S13, obtaining the minimum scheduling plan of the comprehensive indicators according to S12, and completing the power scheduling work of the virtual power plant in the future through the minimum scheduling plan of the comprehensive indicators;

[0010] S2, transactions between power plants and users: The unit price of electricity supplied by each power plant to the corresponding user is obtained based on the actual situation of each power plant in the virtual power plant. The total transaction price between the virtual power plant and the user is obtained by combining the total power consumption of the corresponding user.

[0011] The minimum scheduling solution for obtaining the comprehensive index includes: assuming that there are m power plants with excess capacity and n power plants with insufficient capacity, the formula for obtaining the minimum scheduling solution for the comprehensive index is:

[0012]

[0013] Among them, the formula formula

[0014] In addition, i refers to the i-th power plant with excess capacity, j refers to the j-th power plant with insufficient capacity, p(i, j) refers to the price at which the i-th power plant with excess capacity dispatches to the j-th power plant with insufficient capacity, t(i, j) refers to the time required for the i-th power plant with excess capacity to dispatch to the j-th power plant with insufficient capacity, α and β are weights, x(i, j) refers to the amount of electricity dispatched from the i-th power plant with excess capacity to the j-th power plant with insufficient capacity; Y i represents the total excess electricity of the i-th power plant with excess capacity, y j represents the total power shortage of the j-th power plant with insufficient capacity;

[0015] The total transaction price between the virtual power plant and the user is obtained by combining the total amount of electricity consumed by the corresponding user, which includes: combining the unit price of electricity supplied by each power plant to the corresponding user and the total amount of electricity consumed by the corresponding user, and obtaining the total transaction price between the virtual power plant and the user as follows:

[0016]

[0017] where Q 总 represents the total transaction price between the virtual power plant and the user, a represents the ath power plant in the virtual power plant, R represents that the virtual power plant consists of R power plants, K a W represents the unit price of electricity supplied by the ath power plant to the user. a Represents the total amount of electricity supplied to users by the a-th power plant.

[0018] Specifically, the plurality of distributed energy resources distributed at different locations include: a plurality of distributed power plants distributed at different locations, the power plants generate electricity using different energy resources, and the different energy resources include: wind energy, water energy and solar energy.

[0019] Specifically, the neural network algorithm predicts the power generation of each power plant and the amount of electricity required by the corresponding power plant users in the future period, including: extracting the historical power generation data of each power plant and the historical data of the amount of electricity required by the corresponding power plant users, respectively, training the historical power generation data of each power plant and the historical data of the amount of electricity required by the corresponding power plant users through the long short-term memory neural network LSTM algorithm, and obtaining the LSTM model of each power plant and the LSTM model of the amount of electricity required by the corresponding power plant users; finally, predicting the power generation of each power plant and the amount of electricity required by the corresponding power plant users in the future period through the LSTM model of each power plant and the LSTM model of the amount of electricity required by the corresponding power plant users.

[0020] Specifically, the calculation of the difference between the power generation of each power plant and the power required by the users of the corresponding power plant includes: judging whether the production capacity of the corresponding power plant is excessive by subtracting the power required by the users of the corresponding power plant from the power generation of the power plant; if the value of the power generation of the power plant minus the power required by the users of the corresponding power plant is a positive value, it proves that the production capacity of the corresponding power plant is excessive; if the value of the power generation of the power plant minus the power required by the users of the corresponding power plant is a negative value, it proves that the production capacity of the corresponding power plant is insufficient.

[0021] Specifically, the future period refers to the time set according to the number and status of power plants in the virtual power plant, including: the more power plants in the virtual power plant, the longer the set time; the better the status of each power plant, the shorter the set time.

[0022] Specifically, the minimum scheduling plan for obtaining the comprehensive indicators includes: the minimum scheduling plan corresponds to a plan for power plants with excess capacity to dispatch power supply to power plants with insufficient capacity, and the electricity of the virtual power plant for a period of time in the future is scheduled according to the minimum scheduling plan.

[0023] Specifically, the transaction between the power plant and the user includes: each power plant in the virtual power plant has a corresponding user group, and the corresponding user group needs to pay the power plant for the cost of electricity consumption to complete the transaction between the power plant and the user.

[0024] In addition, the present invention also provides a distributed power trading system based on a virtual power plant, which is used to implement the above-mentioned distributed power trading method based on a virtual power plant. The system includes: modules of various power plants; data acquisition modules; data analysis modules; power dispatching and trading modules; the modules of various power plants are used to convert various energy resources into electric energy, and the energy resources include wind energy, water energy and solar energy; the data acquisition module is used to collect data of various power plants and data on electric energy usage by users, and the data of power plants include historical power generation data and real-time power generation data of power plants; the data on electric energy usage by users include historical user usage data and real-time user usage data. Electric energy data; the data analysis module includes: the production capacity forecast of each power plant in the virtual power plant and the electricity usage forecast of the corresponding users; through the production capacity forecast of each power plant and the electricity usage forecast of the corresponding users, it is judged whether the production capacity of each power plant is excessive or insufficient; the electric energy scheduling and trading module includes: according to the excess and insufficient production capacity of each power plant obtained by the data analysis module, the scheduling and trading between the power plants in the virtual power plant are carried out with the electricity price and the dispatch time as comprehensive indicators; according to the unit price of electricity provided by each power plant to the user and the electricity usage of the corresponding user, the total transaction price between the entire virtual power plant and the user is calculated.

[0025] The beneficial effects of the present invention are:

[0026] The present invention provides a distributed power trading method and system based on a virtual power plant, which has the following advantages:

[0027] 1. This method divides the electricity trading of virtual power plants into: scheduling and trading between power plants, and trading between power plants and users; it makes the scheduling and trading process clearer and simpler, simplifies the scheduling algorithm, and increases the cost and safety of technical implementation.

[0028] 2. This method provides a method for determining whether the power generation of a corresponding power plant is in excess or insufficient capacity when scheduling and trading between power plants. By scheduling power plants with excess capacity to supply power to power plants with insufficient capacity, the minimum scheduling plan with electricity price and dispatch time as comprehensive indicators is obtained, and the calculation formula for obtaining the minimum scheduling plan is given: The energy dispatching work of the virtual power plant for a period of time in the future is completed through the minimum dispatching plan of comprehensive indicators, so that the dispatching work can be carried out automatically and efficiently. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 This is a flow chart of the distributed power trading method based on virtual power plant of the present invention.

[0030] Figure 2 Schematic diagram of the distributed power trading system based on virtual power plant of the present invention. DETAILED DESCRIPTION

[0031] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments given here are only used to illustrate and explain the present invention and cannot be used to limit the present invention.

[0032] It should be noted that many specific details are set forth in the following description to facilitate a full understanding of the present invention. However, the present invention may also have other implementations and variations thereof. Therefore, the scope of protection of the present invention is not limited to the specific embodiments disclosed below.

[0033] like Figure 1 As shown, a flow chart of a distributed power trading method based on a virtual power plant according to an embodiment of the present invention is shown; the flow chart includes: step S1, scheduling and trading between power plants: the power plants refer to a plurality of distributed energy resources distributed in different locations that constitute a virtual power plant; the steps of scheduling and trading between power plants are: S11, using a neural network algorithm to predict the power generation of each power plant and the power required by the users of the corresponding power plants in a period of time in the future, calculate the difference between the power generation of each power plant and the power required by the users of the corresponding power plants, and judge whether the power generation of the corresponding power plant is overcapacity or undercapacity; the period of time in the future refers to The time is set according to the number and status of power plants in the virtual power plant; S12, the power plants with excess production capacity obtained by scheduling S11 to supply power to power plants with insufficient production capacity, and the scheduling takes electricity price and allocation time as comprehensive indicators; S13, the minimum scheduling plan of the comprehensive indicators is obtained according to S12, and the electricity scheduling work of the virtual power plant for a period of time in the future is completed through the minimum scheduling plan of the comprehensive indicators; Step S2, the transaction between the power plant and the user: the unit price of each power plant supplying electricity to the corresponding user is obtained through the actual situation of each power plant in the virtual power plant, and the total transaction price between the virtual power plant and the user is obtained in combination with the total electricity consumption of the corresponding user.

[0034] In the above embodiment, specifically, the method for obtaining the minimum scheduling solution for the comprehensive index is as follows: assuming that there are m power plants with excess capacity and n power plants with insufficient capacity, the formula for obtaining the minimum scheduling solution for the comprehensive index is:

[0035]

[0036] Among them, the formula formula

[0037] In addition, i refers to the i-th power plant with excess capacity, j refers to the j-th power plant with insufficient capacity, p(i, j) refers to the price at which the i-th power plant with excess capacity dispatches to the j-th power plant with insufficient capacity, t(i, j) refers to the time required for the i-th power plant with excess capacity to dispatch to the j-th power plant with insufficient capacity, α and β are weights, x(i, j) refers to the amount of electricity dispatched from the i-th power plant with excess capacity to the j-th power plant with insufficient capacity; Y i represents the total excess electricity of the i-th power plant with excess capacity, y j It represents the total power shortage of the j-th power plant with insufficient production capacity.

[0038] In the above embodiment, specifically, the method for obtaining the total transaction price between the virtual power plant and the user is based on the total amount of electricity consumed by the corresponding user: the unit price of electricity supplied by each power plant to the corresponding user and the total amount of electricity consumed by the corresponding user are combined to obtain the total transaction price between the virtual power plant and the user as follows:

[0039]

[0040] where Q 总 represents the total transaction price between the virtual power plant and the user, a represents the ath power plant in the virtual power plant, R represents that the virtual power plant consists of R power plants, K a W represents the unit price of electricity supplied by the ath power plant to the user. a Represents the total amount of electricity supplied to users by the a-th power plant.

[0041] Wherein, step S1 also includes: a plurality of distributed energy resources distributed at different locations refer to: a plurality of distributed power plants distributed at different locations, said power plants generate electricity using different energy resources, and the different energy resources include: wind energy, water energy and solar energy.

[0042] In the above embodiment, specifically, the steps of the neural network algorithm predicting the power generation of each power plant and the power required by the corresponding power plant users in the future period are: by respectively extracting the historical power generation data of each power plant and the historical power required by the corresponding power plant users, respectively training the historical power generation data of each power plant and the historical power required by the corresponding power plant users through the long short-term memory neural network LSTM algorithm, and obtaining the LSTM model of each power plant and the LSTM model of the power required by the corresponding power plant users; finally, the power generation of each power plant and the power required by the corresponding power plant users in the future period are predicted through the LSTM model of each power plant and the LSTM model of the power required by the corresponding power plant users.

[0043] In the above embodiment, specifically, calculating the difference between the power generation of each power plant and the power required by the users of the corresponding power plant means: judging whether the production capacity of the corresponding power plant is in excess by subtracting the power required by the users of the corresponding power plant from the power generation of the power plant; if the value of the power generation of the power plant minus the power required by the users of the corresponding power plant is a positive value, it proves that the production capacity of the corresponding power plant is in excess; if the value of the power generation of the power plant minus the power required by the users of the corresponding power plant is a negative value, it proves that the production capacity of the corresponding power plant is insufficient.

[0044] In the above embodiment, specifically, the future period refers to the time set according to the number and status of power plants in the virtual power plant; the more power plants in the virtual power plant, the longer the set time; the better the status of each power plant, the shorter the set time.

[0045] In the above embodiment, specifically, the minimum scheduling plan for obtaining the comprehensive index refers to: the minimum scheduling plan corresponds to a plan for scheduling power supply from power plants with excess capacity to power plants with insufficient capacity, and the electricity of the virtual power plant for a period of time in the future is scheduled according to the minimum scheduling plan.

[0046] In the above embodiment, specifically, the transaction between the power plant and the user means that each power plant in the virtual power plant has a corresponding user group, and the corresponding user group needs to pay the power plant for the electricity consumed to complete the transaction between the power plant and the user.

[0047] like Figure 2 As shown, it is a schematic diagram of a distributed power trading system based on a virtual power plant according to the present invention, the schematic diagram includes: each power plant module S100; a data acquisition module S200; a data analysis module S300; an electric energy dispatching and trading module S400; the power plant module S100 is used to convert various energy resources into electric energy, the energy resources include: wind energy, water energy and solar energy; the data acquisition module S200 is used to collect data of each power plant and data on user power usage, the power plant data includes: historical power generation data and real-time power generation data of the power plant; the user power usage data includes: historical power usage data of the user The data analysis module S300 includes: the capacity forecast of each power plant in the virtual power plant and the power usage forecast of the corresponding users; through the capacity forecast of each power plant and the power usage forecast of the corresponding users, it is judged whether the capacity of each power plant is excessive or insufficient; the power scheduling and trading module S400 includes: according to the excess and insufficient capacity of each power plant obtained by the data analysis module, the power price and allocation time are used as comprehensive indicators to schedule and trade between the power plants in the virtual power plant; according to the unit price of electricity provided by each power plant to the user and the power usage of the corresponding user, the total transaction price between the entire virtual power plant and the user is calculated.

Claims

1. A distributed power trading method based on a virtual power plant, characterized in that: The method comprises: S1, scheduling and trading between power plants: the power plants refer to a plurality of distributed energy resources distributed in different locations that make up a virtual power plant; the steps of scheduling and trading between power plants are as follows: S11, predicting the power generation of each power plant and the power required by the users of the corresponding power plants in the future through a neural network algorithm, calculating the difference between the power generation of each power plant and the power required by the users of the corresponding power plants, and judging whether the power generation of the corresponding power plant is in excess or insufficient capacity; the future period refers to the time set according to the number and status of power plants in the virtual power plant; S12, the power plants with excess capacity obtained by scheduling S11 supply power to the power plants with insufficient capacity, and the scheduling uses electricity price and dispatch time as comprehensive indicators; S13, obtaining the minimum scheduling plan of the comprehensive indicators according to S12, and completing the power scheduling work of the virtual power plant in the future through the minimum scheduling plan of the comprehensive indicators; S2, transactions between power plants and users: The unit price of electricity supplied by each power plant to the corresponding user is obtained based on the actual situation of each power plant in the virtual power plant. The total transaction price between the virtual power plant and the user is obtained by combining the total power consumption of the corresponding user. The minimum scheduling solution for obtaining the comprehensive index includes: assuming that there are m power plants with excess capacity and n power plants with insufficient capacity, the formula for obtaining the minimum scheduling solution for the comprehensive index is: Among them, the formula formula In addition, i refers to the i-th power plant with excess capacity, j refers to the j-th power plant with insufficient capacity, p(i, j) refers to the price of dispatching the i-th power plant with excess capacity to the j-th power plant with insufficient capacity, t(i, j) refers to the time required for the i-th power plant with excess capacity to dispatch the j-th power plant with insufficient capacity, α and β are weights, x(i, j) refers to the amount of electricity dispatched from the i-th power plant with excess capacity to the j-th power plant with insufficient capacity; Y i represents the total excess electricity of the i-th power plant with excess capacity, y j represents the total power shortage of the j-th power plant with insufficient capacity; The total transaction price between the virtual power plant and the user is obtained by combining the total amount of electricity consumed by the corresponding user, which includes: combining the unit price of electricity supplied by each power plant to the corresponding user and the total amount of electricity consumed by the corresponding user, and obtaining the total transaction price between the virtual power plant and the user as follows: where Q 总 represents the total transaction price between the virtual power plant and the user, a represents the ath power plant in the virtual power plant, R represents that the virtual power plant consists of R power plants, K a W represents the unit price of electricity supplied by the ath power plant to the user. a Represents the total amount of electricity supplied to users by the a-th power plant.

2. The distributed power trading method based on virtual power plant according to claim 1 is characterized in that: The plurality of distributed energy resources distributed at different locations include: a plurality of distributed power plants distributed at different locations, the power plants generate electricity using different energy resources, and the different energy resources include: wind energy, water energy and solar energy.

3. The distributed power trading method based on virtual power plant according to claim 1 is characterized in that: The neural network algorithm predicts the power generation of each power plant and the power required by the corresponding power plant users in the future period, including: extracting the historical power generation data of each power plant and the historical power required by the corresponding power plant users, training the historical power generation data of each power plant and the historical power required by the corresponding power plant users through a long short-term memory neural network LSTM algorithm, and obtaining an LSTM model of each power plant and an LSTM model of the power required by the corresponding power plant users; finally, predicting the power generation of each power plant and the power required by the corresponding power plant users in the future period through the LSTM model of each power plant and the LSTM model of the power required by the corresponding power plant users.

4. The distributed power trading method based on virtual power plant according to claim 1, characterized in that: The calculation of the difference between the power generation of each power plant and the power required by the corresponding power plant users includes: judging whether the production capacity of the corresponding power plant is excessive by subtracting the power required by the corresponding power plant users from the power generation of the power plant; if the value of the power generation of the power plant minus the power required by the corresponding power plant users is a positive value, it proves that the production capacity of the corresponding power plant is excessive; if the value of the power generation of the power plant minus the power required by the corresponding power plant users is a negative value, it proves that the production capacity of the corresponding power plant is insufficient.

5. The distributed power trading method based on virtual power plant according to claim 1 is characterized in that: The future period refers to the time set according to the number and status of power plants in the virtual power plant, including: the more power plants in the virtual power plant, the longer the set time; the better the status of each power plant, the shorter the set time.

6. The distributed power trading method based on virtual power plant according to claim 1 is characterized in that: The minimum scheduling plan for obtaining the comprehensive indicators includes: the minimum scheduling plan corresponds to a plan for scheduling power supply from power plants with excess capacity to power plants with insufficient capacity, and the electricity of the virtual power plant for a period of time in the future is scheduled according to the minimum scheduling plan.

7. The distributed power trading method based on virtual power plant according to claim 1, characterized in that: The transaction between the power plant and the user includes: each power plant in the virtual power plant has a corresponding user group, and the corresponding user group needs to pay the power plant for the electricity consumed to complete the transaction between the power plant and the user.

8. A distributed power trading system based on a virtual power plant is characterized by: The system is used to implement the distributed power trading method based on a virtual power plant as described in claim 1, and the system includes: power plant modules; a data acquisition module; a data analysis module; and a power scheduling and trading module; the power plant modules are used to convert various energy resources into electricity, the energy resources including wind energy, hydropower, and solar energy; the data acquisition module is used to collect data from each power plant and data on user power usage, the power plant data including historical power generation data and real-time power generation data; the user power usage data including historical power usage data of users; the data analysis module includes: production capacity forecasts for each power plant in the virtual power plant and power usage forecasts for corresponding users; based on the production capacity forecasts for each power plant and the power usage forecasts for corresponding users, it is determined whether the production capacity of each power plant is excessive or insufficient; the power scheduling and trading module includes: based on the excess and insufficient production capacity of each power plant obtained by the data analysis module, scheduling and trading between the power plants in the virtual power plant with electricity price and dispatch time as comprehensive indicators; and calculating the total transaction price between the entire virtual power plant and the user based on the unit price of electricity provided to the user by each power plant and the current power usage of the corresponding user.

Images