Virtual power plant active scheduling equivalent model construction method and active scheduling method

Abstract

The invention discloses a virtual power plant active power scheduling equivalent model construction method and an active power scheduling method. The virtual power plant active power scheduling equivalent model construction method comprises the steps of obtaining an internal optimization scheduling model of a virtual power plant; acquiring a plurality of training electricity price curves, wherein the training electricity price curves comprise electricity prices in a plurality of time periods within the target duration; determining a plurality of training exchange power curves and a plurality of training operation total costs corresponding to the plurality of training electricity price curves based on the virtual power plant internal optimization scheduling model and the plurality of training electricity price curves; the training exchange power curve comprises exchange power of a plurality of time periods within the target duration; based on the plurality of training electricity price curves and the plurality of training exchange power curves, training the first neural network to obtain a power equivalent model of the virtual power plant participating in power grid active scheduling; and based on the plurality of training electricity price curves and the plurality of training operation total costs, training the second neural network to obtain a cost equivalent model of the virtual power plant participating in power grid active scheduling.

Description

Technical Field

[0001] The present application relates to the technical field of virtual power plants, and in particular to a method for constructing an equivalent model of active power scheduling of a virtual power plant and an active power scheduling method. Background Art

[0002] Virtual Power Plants (VPPs) can integrate distributed generators, energy storage systems, and controllable loads, leveraging advanced data communication and coordinated control technologies to achieve integrated control of various distributed generators and loads. Relative to the power grid, they function as a single controllable unit, significantly mitigating the challenges posed by the randomness and volatility of highly permeated distributed generation to grid operations and scheduling. Therefore, research on methods for VPPs to participate in grid active power scheduling is crucial. Summary of the Invention

[0003] In view of this, an embodiment of the present application provides a method for constructing an equivalent model of active power scheduling of a virtual power plant and an active power scheduling method.

[0004] According to the first aspect of the present application, an embodiment of the present application provides a method for constructing an equivalent model of active power scheduling of a virtual power plant, comprising: Obtaining an internal optimization scheduling model for a virtual power plant, the internal optimization scheduling model for a virtual power plant aims to minimize the total operating cost of various types of distributed power sources within the virtual power plant within a target duration; Obtain multiple training electricity price curves, where the training electricity price curves include electricity prices for multiple time periods within a target duration; Based on the internal optimization scheduling model of the virtual power plant and multiple training electricity price curves, multiple training exchange power curves and multiple training total operating costs corresponding to the multiple training electricity price curves are determined; the training exchange power curve includes the exchange power of multiple time periods within the target time period; Based on multiple training electricity price curves and multiple training exchange power curves, the first neural network is trained to obtain a power equivalent model for the virtual power plant to participate in the active power dispatch of the power grid; Based on multiple training electricity price curves and multiple training total operating costs, the second neural network is trained to obtain a cost equivalence model for the virtual power plant to participate in the active power scheduling of the power grid. Based on the power equivalence model and the cost equivalence model, the exchange power and total operating cost of the virtual power plant when participating in the active power scheduling of the power grid are determined.

[0005] Optionally, an internal optimization scheduling model of the virtual power plant is obtained, including: Obtaining an objective function corresponding to the internal optimization scheduling model of the virtual power plant; the objective function represents the goal of the internal optimization scheduling model of the virtual power plant, and the objective function is related to a first operating cost function of the hydropower supply within the virtual power plant within the target duration, a second operating cost function of the energy storage system power supply within the target duration, and a cost function of purchasing electricity from the external power grid within the target duration of the virtual power plant; Determine the constraints corresponding to the objective function; the constraints include the first operating constraint corresponding to the hydropower supply, the second operating constraint corresponding to the energy storage system power supply, the power constraint of the virtual power plant purchased from the external power grid, and the internal power balance constraint of the virtual power plant.

[0006] Optionally, the power balance constraints within the virtual power plant include: The sum of the output power of the photovoltaic power source, the output power of the wind power source, the output power of the hydropower source, the output power of the energy storage system power source and the power purchased by the virtual power plant from the external power grid is greater than or equal to the total load power of the virtual power plant.

[0007] Optionally, multiple training electricity price curves are obtained, including: Determine the electricity price range; Based on the electricity price range, multiple training electricity price curves are generated by uniformly distributed random numbers.

[0008] Optionally, based on the internal optimization scheduling model of the virtual power plant and the multiple training electricity price curves, determining multiple training exchange power curves and multiple training total operating costs corresponding to the multiple training electricity price curves includes: Based on each training electricity price curve, the internal optimization model of the virtual power plant is solved to obtain the minimum total cost of operating each type of distributed power source within the virtual power plant within the corresponding target duration, as well as the first output power curve of the hydropower source within the virtual power plant within the target duration, the second output power curve of the energy storage system power supply within the target duration, and the power curve of electricity purchased from the external power grid within the target duration of the virtual power plant; Determine a training exchange power curve corresponding to the training electricity price curve based on the first output power curve, the second output power curve, and the power curve of electricity purchased from the external power grid; Based on the minimum total cost of operating various types of distributed power sources within the virtual power plant within the target duration, the total training operation cost corresponding to the training electricity price curve is determined.

[0009] Optionally, determining a training exchange power curve corresponding to the training electricity price curve based on the first output power curve, the second output power curve, and the power curve of electricity purchased from the external power grid includes: Determine the output power curve of the photovoltaic power source, the output power curve of the wind power source, and the total load power curve within the virtual power plant within the target duration; Based on the first output power curve, the second output power curve, the power curve of electricity purchased from the external power grid, the output power curve of the photovoltaic power source, the output power curve of the wind power source, and the total load power curve, the training exchange power curve corresponding to the training electricity price curve is calculated.

[0010] According to a second aspect of the present application, an embodiment of the present application provides a method for a virtual power plant to participate in active power dispatching of a power grid, comprising: Obtain the electricity price curve within the target time period; Based on the power equivalent model and cost equivalent model of each virtual power plant participating in the active power dispatch of the power grid, the electricity price curve is processed respectively to obtain the corresponding exchange power curve and the total operating cost; the power equivalent model and the cost equivalent model are established by the virtual power plant active power dispatch equivalent model construction method as in the first aspect or any embodiment of the first aspect; Based on the exchange power curve and total operating cost of each virtual power plant, active power scheduling is performed on each virtual power plant.

[0011] Optionally, active power scheduling is performed on each virtual power plant based on the exchange power curve and total operating cost corresponding to each virtual power plant, including: Determine the dispatch level corresponding to each virtual power plant based on the total operating cost corresponding to each virtual power plant; Based on the dispatch level corresponding to each virtual power plant and the exchange power curve corresponding to each virtual power plant, the active dispatch power corresponding to each virtual power plant is determined.

[0012] According to a third aspect of the present application, an embodiment of the present application provides an electronic device, including: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so as to enable the at least one processor to execute the method for constructing an equivalent model of active power dispatch of a virtual power plant as in the first aspect or any embodiment of the first aspect, or the method for virtual power plant participation in active power dispatch of a power grid as in the second aspect or any embodiment of the second aspect.

[0013] According to the fourth aspect of the present application, an embodiment of the present application provides a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to execute a method for constructing an equivalent model of active power scheduling of a virtual power plant as in the first aspect or any embodiment of the first aspect, or a method for virtual power plants to participate in active power scheduling of a power grid as in the second aspect or any embodiment of the second aspect.

[0014] The embodiment of the present application provides a method for constructing an equivalent model of active power dispatch of a virtual power plant and an active power dispatch method, which obtains an internal optimization dispatch model of the virtual power plant, wherein the internal optimization dispatch model of the virtual power plant aims to minimize the total operating cost of various types of distributed power sources within the virtual power plant within the target time; obtains multiple training electricity price curves, and the training electricity price curve includes electricity prices for multiple time periods within the target time; based on the internal optimization dispatch model of the virtual power plant and the multiple training electricity price curves, determines multiple training exchange power curves and multiple training total operating costs corresponding to the multiple training electricity price curves; the training exchange power curve includes multiple training electricity price curves within the target time The exchange power of each time period; based on multiple training electricity price curves and multiple training exchange power curves, the first neural network is trained to obtain a power equivalent model of the virtual power plant participating in the active power scheduling of the power grid; based on multiple training electricity price curves and multiple training total operating costs, the second neural network is trained to obtain a cost equivalent model of the virtual power plant participating in the active power scheduling of the power grid; in this way, through the active power scheduling equivalent model of each virtual power plant, the exchange power and total operating cost of each virtual power plant when participating in the active power scheduling of the power grid at different times and different electricity prices can be determined, which is convenient for the power grid to perform active power scheduling on the virtual power plant.

[0015] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flowchart of a method for constructing an equivalent model of active power dispatch of a virtual power plant in an embodiment of the present application; Figure 2 Schematic diagram of the process of constructing another virtual power plant active power dispatch equivalent model in the embodiment of the present application Figure 3 A flowchart of a method for a virtual power plant to participate in active power dispatching of a power grid according to an embodiment of the present application; Figure 4 This is a schematic diagram of the hardware structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0017] To make the purpose, technical solutions, and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of this application.

[0018] The embodiment of the present application provides a method for constructing a virtual power plant active power dispatch equivalent model, such as Figure 1 Shown, including: S101, obtaining an internal optimization scheduling model of the virtual power plant, wherein the internal optimization scheduling model of the virtual power plant aims to minimize the total operating cost of various types of distributed power sources within the virtual power plant within a target duration.

[0019] In this embodiment, the virtual power plant is composed of various types of distributed power sources and loads, which may include wind power sources, hydropower sources, photovoltaic power sources, energy storage system power sources, loads, etc.

[0020] In this embodiment, the internal optimization scheduling model of a virtual power plant aims to minimize the total operating cost within the virtual power plant, while also taking into account the operating constraints of the distributed power sources within the virtual power plant. The total operating cost of the virtual power plant may include the operating costs of wind power, hydropower, photovoltaic power, energy storage system power, and the cost of purchasing electricity from the external grid. In some embodiments, wind power and photovoltaic power are clean power sources with zero marginal generation costs, so their operating costs can be zero. The operating cost of hydropower is related to the number of hydrogen generators, the unit power cost of the hydrogen generators, the output power of the hydrogen generators, and the startup costs of the hydrogen generators. The operating cost of the energy storage system power is related to the number of energy storage generators, the discharge cost of the energy storage generators, and the discharge power of the energy storage generators. The cost of purchasing electricity from the external grid is related to the number of metering points purchased from the external grid, the power purchased from the metering points, and the price of electricity purchased from the metering points.

[0021] In this embodiment, different types of distributed power sources may have different operating constraints. For example, for hydropower sources, operating constraints may include power upper and lower limits, ramp rate constraints, minimum downtime constraints, and continuous operation time constraints. For energy storage system power supply operating constraints, they may include charge and discharge constraints, SOC constraints, and so on.

[0022] S102: Acquire multiple training electricity price curves, where the training electricity price curves include electricity prices for multiple time periods within a target duration.

[0023] In this embodiment, multiple training electricity price curves can be automatically generated. The electricity price can be the price of electricity purchased from the metering point.

[0024] S103, based on the internal optimization scheduling model of the virtual power plant and multiple training electricity price curves, determine multiple training exchange power curves and multiple training total operating costs corresponding to the multiple training electricity price curves; the training exchange power curve includes the exchange power of multiple time periods within the target time length.

[0025] In this embodiment, the internal optimization scheduling model of the virtual power plant is solved by using multiple training electricity price curves, and corresponding multiple training exchange power curves and multiple training total operating costs can be obtained.

[0026] In this embodiment, the total operating cost may be the minimum total cost of operating all types of distributed power sources in the virtual power plant.

[0027] In this embodiment, the exchange power is the net output power of the virtual power plant to the external grid. It can be calculated based on the wind power output power, hydropower output power, photovoltaic power output power, energy storage system power output power, total load power, and power purchased from the external grid.

[0028] Among them, the output power of photovoltaic power sources, the output power of wind power sources and the total load power are highly random and uncertain.

[0029] In view of the uncertainty of wind power output, a large number of statistical results show that the change of wind speed also roughly conforms to a certain probability distribution. Among them, the two-parameter Weibull distribution is simple in form and fits the actual wind speed distribution well. It is generally considered to be the most suitable probability density function for the statistical description of wind speed. Its probability density function expression is: , Where v is the wind speed, k and c are two important parameters of the Weibull distribution, k is called the shape parameter, c is called the scale parameter, and c>1.

[0030] Output power P of wind power source WT The relationship between it and wind speed v can be approximately expressed by the following piecewise function relationship: , Among them, v out v in 、v n 、v out are cut-in wind speed, rated wind speed, cut-out wind speed, P r is the rated power of the fan, a WT 、b WT 、c WT The three parameters can be obtained by fitting the wind turbine's wind speed and power characteristic curve. Thus, by predicting the wind speed at multiple time periods within the target duration, the output power of the wind power source at each time period within the target duration can be determined.

[0031] Regarding the uncertainty of photovoltaic power output power, a large number of statistical results show that photovoltaic power output power is closely related to factors such as sunlight intensity and ambient temperature. Like wind power, the change in light intensity also approximately conforms to a certain probability distribution. According to statistics, the sunlight intensity in a certain period of time can be approximately regarded as a Beta distribution, and its probability density function is It can be expressed as follows: , Among them, T is the Gamma function; G and are the actual light intensity and maximum light intensity during this period respectively; α and β are the shape parameters of the Beta distribution, which can be obtained from the average light intensity μ and standard deviation σ during this period.

[0032] The output power P of the photovoltaic power source PV It can be estimated by comparing the output power, light intensity, ambient temperature, etc. under standard test conditions with the light intensity under actual working conditions through the following formula: , Among them, the physical quantities with the subscript STC are the operating parameters under standard test conditions; G STC The solar intensity under standard test conditions is 1000W / m 2 ;T STC is the standard reference temperature, which is 25°C; G is the actual light intensity; P STC is the output power under standard test conditions; k is the power temperature coefficient; and T is the junction temperature of the solar cell array. Thus, by predicting the light intensity at each time period within the target duration, the output power of the photovoltaic power source at each time period within the target duration can be determined.

[0033] In view of the uncertainty of the total load power, a large number of statistical results show that loads can generally be divided into three categories: industrial loads, commercial loads, and residential loads. The total load power P can be expressed as follows: , Among them, P n Indicates the rated load; α indicates the load ratio affected by temperature and humidity; work mode Indicates the working mode of the specified day load, which is related to the day type; GP curve represents the base load curve; P(T,H) represents the relationship between the temperature and humidity sensitive load and temperature T and humidity H; ε is a random number representing the random error of the unmodeled portion. In this way, the total load power can be determined.

[0034] S104: Based on a plurality of training electricity price curves and a plurality of training exchange power curves, the first neural network is trained to obtain a power equivalent model for the virtual power plant to participate in active power dispatching of the power grid.

[0035] In this embodiment, multiple training electricity price curves can be used as training data and multiple training exchange power curves as labels to train the first neural network and obtain a power equivalent model of the virtual power plant participating in the active power scheduling of the power grid.

[0036] S105, based on multiple training electricity price curves and multiple training total operating costs, the second neural network is trained to obtain a cost equivalence model for the virtual power plant to participate in the active power scheduling of the power grid, so as to determine the exchange power and total operating cost of the virtual power plant when participating in the active power scheduling of the power grid based on the power equivalence model and the cost equivalence model.

[0037] In this embodiment, multiple training electricity price curves can be used as training data, and multiple training total operating costs can be used as labels to train the second neural network, thereby obtaining a cost equivalence model for the virtual power plant's participation in grid active power scheduling. This cost equivalence model for the virtual power plant's active power scheduling includes an exchange power equivalence model and a cost equivalence model.

[0038] In this embodiment, the trained exchange power equivalent model and cost equivalent model may also be tested. If the accuracy does not meet the requirements, more training data sets are generated and retrained until a model that meets the accuracy requirements is obtained.

[0039] The embodiment of the present application provides a method for constructing an equivalent model for active power dispatch of a virtual power plant, which obtains an internal optimization dispatch model of the virtual power plant, wherein the internal optimization dispatch model of the virtual power plant aims to minimize the total operating cost of various types of distributed power sources within the virtual power plant within a target duration; obtains multiple training electricity price curves, wherein the training electricity price curve includes electricity prices for multiple time periods within the target duration; based on the internal optimization dispatch model of the virtual power plant and the multiple training electricity price curves, determines multiple training exchange power curves and multiple training total operating costs corresponding to the multiple training electricity price curves; the training exchange power curve includes exchange powers for multiple time periods within the target duration; based on the multiple training electricity price curves and the multiple training exchange power curves, trains a first neural network to obtain a power equivalent model for the virtual power plant to participate in active power dispatch of the power grid; based on the multiple training electricity price curves and the multiple training total operating costs, trains a second neural network to obtain a cost equivalent model for the virtual power plant to participate in active power dispatch of the power grid; in this way, through the active power dispatch equivalent model of each virtual power plant, the exchange power and total operating cost of each virtual power plant when participating in active power dispatch of the power grid at different times and different electricity prices can be determined, thereby facilitating the active power dispatch of the virtual power plant by the power grid.

[0040] In an optional embodiment, step S101, obtaining an internal optimization scheduling model of a virtual power plant, includes: Obtain the objective function corresponding to the internal optimization scheduling model of the virtual power plant; the objective function represents the objective of the internal optimization scheduling model of the virtual power plant, and the objective function is related to the first operating cost function of the hydropower supply within the virtual power plant within the target duration, the second operating cost function of the energy storage system power supply within the target duration, and the cost function of purchasing electricity from the external power grid within the target duration of the virtual power plant; determine the constraints corresponding to the objective function; the constraints include the first operating constraint corresponding to the hydropower supply, the second operating constraint corresponding to the energy storage system power supply, the power constraint of the virtual power plant purchasing electricity from the external power grid, and the power balance constraint within the virtual power plant.

[0041] In some embodiments, the internal power balance constraints of the virtual power plant include: The sum of the output power of the photovoltaic power source, the output power of the wind power source, the output power of the hydropower source, the output power of the energy storage system power source and the power purchased by the virtual power plant from the external power grid is greater than or equal to the total load power of the virtual power plant.

[0042] In specific implementation, the establishment of the internal optimization scheduling model of the virtual power plant takes the minimum total operating cost of the virtual power plant as the goal, taking into account the operating constraints of the distributed power sources contained in the virtual power plant. The steps for establishing the objective function and constraints are as follows: 1) Objective function of the virtual power plant internal optimization scheduling model: , Where C is the total cost of operating the virtual power plant, T is the number of time periods in a day, and when the time period resolution is 15 minutes, its value is 96; C HP (t) represents the operating cost of hydropower during period t, in yuan; C ES (t) represents the operating cost of the energy storage system power supply during period t, in yuan; C WT (t) represents the operating cost of wind power during period t, unit: yuan; C PV (t) represents the operating cost of the photovoltaic power source during period t, in yuan; C Grid (t) represents the cost of electricity purchased from the external power grid (positive values indicate electricity purchase, negative values indicate electricity sales), in RMB. The calculation formulas for each cost component are as follows.

[0043] Operating costs of hydropower: , where N HP Indicates the number of hydropower units; C HP,m Indicates the unit power cost of unit m, unit: yuan / kWh; P HP,m (t) represents the output power of unit m in period t, unit: kW; δt is the duration of a period, unit: hour; C su,mIndicates the startup cost of unit m, unit: yuan; u su,m (t) represents the startup variable of unit m in period t, which is 1 when it is started and 0 when it is not started.

[0044] Operating costs of energy storage system power supply: , where N ES Indicates the number of energy storage units, C ES,e Indicates the discharge cost of unit e when discharging, unit: yuan / kWh; Indicates the discharge power of unit e, unit: kW;.

[0045] Due to the energy storage charging power The electricity cost is included in the production cost of other power sources, so the energy storage charging cost is not included here. It can be expressed as (positive value indicates discharge, negative value indicates charge): , Cost of purchasing electricity from external power grid: , where N Grid Indicates the number of electricity metering points in the external market; P Grid,g (t) represents the power purchased from the metering point g. A positive value indicates power purchase, while a negative value indicates power sale. Unit: kW.

[0046] In addition, wind power and photovoltaic power are clean power sources with zero marginal power generation cost and should be consumed first, so their operating costs are zero and are not reflected in the objective function.

[0047] 2) Constraints of the internal optimization scheduling model of the virtual power plant (1) Constraints on hydropower units ① Power upper and lower limit constraints: , , in 、 Respectively represent the maximum output and minimum output of unit m, unit: kW; is the operating variable, which is 1 if running, otherwise 0; β is the safety margin coefficient.

[0048] ②Climbing rate constraint , , in 、 They represent the upward ramp rate limit and downward ramp rate limit of unit m respectively, in kW / min.

[0049] ③Minimum downtime constraint , in is the minimum downtime of unit m, unit: period; It is the shutdown variable, which is 1 if the shutdown occurs and 0 otherwise.

[0050] ④Continuous running time constraints Minimum continuous running time constraint: , in, The minimum continuous operating time of unit m, unit: period.

[0051] (2) Energy storage constraints ①Charge and discharge constraints , , in 、 Respectively represent the maximum discharge power and maximum charging power of unit e, 、 Respectively represent the minimum discharge power and minimum charging power of unit e, unit: kW; 、 Represent the discharge state and charge state respectively. When the value is 1, it means discharge / charge, and when the value is 0, it means no discharge / no charge. The two are mutually exclusive, that is, they meet the following constraints: .

[0052] ②SOC constraint , Among them, SOC e (t) represents the SOC of unit e in period t; SOC emax (t), SOC emin (t) represents the maximum and minimum allowable values of SOC respectively; SOC e (0) represents the initial capacity of SOC; SOC e (T) represents the SOC capacity of the last period.

[0053] (3) Power constraints of electricity purchased from external markets , in 、 They represent the maximum electricity sales power and the maximum electricity purchase power at the external grid metering point g, respectively, in kW.

[0054] (4) Power balance constraints , Where NPV is the number of photovoltaic units; P PV,P (t) is the output power of the photovoltaic unit in period t; NWT is the number of wind turbines, P WT,w (t) is the output power of the wind turbine in period t; P Load (t) is the total power of the load in time period t, unit: kW.

[0055] In this embodiment, by obtaining the objective function corresponding to the internal optimization scheduling model of the virtual power plant and determining the constraints corresponding to the objective function, the internal optimization scheduling model of the virtual power plant can be quickly constructed, so that the internal optimization scheduling model of the virtual power plant takes into account both the total operating cost within the virtual power plant and the operating constraints of the distributed power sources contained in the virtual power plant.

[0056] In an optional embodiment, step S102, obtaining multiple training electricity price curves, includes: Determine the electricity price range; based on the electricity price range, generate multiple training electricity price curves using uniformly distributed random numbers.

[0057] In specific implementation, the data set size N can be set sample , then randomly generate N sample A data set of electricity price curves containing T time periods: , For the l The electricity price curve of samples is: , In order to make the generated training electricity price curve cover all possible situations, it is generated by uniformly distributed random numbers, namely: , in For interval The uniform distribution law on 、 are the minimum and maximum values allowed for electricity prices, respectively.

[0058] In this embodiment, the electricity price range is determined; based on the electricity price range, multiple training electricity price curves are generated by using uniformly distributed random numbers, so that the generated multiple training electricity price curves can cover all possible situations.

[0059] In an optional embodiment, step S103, based on the virtual power plant internal optimization scheduling model and multiple training electricity price curves, multiple training exchange power curves and multiple training total operating costs corresponding to the multiple training electricity price curves are determined, such as Figure 2 Shown, including: S1031, based on each training electricity price curve, solve the internal optimization model of the virtual power plant to obtain the minimum total cost of operation of various types of distributed power sources within the virtual power plant within the corresponding target time, as well as the first output power curve of the hydropower source in the virtual power plant within the target time, the second output power curve of the energy storage system power supply within the target time, and the power curve of the virtual power plant purchased from the external power grid within the target time.

[0060] S1032: Determine a training exchange power curve corresponding to the training electricity price curve based on the first output power curve, the second output power curve, and the power curve of electricity purchased from the external power grid.

[0061] S1033, based on the minimum total cost of operating various types of distributed power sources within the virtual power plant within the target duration, determine the total training operating cost corresponding to the training electricity price curve.

[0062] In specific implementation, for any given electricity price curve Through the internal optimization scheduling model of the virtual power plant, the corresponding minimum total cost of internal operation of the virtual power plant can be calculated. , as well as the first output power curve of the hydropower source in the virtual power plant within the target duration, the second output power curve of the energy storage system power source within the target duration, and the power purchase power curve of the virtual power plant from the external power grid within the target duration. ,λ Grid is the electricity price from the external grid metering point.

[0063] Then, the exchange power curve between the virtual power plant and the external power grid can be calculated through the first output power curve, the second output power curve of the energy storage system power supply within the target duration, and the power curve of the virtual power plant purchasing electricity from the external power grid within the target duration. The exchange power curve includes the exchange power of multiple time periods within the target duration.

[0064] In one implementation, since the virtual power plant also includes photovoltaic power sources, wind power sources, and loads, step S1032 determines the training exchange power curve corresponding to the training electricity price curve based on the first output power curve, the second output power curve, and the power curve of electricity purchased from the external power grid, including: Determine the output power curve of the photovoltaic power source, the output power curve of the wind power source, and the total load power curve within the virtual power plant within the target duration; based on the first output power curve, the second output power curve, the power curve of electricity purchased from the external power grid, and the output power curve of the photovoltaic power source, the output power curve of the wind power source, and the total load power curve, calculate the training exchange power curve corresponding to the training electricity price curve.

[0065] In this implementation, based on the first output power curve, the second output power curve, the power curve of electricity purchased from the external power grid, the output power curve of the photovoltaic power source, the output power curve of the wind power source, and the total load power curve, the training exchange power curve corresponding to the training electricity price curve is calculated, and the training exchange power curve corresponding to the training electricity price curve can be obtained more accurately.

[0066] In this embodiment, based on each training electricity price curve, the internal optimization model of the virtual power plant is solved to obtain the minimum total operating cost of each type of distributed power source within the virtual power plant within the corresponding target time, as well as the first output power curve of the hydropower source in the virtual power plant within the target time, the second output power curve of the energy storage system power supply within the target time, and the power curve of the virtual power plant purchased from the external power grid within the target time; in this way, the training exchange power curve and the training total operation cost corresponding to the training electricity price curve can be quickly determined.

[0067] The embodiment of the present application provides a method for a virtual power plant to participate in grid active power dispatching, such as Figure 3 As shown, including; S301, obtaining the electricity price curve within the target time period.

[0068] S302, based on the power equivalent model and cost equivalent model of each virtual power plant participating in the active power scheduling of the power grid, the electricity price curve is processed respectively to obtain the corresponding exchange power curve and the total operating cost; the power equivalent model and the cost equivalent model are established by the virtual power plant active power scheduling equivalent model construction method in any of the above-mentioned implementation methods.

[0069] S303: Perform active power scheduling on each virtual power plant based on the exchange power curve and total operating cost corresponding to each virtual power plant.

[0070] In this embodiment, the electricity price curve within the target time period may be the electricity price curve purchased from the external power grid a few days ago.

[0071] In this embodiment, the electricity price curve for the target duration is obtained and can be input into the power equivalence model and the cost equivalence model to obtain the corresponding exchange power curve and total operating cost. The exchange power curve represents the net output power that the virtual power plant can provide at each time period within the target duration. The total operating cost represents the minimum total operating cost corresponding to the virtual power plant providing this net output power.

[0072] In this embodiment, the virtual power plant can determine the corresponding exchange power curve and total operating cost based on the electricity price curve within the target time period, and then send the exchange power curve and total operating cost to the power grid. The power grid performs active power scheduling on each virtual power plant according to the exchange power curve and total operating cost sent by each virtual power plant.

[0073] In this embodiment, the virtual power plant may send the power equivalence model and the cost equivalence model to the power grid. The power grid calculates the corresponding exchange power curve and the total operating cost based on the power equivalence model and the cost equivalence model sent by the virtual power plant, and then performs active power scheduling for each virtual power plant based on the calculated exchange power curve and the total operating cost.

[0074] The method for virtual power plants to participate in active power scheduling of the power grid provided in the embodiment of the present application is achieved by obtaining the electricity price curve within the target time length; based on the power equivalence model and cost equivalence model of each virtual power plant participating in the active power scheduling of the power grid, the electricity price curve is processed respectively to obtain the corresponding exchange power curve and the total operating cost; the power equivalence model and the cost equivalence model are established by the virtual power plant active power scheduling equivalence model construction method in any of the above-mentioned implementation methods; based on the exchange power curve and the total operating cost corresponding to each virtual power plant, each virtual power plant is actively scheduled; in this way, through the active power scheduling equivalence model of each virtual power plant, the exchange power and total operating cost of each virtual power plant when participating in the active power scheduling of the power grid at different times and different electricity prices can be determined, so as to facilitate the power grid to perform active power scheduling on the virtual power plants.

[0075] In an optional embodiment, step S303, performing active power scheduling on each virtual power plant based on the exchange power curve and total operating cost corresponding to each virtual power plant, includes: Based on the total operating cost corresponding to each virtual power plant, the dispatch level corresponding to each virtual power plant is determined; based on the dispatch level corresponding to each virtual power plant and the exchange power curve corresponding to each virtual power plant, the active dispatch power corresponding to each virtual power plant is determined.

[0076] In this embodiment, each virtual power plant can be divided into dispatch levels based on the total operating cost corresponding to each virtual power plant. For example, the lower the total operating cost, the higher the dispatch level, and the higher the dispatch level, the higher the dispatch priority.

[0077] In this embodiment, after determining the dispatch level of each virtual power plant, the active dispatch power corresponding to each virtual power plant can be determined based on the required active dispatch power and the exchange power curve corresponding to each virtual power plant; in this way, the total operating cost of the power grid can be minimized when the overall active dispatch of the power grid is achieved.

[0078] According to an embodiment of the present application, the present application also provides an electronic device and a readable storage medium.

[0079] Figure 4 A schematic block diagram of an example electronic device 800 that can be used to implement an embodiment of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or claimed herein.

[0080] like Figure 4 As shown, electronic device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. RAM 803 may also store various programs and data required for the operation of electronic device 800. Computing unit 801, ROM 802, and RAM 803 are interconnected via a bus 804. An input / output (I / O) interface 805 is also connected to bus 804.

[0081] Multiple components in the electronic device 800 are connected to the I / O interface 805, including an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a magnetic disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the electronic device 800 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0082] The computing unit 801 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as the method for constructing a value model for virtual power plant active power dispatch or the method for virtual power plant participation in grid active power dispatch. For example, in some embodiments, the method for constructing a value model for virtual power plant active power dispatch or the method for virtual power plant participation in grid active power dispatch can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into RAM 803 and executed by computing unit 801, one or more steps of the method for constructing a model equivalent to active power dispatch for a virtual power plant or the method for a virtual power plant to participate in active power dispatch for a power grid described above can be executed. Alternatively, in other embodiments, computing unit 801 can be configured to execute the method for constructing a model equivalent to active power dispatch for a virtual power plant or the method for a virtual power plant to participate in active power dispatch for a power grid using any other suitable means (e.g., via firmware).

[0083] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0084] The program code for implementing the methods of the present application can be written in any combination of one or more programming languages. Such program code can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the program code is executed by the processor or controller, the functions / operations specified in the flow charts and / or block diagrams are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0085] In the context of this application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or apparatus. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fibers, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0086] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0087] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0088] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0089] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this application can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this application can be achieved. This is not a limitation herein.

[0090] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. Throughout the description of this application, "plurality" means two or more, unless otherwise specifically defined.

[0091] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for constructing an equivalent model of active power dispatch of a virtual power plant, characterized in that: include: Obtaining an internal optimization scheduling model for a virtual power plant, wherein the internal optimization scheduling model for a virtual power plant aims to minimize the total operating cost of various types of distributed power sources within the virtual power plant within a target duration; Acquire multiple training electricity price curves, where the training electricity price curves include electricity prices for multiple time periods within a target duration; Based on the internal optimization scheduling model of the virtual power plant and the plurality of training electricity price curves, determining a plurality of training exchange power curves and a plurality of training total operating costs corresponding to the plurality of training electricity price curves; The training exchange power curve includes the exchange power of multiple time periods within the target duration; Based on the plurality of training electricity price curves and the plurality of training exchange power curves, the first neural network is trained to obtain a power equivalent model for the virtual power plant to participate in the active power dispatch of the power grid; Based on multiple training electricity price curves and multiple training total operating costs, the second neural network is trained to obtain a cost equivalence model for the virtual power plant to participate in the active power scheduling of the power grid, so as to determine the exchange power and total operating cost of the virtual power plant when participating in the active power scheduling of the power grid based on the power equivalence model and the cost equivalence model.

2. The method for constructing an equivalent model of active power dispatch of a virtual power plant according to claim 1, characterized in that: Obtain the internal optimization scheduling model of the virtual power plant, including: Obtain an objective function corresponding to the internal optimization scheduling model of the virtual power plant; the objective function represents the target of the internal optimization scheduling model of the virtual power plant, and the objective function is related to a first operating cost function of the hydropower supply within the virtual power plant within the target duration, a second operating cost function of the energy storage system power supply within the target duration, and a cost function of purchasing electricity from the external power grid within the target duration of the virtual power plant; Determine the constraints corresponding to the objective function; the constraints include a first operating constraint corresponding to the hydropower source, a second operating constraint corresponding to the energy storage system power source, a power constraint for the virtual power plant to purchase electricity from the external power grid, and a power balance constraint within the virtual power plant.

3. The method for constructing an equivalent model of active power dispatch of a virtual power plant according to claim 2, characterized in that: The internal power balance constraints of the virtual power plant include: The sum of the output power of the photovoltaic power source, the output power of the wind power source, the output power of the hydropower source, the output power of the energy storage system power source and the power purchased by the virtual power plant from the external power grid is greater than or equal to the total load power of the virtual power plant.

4. The method for constructing an equivalent model of active power dispatch of a virtual power plant according to claim 1, characterized in that: Get multiple training electricity price curves, including: Determine the electricity price range; Based on the electricity price range, a plurality of training electricity price curves are generated by using uniformly distributed random numbers.

5. The method for constructing an equivalent model of active power dispatch of a virtual power plant according to claim 1, characterized in that: Based on the internal optimization scheduling model of the virtual power plant and the plurality of training electricity price curves, determining a plurality of training exchange power curves and a plurality of training total operating costs corresponding to the plurality of training electricity price curves, including: Based on each of the training electricity price curves, the internal optimization model of the virtual power plant is solved to obtain the minimum total cost of operation of each type of distributed power source within the virtual power plant within the corresponding target duration, as well as the first output power curve of the hydropower source in the virtual power plant within the target duration, the second output power curve of the energy storage system power supply within the target duration, and the power purchase power curve of the virtual power plant from the external power grid within the target duration; Determining a training exchange power curve corresponding to the training electricity price curve based on the first output power curve, the second output power curve, and the power curve of electricity purchased from the external power grid; Based on the minimum total operating cost of various types of distributed power sources within the virtual power plant within the target duration, the total training operating cost corresponding to the training electricity price curve is determined.

6. The method for constructing an equivalent model of active power dispatch of a virtual power plant according to claim 5, characterized in that: Determining a training exchange power curve corresponding to the training electricity price curve based on the first output power curve, the second output power curve, and the power curve of electricity purchased from the external power grid includes: Determine the output power curve of the photovoltaic power source, the output power curve of the wind power source, and the total load power curve within the virtual power plant within the target duration; Based on the first output power curve, the second output power curve, the power curve of electricity purchased from the external power grid, the output power curve of the photovoltaic power source, the output power curve of the wind power source, and the total load power curve, the training exchange power curve corresponding to the training electricity price curve is calculated.

7. A method for a virtual power plant to participate in active power dispatching of a power grid, characterized in that: include; Obtain the electricity price curve within the target time period; Based on the power equivalent model and cost equivalent model of each virtual power plant participating in the active power dispatch of the power grid, the electricity price curve is processed respectively to obtain the corresponding exchange power curve and the total operating cost; the power equivalent model and the cost equivalent model are established by the method for constructing the active power dispatch equivalent model of the virtual power plant according to any one of claims 1 to 6; Based on the exchange power curve and total operating cost of each virtual power plant, active power scheduling is performed on each virtual power plant.

8. The method for virtual power plant to participate in grid active power dispatching according to claim 7, characterized in that: Based on the exchange power curve and total operating cost of each virtual power plant, active power scheduling is performed on each virtual power plant, including: Determine the dispatch level corresponding to each virtual power plant based on the total operating cost corresponding to each virtual power plant; Based on the dispatch level corresponding to each virtual power plant and the exchange power curve corresponding to each virtual power plant, the active dispatch power corresponding to each virtual power plant is determined.

9. An electronic device, characterized in that: include: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor executes the method for constructing an equivalent model of active power dispatch of a virtual power plant as described in any one of claims 1 to 6, or the method for virtual power plant participation in active power dispatch of a power grid as described in claim 7 or 8.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, which are used to enable a computer to execute the method for constructing an equivalent model of active power dispatch of a virtual power plant as described in any one of claims 1 to 6, or the method for virtual power plant participation in active power dispatch of a power grid as described in claim 7 or 8.

Images