Cost optimization method of electro-thermal coupling virtual power plant based on stochastic optimization method

Abstract

The invention provides an electro-thermal coupling virtual power plant cost optimization method based on a stochastic optimization method. The method comprises the steps of obtaining historical operation parameters; constructing a physical simulation model of each component according to the historical operation parameters to obtain a power plant operation model; constructing an operation cost model of each component according to the historical operation parameters to obtain a power plant cost model; determining uncertainty parameters of the virtual power plant according to the historical operation parameters and constructing a random model; constructing a target constraint group based on the power plant operation model; and based on the system uncertainty, risk avoidance solution and opportunity seeking solution are carried out through an IGDT method to obtain first uncertainty and second uncertainty, power plant control parameters are further solved, and operation of the virtual power plant is controlled according to the power plant control parameters. The method solves the problem that in the prior art, a virtual power plant scheduling optimization method integrating a combined heat and power generation unit, carbon capture and electrical conversion equipment and meeting the low-cost and low-carbon requirements is lacked.

Description

Technical Field

[0001] The present invention relates to the field of scheduling of thermal virtual power plants, and in particular to a cost optimization method, device, computer-readable storage medium, processor and planning system for an electric-thermal coupled virtual power plant based on a stochastic optimization method. Background Art

[0002] As an aggregate of distributed resources, virtual power plants (VPPs) have great potential in improving the utilization rate of distributed renewable energy. With the continuous implementation of pilot projects in various places in recent years, the forms of virtual power plants have gradually diversified, and the economic benefits have continued to expand.

[0003] With the implementation of virtual power plants, the combination of distributed resources is constantly innovating. In addition to power supply and composite virtual power plants, multi-energy resources are also being integrated. Combined with cogeneration units, heat supply is also included in the real-time scheduling of virtual power plants. The virtual power plant scheduling scheme in the existing technology is still based on the traditional virtual power plant, ignoring the uncertainty factors brought about by the introduction of new energy. Therefore, the existing technology lacks a scheduling method that takes into account the energy conversion relationship in the virtual power plant that integrates multiple energy sources. Summary of the invention

[0004] The main purpose of this application is to provide a cost optimization method, optimization device, computer-readable storage medium, processor and planning system for an electric-thermal coupled virtual power plant based on a random optimization method, so as to at least solve the problem in the prior art of the lack of a virtual power plant scheduling optimization method that integrates cogeneration units, carbon capture and electrical conversion equipment to meet low cost and low carbon requirements.

[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a cost optimization method for an electric-thermal coupled virtual power plant based on a stochastic optimization method is provided, comprising: obtaining historical operating parameters, wherein the historical operating parameters include input data and output data of each component of the virtual power plant, and the operating cost of each of the components, wherein the components include a CHP unit, a WPP unit, a PV unit, a carbon capture device, and an electrical conversion device, wherein the CHP unit receives natural gas and outputs electrical energy and thermal energy, the PV unit receives light energy and outputs electrical energy, the WPP unit receives wind energy and outputs electrical energy, the carbon capture device receives the electrical energy of the CHP unit for collecting the carbon dioxide output by the CHP unit and outputting it to the electrical conversion device, and the electrical conversion device receives the electrical energy of the WPP unit for converting the carbon dioxide of the carbon capture device into methane; constructing a physical simulation model of each of the components according to the historical operating parameters to obtain a power plant operation model, wherein the power plant operation model is used to simulate the changing trend of the output data and energy flow of each of the components with the input data; constructing the operating cost of each of the components according to the historical operating parameters According to this model, a power plant cost model is obtained, and the operating cost model is used to simulate the changing trend of the operating cost of each component with the input data; the uncertainty parameters of the output load of the PV unit, the WPP unit and the virtual power plant are determined according to the historical operating parameters to obtain an uncertainty factor group, and a stochastic model is constructed according to the uncertainty factor group, and the stochastic model is used to simulate the changing trend of system uncertainty with the uncertainty factor group; a target constraint group is constructed based on the power plant operation model, and the target constraint group is used to limit the parameter values ​​of the power plant operation model, and the target constraint group at least includes system balance constraints, CHP unit constraints, WPP unit constraints, PV unit constraints, spare capacity constraints and carbon capture device constraints; based on the system uncertainty, risk avoidance solutions and opportunity seeking solutions are respectively performed by the IGDT method to obtain a first uncertainty and a second uncertainty; based on the first uncertainty and the second uncertainty, the power plant operation model is solved with the output minimization of the operating cost model as the objective function to obtain power plant control parameters, and the operation of the virtual power plant is controlled according to the power plant control parameters.

[0006] Optionally, a physical simulation model of each of the components is constructed according to the historical operating parameters to obtain a power plant operation model, including: determining the power generation power, heat generation power, and gas input power of the CHP unit according to the historical operating parameters, and determining the power conversion efficiency according to the power generation power and the gas input power, determining the thermal conversion efficiency according to the heat generation power and the gas input power, constructing a power output formula according to the power generation power, the gas input power, and the power conversion efficiency, constructing a thermal output formula according to the heat generation power, the gas input power, and the thermal conversion efficiency, and constructing a thermal output formula according to the CHP unit. The physical simulation model of the CHP unit is constructed according to the power output formula and the thermal output formula of the unit to obtain a first simulation model; the power generation power, real-time wind speed, cut-in wind speed, cut-off wind speed and rated wind speed of the WPP unit are determined according to the historical operating parameters, and the physical simulation model of the WPP unit is constructed according to the correlation between the power generation power, the real-time wind speed, the cut-in wind speed, the cut-off wind speed and the rated wind speed of the WPP unit to obtain a second simulation model; the power generation power, photovoltaic panel area, average efficiency and light intensity of the PV unit are determined according to the historical operating parameters, and the power generation power, the real-time wind speed, the cut-in wind speed, the cut-off wind speed and the rated wind speed of the WPP unit are determined according to the correlation between the rated wind speed and the cut-off wind speed to obtain a second simulation model. The photovoltaic panel area, the average efficiency and the light intensity determine the solar energy absorption rate and the solar energy conversion rate, the generated power, the photovoltaic panel area, the average efficiency, the light intensity, the solar energy absorption rate and the solar energy conversion rate construct an electric power output formula, and a physical simulation model of the PV unit is constructed according to the electric power output formula of the PV unit to obtain a third simulation model; the fixed energy consumption, operating energy consumption and total energy consumption of the carbon capture device are determined according to the historical operating parameters, the energy consumption expression of the carbon capture device is constructed according to the fixed energy consumption, operating energy consumption and total energy consumption of the carbon capture device, and the carbon capture device is constructed according to the carbon capture device. The physical simulation model of the carbon capture device is constructed according to the energy consumption expression of the carbon capture device to obtain a fourth simulation model; the total energy consumption, fixed energy consumption and operating energy consumption of the electrical conversion device are determined according to the historical operating parameters, and the energy consumption expression of the electrical conversion device is constructed according to the fixed energy consumption, operating energy consumption and total energy consumption of the electrical conversion device; the physical simulation model of the electrical conversion device is constructed according to the energy consumption expression of the electrical conversion device to obtain a fifth simulation model; the power plant operation model is constructed according to the first simulation model, the second simulation model, the third simulation model, the fourth simulation model and the fifth simulation model.

[0007] Optionally, before constructing the power plant operation model according to the first simulation model, the second simulation model, the third simulation model, the fourth simulation model and the fifth simulation model, the method also includes: constructing a first target formula according to the power generation power of the CHP unit and the total energy consumption of the electrical conversion device, the first target formula being used to simulate the flow direction of the power output of the CHP unit; determining the demand response power according to the historical operating parameters, and constructing a load transfer formula according to the power generation power of the CHP unit, the power generation power of the WPP unit, the power generation power of the PV unit and the demand response power to obtain a second target formula, the second target formula being used to simulate the load transfer amount of the virtual power plant at any time as the power generation power changes trend.

[0008] Optionally, an operating cost model of each of the components is constructed according to the historical operating parameters to obtain a power plant cost model, including: determining the fuel cost and power generation of the CHP unit according to the historical operating parameters, fitting the fuel cost and the power generation to obtain a third target formula, the third target formula is used to simulate the changing trend of the fuel cost with the power generation; determining the start-stop cost and a first variable of the CHP unit according to the historical operating parameters, fitting the start-stop cost and the first variable to obtain a fourth target formula, the fourth target formula is used to simulate the changing trend of the start-stop cost with the first variable, the first variable is a binary variable indicating whether the CHP unit is started; combining the third target formula and the fourth target formula to obtain the operating cost model of the CHP unit; determining the operating cost, depreciation cost and power generation of the WPP unit according to the historical operating parameters, constructing the operating cost model of the WPP unit according to the operating cost, depreciation cost and power generation of the WPP unit, the operating cost model of the WPP unit is used to simulate the changing trend of the total cost of the WPP unit with the power generation; The operating cost, depreciation cost and power generation of the PV unit are determined by using the historical operating parameters, and an operating cost model of the PV unit is constructed according to the operating cost, depreciation cost and power generation of the PV unit. The operating cost model of the PV unit is used to simulate the changing trend of the total cost of the PV unit with the power generation; the energy consumption of the carbon capture device is determined according to the historical operating parameters, and an operating cost model of the carbon capture device is constructed according to the energy consumption of the carbon capture device. The operating cost model of the carbon capture device is used to simulate the changing trend of the total cost of the carbon capture device with the energy consumption; according to the load of the virtual power plant transfer amount, construct a demand response cost model, the demand response cost model is used to simulate the changing trend of the demand response cost with the load transfer amount; determine the solar and wind abandonment cost model of the virtual power plant according to the historical operating parameters, the solar and wind abandonment cost model is used to simulate the wind abandonment and solar abandonment penalties of the virtual power plant with the changing trend of the solar and wind abandonment costs; construct the operating cost model according to the operating cost model of the CHP unit, the operating cost model of the WPP unit, the operating cost model of the PV unit, the operating cost model of the carbon capture device and the demand response cost model.

[0009] Optionally, the uncertainty parameters of the output loads of the PV unit, the WPP unit and the virtual power plant are determined according to the historical operating parameters, including: determining the fluctuation range of the WPP unit based on the historical operating parameters, and determining the uncertainty parameters of the WPP unit through an envelope constraint model according to the fluctuation range and the historical operating parameters to obtain a first uncertainty parameter; determining the fluctuation range of the PV unit based on the historical operating parameters, and determining the uncertainty parameters of the PV unit through an envelope constraint model according to the fluctuation range and the historical operating parameters to obtain a second uncertainty parameter; determining the fluctuation range of the output load of the virtual power plant based on the historical operating parameters, and determining the uncertainty parameters of the output load of the virtual power plant through an envelope constraint model according to the fluctuation range and the historical operating parameters to obtain a third uncertainty parameter; constructing the uncertainty factor group according to the first uncertainty parameter, the second uncertainty parameter and the third uncertainty parameter, and constructing a randomness model according to the uncertainty factor group.

[0010] Optionally, constructing a target constraint group based on the power plant operation model includes: constructing the system balance constraint of the virtual power plant corresponding to the power plant operation model to obtain a first target constraint; constructing the CHP unit constraint of the virtual power plant corresponding to the power plant operation model to obtain a second target constraint; constructing the WPP unit constraint of the virtual power plant corresponding to the power plant operation model to obtain a third target constraint; constructing the PV unit constraint of the virtual power plant corresponding to the power plant operation model to obtain a fourth target constraint; constructing the standby capacity constraint of the virtual power plant corresponding to the power plant operation model to obtain a fifth target constraint; constructing the carbon capture device constraint of the virtual power plant corresponding to the power plant operation model to obtain a sixth target constraint; and combining the first target constraint, the second target constraint, the third target constraint, the fourth target constraint, the fifth target constraint and the sixth target constraint to obtain the target constraint group.

[0011] Optionally, based on the system uncertainty, risk avoidance solution and opportunity seeking solution are respectively performed through the IGDT method to obtain a first uncertainty and a second uncertainty, including: obtaining a preset robust coefficient, and based on the system uncertainty and the preset robust coefficient, converting the objective function to obtain a risk avoidance formula group; substituting the uncertainty factor group into the risk avoidance formula group to obtain the first uncertainty; obtaining a minimum value based on the system uncertainty, converting the objective function to obtain an opportunity seeking formula group; substituting the uncertainty factor group into the opportunity seeking formula group to obtain the second uncertainty.

[0012] According to another aspect of the present application, a cost optimization device for an electric-thermal coupled virtual power plant based on a stochastic optimization method is provided, the device comprising: an acquisition unit for acquiring historical operating parameters, the historical operating parameters comprising input data and output data of each component of the virtual power plant, and the operating cost of each component, the components comprising a CHP unit, a WPP unit, a PV unit, a carbon capture device and an electrical conversion device, the CHP unit receiving natural gas and outputting electrical energy and thermal energy, the PV unit receiving light energy and outputting electrical energy, the WPP unit receiving wind energy and outputting electrical energy, the carbon capture device a first construction unit, for constructing a physical simulation model of each of the components according to the historical operating parameters to obtain a power plant operation model, wherein the power plant operation model is used to simulate the output data of each of the components and the change trend of the energy flow with the input data; and a second construction unit, for constructing an operation cost model of each of the components according to the historical operating parameters. A power plant cost model is obtained, and the operating cost model is used to simulate the changing trend of the operating cost of each of the components with the input data; a third construction unit is used to determine the uncertainty parameters of the output load of the PV unit, the WPP unit and the virtual power plant according to the historical operating parameters, and obtain an uncertainty factor group, and a stochastic model is constructed according to the uncertainty factor group, and the stochastic model is used to simulate the changing trend of system uncertainty with the uncertainty factor group; a fourth construction unit is used to construct a target constraint group based on the power plant operation model, and the target constraint group is used to limit the parameter values ​​of the power plant operation model, and the target constraint group at least includes system balance constraints, CHP unit constraints, WPP unit constraints, PV unit constraints, spare capacity constraints and carbon capture device constraints; a calculation unit is used to perform risk avoidance solutions and opportunity seeking solutions respectively based on the system uncertainty through the IGDT method to obtain a first uncertainty and a second uncertainty, and based on the first uncertainty and the second uncertainty, the power plant operation model is solved with the output minimization of the operating cost model as the objective function to obtain power plant control parameters, and the operation of the virtual power plant is controlled according to the power plant control parameters.

[0013] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium includes a stored program, wherein when the program is executed, the method described in any one of the devices where the computer-readable storage medium is located is controlled.

[0014] According to another aspect of the present application, a virtual power plant planning system is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of the described methods.

[0015] By applying the technical solution of the present application, cost modeling is performed based on physical modeling, and then minimizing cost is used as the objective function under constraints. The negative expectation and positive expectation of the objective function are solved separately according to the IGDT theory, and finally integrated to determine the scheduling parameters of the virtual power plant and control the virtual power plant. This method solves the problem in the prior art of the lack of a virtual power plant scheduling optimization method that integrates cogeneration units, carbon capture and electrical conversion equipment to meet low cost and low carbon requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A hardware structure block diagram of a mobile terminal according to a cost optimization method of an electric-thermal coupled virtual power plant based on a stochastic optimization method provided in an embodiment of the present application is shown;

[0017] Figure 2 A schematic flow chart of a cost optimization method for an electric-thermal coupled virtual power plant based on a stochastic optimization method according to an embodiment of the present application is shown;

[0018] Figure 3 A structural block diagram of a cost optimization device for an electric-thermal coupled virtual power plant based on a stochastic optimization method provided according to an embodiment of the present application is shown.

[0019] The above drawings include the following reference numerals:

[0020] 102, processor; 104, memory; 106, transmission device; 108, input and output devices. DETAILED DESCRIPTION

[0021] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0022] In order to enable those skilled in the art to better understand the present application, 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 only 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 ordinary technicians in this field without creative work should fall within the scope of protection of this application.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present application described here. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] As introduced in the background technology, the virtual power plant scheduling scheme in the prior art is still based on the traditional virtual power plant, ignoring the uncertainty factors brought about by the introduction of new energy. Therefore, the prior art lacks a scheduling method that takes into account the energy conversion relationship in the virtual power plant that integrates multiple energy sources. In order to solve the problem that the prior art lacks a virtual power plant scheduling optimization method that integrates cogeneration units, carbon capture and electrical conversion equipment to meet the low cost and low carbon requirements, the embodiments of the present application provide a cost optimization method, optimization device, computer-readable storage medium, processor and optimization system for an electric-thermal coupled virtual power plant based on a random optimization method.

[0025] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0026] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 1 is a hardware structure block diagram of a mobile terminal for a cost optimization method of an electric-thermal coupling virtual power plant based on a random optimization method according to an embodiment of the present invention. Figure 1 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 and an input / output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0027] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the display method of device information in the embodiment of the present invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, the above method is implemented. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The transmission device 106 is used to receive or send data via a network. The above-mentioned specific examples of the network may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0028] In this embodiment, a cost optimization method for an electric-thermal coupled virtual power plant based on a stochastic optimization method is provided, which runs on a mobile terminal, a computer terminal or a similar computing device. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0029] Figure 2 1 is a flow chart of a cost optimization method for an electric-thermal coupled virtual power plant based on a stochastic optimization method according to an embodiment of the present application. Figure 2 As shown, the method comprises the following steps:

[0030] Step S201, obtaining historical operating parameters, the above historical operating parameters include input data and output data of each component of the virtual power plant, and the operating cost of each of the above components, the above components include CHP units, WPP units, PV units, carbon capture devices and electrical conversion devices, the above CHP units receive natural gas and output electrical energy and thermal energy, the above PV units receive light energy and output electrical energy, the above WPP units receive wind energy and output electrical energy, the above carbon capture device receives the electrical energy of the above CHP units for collecting the carbon dioxide output by the above CHP units and outputting it to the above electrical conversion device, and the above electrical conversion device receives the electrical energy of the above WPP units for converting the carbon dioxide of the above carbon capture device into methane.

[0031] Specifically, first, the internal structure of the virtual power plant is clarified. In the embodiment of the present application, the virtual power plant includes a wind turbine (WPP unit), a photovoltaic unit (PV unit) and a combined heat and power unit (CHP unit). The power generation is based on the above-mentioned generator set to supply the main power grid. In addition, the present application is also provided with an electric-assisted carbon capture device, which absorbs carbon dioxide to supply the above-mentioned electrical conversion device (P2G) to catalyze the production of methane. Step S202, construct a physical simulation model of each of the above-mentioned components according to the above-mentioned historical operating parameters to obtain a power plant operation model, which is used to simulate the output data of each of the above-mentioned components and the change trend of energy flow with the input data.

[0032] Specifically, based on the above structure, the energy flow between the various components of the virtual power plant is determined. The virtual power plant system mainly includes electrical energy flow, thermal energy flow, carbon energy flow and natural gas flow. The thermal energy flow is mainly generated by the CHP unit and supplies the heat load. The natural gas flow and the carbon energy flow can be combined, including generation and consumption. The consumption is the power generation by the CHP unit, and the generation is the carbon dioxide absorbed by the carbon capture equipment entering the electrical conversion equipment, converted into methane, supplied for consumption and sold to the natural gas grid. Based on the above energy flow, the above power plant operation model is obtained by associating the energy flow on the basis of establishing the physical simulation model of each component.

[0033] Step S203, constructing an operation cost model of each of the above components according to the above historical operation parameters to obtain a power plant cost model, wherein the above operation cost model is used to simulate the change trend of the operation cost of each of the above components with the input data.

[0034] Specifically, based on the operating parameters of the power plant operation model, the cost of the power generation unit, the operating cost of the carbon capture device, and the operating cost of the electrical conversion device are determined respectively, and the operating cost models are constructed respectively to obtain the power plant cost model.

[0035] Step S204, determining the uncertainty parameters of the output load of the PV unit, the WPP unit and the virtual power plant according to the historical operating parameters, obtaining an uncertainty factor group, and constructing a stochastic model according to the uncertainty factor group. The stochastic model is used to simulate the changing trend of system uncertainty with the uncertainty factor group.

[0036] Specifically, the uncertainty parameters of the load are simulated and the above model is optimized in combination with the information gap decision theory.

[0037] Step S205, constructing a target constraint group based on the power plant operation model, wherein the target constraint group is used to limit parameter values ​​of the power plant operation model, and the target constraint group at least includes system balance constraints, CHP unit constraints, WPP unit constraints, PV unit constraints, spare capacity constraints and carbon capture device constraints.

[0038] Specifically, in order to ensure the normal operation of the virtual power plant, the physical simulation model input parameters and / or output parameters of each of the above-mentioned components are set to restrict and construct the above-mentioned target constraint group.

[0039] Step S206, based on the above system uncertainty, risk avoidance solution and opportunity seeking solution are respectively performed through the IGDT method to obtain a first uncertainty and a second uncertainty. Based on the above first uncertainty and the above second uncertainty, the above power plant operation model is solved with the output minimization of the above operation cost model as the objective function to obtain the power plant control parameters, and the operation of the above virtual power plant is controlled according to the above power plant control parameters.

[0040] Specifically, based on the IGDT method, the power plant operation model is solved to obtain power plant control parameters by taking the output minimization of the operation cost model as the objective function while considering uncertainty, and the operation of the virtual power plant is controlled according to the power plant control parameters.

[0041] Through this embodiment, first, historical operating parameters are obtained, and the above historical operating parameters include input data and output data of each component of the virtual power plant, and the operating cost of each of the above components. The above components include CHP units, WPP units, PV units, carbon capture devices and electrical conversion devices. The above CHP units receive natural gas and output electrical energy and thermal energy, the above PV units receive light energy and output electrical energy, the above WPP units receive wind energy and output electrical energy, the above carbon capture device receives the electrical energy of the above CHP units for collecting the carbon dioxide output by the above CHP units and outputting it to the above electrical conversion device, and the above electrical conversion device receives the electrical energy of the above WPP units for converting the carbon dioxide of the above carbon capture device into methane; then, a physical simulation model of each of the above components is constructed according to the above historical operating parameters to obtain a power plant operation model, and the above power plant operation model is used to simulate the output data of each of the above components and the energy flow changing trend with the input data; then, an operating cost model of each of the above components is constructed according to the above historical operating parameters to obtain a power plant cost model, and the above operating cost model is used to Simulate the changing trend of the operating cost of each of the above-mentioned components with the input data; then, determine the uncertainty parameters of the output load of the above-mentioned PV unit, the above-mentioned WPP unit and the above-mentioned virtual power plant according to the above-mentioned historical operating parameters, and obtain the uncertainty factor group; construct a stochastic model according to the above-mentioned uncertainty factor group, and the above-mentioned stochastic model is used to simulate the changing trend of the system uncertainty with the above-mentioned uncertainty factor group; then, construct a target constraint group based on the above-mentioned power plant operation model, and the above-mentioned target constraint group is used to limit the parameter values ​​of the above-mentioned power plant operation model, and the above-mentioned target constraint group at least includes system balance constraints, CHP unit constraints, WPP unit constraints, PV unit constraints, spare capacity constraints and carbon capture device constraints; finally, based on the above-mentioned system uncertainty, the IGDT method is used to perform risk avoidance solutions and opportunity seeking solutions respectively to obtain the first uncertainty and the second uncertainty; based on the above-mentioned first uncertainty and the above-mentioned second uncertainty, the above-mentioned power plant operation model is solved with the output minimization of the above-mentioned operating cost model as the objective function to obtain the power plant control parameters, and the operation of the above-mentioned virtual power plant is controlled according to the above-mentioned power plant control parameters. This application performs cost modeling based on physical modeling, and then takes minimizing cost as the objective function under constraints. According to the IGDT theory, the negative expectation and positive expectation of the objective function are solved separately, and finally integrated to determine the scheduling parameters of the virtual power plant and control the virtual power plant. This method solves the problem in the prior art of the lack of a virtual power plant scheduling optimization method that integrates cogeneration units, carbon capture and electrical conversion equipment to meet low cost and low carbon requirements.

[0042] In order to obtain the power plant operation model, in an optional implementation, the above step S202 includes:

[0043] Step S2021, determining the power generation power, heat generation power and gas input power of the CHP unit according to the historical operation parameters, determining the power conversion efficiency according to the power generation power and the gas input power, determining the thermal conversion efficiency according to the heat generation power and the gas input power, constructing a power output formula according to the power generation power, the gas input power and the power conversion efficiency, constructing a thermal output formula according to the heat generation power, the gas input power and the thermal conversion efficiency, constructing a physical simulation model of the CHP unit according to the power output formula and the thermal output formula of the CHP unit, and obtaining a first simulation model;

[0044] Specifically, the first four simulation models are:

[0045]

[0046] in, and are the power generation and heat generation of the CHP unit at time t, is the gas input power of the above CHP unit at time t, η e,CHP and η h,CHP are the power and heat conversion efficiencies of the above CHP units, is the natural gas power input to the CHP unit at time t, and is the lower and upper limits of the natural gas power input to the CHP unit, P CHP,down and P CHP,up are the lower and upper limits of the ramp power of the above CHP units, and They are respectively the lower and upper limits of the power-to-heat ratio of the above-mentioned CHP unit.

[0047] The distribution relationship of the electricity generated by cogeneration is as follows:

[0048]

[0049] It indicates that the amount of electricity generated by the CHP unit at time t is supplied to the electrical load; It indicates that the electricity generated by the CHP unit at time t is supplied to the carbon capture equipment.

[0050] Step S2022, determining the power generation power, real-time wind speed, cut-in wind speed, cut-out wind speed and rated wind speed of the WPP unit according to the historical operation parameters, and constructing a physical simulation model of the WPP unit according to the correlation between the power generation power, the real-time wind speed, the cut-in wind speed, the cut-out wind speed and the rated wind speed of the WPP unit to obtain a second simulation model;

[0051] Specifically, the second simulation model is:

[0052]

[0053] in, is the power generation capacity of the WPP unit at time t, v t is the above real-time wind speed, v in is the above cut-in wind speed, v out is the above cut-out wind speed, v ra For the above rated wind speed, is the rated power of the fan of the above WPP unit.

[0054] Step S2023, determining the power generation power, photovoltaic panel area, average efficiency and light intensity of the PV unit according to the historical operation parameters, determining the solar energy absorption rate and the solar energy conversion rate according to the power generation power, the photovoltaic panel area, the average efficiency and the light intensity, constructing a power output formula with the power generation power, the photovoltaic panel area, the average efficiency, the light intensity, the solar energy absorption rate and the solar energy conversion rate, and constructing a physical simulation model of the PV unit according to the power output formula of the PV unit to obtain a third simulation model;

[0055] Specifically, the third simulation model is:

[0056]

[0057] in, is the power generation of the above PV unit at time t, S PV is the area of ​​the above photovoltaic panels; is the light intensity at time t; η PV is the above average efficiency; μ inv and μ sor are the conversion rate and absorption rate of the above solar energy respectively; loss is the photovoltaic power generation loss.

[0058] Step S2024, determining the fixed energy consumption, operating energy consumption and total energy consumption of the carbon capture device according to the historical operating parameters, constructing an energy consumption expression of the carbon capture device according to the fixed energy consumption, operating energy consumption and total energy consumption of the carbon capture device, and constructing a physical simulation model of the carbon capture device according to the energy consumption expression of the carbon capture device to obtain a fourth simulation model;

[0059] Specifically, the fourth simulation model is:

[0060]

[0061] in, is the total energy consumption of the above carbon capture device, is the fixed energy consumption of the carbon capture device, is the operating energy consumption of the above carbon capture device.

[0062] Since the energy consumption of the carbon capture equipment is provided by the CHP unit,

[0063] Step S2025, determine the total energy consumption, fixed energy consumption and operating energy consumption of the above-mentioned electrical conversion device based on the above-mentioned historical operating parameters, construct an energy consumption expression of the above-mentioned electrical conversion device based on the fixed energy consumption, operating energy consumption and total energy consumption of the above-mentioned electrical conversion device, and construct a physical simulation model of the above-mentioned electrical conversion device based on the energy consumption expression of the above-mentioned electrical conversion device to obtain a fifth simulation model.

[0064] Specifically, the fifth simulation model is: Q pg,t =P pg,t η pg , Q pg,t is the amount of gas generated by power-to-gas conversion. pg,t is the electricity consumption of power-to-gas. pg Represents electrical conversion efficiency.

[0065] Step S2026: construct the power plant operation model according to the first simulation model, the second simulation model, the third simulation model, the fourth simulation model and the fifth simulation model.

[0066] In order to obtain the second target formula, in an optional implementation manner, before constructing the power plant operation model according to the first simulation model, the second simulation model, the third simulation model, the fourth simulation model and the fifth simulation model, the method further includes:

[0067] Step S301, constructing a first target formula according to the power generation power of the CHP unit and the total energy consumption of the electrical conversion device, wherein the first target formula is used to simulate the flow direction of the output power of the CHP unit;

[0068] Specifically, the above first objective formula is:

[0069] Q pg,t =P pg,t η pg ;

[0070] Among them, Q pg,t The amount of gas converted by the above-mentioned electrical conversion device. pg,t is the total energy consumption of the above electrical conversion device, η pg Represents electrical conversion efficiency.

[0071] Step S302, determining the demand response power according to the historical operation parameters, constructing a load transfer formula according to the power generation power of the CHP unit, the power generation power of the WPP unit, the power generation power of the PV unit and the demand response power, and obtaining a second target formula, wherein the second target formula is used to simulate the change trend of the load transfer amount of the virtual power plant with the power generation power at any time;

[0072] Specifically, the second objective formula is:

[0073]

[0074]

[0075] in, is the load transfer amount of the nth load at time t, is the initial load transfer of the nth load at time t, M is the price demand elasticity matrix, P j (t) is the power of unit j at time t, is the initial power of unit j at time t, is the load transfer-in / transfer-out coefficient, which is a 0-1 variable. When the load is turned on, When , it indicates load transfer out, that is, load transfer in and load transfer out cannot occur at the same time. is the maximum load transfer amount.

[0076] In order to obtain the power plant cost model, in an optional implementation, the above step S203 includes:

[0077] Step S2031, determining the fuel cost and power generation of the CHP unit according to the historical operating parameters, and obtaining a third target formula according to the fuel cost and the power generation, wherein the third target formula is used to simulate the variation trend of the fuel cost with the power generation;

[0078] Specifically, the third objective formula is:

[0079]

[0080] in, is the fuel cost of the above CHP unit, a CHP ,b CHP and c CHP is the energy consumption coefficient of the above CHP unit, Q CHP,t is the power generation capacity of the above CHP unit.

[0081] Step S2032, determining the start-stop cost and the first variable of the CHP unit according to the historical operating parameters, and fitting the start-stop cost and the first variable to obtain a fourth target formula, wherein the fourth target formula is used to simulate the change trend of the start-stop cost with the first variable, and the first variable is a binary variable indicating whether the CHP unit is started;

[0082] Specifically, the fourth objective formula is:

[0083]

[0084] in, is the startup and shutdown cost of the above CHP unit, u CHP,t is the power generation state variable of the above CHP unit, which is a 0-1 variable, 1 means the CHP unit is in operation, 0 means the CHP unit is in shutdown, D CHP,t is the startup cost of the above CHP unit.

[0085] Step S2033, combining the third target formula and the fourth target formula to obtain the operation cost model of the CHP unit;

[0086] Specifically, the operating cost model of the above CHP unit is:

[0087]

[0088] Among them, C CHP is the operating cost of the above CHP unit.

[0089] Step S2034, determining the operating cost, depreciation cost and power generation of the WPP unit according to the historical operating parameters, and constructing an operating cost model of the WPP unit according to the operating cost, depreciation cost and power generation of the WPP unit, wherein the operating cost model of the WPP unit is used to simulate the variation trend of the total cost of the WPP unit with the power generation;

[0090] Specifically, the operating cost model of the above WPP unit is:

[0091]

[0092] Among them, C WPP is the operating cost of the above WPP unit, is the operating cost of the above WPP unit at time t, is the depreciation cost of the above WPP unit, is the power generation capacity of the above WPP unit at time t, p WPP is the conversion factor of the WPP unit.

[0093] Step S2035, determining the operating cost, depreciation cost and power generation of the PV unit according to the historical operating parameters, and constructing an operating cost model of the PV unit according to the operating cost, depreciation cost and power generation of the PV unit, wherein the operating cost model of the PV unit is used to simulate the variation trend of the total cost of the PV unit with the power generation;

[0094] Specifically, the operating cost model of the above PV unit is:

[0095]

[0096] Among them, C PV is the operating cost of the above PV unit, is the operating cost of the above PV unit at time t, is the depreciation cost of the above PV unit, is the power generation of the above PV unit at time t, p PV is the conversion factor of the PV unit.

[0097] Step S2036, determining the energy consumption of the carbon capture device according to the historical operating parameters, and constructing an operating cost model of the carbon capture device according to the energy consumption of the carbon capture device, wherein the operating cost model of the carbon capture device is used to simulate the variation trend of the total cost of the carbon capture device with the energy consumption;

[0098] Specifically, the operating cost model of the above carbon capture device is:

[0099]

[0100] Among them, C CC is the total cost of the above carbon capture device, is the energy consumption of the carbon capture device at time t, and a, b, and c are the operating cost coefficients of the carbon capture equipment.

[0101] Step S2037, constructing a demand response cost model according to the load transfer amount of the virtual power plant, wherein the demand response cost model is used to simulate the changing trend of the demand response cost with the load transfer amount;

[0102] Specifically, the above demand response cost model is:

[0103]

[0104] in, are the electric load transfer cost and thermal load transfer cost of the nth load, and are the subsidy prices for transferring electrical load and transferring thermal load respectively.

[0105] Step S2038, determining a solar power abandonment and wind power abandonment cost model of the virtual power plant according to the historical operating parameters, wherein the solar power abandonment and wind power abandonment cost model is used to simulate the change trend of wind power abandonment and solar power abandonment penalties of the virtual power plant along with the solar power abandonment and wind power abandonment costs;

[0106] Specifically, the cost model of curtailed solar power and wind power in the above virtual power plant is:

[0107]

[0108] Among them, wpp is the wpp conversion coefficient, ζ pv is the pv conversion coefficient, To abandon wind power, To abandon the amount of photovoltaic power, is the actual amount of wind power connected to the grid, The actual amount of photovoltaic power connected to the grid.

[0109] Step S2039, constructing the above-mentioned operation cost model according to the operation cost model of the CHP unit, the operation cost model of the WPP unit, the operation cost model of the PV unit, the operation cost model of the carbon capture device and the demand response cost model:

[0110] minC VPP =min(C CHP +C WPP +C PV +C CC +C DR +C cur );

[0111] Among them, C VPP is the total cost of the virtual power plant.

[0112] In order to determine the uncertain parameters, in an optional implementation, the above step S204 includes:

[0113] Step S2041, determining the fluctuation range of the WPP unit based on the historical operating parameters, and determining the uncertainty parameter of the WPP unit through an envelope constraint model according to the fluctuation range and the historical operating parameters to obtain a first uncertainty parameter;

[0114] Specifically, the first uncertainty parameter mentioned above:

[0115]

[0116] Among them, P WPP is the actual power generation of the above WPP unit, is the historical data of the above WPP units during the dispatch period, α WPPis the fluctuation range of the above WPP unit, which is a dimensionless value, reflecting the maximum degree of deviation of the above WPP unit from historical data.

[0117] Step S2042, determining the fluctuation range of the PV unit based on the historical operating parameters, and determining the uncertainty parameter of the PV unit through an envelope constraint model according to the fluctuation range and the historical operating parameters to obtain a second uncertainty parameter;

[0118] Specifically, the second uncertainty parameter is:

[0119]

[0120] Among them, P PV is the actual power generation of the above PV unit; is the historical data of the above PV units during the dispatch period; α PV is the fluctuation range of the above PV unit, which is a dimensionless value, reflecting the maximum degree of deviation of the above PV unit from historical data.

[0121] Step S2043, determining the fluctuation range of the output load of the virtual power plant based on the historical operating parameters, and determining the uncertainty parameter of the output load of the virtual power plant through an envelope constraint model according to the fluctuation range and the historical operating parameters to obtain a third uncertainty parameter;

[0122] Specifically, the third uncertainty parameter is:

[0123]

[0124] Among them, P L is the output load of the above virtual power plant; is the historical data of the output load of the above virtual power plant during the dispatch period; α L is the fluctuation range of the output load of the above virtual power plant, which is a dimensionless value, reflecting the maximum degree to which the above output load deviates from historical data.

[0125] Step S2044, constructing the uncertainty factor group according to the first uncertainty parameter, the second uncertainty parameter and the third uncertainty parameter, and constructing a stochastic model according to the uncertainty factor group;

[0126] Specifically, the above stochastic model is:

[0127] α=α WPP *λ WPP +α PV *λ PV +α L *λ L ;

[0128] Among them, α is the comprehensive uncertainty level of the system; λ WPP ,λ PV and λ L are the weights of the above-mentioned WPP unit, the above-mentioned PV unit and the above-mentioned output load uncertainty, respectively, and their weights can be determined by an objective weighting method.

[0129] In order to construct the target constraint group, in an optional implementation, the above step S205 includes:

[0130] Step S2051, construct the system balance constraint of the virtual power plant corresponding to the power plant operation model to obtain the first target constraint:

[0131]

[0132] Among them, Q CHP is the active power output of the above CHP unit, Q j,WPP is the active power output of the above WPP unit j, Q m,pv is the active output of the above PV unit m, and D represents the system load demand value;

[0133] Step S2052, construct the CHP unit constraints of the virtual power plant corresponding to the power plant operation model to obtain the second target constraint:

[0134]

[0135] in, is the maximum dispatchable output of the above CHP unit; is the minimum dispatchable output of the above CHP unit;

[0136] Step S2053, construct the WPP unit constraints of the virtual power plant corresponding to the power plant operation model to obtain the third target constraint:

[0137]

[0138] in, is the maximum dispatchable output of the above WPP unit j, is the minimum dispatchable output of the above WPP unit j;

[0139] Step 2054, construct the PV unit constraints of the virtual power plant corresponding to the power plant operation model to obtain the fourth target constraint:

[0140]

[0141] in, is the maximum dispatchable output of the above PV unit m; is the minimum dispatchable output of the above PV unit m;

[0142] Step S2055, construct the above-mentioned reserve capacity constraint of the above-mentioned virtual power plant corresponding to the above-mentioned power plant operation model to obtain the fifth target constraint:

[0143]

[0144] Where D(t) is the load demand of the virtual power plant system at time t, R(t) is the reserve demand of the virtual power plant system at time t, l is the line loss rate of the virtual power plant system, θ is the self-use rate of the virtual power plant unit, Q max (t) is the maximum unit output of the above virtual power plant unit at time t;

[0145] Step S2056, construct the carbon capture device constraint of the virtual power plant corresponding to the power plant operation model to obtain the sixth target constraint:

[0146]

[0147] Among them, P CC,min and P CC,max are the minimum and maximum output limits of the above carbon capture device, is the ramp rate constraint of the carbon capture device;

[0148] Step S2057, combining the first objective constraint, the second objective constraint, the third objective constraint, the fourth objective constraint, the fifth objective constraint and the sixth objective constraint to obtain the objective constraint group;

[0149] In order to obtain uncertainty, in an optional implementation, the above step S206 includes:

[0150] Step S2061, obtaining a preset robustness coefficient, and based on the above system uncertainty and the above preset robustness coefficient, converting the above objective function to obtain a risk avoidance formula group;

[0151] Specifically, the above risk aversion formula group is:

[0152]

[0153] Among them, β1 is the above-mentioned preset robustness coefficient. The larger β1 is, the stronger the system's robustness and risk resistance are. F is the objective function of the deterministic model, that is, the above-mentioned operating cost model. F0 is the optimization target benchmark value, that is, when the above-mentioned WPP unit, PV unit, and load are all historical data, the cost size obtained by solving the model. (1+β1)F0 is the expected cost of the model under risk-averse decision-making. and is the uncertainty of the above WPP units, PV units and loads under risk-averse decision-making.

[0154] Step S2062, substituting the above uncertainty factor group into the above risk avoidance formula group to obtain the above first uncertainty;

[0155] Specifically, if in actual operation, the actual processing of wind power and photovoltaic power is lower than the historical data, that is, The dispatch cost of the system increases. In order to achieve the worst expectation under the robust model, the output of wind power and photovoltaic power is minimized, and the upward fluctuation of load is maximized. At this time, the cost of the objective function takes the maximum value, and the above-mentioned risk aversion formula group is transformed as shown in the following formula. Then, the above-mentioned first uncertainty parameter, the above-mentioned second uncertainty parameter and the above-mentioned third uncertainty parameter are solved according to the following formula and substituted into the above-mentioned randomness model to solve the above-mentioned first uncertainty.

[0156]

[0157] Step S2063, obtaining a minimum value based on the above system uncertainty, and converting the above objective function to obtain an opportunity seeking formula group;

[0158] Specifically, the above opportunity seeks a formula group:

[0159]

[0160] Among them, α2 is the system comprehensive uncertainty of the opportunity-seeking model, β2 is the opportunity deviation factor, (1-β2)F0 is the expected cost in this scenario, and The uncertainty of the above WPP units, PV units and loads under the opportunity-seeking decision;

[0161] Step S2064, substituting the above uncertainty factor group into the above opportunity seeking formula group to obtain the above second uncertainty;

[0162] Specifically, when the processing is the largest within the fluctuation range of wind power and photovoltaic units and the upward fluctuation of load is the smallest, the solution is performed under the condition of minimum uncertainty, and the above opportunity seeking formula group is converted as shown in the following formula, and then the above first uncertainty parameter, the above second uncertainty parameter and the above third uncertainty parameter are solved according to the following formula and substituted into the above randomness model to solve the above second uncertainty, so as to obtain the above second uncertainty.

[0163]

[0164] In the above embodiment, the power plant operation model is further constrained based on the above first uncertainty and the above second uncertainty:

[0165]

[0166] Specifically, under the above constraints, uncertainty is introduced into the above power plant operation model, and then the above power plant operation model is solved with the output minimization of the above operation cost model as the objective function to obtain the power plant control parameters, and the operation of the above virtual power plant is controlled according to the above power plant control parameters.

[0167] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0168] The embodiment of the present application also provides a cost optimization device for an electric-thermal coupled virtual power plant based on a random optimization method. It should be noted that the cost optimization device for an electric-thermal coupled virtual power plant based on a random optimization method in the embodiment of the present application can be used to execute the cost optimization method for an electric-thermal coupled virtual power plant based on a random optimization method provided in the embodiment of the present application. The device is used to implement the above-mentioned embodiments and preferred implementation modes, and those that have been described will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware for a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0169] The following introduces the cost optimization device of the electric-thermal coupled virtual power plant based on the stochastic optimization method provided in the embodiment of the present application.

[0170] Figure 3 1 is a structural block diagram of a cost optimization device for an electric-thermal coupled virtual power plant based on a stochastic optimization method according to an embodiment of the present application. Figure 3 As shown, the device comprises:

[0171] The acquisition unit 10 is used to acquire historical operation parameters, wherein the historical operation parameters include input data and output data of each component of the virtual power plant and the operation cost of each of the above components, wherein the above components include a CHP unit, a WPP unit, a PV unit, a carbon capture device and an electrical conversion device, wherein the CHP unit receives natural gas and outputs electrical energy and thermal energy, the PV unit receives light energy and outputs electrical energy, the WPP unit receives wind energy and outputs electrical energy, the carbon capture device receives the electrical energy of the CHP unit for collecting the carbon dioxide output by the CHP unit and outputting it to the electrical conversion device, and the electrical conversion device receives the electrical energy of the WPP unit for converting the carbon dioxide of the carbon capture device into methane;

[0172] A first construction unit 20 is used to construct a physical simulation model of each of the above-mentioned components according to the above-mentioned historical operation parameters to obtain a power plant operation model, wherein the power plant operation model is used to simulate the output data of each of the above-mentioned components and the change trend of energy flow with input data;

[0173] A second construction unit 30 is used to construct an operation cost model of each of the above-mentioned components according to the above-mentioned historical operation parameters to obtain a power plant cost model, wherein the above-mentioned operation cost model is used to simulate the change trend of the operation cost of each of the above-mentioned components with the input data;

[0174] A third construction unit 40 is used to determine uncertainty parameters of the output loads of the PV unit, the WPP unit and the virtual power plant according to the historical operating parameters, obtain an uncertainty factor group, and construct a stochastic model according to the uncertainty factor group, wherein the stochastic model is used to simulate the changing trend of system uncertainty with the uncertainty factor group;

[0175] A fourth construction unit 50 is used to construct a target constraint group based on the power plant operation model, wherein the target constraint group is used to limit parameter values ​​of the power plant operation model, and the target constraint group at least includes system balance constraints, CHP unit constraints, WPP unit constraints, PV unit constraints, spare capacity constraints and carbon capture device constraints;

[0176] The calculation unit 60 is used to perform risk avoidance solutions and opportunity seeking solutions respectively based on the above-mentioned system uncertainty through the IGDT method to obtain a first uncertainty and a second uncertainty. Based on the above-mentioned first uncertainty and the above-mentioned second uncertainty, the above-mentioned power plant operation model is solved with minimization of the output of the above-mentioned operation cost model as the objective function to obtain power plant control parameters, and the operation of the above-mentioned virtual power plant is controlled according to the above-mentioned power plant control parameters.

[0177] Through this embodiment, the acquisition unit acquires historical operating parameters, and the above historical operating parameters include input data and output data of each component of the virtual power plant, and the operating cost of each of the above components. The above components include CHP units, WPP units, PV units, carbon capture devices and electrical conversion devices. The above CHP units receive natural gas and output electrical energy and thermal energy, the above PV units receive light energy and output electrical energy, the above WPP units receive wind energy and output electrical energy, the above carbon capture device receives the electrical energy of the above CHP units for collecting the carbon dioxide output by the above CHP units and outputting it to the above electrical conversion device, and the above electrical conversion device receives the electrical energy of the above WPP units for converting the carbon dioxide of the above carbon capture device into methane; the first construction unit constructs a physical simulation model of each of the above components according to the above historical operating parameters to obtain a power plant operation model, and the above power plant operation model is used to simulate the output data of each of the above components and the energy flow changing trend with the input data; the second construction unit constructs an operating cost model of each of the above components according to the above historical operating parameters to obtain a power plant cost model, and the above operating cost model is used to Simulate the changing trend of the operating cost of each of the above-mentioned components with the input data; the third construction unit determines the uncertainty parameters of the output load of the above-mentioned PV unit, the above-mentioned WPP unit and the above-mentioned virtual power plant according to the above-mentioned historical operating parameters, and obtains the uncertainty factor group, and constructs a stochastic model according to the above-mentioned uncertainty factor group, and the above-mentioned stochastic model is used to simulate the changing trend of the system uncertainty with the above-mentioned uncertainty factor group; the fourth construction unit constructs a target constraint group based on the above-mentioned power plant operation model, and the above-mentioned target constraint group is used to limit the parameter values ​​of the above-mentioned power plant operation model, and the above-mentioned target constraint group at least includes system balance constraints, CHP unit constraints, WPP unit constraints, PV unit constraints, spare capacity constraints and carbon capture device constraints; the calculation unit performs risk avoidance solutions and opportunity seeking solutions respectively based on the above-mentioned system uncertainty through the IGDT method to obtain the first uncertainty and the second uncertainty, based on the above-mentioned first uncertainty and the above-mentioned second uncertainty, the above-mentioned power plant operation model is solved with the output minimization of the above-mentioned operation cost model as the objective function to obtain the power plant control parameters, and the operation of the above-mentioned virtual power plant is controlled according to the above-mentioned power plant control parameters. This application performs cost modeling based on physical modeling, and then takes minimizing cost as the objective function under constraints. According to the IGDT theory, the negative expectation and positive expectation of the objective function are solved separately, and finally integrated to determine the scheduling parameters of the virtual power plant and control the virtual power plant. This method solves the problem in the prior art of the lack of a virtual power plant scheduling optimization method that integrates cogeneration units, carbon capture and electrical conversion equipment to meet low cost and low carbon requirements.

[0178] The cost optimization device of the electric-thermal coupling virtual power plant based on the stochastic optimization method comprises a processor and a memory, wherein the acquisition unit, the first construction unit, the second construction unit, the third construction unit, the fourth construction unit, the calculation unit, etc. are all stored in the memory as program units, and the processor executes the program units stored in the memory to realize the corresponding functions. The above modules are all located in the same processor; or, the above modules are located in different processors in any combination.

[0179] The processor includes a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set, and the cost optimization efficiency of the virtual power plant can be improved by adjusting the kernel parameters.

[0180] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0181] An embodiment of the present invention provides a computer-readable storage medium, which includes a stored program, wherein when the program is running, the device where the computer-readable storage medium is located is controlled to execute the cost optimization method of the electric-thermal coupled virtual power plant based on the random optimization method.

[0182] Specifically, the cost optimization method of the electric-thermal coupled virtual power plant based on the stochastic optimization method includes:

[0183] Step S201, obtaining historical operating parameters, the historical operating parameters including input data and output data of each component of the virtual power plant, and operating costs of each of the above components, the above components including CHP units, WPP units, PV units, carbon capture devices and electrical conversion devices, the CHP units receiving natural gas and outputting electrical energy and thermal energy, the PV units receiving light energy and outputting electrical energy, the WPP units receiving wind energy and outputting electrical energy, the carbon capture devices receiving electrical energy from the CHP units for collecting carbon dioxide outputted by the CHP units and outputting it to the electrical conversion devices, the electrical conversion devices receiving electrical energy from the WPP units for converting carbon dioxide from the carbon capture devices into methane;

[0184] Step S202, constructing a physical simulation model of each of the above-mentioned components according to the above-mentioned historical operating parameters to obtain a power plant operation model, wherein the above-mentioned power plant operation model is used to simulate the output data of each of the above-mentioned components and the change trend of energy flow with input data;

[0185] Step S203, constructing an operation cost model of each of the above-mentioned components according to the above-mentioned historical operation parameters to obtain a power plant cost model, wherein the above-mentioned operation cost model is used to simulate the change trend of the operation cost of each of the above-mentioned components with the input data;

[0186] Step S204, determining uncertainty parameters of the output loads of the PV unit, the WPP unit and the virtual power plant according to the historical operating parameters, obtaining an uncertainty factor group, and constructing a stochastic model according to the uncertainty factor group, wherein the stochastic model is used to simulate the changing trend of system uncertainty with the uncertainty factor group;

[0187] Step S205, constructing a target constraint group based on the power plant operation model, the target constraint group is used to limit parameter values ​​of the power plant operation model, and the target constraint group at least includes system balance constraints, CHP unit constraints, WPP unit constraints, PV unit constraints, spare capacity constraints and carbon capture device constraints;

[0188] Step S206, based on the above system uncertainty, risk avoidance solution and opportunity seeking solution are respectively performed through the IGDT method to obtain a first uncertainty and a second uncertainty. Based on the above first uncertainty and the above second uncertainty, the above power plant operation model is solved with the output minimization of the above operation cost model as the objective function to obtain the power plant control parameters, and the operation of the above virtual power plant is controlled according to the above power plant control parameters.

[0189] An embodiment of the present invention provides a processor, which is used to run a program, wherein the cost optimization method of the electric-thermal coupled virtual power plant based on the random optimization method is executed when the program is running.

[0190] An embodiment of the present invention provides a virtual power plant planning system, the virtual power plant planning system includes a processor, a memory, and a program stored in the memory and executable on the processor, and when the processor executes the program, the following steps of a cost optimization method of an electric-thermal coupling virtual power plant based on at least a random optimization method are implemented:

[0191] Step S201, obtaining historical operating parameters, the historical operating parameters including input data and output data of each component of the virtual power plant, and operating costs of each of the above components, the above components including CHP units, WPP units, PV units, carbon capture devices and electrical conversion devices, the CHP units receiving natural gas and outputting electrical energy and thermal energy, the PV units receiving light energy and outputting electrical energy, the WPP units receiving wind energy and outputting electrical energy, the carbon capture devices receiving electrical energy from the CHP units for collecting carbon dioxide outputted by the CHP units and outputting it to the electrical conversion devices, the electrical conversion devices receiving electrical energy from the WPP units for converting carbon dioxide from the carbon capture devices into methane;

[0192] Step S202, constructing a physical simulation model of each of the above-mentioned components according to the above-mentioned historical operating parameters to obtain a power plant operation model, wherein the above-mentioned power plant operation model is used to simulate the output data of each of the above-mentioned components and the change trend of energy flow with input data;

[0193] Step S203, constructing an operation cost model of each of the above-mentioned components according to the above-mentioned historical operation parameters to obtain a power plant cost model, wherein the above-mentioned operation cost model is used to simulate the change trend of the operation cost of each of the above-mentioned components with the input data;

[0194] Step S204, determining uncertainty parameters of the output loads of the PV unit, the WPP unit and the virtual power plant according to the historical operating parameters, obtaining an uncertainty factor group, and constructing a stochastic model according to the uncertainty factor group, wherein the stochastic model is used to simulate the changing trend of system uncertainty with the uncertainty factor group;

[0195] Step S205, constructing a target constraint group based on the power plant operation model, the target constraint group is used to limit parameter values ​​of the power plant operation model, and the target constraint group at least includes system balance constraints, CHP unit constraints, WPP unit constraints, PV unit constraints, spare capacity constraints and carbon capture device constraints;

[0196] Step S206, based on the above system uncertainty, risk avoidance solution and opportunity seeking solution are respectively performed through the IGDT method to obtain a first uncertainty and a second uncertainty. Based on the above first uncertainty and the above second uncertainty, the above power plant operation model is solved with the output minimization of the above operation cost model as the objective function to obtain the power plant control parameters, and the operation of the above virtual power plant is controlled according to the above power plant control parameters.

[0197] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that initializes at least the cost optimization method steps of the above-mentioned electric-thermal coupled virtual power plant based on the stochastic optimization method.

[0198] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0199] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0200] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0201] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0202] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0203] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0204] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0205] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0206] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0207] From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

[0208] The cost optimization method of the electric-thermal coupling virtual power plant based on the stochastic optimization method of the present application first obtains historical operating parameters, the above historical operating parameters include input data and output data of each component of the virtual power plant, and the operating cost of each of the above components, the above components include CHP units, WPP units, PV units, carbon capture devices and electrical conversion devices, the above CHP units receive natural gas and output electrical energy and thermal energy, the above PV units receive light energy and output electrical energy, the above WPP units receive wind energy and output electrical energy, the above carbon capture device receives the electrical energy of the above CHP units for collecting the carbon dioxide output by the above CHP units and outputting it to the above electrical conversion device, and the above electrical conversion device receives the electrical energy of the above WPP units for converting the carbon dioxide of the above carbon capture device into methane; then, a physical simulation model of each of the above components is constructed according to the above historical operating parameters to obtain a power plant operation model, the above power plant operation model is used to simulate the output data of each of the above components and the energy flow changing trend with the input data; then, an operation cost model of each of the above components is constructed according to the above historical operating parameters to obtain a power plant cost model , the above-mentioned operating cost model is used to simulate the changing trend of the operating cost of each of the above-mentioned components with the input data; then, the uncertainty parameters of the output load of the above-mentioned PV unit, the above-mentioned WPP unit and the above-mentioned virtual power plant are determined according to the above-mentioned historical operating parameters to obtain an uncertainty factor group, and a stochastic model is constructed according to the above-mentioned uncertainty factor group. The above-mentioned stochastic model is used to simulate the changing trend of system uncertainty with the above-mentioned uncertainty factor group; then, a target constraint group is constructed based on the above-mentioned power plant operation model, and the above-mentioned target constraint group is used to limit the parameter values ​​of the above-mentioned power plant operation model. The above-mentioned target constraint group at least includes system balance constraints, CHP unit constraints, WPP unit constraints, PV unit constraints, spare capacity constraints and carbon capture device constraints; finally, based on the above-mentioned system uncertainty, risk avoidance solutions and opportunity seeking solutions are respectively performed through the IGDT method to obtain the first uncertainty and the second uncertainty. Based on the above-mentioned first uncertainty and the above-mentioned second uncertainty, the above-mentioned power plant operation model is solved with the output minimization of the above-mentioned operating cost model as the objective function to obtain the power plant control parameters, and the operation of the above-mentioned virtual power plant is controlled according to the above-mentioned power plant control parameters. This application performs cost modeling based on physical modeling, and then takes minimizing cost as the objective function under constraints. According to the IGDT theory, the negative expectation and positive expectation of the objective function are solved separately, and finally integrated to determine the scheduling parameters of the virtual power plant and control the virtual power plant. This method solves the problem in the prior art of the lack of a virtual power plant scheduling optimization method that integrates cogeneration units, carbon capture and electrical conversion equipment to meet low cost and low carbon requirements.

[0209] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A cost optimization method for an electric-thermal coupled virtual power plant based on a stochastic optimization method, characterized in that: The method comprises: Acquire historical operating parameters, wherein the historical operating parameters include input data and output data of each component of the virtual power plant, and operating costs of each component, wherein the components include a CHP unit, a WPP unit, a PV unit, a carbon capture device, and an electrical conversion device, wherein the CHP unit receives natural gas and outputs electrical energy and thermal energy, the PV unit receives light energy and outputs electrical energy, the WPP unit receives wind energy and outputs electrical energy, the carbon capture device receives electrical energy from the CHP unit for collecting carbon dioxide output by the CHP unit and outputting it to the electrical conversion device, and the electrical conversion device receives electrical energy from the WPP unit for converting carbon dioxide from the carbon capture device into methane; Constructing a physical simulation model of each of the components according to the historical operating parameters to obtain a power plant operation model, wherein the power plant operation model is used to simulate the output data of each of the components and the change trend of energy flow with input data; Constructing an operation cost model of each of the components according to the historical operation parameters to obtain a power plant cost model, wherein the operation cost model is used to simulate the change trend of the operation cost of each of the components with the input data; Determine uncertainty parameters of the output loads of the PV unit, the WPP unit and the virtual power plant according to the historical operating parameters to obtain an uncertainty factor group, and construct a stochastic model according to the uncertainty factor group, wherein the stochastic model is used to simulate the changing trend of system uncertainty with the uncertainty factor group; Constructing a target constraint group based on the power plant operation model, wherein the target constraint group is used to limit parameter values ​​of the power plant operation model, and the target constraint group at least includes system balance constraints, CHP unit constraints, WPP unit constraints, PV unit constraints, spare capacity constraints, and carbon capture device constraints; Based on the system uncertainty, the IGDT method is used to perform risk avoidance solutions and opportunity seeking solutions respectively to obtain a first uncertainty and a second uncertainty. Based on the first uncertainty and the second uncertainty, the power plant operation model is solved with the output minimization of the operation cost model as the objective function to obtain power plant control parameters, and the operation of the virtual power plant is controlled according to the power plant control parameters.

2. The method according to claim 1, characterized in that Constructing a physical simulation model of each of the components according to the historical operating parameters to obtain a power plant operation model, including: Determine the power generation power, heat generation power, and gas input power of the CHP unit according to the historical operating parameters, determine the power conversion efficiency according to the power generation power and the gas input power, determine the thermal conversion efficiency according to the heat generation power and the gas input power, construct a power output formula according to the power generation power, the gas input power, and the power conversion efficiency, construct a thermal output formula according to the heat generation power, the gas input power, and the thermal conversion efficiency, and construct a physical simulation model of the CHP unit according to the power output formula and the thermal output formula of the CHP unit to obtain a first simulation model; Determine the power generation power, real-time wind speed, cut-in wind speed, cut-out wind speed and rated wind speed of the WPP unit according to the historical operation parameters, and construct a physical simulation model of the WPP unit according to the correlation between the power generation power, the real-time wind speed, the cut-in wind speed, the cut-out wind speed and the rated wind speed of the WPP unit to obtain a second simulation model; Determine the power generation power, photovoltaic panel area, average efficiency and light intensity of the PV group according to the historical operation parameters, determine the solar energy absorption rate and solar energy conversion rate according to the power generation power, the photovoltaic panel area, the average efficiency and the light intensity, construct a power output formula with the power generation power, the photovoltaic panel area, the average efficiency, the light intensity, the solar energy absorption rate and the solar energy conversion rate, and construct a physical simulation model of the PV group according to the power output formula of the PV group to obtain a third simulation model; determining the fixed energy consumption, operating energy consumption and total energy consumption of the carbon capture device according to the historical operating parameters, constructing an energy consumption expression of the carbon capture device according to the fixed energy consumption, operating energy consumption and total energy consumption of the carbon capture device, and constructing a physical simulation model of the carbon capture device according to the energy consumption expression of the carbon capture device to obtain a fourth simulation model; Determine the total energy consumption, fixed energy consumption and operating energy consumption of the electrical conversion device according to the historical operating parameters, construct an energy consumption expression of the electrical conversion device according to the fixed energy consumption, operating energy consumption and total energy consumption of the electrical conversion device, and construct a physical simulation model of the electrical conversion device according to the energy consumption expression of the electrical conversion device to obtain a fifth simulation model; The power plant operation model is constructed according to the first simulation model, the second simulation model, the third simulation model, the fourth simulation model and the fifth simulation model.

3. The method according to claim 2, characterized in that Before constructing the power plant operation model according to the first simulation model, the second simulation model, the third simulation model, the fourth simulation model and the fifth simulation model, the method further includes: constructing a first target formula according to the power generation power of the CHP unit and the total energy consumption of the electrical conversion device, wherein the first target formula is used to simulate the flow direction of the output power of the CHP unit; The demand response power is determined according to the historical operating parameters, and a load transfer formula is constructed according to the power generation power of the CHP unit, the power generation power of the WPP unit, the power generation power of the PV unit and the demand response power to obtain a second target formula. The second target formula is used to simulate the load transfer amount of the virtual power plant at any time as the power generation power changes.

4. The method according to claim 3, characterized in that An operation cost model of each of the components is constructed according to the historical operation parameters to obtain a power plant cost model, including: Determine the fuel cost and power generation of the CHP unit according to the historical operating parameters, and obtain a third target formula according to the fuel cost and the power generation, wherein the third target formula is used to simulate the change trend of the fuel cost with the power generation; Determine the start-up and shutdown cost and a first variable of the CHP unit according to the historical operating parameters, and perform fitting according to the start-up and shutdown cost and the first variable to obtain a fourth target formula, wherein the fourth target formula is used to simulate the change trend of the start-up and shutdown cost with the first variable, and the first variable is a binary variable indicating whether the CHP unit is started; Combining the third target formula and the fourth target formula to obtain an operation cost model of the CHP unit; Determine the operating cost, depreciation cost and power generation of the WPP unit according to the historical operating parameters, and construct an operating cost model of the WPP unit according to the operating cost, depreciation cost and power generation of the WPP unit, wherein the operating cost model of the WPP unit is used to simulate the variation trend of the total cost of the WPP unit with the power generation; Determine the operating cost, depreciation cost and power generation of the PV unit according to the historical operating parameters, and construct an operating cost model of the PV unit according to the operating cost, depreciation cost and power generation of the PV unit, wherein the operating cost model of the PV unit is used to simulate the variation trend of the total cost of the PV unit with the power generation; determining the energy consumption of the carbon capture device according to the historical operating parameters, and constructing an operating cost model of the carbon capture device according to the energy consumption of the carbon capture device, wherein the operating cost model of the carbon capture device is used to simulate the variation trend of the total cost of the carbon capture device with the energy consumption; According to the load transfer amount of the virtual power plant, a demand response cost model is constructed, wherein the demand response cost model is used to simulate the change trend of the demand response cost with the load transfer amount; Determine a solar power abandonment and wind power abandonment cost model of the virtual power plant according to the historical operating parameters, wherein the solar power abandonment and wind power abandonment cost model is used to simulate the change trend of wind power abandonment and solar power abandonment penalties of the virtual power plant as the solar power abandonment and wind power abandonment costs change; The operation cost model is constructed according to the operation cost model of the CHP unit, the operation cost model of the WPP unit, the operation cost model of the PV unit, the operation cost model of the carbon capture device and the demand response cost model.

5. The method according to claim 1, characterized in that: Determining uncertainty parameters of the output loads of the PV unit, the WPP unit, and the virtual power plant according to the historical operating parameters includes: Determine the fluctuation range of the WPP unit based on the historical operating parameters, and determine the uncertainty parameter of the WPP unit through an envelope constraint model according to the fluctuation range and the historical operating parameters to obtain a first uncertainty parameter; Determine the fluctuation range of the PV unit based on the historical operating parameters, determine the uncertainty parameter of the PV unit through an envelope constraint model according to the fluctuation range and the historical operating parameters, and obtain a second uncertainty parameter; Determine a fluctuation range of the output load of the virtual power plant based on the historical operating parameters, and determine an uncertainty parameter of the output load of the virtual power plant through an envelope constraint model according to the fluctuation range and the historical operating parameters to obtain a third uncertainty parameter; The uncertainty factor group is constructed according to the first uncertainty parameter, the second uncertainty parameter and the third uncertainty parameter, and a stochastic model is constructed according to the uncertainty factor group.

6. The method according to claim 1, characterized in that A target constraint group is constructed based on the power plant operation model, including: Constructing the system balance constraint of the virtual power plant corresponding to the power plant operation model to obtain a first target constraint; Constructing the CHP unit constraints of the virtual power plant corresponding to the power plant operation model to obtain a second target constraint; Constructing the WPP unit constraints of the virtual power plant corresponding to the power plant operation model to obtain a third target constraint; Constructing the PV unit constraints of the virtual power plant corresponding to the power plant operation model to obtain a fourth target constraint; Constructing the reserve capacity constraint of the virtual power plant corresponding to the power plant operation model to obtain a fifth target constraint; Constructing the carbon capture device constraint of the virtual power plant corresponding to the power plant operation model to obtain a sixth target constraint; The objective constraint group is obtained by combining the first objective constraint, the second objective constraint, the third objective constraint, the fourth objective constraint, the fifth objective constraint and the sixth objective constraint.

7. The method according to claim 1, characterized in that Based on the system uncertainty, the risk avoidance solution and the opportunity seeking solution are respectively performed through the IGDT method to obtain the first uncertainty and the second uncertainty, including: Obtaining a preset robustness coefficient, and based on the system uncertainty and the preset robustness coefficient, converting the objective function to obtain a risk avoidance formula group; Substituting the uncertainty factor group into the risk aversion formula group to obtain the first uncertainty; Based on the system uncertainty, a minimum value is obtained, and the objective function is converted to obtain an opportunity seeking formula group; Substituting the uncertainty factor group into the opportunity seeking formula group, the second uncertainty is obtained.

8. A cost optimization device for an electric-thermal coupled virtual power plant based on a stochastic optimization method, characterized in that: The device comprises: an acquisition unit, for acquiring historical operation parameters, wherein the historical operation parameters include input data and output data of each component of the virtual power plant and the operation cost of each component, wherein the components include a CHP unit, a WPP unit, a PV unit, a carbon capture device and an electrical conversion device, wherein the CHP unit receives natural gas and outputs electrical energy and thermal energy, the PV unit receives light energy and outputs electrical energy, the WPP unit receives wind energy and outputs electrical energy, the carbon capture device receives the electrical energy of the CHP unit for collecting the carbon dioxide output by the CHP unit and outputting it to the electrical conversion device, and the electrical conversion device receives the electrical energy of the WPP unit for converting the carbon dioxide of the carbon capture device into methane; A first construction unit is used to construct a physical simulation model of each of the components according to the historical operation parameters to obtain a power plant operation model, wherein the power plant operation model is used to simulate the output data of each of the components and the change trend of energy flow with input data; A second construction unit is used to construct an operation cost model of each of the components according to the historical operation parameters to obtain a power plant cost model, wherein the operation cost model is used to simulate the change trend of the operation cost of each of the components with the input data; A third construction unit is used to determine uncertainty parameters of the output loads of the PV unit, the WPP unit and the virtual power plant according to the historical operating parameters, obtain an uncertainty factor group, and construct a stochastic model according to the uncertainty factor group, wherein the stochastic model is used to simulate the changing trend of system uncertainty with the uncertainty factor group; a fourth construction unit, configured to construct a target constraint group based on the power plant operation model, wherein the target constraint group is used to limit parameter values ​​of the power plant operation model, and the target constraint group at least includes a system balance constraint, a CHP unit constraint, a WPP unit constraint, a PV unit constraint, a spare capacity constraint, and a carbon capture device constraint; A calculation unit is used to perform risk avoidance solutions and opportunity seeking solutions respectively based on the system uncertainty through the IGDT method to obtain a first uncertainty and a second uncertainty. Based on the first uncertainty and the second uncertainty, the power plant operation model is solved with the output minimization of the operation cost model as the objective function to obtain power plant control parameters, and the operation of the virtual power plant is controlled according to the power plant control parameters.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein when the program is executed, the device where the computer-readable storage medium is located is controlled to execute the method according to any one of claims 1 to 7.

10. A virtual power plant planning system, characterized in that: include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and the one or more programs include methods for executing any one of claims 1 to 7.

Images