Energy scheduling method based on virtual power plant, electronic equipment and storage medium
By acquiring predicted weather data and determining the status parameters of the virtual power plant using preset network models, the problem of inaccurate source load prediction accuracy of virtual power plants under climate change conditions is solved, and the accuracy and effect of energy scheduling are improved.
Patent Information
- Application Number
- CN202411694599.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-25
- Publication Date
- 2025-03-18
AI Technical Summary
In the prior art, the energy scheduling based on virtual power plants is not accurate enough under climate change conditions, which affects the energy scheduling effect.
By obtaining the predicted weather data of the target scheduling area, the first state parameters of the virtual power plant are determined using the preset network model, and energy scheduling parameters are determined based on the state interval parameters and operation model, and then energy scheduling is carried out.
It improves the source load prediction accuracy of traditional virtual power plants under climate change conditions, and improves the accuracy and effectiveness of energy scheduling.
Smart Images
Figure CN119651768A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of energy scheduling, and in particular to an energy scheduling method, electronic equipment and storage medium based on a virtual power plant. Background Art
[0002] With the continuous advancement of the "3060" (i.e. "dual carbon") goals, the energy industry is undergoing a new round of green and low-carbon transformation. The new energy system with new energy as the main body and multi-energy complementary operation will become the main energy supply model for the market and people's livelihood. Therefore, it is urgent to fully tap the potential for promoting new energy consumption and take multiple measures to achieve energy regulation and management with multi-energy complementarity and efficient operation.
[0003] Virtual power plants (VPPs) can break through the barriers of spatial constraints, unify and flexibly regulate multiple dispersed energy supply units, and effectively improve energy supply efficiency and the absorption rate of new energy. In practical applications, virtual power plants should comprehensively consider the energy output characteristics, transmission efficiency, production costs and load characteristics of each energy supply unit, and coordinate the coordinated and complementary work among various energy sources. Therefore, how to find the optimal coupling interaction path between various devices to achieve efficient, safe and low-carbon energy supply is the focus of virtual power plants.
[0004] In the existing technology, energy scheduling based on virtual power plants has achieved the optimization of data volatility and uncertainty in the prediction of the source and load (i.e., energy output and load demand) of the virtual power field. However, under the conditions of climate change, the accuracy of source and load prediction of virtual power plants is still not accurate enough. Summary of the invention
[0005] In view of this, the purpose of the embodiments of the present application is to provide an energy scheduling method, electronic device and storage medium based on a virtual power plant, which can improve the problem of inaccurate source and load prediction accuracy of energy scheduling in traditional virtual power plants under climate change conditions, thereby affecting the energy scheduling effect.
[0006] In order to achieve the above technical objectives, the technical solutions adopted in this application are as follows:
[0007] In a first aspect, an embodiment of the present application provides an energy scheduling method based on a virtual power plant, the method comprising:
[0008] Obtaining forecast weather data for a target scheduling area, where the target scheduling area represents an area currently controlled by the virtual power plant;
[0009] According to the predicted weather data, determining a first state parameter of the current virtual power plant through a preset network model;
[0010] Determine, according to the first state parameter, a state interval parameter corresponding to the first state parameter, wherein the state interval parameter represents a preset value interval including the first state parameter, and the preset value interval satisfies a first preset condition;
[0011] Acquire a second state parameter characterizing the current operating state of the virtual power plant;
[0012] constructing an operation model of the current virtual power plant according to the second state parameter;
[0013] Determining energy dispatch parameters of the current virtual power plant according to the state interval parameters and the operation model;
[0014] The energy scheduling of the current virtual power plant is performed according to the energy scheduling parameters.
[0015] In combination with the first aspect, in some optional implementations, the preset network model includes a first BP neural network sub-model and a second BP neural network sub-model, and the first state parameter includes photovoltaic power generation, electrical load, and thermal load;
[0016] The determining, according to the predicted weather data, the first state parameter of the current virtual power plant by a preset network model includes:
[0017] Determining the photovoltaic power generation through a first BP neural network sub-model according to the predicted weather data;
[0018] According to the predicted weather data, the electric load and the thermal load are determined by a second BP neural network sub-model.
[0019] In combination with the first aspect, in some optional implementations, determining, according to the first state parameter, a state interval parameter corresponding to the first state parameter includes:
[0020] The state interval parameter is constructed according to the photovoltaic power generation, the electrical load and the thermal load:
[0021]
[0022] in, , and They represent the state interval parameters corresponding to photovoltaic power generation, electrical load and thermal load respectively. , Respectively The upper and lower bounds of the value, , Respectively The upper and lower bounds of the value, , Respectively The upper and lower bounds of the values, any two different state interval parameters satisfy the following first preset condition:
[0023]
[0024]
[0025]
[0026]
[0027]
[0028] Where a and b represent any two different parameters in the state interval parameters, and k is any real number greater than or equal to 0.
[0029] In combination with the first aspect, in some optional embodiments, the second state parameter includes the total amount of electricity purchased, the unit price of electricity purchased, the natural gas consumption, the unit price of natural gas, the equipment output, the unit output maintenance cost of the equipment and the statistical period of the current virtual power plant.
[0030] In combination with the first aspect, in some optional implementations, constructing the operation model of the current virtual power plant according to the second state parameter includes:
[0031] According to the second state parameter, the operation model is constructed:
[0032]
[0033]
[0034]
[0035]
[0036] In the formula, represents the total operating cost of the current virtual power plant, represents the current electricity purchase cost of the virtual power plant, represents the primary energy acquisition cost of the current virtual power plant, represents the maintenance cost of each power generation unit in the virtual power plant, represents the total amount of electricity purchased by the current virtual power plant at time t, represents the unit price of electricity at time t, represents the natural gas consumption of the jth energy supply equipment in the current virtual power plant at time t, represents the natural gas price at time t, represents the output of the jth energy supply device in the current virtual power plant at time t, represents the maintenance cost per unit output of the j-th energy supply device at time t, Indicates the statistical period.
[0037] In combination with the first aspect, in some optional implementations, determining the energy dispatch parameter of the current virtual power plant according to the state interval parameter and the operation model includes:
[0038] According to the state interval parameter and the operation model, the energy scheduling parameter is determined by the following formula:
[0039]
[0040]
[0041] In the formula, represents the total operating cost of the current virtual power plant, represents the energy scheduling parameters, , and Respectively represent the state interval parameters corresponding to photovoltaic power generation, electrical load and thermal load. For each parameter in the energy scheduling parameter , , ;
[0042] in:
[0043]
[0044]
[0045]
[0046] In the formula, , , and Represents the total operating cost , state interval parameters , Energy dispatch parameters and state interval parameters The lower bound of the value of Indicates the state interval parameter The upper bound of the value of ;
[0047] in:
[0048]
[0049]
[0050]
[0051] In the formula, , , and Represents the total operating cost , state interval parameters , Energy dispatch parameters and state interval parameters The upper bound of the value of Indicates the state interval parameter The lower bound of the value of .
[0052] In combination with the first aspect, in some optional implementations, before acquiring the historical weather data of the target scheduling area, the method further includes:
[0053] Constructing a first initial BP model and a second initial BP model;
[0054] Acquiring climate data for training the first initial BP model and the second initial BP model;
[0055] Dividing the climate data into a training set and a test set according to a preset ratio;
[0056] The first initial BP model and the second initial BP model are trained by the training set and the test set to obtain a trained first initial BP model and a trained second initial BP model as the first BP neural network sub-model and the second BP neural network sub-model;
[0057] The preset network model is constructed based on the first BP neural network sub-model and the second BP neural network sub-model.
[0058] In combination with the first aspect, in some optional implementations, the preset ratio is 8:2.
[0059] In a second aspect, an embodiment of the present application further provides an electronic device, comprising a processor and a memory coupled to each other, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the electronic device executes the above method.
[0060] In a third aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium. When the computer program is executed on a computer, the computer executes the above method.
[0061] The invention adopting the above technical solution has the following advantages:
[0062] In the technical solution provided in the present application, the predicted weather data of the target scheduling area is first obtained, and based on the predicted weather data, the first state parameter of the current virtual power plant is determined through a preset network model. Then, based on the first state parameter, the state interval parameter corresponding to the first state parameter is determined. Then, the second state parameter characterizing the operating condition of the current virtual power plant is obtained, and based on the second state parameter, the operation model of the current virtual power plant is constructed. Then, based on the state interval parameter and the operation model, the energy scheduling parameters of the current virtual power plant are determined. Finally, based on the energy scheduling parameters, the current virtual power plant is energy scheduled. In this way, in the process of determining the energy scheduling parameters, the negative impact of different climate factors and the prediction error of the network model on the parameter results is fully considered, so as to improve the problem that the energy scheduling of traditional virtual power plants is inaccurate in source-load prediction accuracy under climate change conditions, thereby affecting the energy scheduling effect. BRIEF DESCRIPTION OF THE DRAWINGS
[0063] The present application may be further described by the non-limiting embodiments given in the accompanying drawings. It should be understood that the following drawings only illustrate certain embodiments of the present application and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings may be obtained based on these drawings without creative effort.
[0064] Figure 1 A structural block diagram of an electronic device provided in an embodiment of the present application.
[0065] Figure 2 A flow chart of an energy scheduling method based on a virtual power plant provided in an embodiment of the present application.
[0066] Icon: 100 - electronic device; 101 - processor; 102 - memory. DETAILED DESCRIPTION
[0067] The present application will be described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that in the drawings or descriptions, similar or identical parts use the same figure numbers, and the implementation methods not shown or described in the drawings are forms known to ordinary technicians in the relevant technical field. In the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.
[0068] Please refer to Figure 1 , an embodiment of the present application provides an electronic device 100 that may include a processor 101 and a memory 102. The memory 102 stores a computer program, and when the computer program is executed by the processor 101, the electronic device 100 can execute the corresponding steps in the following energy scheduling method based on a virtual power plant.
[0069] In this embodiment, the electronic device 100 can be a personal computer, a laptop computer, a cloud server, etc., which is used to obtain the predicted weather data and determine the first state parameter according to the predicted weather data. Then, according to the first state parameter, the state interval parameter corresponding to the first state parameter is determined. Then, the second state parameter is obtained, and the operation model of the current virtual power plant is constructed. Then, according to the state interval parameter and the operation model, the energy scheduling parameter of the current virtual battery is determined. Finally, the current virtual power plant is energy scheduled according to the energy scheduling parameter.
[0070] In this embodiment, the processor 101 may be an integrated circuit chip having signal processing capability. The processor 101 may be a general-purpose processor 101. For example, the processor 101 may be a central processing unit 101 (CPU), a digital signal processor 101 (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and may implement or execute the methods, steps and logic block diagrams disclosed in the embodiments of the present application.
[0071] The memory 102 may be, but is not limited to, a random access memory 102, a read-only memory 102, a programmable read-only memory 102, an erasable programmable read-only memory 102, an electrically erasable programmable read-only memory 102, etc. In this embodiment, the memory 102 may be used to store forecasted weather data, a first state parameter, a second state parameter, a preset network model, a first preset condition, an operation model, energy scheduling parameters, etc. Of course, the memory 102 may also be used to store a program, and the processor 101 executes the program after receiving an execution instruction.
[0072] Please refer to Figure 2 The present application also provides an energy scheduling method based on a virtual power plant, which can be applied to the above-mentioned electronic device 100, and each step in the method is executed or implemented by the electronic device 100. The energy scheduling method based on a virtual power plant can include the following steps:
[0073] Step 210, obtaining forecast weather data of a target scheduling area, where the target scheduling area represents an area controlled by the current virtual power plant;
[0074] Step 220, determining a first state parameter of the current virtual power plant through a preset network model according to the predicted weather data;
[0075] Step 230: determining a state interval parameter corresponding to the first state parameter according to the first state parameter, wherein the state interval parameter represents a preset value interval including the first state parameter, and the preset value interval satisfies a first preset condition;
[0076] Step 240, obtaining a second state parameter characterizing the current operating state of the virtual power plant;
[0077] Step 250, constructing an operation model of the current virtual power plant according to the second state parameter;
[0078] Step 260, determining energy dispatch parameters of the current virtual power plant according to the state interval parameters and the operation model;
[0079] Step 270: Perform energy scheduling on the current virtual power plant according to the energy scheduling parameters.
[0080] In the above-mentioned implementation, the predicted weather data of the target scheduling area is first obtained, and based on the predicted weather data, the first state parameter of the current virtual power plant is determined through a preset network model. Then, based on the first state parameter, the state interval parameter corresponding to the first state parameter is determined. Then, the second state parameter characterizing the current operating condition of the virtual power plant is obtained, and based on the second state parameter, the operation model of the current virtual power plant is constructed. Then, based on the state interval parameter and the operation model, the energy scheduling parameters of the current virtual power plant are determined. Finally, based on the energy scheduling parameters, the current virtual power plant is energy scheduled. In this way, in the process of determining the energy scheduling parameters, the negative impact of different climate factors and the prediction error of the network model on the parameter results is fully considered, so as to improve the problem that the energy scheduling of the traditional virtual power plant is inaccurate in the source-load prediction accuracy under the conditions of climate change, thereby affecting the energy scheduling effect.
[0081] The following will describe in detail the various steps of the energy dispatch method based on virtual power plants, as follows:
[0082] Prior to step 210, the method may include:
[0083] Constructing a first initial BP model and a second initial BP model;
[0084] Acquiring climate data for training the first initial BP model and the second initial BP model;
[0085] Dividing the climate data into a training set and a test set according to a preset ratio;
[0086] The first initial BP model and the second initial BP model are trained by the training set and the test set to obtain a trained first initial BP model and a trained second initial BP model as the first BP neural network sub-model and the second BP neural network sub-model;
[0087] The preset network model is constructed based on the first BP neural network sub-model and the second BP neural network sub-model.
[0088] In this embodiment, the framework of a conventional BP neural network is adopted, and the number of its hidden layers is set to 3 layers, the number of neurons in each hidden layer is set to 7, the transfer function of the hidden layer node is the tansig function, the transfer function of the output layer node is the purelin function, the training function is the trainoss function, and the learning function is the learngdm function. In this way, two network models with the same structure are constructed respectively as the first initial BP model and the second initial BP model. Then, the climate data used to train the first initial BP model and the second initial BP model are obtained respectively, including different types of meteorological data such as historical temperature, customs, and radiation, and are divided into training sets and test sets according to a preset ratio (flexibly set according to user needs, such as 8:2, 7:3, etc., and 8:2 is used as an example in this embodiment), and then the first initial BP model and the second initial BP model are respectively input through the training set and the test set for model training. The outputs of the two models are the power generation of the photovoltaic power station and the electric and thermal loads. The trained first initial BP model and the second initial BP model are obtained as the first BP neural network submodel and the second BP neural network submodel. Finally, the two are combined to construct a preset network model for the subsequent prediction of the first state parameters (i.e., photovoltaic power generation, electrical load, and thermal load).
[0089] In step 210, the target dispatching area can be determined based on the current location of the virtual power plant and the size of the controlled area; the predicted weather data can be flexibly determined in the time interval according to user needs, and then the historical weather data of the target dispatching area is predicted based on the climate forecast of the meteorological website or through a neural network model with weather forecast function to obtain the predicted weather data within the user-defined time interval. Exemplarily, the current virtual power plant can be located in District A of City A and is used to dispatch energy in District A. The target dispatching area can be District A of City A, and the predicted weather data can be the weather data for January 2025 predicted based on the annual weather data of District A in 2024, including the weather conditions of District A on each day in January 2025.
[0090] In this embodiment, the acquisition of the forecast weather data may be downloaded in real time from a climate publishing website, and subsequently processed by the processor 101 of the electronic device 100; or, the acquisition of the forecast weather data may be pre-entered by the user into the memory 102 of the electronic device 100 for storage, and in the subsequent determination process of the first state parameter, the processor 101 calls the forecast weather data from the memory 102 based on the user's instruction. The acquisition method of the forecast weather data is not specifically limited here.
[0091] In step 220, the preset network model may include a first BP neural network sub-model and a second BP neural network sub-model, and the first state parameter includes photovoltaic power generation, electrical load, and thermal load;
[0092] Determining the first state parameter of the current virtual power plant by using a preset network model according to the predicted weather data may include:
[0093] Determining the photovoltaic power generation through a first BP neural network sub-model according to the predicted weather data;
[0094] According to the predicted weather data, the electric load and the thermal load are determined by a second BP neural network sub-model.
[0095] In this embodiment, the predicted weather data (in this embodiment, the predicted weather data for zone a in January 2025) are respectively input into the first BP neural network sub-model, and the photovoltaic power generation of the virtual power plant within the time interval of the predicted weather data is obtained through the first BP neural network sub-model; and, the predicted weather data are input into the second BP neural network sub-model, and the electric load and thermal load of the virtual power plant within the time interval of the predicted weather data are obtained through the second BP neural network sub-model.
[0096] In step 230, determining the state interval parameter corresponding to the first state parameter according to the first state parameter may include:
[0097] The state interval parameter is constructed according to the photovoltaic power generation, the electrical load and the thermal load:
[0098]
[0099] in, , and They represent the state interval parameters corresponding to photovoltaic power generation, electrical load and thermal load respectively. , Respectively The upper and lower bounds of the value, , Respectively The upper and lower bounds of the value, , Respectively The upper and lower bounds of the values, any two different state interval parameters satisfy the following first preset condition:
[0100]
[0101]
[0102]
[0103]
[0104]
[0105] Where a and b represent any two different parameters in the state interval parameters, and k is any real number greater than or equal to 0.
[0106] In this embodiment, in order to reduce the negative impact of the prediction errors of photovoltaic power generation, electric load and thermal load on the energy dispatching effect of the virtual power plant, the first state parameter (i.e. photovoltaic power generation, electric load and thermal load) is transformed into an interval parameter with upper and lower bounds, i.e. a state interval parameter.
[0107] In step 240, the second state parameter may include the total amount of electricity purchased, the unit price of electricity purchased, the natural gas consumption, the unit price of natural gas, the equipment output, the maintenance cost per unit output of the equipment and the statistical period of the current virtual power plant.
[0108] In step 250, constructing the operation model of the current virtual power plant according to the second state parameter may include:
[0109] According to the second state parameter, the operation model is constructed:
[0110]
[0111]
[0112]
[0113]
[0114] In the formula, represents the total operating cost of the current virtual power plant, represents the current electricity purchase cost of the virtual power plant, represents the primary energy acquisition cost of the current virtual power plant, represents the maintenance cost of each power generation unit in the virtual power plant, represents the total amount of electricity purchased by the current virtual power plant at time t, represents the unit price of electricity at time t, represents the natural gas consumption of the jth energy supply equipment in the current virtual power plant at time t, represents the natural gas price at time t, represents the output of the jth energy supply device in the current virtual power plant at time t, represents the maintenance cost per unit output of the j-th energy supply device at time t, Indicates the statistical period.
[0115] In this embodiment, during the virtual power plant dispatching process, the output of each functional device is as follows:
[0116]
[0117]
[0118]
[0119]
[0120]
[0121]
[0122] In the formula, , , and They represent the power generation of the gas turbine, the exhaust volume of the gas turbine, the heating capacity of the waste heat boiler and the heating capacity of the supplementary combustion boiler at time t respectively; , , and They represent the power supply efficiency of gas turbine, thermal efficiency of gas turbine, efficiency of waste heat boiler and efficiency of supplementary combustion boiler respectively; H represents the lower calorific value of natural gas; and Respectively represent the gas consumption of gas turbine and supplementary-fired boiler; , and They represent the storage capacity, storage capacity and discharge capacity of the electrochemical energy storage device at time t respectively; and They represent the storage efficiency and discharge efficiency of the energy storage device respectively; represents the output of the jth energy supply device, and They respectively represent the minimum and maximum output of the j-th energy supply device.
[0123] In this embodiment, the energy supply balance of the virtual power plant is as follows:
[0124]
[0125]
[0126] In the formula, represents the power generation of the photovoltaic power generation unit at time t; and They represent the electric load and thermal load of the virtual power plant at time t respectively.
[0127] In step 260, determining the energy dispatching parameters of the current virtual power plant according to the state interval parameters and the operation model may include:
[0128] According to the state interval parameter and the operation model, the energy scheduling parameter is determined by the following formula:
[0129]
[0130]
[0131] In the formula, represents the total operating cost of the current virtual power plant, represents the energy scheduling parameters, , and Respectively represent the state interval parameters corresponding to photovoltaic power generation, electrical load and thermal load. For each parameter in the energy scheduling parameter , , ;
[0132] in:
[0133]
[0134]
[0135]
[0136] In the formula, , , and Represents the total operating cost , state interval parameters , Energy dispatch parameters and state interval parameters The lower bound of the value of Indicates the state interval parameter The upper bound of the value of ;
[0137] in:
[0138]
[0139]
[0140]
[0141] In the formula, , , and Represents the total operating cost , state interval parameters , Energy dispatch parameters and state interval parameters The upper bound of the value of Indicates the state interval parameter The lower bound of the value of .
[0142] In this embodiment, the decision variable can be any scheduling parameter that the user needs to adjust, such as the storage period of the power storage equipment in the virtual power plant, the primary and secondary relationship of the power supply equipment selected based on the electricity price or gas purchase cost, etc.
[0143] In this embodiment, based on the formula proposed in step 260, (i.e. minimum operating cost) and Solve and get the optimal value range of the two:
[0144]
[0145]
[0146] In the formula, and They represent the lower and upper bounds of the optimal value of the minimum operating cost, respectively. and They represent the lower and upper bounds of the optimal value of the j-th decision variable.
[0147] In step 270, after obtaining the minimum operating cost and the optimal value range of the decision variable through step 260, the user can use the two as reference strategies for the energy scheduling of the virtual power plant. Specifically, the user can select the values of the two as parameters for the energy scheduling of the virtual power plant according to the value range of the two, and implement the energy scheduling of the virtual power plant according to the parameters. In this way, through the aforementioned energy scheduling method based on the virtual power plant, the negative impact of weather and photovoltaic power generation and electricity and heat load prediction errors on the parameter results is eliminated or weakened in the calculation process of the energy scheduling parameters.
[0148] Understandably, Figure 1The structure of the electronic device 100 shown in FIG. 1 is only a schematic diagram of a structure. The electronic device 100 may also include Figure 1 More components are shown. Figure 1 Each component shown in the figure can be implemented by hardware, software or a combination thereof.
[0149] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the electronic device 100 described above can refer to the corresponding processes of each step in the aforementioned method, and will not be elaborated herein.
[0150] The embodiment of the present application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed on a computer, the computer executes the energy scheduling method based on a virtual power plant as described in the above embodiment.
[0151] Through the description of the above implementation methods, technical personnel in this field can clearly understand that the present application can be implemented by hardware, and can also be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present application.
[0152] In summary, the embodiments of the present application provide an energy scheduling method, electronic device and storage medium based on a virtual power plant. In this technical solution, the predicted weather data is first obtained, and based on the predicted weather data, the first state parameter of the current virtual power plant is determined through a preset network model. Then, based on the first state parameter, the state interval parameter corresponding to the first state parameter is determined. Then, the second state parameter characterizing the current operating condition of the virtual power plant is obtained, and based on the second state parameter, the operation model of the current virtual power plant is constructed. Then, based on the state interval parameter and the operation model, the energy scheduling parameter of the current virtual power plant is determined. Finally, based on the energy scheduling parameter, the current virtual power plant is energy scheduled. In this way, in the process of determining the energy scheduling parameters, the negative impact of different climate factors and the prediction error of the network model on the parameter results is fully considered, so as to improve the problem that the energy scheduling of the traditional virtual power plant is inaccurate in the source-load prediction accuracy under the conditions of climate change, thereby affecting the energy scheduling effect.
[0153] In the embodiments provided in the present application, it should be understood that the disclosed method can also be implemented in other ways. The method embodiments described above are merely schematic, for example, the flow charts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the methods according to the multiple embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a part of a module, a program segment or a code, and a part of the module, a program segment or a code includes one or more executable instructions for implementing the specified logical function. It should also be noted that each box in the block diagram and / or the flow chart, and the combination of the boxes in the block diagram and / or the flow chart can be implemented by a dedicated hardware-based system that performs the specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions. In addition, each functional module in each embodiment of the present application can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part.
[0154] The above description is only an embodiment of the present application and is not intended to limit the protection scope of 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. An energy scheduling method based on a virtual power plant, characterized in that: The method comprises: Obtaining forecast weather data for a target scheduling area, where the target scheduling area represents an area currently controlled by the virtual power plant; According to the predicted weather data, determining a first state parameter of the current virtual power plant through a preset network model; Determine, according to the first state parameter, a state interval parameter corresponding to the first state parameter, wherein the state interval parameter represents a preset value interval including the first state parameter, and the preset value interval satisfies a first preset condition; Acquire a second state parameter characterizing the current operating state of the virtual power plant; constructing an operation model of the current virtual power plant according to the second state parameter; Determining energy dispatch parameters of the current virtual power plant according to the state interval parameters and the operation model; The energy scheduling of the current virtual power plant is performed according to the energy scheduling parameters.
2. The method according to claim 1, characterized in that: The preset network model includes a first BP neural network sub-model and a second BP neural network sub-model, and the first state parameter includes photovoltaic power generation, electrical load and thermal load; The determining, according to the predicted weather data, the first state parameter of the current virtual power plant by a preset network model includes: Determining the photovoltaic power generation through a first BP neural network sub-model according to the predicted weather data; According to the predicted weather data, the electric load and the thermal load are determined by a second BP neural network sub-model.
3. The method according to claim 2, characterized in that The determining, according to the first state parameter, a state interval parameter corresponding to the first state parameter includes: The state interval parameter is constructed according to the photovoltaic power generation, the electrical load and the thermal load: ； in, , and They represent the state interval parameters corresponding to photovoltaic power generation, electrical load and thermal load respectively. , Respectively The upper and lower bounds of the value, , Respectively The upper and lower bounds of the value, , Respectively The upper and lower bounds of the values, any two different state interval parameters satisfy the following first preset condition: ； ； ； ； ； Where a and b represent any two different parameters in the state interval parameters, and k is any real number greater than or equal to 0.
4. The method according to claim 1, characterized in that: The second state parameters include the total amount of electricity purchased by the current virtual power plant, the unit price of electricity purchased, the natural gas consumption, the unit price of natural gas, the equipment output, the maintenance cost per unit output of the equipment and the statistical period.
5. The method according to claim 4, characterized in that The step of constructing the operation model of the current virtual power plant according to the second state parameter includes: According to the second state parameter, the operation model is constructed: ； ； ； ； In the formula, represents the total operating cost of the current virtual power plant, represents the current electricity purchase cost of the virtual power plant, represents the primary energy acquisition cost of the current virtual power plant, represents the maintenance cost of each power generation unit in the virtual power plant, represents the total amount of electricity purchased by the current virtual power plant at time t, represents the unit price of electricity at time t, represents the natural gas consumption of the jth energy supply equipment in the current virtual power plant at time t, represents the natural gas price at time t, represents the output of the jth energy supply device in the current virtual power plant at time t, represents the maintenance cost per unit output of the j-th energy supply device at time t, Indicates the statistical period.
6. The method according to claim 1, characterized in that Determining energy dispatch parameters of the current virtual power plant according to the state interval parameters and the operation model includes: According to the state interval parameter and the operation model, the energy scheduling parameter is determined by the following formula: ； ； In the formula, represents the total operating cost of the current virtual power plant, represents the energy scheduling parameters, , and Respectively represent the state interval parameters corresponding to photovoltaic power generation, electrical load and thermal load. For each parameter in the energy scheduling parameter , , ; in: ； ； ； In the formula, , , and Represents the total operating cost , state interval parameters , Energy dispatch parameters and state interval parameters The lower bound of the value of Indicates the state interval parameter The upper bound of the value of ; in: ； ； ； In the formula, , , and Represents the total operating cost , state interval parameters , Energy dispatch parameters and state interval parameters The upper bound of the value of Indicates the state interval parameter The lower bound of the value of .
7. The method according to claim 2, characterized in that: Before acquiring the historical weather data of the target scheduling area, the method further includes: Constructing a first initial BP model and a second initial BP model; Acquiring climate data for training the first initial BP model and the second initial BP model; Dividing the climate data into a training set and a test set according to a preset ratio; The first initial BP model and the second initial BP model are trained by the training set and the test set to obtain a trained first initial BP model and a trained second initial BP model as the first BP neural network sub-model and the second BP neural network sub-model; The preset network model is constructed based on the first BP neural network sub-model and the second BP neural network sub-model.
8. The method according to claim 2, characterized in that: The preset ratio is 8:
2.
9. An electronic device, characterized in that: The electronic device comprises a processor and a memory coupled to each other, wherein the memory stores a computer program. When the computer program is executed by the processor, the electronic device executes the method according to any one of claims 1 to 8.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed on a computer, the computer is enabled to execute the method according to any one of claims 1 to 8.