Virtual power plant load acquisition method and device based on physical weight and medium

Abstract

The invention relates to a virtual power plant load acquisition method and device based on physical weight and a medium, and belongs to the technical field of virtual power plant load regulation, and the method comprises the following steps: determining distributed resources of a virtual power plant; formulating a constraint condition for each resource, projecting the constraint condition to a constraint space, and constructing a first load adjustable range; thirdly, relevant data are collected, load intervals of the adjustable load, the virtual energy storage and the virtual generator set are calculated respectively, and the upper limit and the lower limit of the load intervals are added to form a second load adjustable range; and comprehensively acquiring a target load adjustable range of the virtual power plant based on the first load adjustable range and the second load adjustable range, and performing load adjustment of the distributed resources according to the target load adjustable range. According to the method, uncertain factors such as market fluctuation and user load change are considered, and the physical weight and the data driving weight are adjusted through the adaptive weight calculation formula, so that the load adjustment strategy is more flexible and high in adaptability, and the response capability of the virtual power plant is enhanced.

Description

Technical Field

[0001] The present invention relates to a method, device and medium for obtaining the load of a virtual power plant based on physical weights, and belongs to the technical field of virtual power plant load regulation. Background Art

[0002] With the acceleration of energy transformation, the proportion of distributed energy resources in the power system is increasing day by day, and virtual power plants emerge as an innovative energy management model. By integrating various resources such as distributed generation equipment, adjustable loads and energy storage systems, virtual power plants achieve centralized management and optimal scheduling of distributed energy, aiming to improve energy utilization efficiency, enhance grid stability and reliability, and at the same time meet the growing electricity demand.

[0003] During the operation of a virtual power plant, load regulation is one of its core functions. Traditional technical solutions usually adopt fixed regulation strategies, and uniformly schedule various distributed resources according to pre-set rules to achieve load balance and optimization. However, these traditional methods gradually reveal many deficiencies in practical applications.

[0004] The prior art, such as the Chinese patent application with the publication number CN119209506A, discloses a virtual power plant scheduling system based on multi-source information fusion. The system includes a data source acquisition module, a resource aggregation and analysis module, and a resource balance evaluation module. The data source acquisition module is used to acquire first multi-source data and second multi-source data, store the first multi-source data in the virtual power plant resource type library, and store the second multi-source data in the resource regulation feature library; the resource aggregation and analysis module analyzes the stability of resource scheduling based on the first multi-source data; the resource aggregation and analysis module includes a third resource adjustable capacity analysis sub-module, and the third resource adjustable capacity analysis sub-module is used to import the adjustable data of the energy storage device in the first multi-source data into the third resource adjustable capacity analysis model to analyze the adjustable capacity value of the energy storage device resources. However, although the above patent divides the data into first multi-source data and second multi-source data and stores them separately, when performing fusion analysis, it mainly performs feature extraction and analysis on various types of data separately, such as separately modeling and analyzing wind power, photovoltaic power, energy storage devices, and different types of load data, without fully exploring the deep associations and fusion points between different types of data. Summary of the Invention

[0005] In order to solve the problems existing in the above prior art, the present invention proposes a method, device and medium for obtaining the load of a virtual power plant based on physical weights.

[0006] The technical solution of the present invention is as follows: On the one hand, the present invention provides a method for obtaining the load of a virtual power plant based on physical weights, including the following steps: Determine the distributed resources of the virtual power plant, including virtual generating units, adjustable loads, and virtual energy storage; Formulate constraint conditions for virtual generating units, adjustable loads, and virtual energy storage respectively, project the constraint conditions of the distributed resources of the virtual power plant into the constraint space, and construct the first load adjustable range of the distributed resources; Collect relevant data of adjustable loads, virtual energy storage, and virtual generating units, obtain the load intervals of adjustable loads, virtual energy storage, and virtual generating units respectively, and obtain the second load adjustable range of the distributed resources according to the load intervals of each distributed resource; Determine the physical weight and data-driven weight, and obtain the target load adjustable range of the virtual power plant based on the first load adjustable range, the second load adjustable range, the physical weight, and the data-driven weight; Conduct load regulation on the virtual power plant based on the target load adjustable range.

[0007] Preferably, formulate the constraint conditions of the virtual generating unit, including the power constraint of the virtual generating unit and the ramp constraint of the virtual generating unit; The power constraint of the virtual generating unit is used to constrain the power of the virtual generating unit at time, and the ramp constraint of the virtual generating unit is used to constrain the power change of the virtual generating unit from time to time; Formulate the constraint conditions of the adjustable load, including the power constraint of the adjustable load and the ramp constraint of the adjustable load; The power constraint of the adjustable load is used to constrain the power of the adjustable load at time, and the ramp constraint of the adjustable load is used to constrain the power change of the adjustable load from time to time; Formulate the constraint conditions of the virtual energy storage, including the power constraint of the virtual energy storage, which is used to constrain the power of the virtual energy storage at time.

[0008] Preferably, collect the relevant data of the adjustable load, extract the features of the relevant data of the adjustable load, construct an adjustable load vector based on the features of the relevant data of the adjustable load, and use the adjustable load vector and the relevant data of the adjustable load as the input of the support vector regression model to output the load interval of the adjustable load.

[0009] Preferably, collect the relevant data of the virtual energy storage, extract the features of the relevant data of the virtual energy storage, and use the features of the relevant data of the virtual energy storage as the input of the decision tree model to output the load interval of the virtual energy storage.

[0010] Preferably, relevant data of the virtual generating unit are collected, including historical load, and the historical load is linearly processed; The linearly processed historical load is decomposed into the adjustable load and the non-adjustable load of the virtual generating unit; For the adjustable load of the virtual generating unit, the adjustable load of the virtual generating unit is used as the input of the autoregressive integrated moving average model, and the load interval of the virtual generating unit is output.

[0011] Preferably, a physical weight and a data-driven weight are determined, and the target load adjustable range of the virtual power plant is obtained based on the first load adjustable range, the second load adjustable range, the physical weight, and the data-driven weight, which is expressed by the formula: ; In the formula, represents the target load adjustable range of the virtual power plant, represents the first load adjustable range of the distributed resource, represents the physical weight, represents the second load adjustable range of the distributed resource, represents the data-driven weight.

[0012] Preferably, the physical weight is expressed by the formula: ; In the formula, represents the weight offset, represents the scaling factor, represents the smoothing coefficient, represents the stability requirement factor, represents the sensitivity factor, represents the natural constant; The data-driven weight is expressed by the formula: .

[0013] Preferably, the sensitivity factor is expressed by the formula: ; In the formula, represents the market volatility index, represents the user volatility index, represents the maximum value function; Among them, the market volatility index is expressed by the formula: ; In the formula, represents the short-term market price fluctuation, represents the long-term market price fluctuation; The user fluctuation index is expressed by the formula: ; In the formula, represents the short-term load variance of the user, represents the long-term load variance of the user; The sensitivity factor is mapped to the interval by using the Sigmoid function, and is expressed by the formula: .

[0014] On the other hand, the present invention also provides an electronic device, on which a computer program is stored. When the computer program is executed by a processor, the method for obtaining the load of a virtual power plant based on physical weights as described in any embodiment of the present invention is implemented.

[0015] On the other hand, the present invention also provides a computer-readable storage medium for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method for obtaining the load of a virtual power plant based on physical weights as described in any embodiment of the present invention.

[0016] The present invention has the following beneficial effects: 1. By comprehensively considering the characteristics of various distributed resources such as virtual generating units, adjustable loads, and virtual energy storage, the present invention formulates a set of refined load regulation strategies. These strategies can dynamically adjust the load levels according to the real-time states and demands of different resources, thus avoiding the idleness and waste of resources.

[0017] 2. The constraint conditions formulated by the present invention, such as power constraints, ramp constraints, and energy storage constraints, provide clear safety boundaries for the operation of the virtual power plant. These constraint conditions ensure that the distributed resources will not exceed their safe operating ranges during the regulation process, thus avoiding system failures caused by overload or underload. At the same time, the load regulation strategy can make adjustments in advance according to the real-time state and prediction information of the power grid to cope with possible market fluctuations and user load changes. This forward-looking regulation method helps to maintain the stability of the virtual power plant system and reduce the risks of faults and outages.

[0018] 3. The present invention takes into account various uncertain factors such as market fluctuations and user load changes, and adjusts the physical weight and data-driven weight through an adaptive weight calculation formula, making the load regulation strategy more flexible and adaptable. The physical weight reflects the actual physical characteristics of distributed resources, such as power generation capacity, energy storage capacity, etc.; while the data-driven weight is based on historical data and prediction information, reflecting the changing trends of the market and user load. By dynamically adjusting the ratio of these two weights, the invention can automatically optimize the load regulation strategy according to different operating environments and requirements, ensuring that the virtual power plant always operates in an optimal state. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a flowchart of the implementation of the method of the present invention.

[0020] Figure 2 It is a curve graph of the power market price data of the present invention.

[0021] Figure 3 It is a curve graph of the user load data of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the protection scope of the present invention.

[0023] It should be understood that the step numbers used in the text are only for convenient description and do not limit the execution order of the steps.

[0024] It should be understood that the terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless otherwise clearly specified in the context, the singular forms "a", "an" and "the" are intended to include the plural forms.

[0025] The terms "comprising" and "including" indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their combinations.

[0026] The term "and / or" refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0027] Embodiment 1: Refer to Figure 1, this embodiment provides a method for obtaining the load of a virtual power plant based on physical weights, including the following steps: Determine the distributed resources of the virtual power plant, including virtual power generation units, adjustable loads, and virtual energy storage; Among them, the virtual power generation unit refers to a distributed energy resource that simulates the behavior of a traditional power generation unit, including renewable energy power generation facilities such as solar photovoltaic and wind energy.

[0028] The adjustable load includes price-based shiftable load and incentive-based interruptible load. Reasonable scheduling of the adjustable load is conducive to maximizing resource utilization. For the price-based shiftable load, adjust the operation period according to high or low electricity prices, specifically including: 1. Transfer the load from high electricity price periods (such as daytime) to low electricity price periods (such as late at night); 2. When the grid issues a peak electricity price warning, completely shut down or significantly reduce the interruptible load.

[0029] For the incentive-based interruptible load, when the reliability of the power grid system is affected or the electricity consumption reaches the peak, issue an interruption instruction to power users to effectively reduce the grid load and achieve the effect of peak shaving and valley filling.

[0030] The virtual energy storage is not a traditional physical energy storage device (such as a battery, pumped storage, etc.), but an energy balance mechanism realized through intelligent management and optimization technologies. Its core lies in utilizing the flexibility of demand-side resources (such as adjustable loads, virtual power generation units) to simulate the charging and discharging behavior of physical energy storage, thereby optimizing the energy flow of the power system and achieving goals such as peak shaving and valley filling and improving the utilization rate of renewable energy.

[0031] Formulate constraint conditions for virtual power generation units, adjustable loads, and virtual energy storage respectively, project the constraint conditions of the distributed resources of the virtual power plant into the constraint space, and construct the first load adjustable range of the distributed resources; Collect relevant data of adjustable loads, virtual energy storage, and virtual power generation units, obtain the load intervals of adjustable loads, virtual energy storage, and virtual power generation units respectively, and add the upper and lower limits respectively as the second load adjustable range of the distributed resources of the virtual power plant; Determine the physical weight and data-driven weight, and obtain the target load adjustable range of the virtual power plant based on the first load adjustable range, the second load adjustable range, the physical weight, and the data-driven weight; Adjust the load of the virtual power plant based on the target load adjustable range.

[0032] Preferably, the constraint conditions of the distributed resources are formulated, and the first load adjustable range of the distributed resources of the virtual power plant is obtained based on the constraint conditions. The specific steps are as follows: Formulate the constraint conditions of the virtual generating unit, including the power constraint of the virtual generating unit and the ramping constraint of the virtual generating unit; The power constraint of the virtual generating unit is used to constrain the power of the virtual generating unit at time, which is expressed by the formula: ; In the formula, represents the lower power limit of the virtual generating unit at time, represents the power of the virtual generating unit at time, represents the upper power limit of the virtual generating unit at time; The ramping constraint of the virtual generating unit is used to constrain the power change amount of the virtual generating unit from time to time, which is expressed by the formula: ; In the formula, represents the lower limit of the power change amount of the virtual generating unit at time, represents the upper limit of the power change amount of the virtual generating unit at time, represents the power of the virtual generating unit at time; Formulate the constraint conditions of the adjustable load, including the power constraint of the adjustable load and the ramping constraint of the adjustable load; The power constraint of the adjustable load is used to constrain the power of the adjustable load at time, which is expressed by the formula: ; In the formula, represents the lower power limit of the adjustable load at time, represents the power of the adjustable load at time, represents the upper power limit of the adjustable load at time; Among them, the power of the adjustable load is expressed by the formula: ; In the formula, represents the baseline load of the adjustable load at time, represents the adjustable load The upward regulation power at a moment, represents an adjustable load The downward regulation power at a moment; The ramp constraint of the adjustable load is used to constrain the power change amount of the adjustable load from the moment to the moment, which is expressed by the formula: ; In the formula, represents the lower limit of the power change amount of the adjustable load at the moment, represents the adjustable load the upper limit of the power change amount at the moment, represents the adjustable load the power at the moment; Formulate the constraint conditions of the virtual energy storage, including the power constraint of the virtual energy storage and the energy storage constraint of the virtual energy storage; The power constraint of the virtual energy storage is used to constrain the power of the virtual energy storage at the moment, which is expressed by the formula: ; In the formula, represents the minimum discharge power of the virtual energy storage at the moment, represents the power of the virtual energy storage at the moment (including discharge power and charge power), represents the maximum charge power of the virtual energy storage at the moment; The energy storage constraint of the virtual energy storage is used to constrain the energy storage of the virtual energy storage at the moment, which is expressed by the formula: ; In the formula, represents the lower limit of the energy storage of the virtual energy storage at the moment, represents the energy storage of the virtual energy storage at the moment, represents the upper limit of the energy storage of the virtual energy storage at the moment; Project the power constraints of each distributed resource into the constraint space, sum the upper and lower limits of the power intervals constrained by each distributed resource respectively, and obtain the first load adjustable range.

[0033] Preferably, relevant data of adjustable loads are collected, features of the relevant data of adjustable loads are extracted, an adjustable load vector is constructed based on the features of the relevant data of adjustable loads, and the adjustable load vector and the relevant data of adjustable loads are used as inputs of a support vector regression model to output the load interval of the adjustable loads, which is expressed by the formula as follows: ; In the formula, represents the load interval of the adjustable loads, represents the adjustable load vector, represents the data index, represents the quantity of the relevant data of the adjustable loads, represents the -th Lagrange multiplier corresponding to the relevant data of the adjustable loads, represents the kernel function, represents the -th relevant data of the adjustable loads, represents the offset; In at least one embodiment, the kernel function is a linear kernel function, the similarity is obtained by calculating the inner product of the adjustable load vector and the relevant data of the adjustable loads, the adjustable load vector is a one-dimensional vector arranged in the order of the features of the relevant data of the adjustable loads, the relevant data of the adjustable loads include historical power consumption data, ambient temperature data, and time information data, and the features of the relevant data of the adjustable loads include daily average temperature, maximum temperature, minimum temperature, time period index, date type index, load value at the same time period of the previous day, and load value at the same time period of the previous week. The features of the relevant data of the adjustable loads are extracted by an intelligent electricity meter acquisition system.

[0034] Preferably, relevant data of virtual energy storage are collected, features of the relevant data of virtual energy storage are extracted, and the features of the relevant data of virtual energy storage are used as inputs of a decision tree model to output the load interval of the virtual energy storage, which is expressed by the formula as follows: ; In the formula, represents the load interval of the virtual energy storage, represents the prediction function of the decision tree model, represents the features of the relevant data of the virtual energy storage, represents the decision tree.

[0035] In at least one embodiment, the relevant data of the virtual energy storage include charging session data, operation data, and time information, and the features of the relevant data of the virtual energy storage include time period features, date type, historical load features, and charging behavior features.

[0036] Preferably, relevant data of the virtual generator set are collected, including historical load, and the historical load is linearized, which is expressed by the formula: ; In the formula, represents the historical load of the virtual generator set after linearization, , represent linear optimization parameters, represents the historical load of the virtual generator set; The historical load of the virtual generator set after linearization is decomposed into the adjustable load and the non-adjustable load of the virtual generator set; For the adjustable load of the virtual generator set, the adjustable load of the virtual generator set is used as the input of the autoregressive integrated moving average model, and the load range of the virtual generator set is output; The decomposition method is divided according to whether it can be interrupted; In at least one embodiment, the decomposition method includes: 1. The load of basic equipment such as production lines, safety systems, and lighting systems that must operate continuously is classified as the non-adjustable load of the virtual generator set; 2. The air conditioning system, non-critical production equipment, energy storage system, etc. are classified as the adjustable load of the virtual generator set.

[0037] Due to its non-adjustable nature, the non-adjustable load of the virtual generator set is not processed in this embodiment.

[0038] Preferably, the physical weight and the data-driven weight are determined, and the target load adjustable range of the virtual power plant is obtained based on the first load adjustable range, the second load adjustable range, the physical weight and the data-driven weight, which is expressed by the formula: ; In the formula, represents the target load adjustable range of the virtual power plant, represents the first load adjustable range of the distributed resource, represents the physical weight, represents the second load adjustable range of the distributed resource, represents the data-driven weight.

[0039] Preferably, the physical weight is expressed by the formula: ; In the formula, represents the weight offset, represents the scaling factor, represents the smoothing coefficient, Denote the stability requirement factor, which is a binary variable with a value of 0 or 1. It takes 0 for high-stability requirement scenarios and 1 otherwise. Denote the sensitivity factor. Denote the natural constant. In at least one embodiment, the high-stability requirement scenarios include emergency dispatch scenarios and peak shaving and frequency modulation scenarios.

[0040] The data-driven weight is expressed by the formula: .

[0041] Preferably, the sensitivity factor is expressed by the formula: ; In the formula, Denote the market volatility index. Denote the user volatility index. Denote the maximum value function. Among them, the market volatility index is expressed by the formula: ; In the formula, Denote the short-term market price volatility. Denote the long-term market price volatility. The user volatility index is expressed by the formula: ; In the formula, Denote the short-term user load variance. Denote the long-term user load variance. Use the Sigmoid function to map the sensitivity factor to the interval and express it by the formula: .

[0042] Specific implementation scenario: Consider a virtual power plant (VPP) that includes the following distributed resources: 1 small gas generator (DG): rated power 200kW; 100 controllable air-conditioning loads (AC): total capacity 150kW; 1 battery energy storage system (ESS): power 100kW, capacity 200kWh, current SOC is 50%; Power constraint range of the virtual generator set: [40kW, 180kW]; Power constraint range of the adjustable load: [30kW, 120kW]; Power constraint range of the virtual energy storage: [0kW, 80kW]; Load range of the predicted virtual generating unit: [50 kW, 170 kW]; Load range of the predicted adjustable load: [40 kW, 110 kW]; Load range of the predicted virtual energy storage: [0 kW, 70 kW]; Aggregate distributed resources to obtain the first load adjustable range and the second load adjustable range of the distributed resources as [70 kW, 380 kW] and [90 kW, 350 kW] respectively.

[0043] Calculate the sensitivity factor: See Figure 2 , by analyzing Figure 2 's electricity market price data, calculate the short-term market price fluctuation = 0.003641, the long-term market price fluctuation = 0.008, the market fluctuation index = 0.455125.

[0044] See Figure 3 , by analyzing Figure 3 's recent user load data, calculate the short-term user load variance = 30.96, the long-term user load variance = 100, then the user fluctuation index = 0.3096.

[0045] Sensitivity factor It can then be determined as 0.455125, and according to the Sigmoid function map the sensitivity factor to 0.2516, and at this time the value of k is 2.

[0046] Calculate the weights: Adopt the adaptive weight calculation formula of the present invention, and the parameter settings are: weight offset = 0.3, scaling factor = 0.5. The physical weights are calculated as follows: ; When the stability requirement parameter = 0 for the low-stability scenario, the physical weight is solved to be 0.3914, and the data-driven weight is then 0.6086.

[0047] When the stability requirement parameter = 1 for the high-stability scenario, the physical weight is solved to be 0.6116, and the data-driven weight is then 0.3884.

[0048] Stability requirement parameter When = 0 for the low - stability scenario, the adjustable range of the target load of the virtual power plant is [82.2 kW, 361.7 kW]; Stability requirement parameter When = 1 for the high - stability scenario, the adjustable range of the target load of the virtual power plant is [77.8 kW, 368.3 kW].

[0049] Example 2: This embodiment provides an electronic device with a computer program stored thereon. When the computer program is executed by a processor, it implements the method for obtaining the load of a virtual power plant based on physical weights as described in any embodiment of the present invention.

[0050] Example 3: This embodiment provides a computer - readable storage medium for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method for obtaining the load of a virtual power plant based on physical weights as described in any embodiment of the present invention.

[0051] In the embodiments of the present application, "at least one" means one or more, and "a plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent the situation of A existing alone, A and B existing simultaneously, and B existing alone. Where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects before and after. "At least one of the following" and its similar expressions refer to any combination of these items, including any combination of single - item or plural - item. For example, at least one of a, b, and c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple.

[0052] Those of ordinary skill in the art can realize that the units and algorithm steps described in the embodiments disclosed herein can be implemented by a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present application.

[0053] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0054] In several embodiments provided by the present application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs that can store program codes.

[0055] The above are only the embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A method for obtaining the load of a virtual power plant based on physical weights, characterized in that, The method includes the following steps: Determine the distributed resources of the virtual power plant, including virtual power generation units, adjustable loads, and virtual energy storage; formulate constraint conditions for the virtual power generation units, adjustable loads, and virtual energy storage respectively, project the constraint conditions of the distributed resources of the virtual power plant into the constraint space, and construct the first load adjustable range of the distributed resources; collect the relevant data of the adjustable loads, virtual energy storage, and virtual power generation units, obtain the load intervals of the adjustable loads, virtual energy storage, and virtual power generation units respectively, and obtain the second load adjustable range of the distributed resources according to the load intervals of each distributed resource; determine the physical weight and data-driven weight, and obtain the target load adjustable range of the virtual power plant based on the first load adjustable range, the second load adjustable range, the physical weight, and the data-driven weight; perform load regulation on the virtual power plant based on the target load adjustable range.

2. The method for obtaining the virtual power plant load based on physical weights according to claim 1, wherein Formulate the constraint conditions of the virtual power generation unit, including the power constraint of the virtual power generation unit and the ramp constraint of the virtual power generation unit; The power constraint of the virtual generating set is used to constrain the power of the virtual generating set at a certain moment, and the ramping constraint of the virtual generating set is used to constrain the virtual generating set from a certain moment to the power change amount at a certain moment; Formulate the constraint conditions of the adjustable load, including the power constraint of the adjustable load and the ramp constraint of the adjustable load; The power constraint of the adjustable load is used to constrain the power of the adjustable load at a certain moment, and the ramping constraint of the adjustable load is used to constrain the change in power of the adjustable load from a certain moment to a certain moment; Formulate the constraint conditions of virtual energy storage, including the power constraint of virtual energy storage, which is used to constrain the power of virtual energy storage at a certain moment.

3. The method for obtaining the virtual power plant load based on physical weights according to claim 1, characterized in that Collect the relevant data of the adjustable load, extract the features of the relevant data of the adjustable load, construct an adjustable load vector based on the features of the relevant data of the adjustable load, and use the adjustable load vector and the relevant data of the adjustable load as the input of the support vector regression model to output the load interval of the adjustable load.

4. The method for obtaining the virtual power plant load based on physical weights according to claim 1, characterized in that Collect the relevant data of the virtual energy storage, extract the features of the relevant data of the virtual energy storage, and use the features of the relevant data of the virtual energy storage as the input of the decision tree model to output the load interval of the virtual energy storage.

5. The method for obtaining the virtual power plant load based on physical weights according to claim 1, wherein Collect the relevant data of the virtual power generation unit, including the historical load, and perform linearization processing on the historical load; Decompose the linearly processed historical load into the adjustable load of the virtual power generation unit and the non-adjustable load of the virtual power generation unit; For the adjustable load of the virtual power generation unit, use the adjustable load of the virtual power generation unit as the input of the autoregressive integrated moving average model to output the load interval of the virtual power generation unit.

6. The method for obtaining the virtual power plant load based on physical weights according to claim 1, wherein Determine the physical weight and data-driven weight, and obtain the target load adjustable range of the virtual power plant based on the first load adjustable range, the second load adjustable range, the physical weight, and the data-driven weight, which is expressed by the formula: ； In the formula, represents the target load adjustable range of the virtual power plant, represents the first load adjustable range of the distributed resources, represents the physical weight, represents the second load adjustable range of the distributed resources, represents the data-driven weight.

7. The method for obtaining the virtual power plant load based on physical weights according to claim 6, characterized in that The physical weight is expressed by the formula: ； In the formula, represents the weight offset,[ represents the scaling factor,[ represents the smoothing coefficient,[ represents the stability requirement factor,[ represents the sensitivity factor,[ represents the natural constant;[ The data-driven weight is expressed by the formula: 。 8. The method for obtaining the virtual power plant load based on physical weights according to claim 7, wherein The sensitivity factor is expressed by the formula: ； Wherein, represents the market volatility index, represents the user volatility index, represents the maximum value function; Among them, the market fluctuation index is expressed by the formula: ； In the formula, represents the short-term fluctuation of the market price, represents the long-term fluctuation of the market price; The user fluctuation index is expressed by the formula: ； In the formula, represents the short-term load variance of the user, represents the long-term load variance of the user; The Sigmoid function is used to map the sensitivity factor to the interval which is expressed by the formula as follows: 。 9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method for obtaining the load of the virtual power plant based on physical weight according to any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method for obtaining the load of the virtual power plant based on physical weight according to any one of claims 1 to 8.

Images