A virtual power plant load acquisition method, device and medium based on physical weight

Abstract

The present invention relates to a method, device and medium for acquiring the load of a virtual power plant based on physical weights, and belongs to the technical field of virtual power plant load regulation, comprising the following steps: determining the distributed resources of the virtual power plant; formulating constraint conditions for each resource, and projecting them into the constraint space to construct a first load adjustable range. Then, relevant data is collected, and the load intervals of the adjustable load, virtual energy storage and virtual generator set are calculated respectively, and their upper and lower limits are added to form a second load adjustable range. Based on the first and second load adjustable ranges, the target load adjustable range of the virtual power plant is comprehensively obtained, and the load regulation of distributed resources is performed accordingly. The present invention takes into account uncertain factors such as market fluctuations and user load changes, and adjusts the physical weights and data-driven weights through an adaptive weight calculation formula, so that the load regulation strategy is more flexible and adaptable, and the responsiveness of the virtual power plant is enhanced.

Description

Technical Field

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

[0002] With the acceleration of energy transformation, distributed energy resources are increasingly accounting for a larger share of the power system. Virtual power plants (VPPs) have emerged as an innovative energy management model. By integrating multiple resources, including distributed generation equipment, adjustable loads, and energy storage systems, VPPs enable centralized management and optimized dispatch of distributed energy resources. This approach aims to improve energy efficiency, enhance grid stability and reliability, and meet growing electricity demand.

[0003] Load regulation is one of the core functions of a virtual power plant. Traditional solutions typically employ fixed regulation strategies, centrally scheduling various distributed resources according to pre-defined rules to achieve load balancing and optimization. However, these traditional approaches have gradually revealed numerous shortcomings in practical applications.

[0004] Prior art, such as the Chinese invention patent application with publication number CN119209506A, discloses a virtual power plant scheduling system based on multivariate information fusion. The system includes: a data source acquisition module, a resource aggregation and analysis module, and a resource balance assessment module. The data source acquisition module is used to acquire first multivariate data and second multivariate data, and store the first multivariate data in a virtual power plant resource type library, and store the second multivariate data in a resource regulation feature library; the resource aggregation and analysis module analyzes the stability of resource scheduling based on the first multivariate data; the resource aggregation and analysis module includes a third resource adjustable capacity analysis submodule, which is used to import the energy storage device adjustable data in the first multivariate data into a third resource adjustable capacity analysis model to analyze the energy storage device resource adjustable capacity value. However, although the above patent divides the data into first multivariate data and second multivariate data and stores them separately, during the fusion analysis, it mainly extracts and analyzes features of each type of data separately, such as separately modeling and analyzing wind power, photovoltaic, energy storage equipment, and different types of load data, without fully exploring the deep-level correlations and fusion points between different types of data. Summary of the Invention

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

[0006] The technical solutions of the present invention are as follows:

[0007] In one aspect, the present invention provides a method for acquiring virtual power plant load based on physical weights, comprising the following steps:

[0008] Determine the distributed resources of the virtual power plant, including virtual generators, adjustable loads, and virtual energy storage;

[0009] Constraints are formulated for virtual generators, adjustable loads, and virtual energy storage, and the constraints of the distributed resources of the virtual power plant are projected into the constraint space to construct the first load adjustable range of the distributed resources.

[0010] Collect relevant data of adjustable load, virtual energy storage, and virtual generator set, obtain the load range of adjustable load, the load range of virtual energy storage, and the load range of virtual generator set respectively, and obtain the second load adjustable range of distributed resources according to the load range of each distributed resource;

[0011] Determining a physical weight and a data-driven weight, and obtaining a 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;

[0012] The virtual power plant is load regulated based on the target load adjustable range.

[0013] Preferably, constraining conditions of the virtual generator set are formulated, including power constraints of the virtual generator set and ramp constraints of the virtual generator set;

[0014] The power constraint of the virtual generator set is used to constrain the virtual generator set The power at the moment, the ramp constraint of the virtual generator set is used to constrain the virtual generator set Time to Power change at each moment;

[0015] Formulate constraints for adjustable loads, including power constraints and ramp constraints for adjustable loads;

[0016] The power constraint of the adjustable load is used to constrain the adjustable load The power at the moment, the climbing constraint of the adjustable load is used to constrain the adjustable load Time to Power change at each moment;

[0017] Formulate virtual energy storage constraints, including virtual energy storage power constraints, to constrain virtual energy storage The power of the moment.

[0018] Preferably, relevant data of the adjustable load is collected, and features of the relevant data of the adjustable load are extracted. An adjustable load vector is constructed based on the features of the relevant data of the adjustable load. The adjustable load vector and the relevant data of the adjustable load are used as inputs of a support vector regression model to output the load range of the adjustable load.

[0019] Preferably, relevant data of virtual energy storage is collected, features of the relevant data of virtual energy storage are extracted, the features of the relevant data of virtual energy storage are used as input of a decision tree model, and the load range of the virtual energy storage is output.

[0020] Preferably, relevant data of the virtual generator set, including historical load, is collected, and linearization processing is performed on the historical load;

[0021] Decomposing the linearized historical load into the virtual generator set adjustable load and the virtual generator set non-adjustable load;

[0022] 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 integral moving average model to output the load range of the virtual generator set.

[0023] Preferably, a physical weight and a data-driven weight are determined, and a 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 can be expressed as follows:

[0024] ;

[0025] Where, Indicates the target load adjustable range of the virtual power plant, Indicates the first load adjustable range of distributed resources, represents the physical weight, Indicates the second load adjustable range of distributed resources, represents data-driven weights.

[0026] Preferably, the physical weight is expressed as:

[0027] ;

[0028] Where, represents the weight offset, represents the scaling factor, represents the smoothing coefficient, represents the stability demand factor, represents the sensitivity factor, represents a natural constant;

[0029] The data-driven weight is expressed as follows:

[0030] .

[0031] Preferably, the sensitivity factor is expressed as:

[0032] ;

[0033] Where, represents the market volatility indicator, represents the user fluctuation index, represents the maximum value function;

[0034] Among them, the market volatility index is expressed as follows:

[0035] ;

[0036] Where, Indicates short-term fluctuations in market prices. Indicates long-term fluctuations in market prices;

[0037] The user volatility index is expressed as:

[0038] ;

[0039] Where, represents the short-term load variance of users, represents the user's long-term load variance;

[0040] Use Sigmoid function to map the sensitivity factor to the interval In the formula, it is expressed as:

[0041] .

[0042] On the other hand, the present invention further provides an electronic device having a computer program stored thereon, wherein when the computer program is executed by a processor, the method for acquiring virtual power plant load based on physical weights as described in any embodiment of the present invention is implemented.

[0043] On the other hand, the present invention also provides a computer-readable storage medium for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the virtual power plant load acquisition method based on physical weights as described in any embodiment of the present invention.

[0044] The present invention has the following beneficial effects:

[0045] 1. This invention develops a set of refined load regulation strategies by comprehensively considering the characteristics of multiple distributed resources, including virtual generators, adjustable loads, and virtual energy storage. These strategies dynamically adjust the load levels of different resources based on their real-time status and demand, thereby avoiding idle and wasted resources.

[0046] 2. The constraints established by this invention, such as power constraints, ramping constraints, and energy storage constraints, provide clear safety boundaries for the operation of the virtual power plant. These constraints ensure that distributed resources do not exceed their safe operating range during regulation, thereby avoiding system failures caused by overload or underload. Furthermore, the load regulation strategy can make advance adjustments based on the real-time status and forecast information of the power grid to address potential market fluctuations and user load changes. This proactive regulation approach helps maintain the stability of the virtual power plant system and reduce the risk of failures and downtime.

[0047] 3. The present invention takes into account various uncertain factors such as market fluctuations and changes in user loads, and adjusts the physical weights and data-driven weights through an adaptive weight calculation formula to make the load regulation strategy more flexible and adaptable. The physical weights reflect the actual physical characteristics of distributed resources, such as power generation capacity and energy storage capacity; while the data-driven weights are based on historical data and forecast information, reflecting the changing trends of market and user loads. By dynamically adjusting the ratio of these two weights, the invention can automatically optimize the load regulation strategy according to different operating environments and needs, ensuring that the virtual power plant always operates in the optimal state. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 The present invention is a flowchart for implementing the method.

[0049] Figure 2 This is a graph of electricity market price data according to the present invention.

[0050] Figure 3 This is a user load data curve diagram of the present invention. DETAILED DESCRIPTION

[0051] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0052] It should be understood that the step numbers used herein are only for convenience of description and are not intended to limit the order in which the steps are to be executed.

[0053] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, the singular forms "a", "an" and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0054] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0055] The term "and / or" refers to and includes any and all possible combinations of one or more of the associated listed items.

[0056] Example 1:

[0057] See also Figure 1 This embodiment provides a method for acquiring virtual power plant load based on physical weights, comprising the following steps:

[0058] Determine the distributed resources of the virtual power plant, including virtual generators, adjustable loads, and virtual energy storage;

[0059] Among them, virtual generator sets refer to distributed energy resources that simulate the behavior of traditional generator sets, including renewable energy power generation facilities such as solar photovoltaic and wind power.

[0060] Adjustable loads include transferable loads based on electricity prices and interruptible loads based on incentives. Reasonable scheduling of adjustable loads is conducive to maximizing resource utilization. For transferable loads based on electricity prices, the operating time period is adjusted according to high or low electricity prices, including:

[0061] 1. Shift the load from high electricity price period (such as daytime) to low electricity price period (such as late at night);

[0062] 2. When the power grid issues a peak electricity price warning, completely shut down or significantly reduce the interruptible load.

[0063] For incentive-based interruptible loads, when the reliability of the power grid system is affected or the power consumption reaches its peak, interruption instructions are issued to power users to effectively reduce the power grid load and achieve the effect of peak shaving and valley filling.

[0064] Virtual energy storage is not a traditional physical energy storage device (such as batteries or pumped hydro). Instead, it is an energy balancing mechanism achieved through intelligent management and optimization technologies. Its core is to leverage the flexibility of demand-side resources (such as adjustable loads and virtual generators) to simulate the charging and discharging behavior of physical energy storage, thereby optimizing the energy flow of the power system, achieving peak load shifting, and increasing the utilization rate of renewable energy.

[0065] Constraints are formulated for virtual generators, adjustable loads, and virtual energy storage, and the constraints of the distributed resources of the virtual power plant are projected into the constraint space to construct the first load adjustable range of the distributed resources.

[0066] Collect relevant data of adjustable load, virtual energy storage, and virtual generator set, obtain the load range of adjustable load, the load range of virtual energy storage, and the load range of virtual generator set respectively, and add the upper and lower limits respectively as the second load adjustable range of distributed resources of the virtual power plant;

[0067] Determining a physical weight and a data-driven weight, and obtaining a 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;

[0068] The virtual power plant is load regulated based on the target load adjustable range.

[0069] Preferably, the constraints 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 constraints, specifically in the following steps:

[0070] Formulate constraints for virtual generator sets, including power constraints and ramp constraints for virtual generator sets;

[0071] The power constraint of the virtual generator set is used to constrain the virtual generator set The power at the moment is expressed as:

[0072] ;

[0073] Where, Represents a virtual generator set The lower power limit at the moment, Represents a virtual generator set The power of the moment, Represents a virtual generator set The power limit at the moment;

[0074] The climbing constraint of the virtual generator set is used to constrain the virtual generator set Time to The power change at the moment is expressed as:

[0075] ;

[0076] Where, Represents a virtual generator set The lower limit of power change at the moment, Represents a virtual generator set The upper limit of power change at the moment, Represents a virtual generator set Power at the moment;

[0077] Formulate constraints for adjustable loads, including power constraints and ramp constraints for adjustable loads;

[0078] The power constraint of the adjustable load is used to constrain the adjustable load The power at the moment is expressed as:

[0079] ;

[0080] Where, Indicates adjustable load The lower power limit at the moment, Indicates adjustable load The power of the moment, Indicates adjustable load The power limit at the moment;

[0081] The power of the adjustable load is expressed as follows:

[0082] ;

[0083] Where, Indicates adjustable load Baseline load at time Indicates adjustable load Adjust the power upward at all times, Indicates adjustable load Adjust power downward at all times;

[0084] The climbing constraint of the adjustable load is used to constrain the adjustable load Time to The power change at the moment is expressed as:

[0085] ;

[0086] Where, Indicates adjustable load The lower limit of power change at the moment, Indicates adjustable load The upper limit of power change at the moment, Indicates adjustable load Power at the moment;

[0087] Formulate constraints for virtual energy storage, including power constraints and energy storage constraints;

[0088] The power constraint of the virtual energy storage is used to constrain the virtual energy storage The power at the moment is expressed as:

[0089] ;

[0090] Where, Virtual energy storage The minimum discharge power at the moment, Virtual energy storage Power at the moment (including discharge power and charging power), Virtual energy storage Maximum charging power at the moment;

[0091] The energy storage constraint of the virtual energy storage is used to constrain the virtual energy storage The energy storage at the moment is expressed as:

[0092] ;

[0093] Where, Virtual energy storage The lower limit of energy storage at the moment, Virtual energy storage Energy storage at all times, Virtual energy storage The energy storage limit at the moment;

[0094] The power constraints of each distributed resource are projected into the constraint space, and the upper and lower limits of the power intervals constrained by each distributed resource are summed to obtain a first load adjustable range.

[0095] Preferably, relevant data of the adjustable load is collected, and features of the relevant data of the adjustable load are extracted. An adjustable load vector is constructed based on the features of the relevant data of the adjustable load. The adjustable load vector and the relevant data of the adjustable load are used as inputs of a support vector regression model, and a load range of the adjustable load is output, which is expressed as follows:

[0096] ;

[0097] Where, Indicates the load range of the adjustable load, represents the adjustable load vector, Indicates the data index, Indicates the number of relevant data of adjustable load, Indicates the The Lagrange multiplier corresponding to the relevant data of the adjustable load, represents the kernel function, Indicates the The relevant data of the adjustable load, Indicates the offset;

[0098] In at least one embodiment, the kernel function It is a linear kernel function, and the similarity is obtained by calculating the inner product of the adjustable load vector and the related data of the adjustable load. The adjustable load vector is a one-dimensional vector arranged in order based on the characteristics of the related data of the adjustable load. The related data of the adjustable load includes historical electricity consumption data, ambient temperature data, and time information data. The characteristics of the related data of the adjustable load include average daily temperature, maximum temperature, minimum temperature, time period index, date type index, load value of the same period of the previous day, and load value of the same period of the previous week. The characteristics of the related data of the adjustable load are extracted by the smart meter acquisition system.

[0099] Preferably, relevant data of virtual energy storage is collected, features of the relevant data of virtual energy storage are extracted, the features of the relevant data of virtual energy storage are used as input of the decision tree model, and the load range of virtual energy storage is output, which is expressed as follows:

[0100] ;

[0101] Where, represents the load range of virtual energy storage, represents the prediction function of the decision tree model, The characteristics of the data related to virtual energy storage, Represents a decision tree.

[0102] In at least one embodiment, the data related to virtual energy storage includes charging session data, operation data, and time information. The characteristics of the data related to virtual energy storage include time period characteristics, date type, historical load characteristics, and charging behavior characteristics.

[0103] Preferably, relevant data of the virtual generator set, including historical load, is collected, and the historical load is linearized and expressed as follows:

[0104] ;

[0105] Where, represents the historical load of the virtual generator set after linearization, 、 represents the linear optimization parameter, Represents the historical load of the virtual generator set;

[0106] Decomposing the historical load of the virtual generator set after linearization into the adjustable load of the virtual generator set and the non-adjustable load of the virtual generator set;

[0107] 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 integral moving average model to output the load range of the virtual generator set;

[0108] The decomposition method is based on whether it can be interrupted or not;

[0109] In at least one embodiment, the decomposition method includes:

[0110] 1. Divide the load of basic equipment such as production lines, safety systems, and lighting systems that must operate continuously into the non-adjustable load of virtual generator sets;

[0111] 2. Divide the air-conditioning system, non-critical production equipment, energy storage system, etc. into adjustable loads of virtual generator sets.

[0112] The non-adjustable load of the virtual generator set is not processed in this embodiment due to its non-adjustable nature.

[0113] Preferably, a physical weight and a data-driven weight are determined, and a 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 can be expressed as follows:

[0114] ;

[0115] Where, Indicates the target load adjustable range of the virtual power plant, Indicates the first load adjustable range of distributed resources, represents the physical weight, Indicates the second load adjustable range of distributed resources, represents data-driven weights.

[0116] Preferably, the physical weight is expressed as:

[0117] ;

[0118] Where, represents the weight offset, represents the scaling factor, represents the smoothing coefficient, Represents 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. represents the sensitivity factor, represents a natural constant;

[0119] In at least one embodiment, the high stability requirement scenario includes an emergency dispatch scenario and a peak and frequency regulation scenario.

[0120] The data-driven weight is expressed as follows:

[0121] .

[0122] Preferably, the sensitivity factor is expressed as:

[0123] ;

[0124] Where, represents the market volatility indicator, represents the user fluctuation index, represents the maximum value function;

[0125] Among them, the market volatility index is expressed as follows:

[0126] ;

[0127] Where, Indicates short-term fluctuations in market prices. Indicates long-term fluctuations in market prices;

[0128] The user volatility index is expressed as:

[0129] ;

[0130] Where, represents the short-term load variance of users, represents the user's long-term load variance;

[0131] Use Sigmoid function to map the sensitivity factor to the interval In the formula, it is expressed as:

[0132] .

[0133] Specific implementation scenarios:

[0134] Consider a virtual power plant (VPP) consisting of the following distributed resources:

[0135] 1 small gas generator set (DG): rated power 200kW;

[0136] 100 controllable air conditioning loads (AC): total capacity 150kW;

[0137] 1 battery energy storage system (ESS): 100kW power, 200kWh capacity, current SOC 50%;

[0138] Power constraint range of virtual generator set: [40kW, 180kW];

[0139] Power constraint range of adjustable load: [30kW, 120kW];

[0140] Power constraint range of virtual energy storage: [0kW, 80kW];

[0141] Predicted load range of virtual generator set: [50kW, 170kW];

[0142] Predicted adjustable load range: [40kW, 110kW];

[0143] Predicted load range of virtual energy storage: [0kW, 70kW];

[0144] By aggregating the distributed resources, the first load adjustable range of the distributed resources and the second load adjustable range of the distributed resources are obtained as [70kW, 380kW] and [90kW, 350kW] respectively.

[0145] Calculate the sensitivity factor:

[0146] See also Figure 2 , through analysis Figure 2 The electricity market price data is used to calculate the short-term fluctuation of market prices. =0.003641, market price fluctuates over a long period of time =0.008, market volatility index = 0.455125.

[0147] See also Figure 3 , through analysis Figure 3 The user's recent load data is used to calculate the user's short-term load variance =30.96, user long-term load variance =100, then the user fluctuation index = 0.3096.

[0148] Sensitivity factor It can be determined to be 0.455125, and according to the Sigmoid function The sensitivity factor is mapped to 0.2516, and the value of k is 2.

[0149] Calculate weights:

[0150] The adaptive weight calculation formula of the present invention is used, and the parameters are set as: weight offset = 0.3, scaling factor = 0.5. The physical weight is calculated as follows:

[0151] ;

[0152] When the stability requirement parameter =0 is a low stability scenario, and the physical weight is obtained is 0.3914, data-driven weight It is 0.6086.

[0153] When the stability requirement parameter =1 for high stability scenario, the physical weight is obtained is 0.6116, data-driven weight It is 0.3884.

[0154] Stability requirement parameters =0 for low stability scenario, the target load adjustable range of the virtual power plant is [82.2kW, 361.7kW]; the stability requirement parameter =1 for a high stability scenario, the target load adjustable range of the virtual power plant is [77.8kW, 368.3kW].

[0155] Example 2:

[0156] This embodiment provides an electronic device having a computer program stored thereon. When the computer program is executed by a processor, the method for acquiring virtual power plant load based on physical weight as described in any embodiment of the present invention is implemented.

[0157] Example 3:

[0158] 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 implement the virtual power plant load acquisition method based on physical weight as described in any embodiment of the present invention.

[0159] In the embodiments of the present application, "at least one" refers to one or more, and "more" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. 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, c can be single or multiple.

[0160] Those skilled in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented using a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0161] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0162] In the several embodiments provided in this 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 this application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of this application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), magnetic disk or optical disk, and other media that can store program code.

[0163] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structures or equivalent process changes made using the contents of the present invention's description and drawings, or directly or indirectly applied to other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A virtual power plant load acquisition method based on physical weight, characterized in that: The following steps are involved: Determine the distributed resources of the virtual power plant, including virtual generators, adjustable loads, and virtual energy storage; Constraints are formulated for virtual generators, adjustable loads, and virtual energy storage, and the constraints of the distributed resources of the virtual power plant are projected into the constraint space to construct the first load adjustable range of the distributed resources. Among them, the constraints of the virtual generator set include the power constraint of the virtual generator set and the ramp constraint of the virtual generator set; The power constraint of the virtual generator set is used to constrain the virtual generator set The power at the moment, the ramp constraint of the virtual generator set is used to constrain the virtual generator set Time to Power change at each moment; The constraints of the adjustable load include 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 adjustable load The power at the moment, the climbing constraint of the adjustable load is used to constrain the adjustable load Time to Power change at each moment; The constraints of virtual energy storage include power constraints of virtual energy storage, which are used to constrain virtual energy storage. Power at the moment; Collect relevant data of adjustable load, virtual energy storage, and virtual generator set, obtain the load range of adjustable load, the load range of virtual energy storage, and the load range of virtual generator set respectively, and obtain the second load adjustable range of distributed resources according to the load range of each distributed resource; Determine the physical weight and the data-driven weight, wherein the physical weight is expressed as follows: ； Where, represents the weight offset, represents the scaling factor, represents the smoothing coefficient, represents the stability demand factor, represents the sensitivity factor, represents a natural constant; The data-driven weight is expressed as follows: ； 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, and is expressed as follows: ； Where, Indicates the target load adjustable range of the virtual power plant, Indicates the first load adjustable range of distributed resources, represents the physical weight, Indicates the second load adjustable range of distributed resources, represents data-driven weights; The virtual power plant is load regulated based on the target load adjustable range.

2. The method for acquiring virtual power plant load based on physical weight according to claim 1, characterized in that: Collect relevant data of the adjustable load, extract 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, use the adjustable load vector and the relevant data of the adjustable load as inputs of the support vector regression model, and output the load range of the adjustable load.

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

4. The method for acquiring virtual power plant load based on physical weight according to claim 1, characterized in that: Collect relevant data of the virtual generator set, including historical load, and perform linearization processing on the historical load; Decomposing the linearized historical load into the virtual generator set adjustable load and the virtual generator set non-adjustable load; 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 integral moving average model to output the load range of the virtual generator set.

5. The method for acquiring virtual power plant load based on physical weight according to claim 1, characterized in that: The sensitivity factor is expressed as follows: ； Where, represents the market volatility indicator, represents the user fluctuation index, represents the maximum value function; Among them, the market volatility index is expressed as follows: ； Where, Indicates short-term fluctuations in market prices. Indicates long-term fluctuations in market prices; The user volatility index is expressed as: ； Where, represents the short-term load variance of users, represents the user's long-term load variance; Use Sigmoid function to map the sensitivity factor to the interval In the formula, it is expressed as: 。 6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the virtual power plant load acquisition method based on physical weight is implemented as described in any one of claims 1 to 5.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the virtual power plant load acquisition method based on physical weights as described in any one of claims 1 to 5 is implemented.

Images