Virtual power plant resource aggregation planning method and device based on dynamic reconstruction and computer equipment

Abstract

The invention relates to a virtual power plant resource aggregation planning method and device based on dynamic reconstruction, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: for each distributed energy resource in a target region, determining a resource aggregation category to which each distributed energy resource belongs according to a franchise feature and a response feature corresponding to each distributed energy resource; through a pre-trained franchise probability evaluation model, outputting a franchise probability evaluation result corresponding to each resource aggregation category, and determining a franchise capacity corresponding to each resource aggregation category; in each reconstruction stage of the resource operation cycle of the target region, combining the resource aggregation categories to construct all reconstruction time sequence combinations; and through a double-layer optimization model, screening in each reconstruction stage to obtain a reconstruction time sequence combination with the optimal return on investment, and taking the reconstruction time sequence combination as a virtual power plant resource dynamic aggregation planning scheme. By adopting the method, the flexibility of a virtual power plant resource aggregation scheme can be improved.

Description

Technical Field

[0001] This application relates to the field of power technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for virtual power plant resource aggregation planning based on dynamic reconfiguration. Background Technology

[0002] With the rapid development of new power systems and the energy internet, the penetration rate of new energy sources is constantly increasing. Distributed energy resources (DERs) are being connected in large quantities on the distribution side, exhibiting characteristics such as large scale, small size, geographical dispersion, and diverse types. These resources have potential regulation capabilities, such as controllable loads, distributed generation, energy storage, and electric vehicles. If they can be effectively aggregated and utilized, they will help support the safe and stable operation of the power grid and improve the flexibility of regulation and energy efficiency.

[0003] Virtual Power Plants (VPPs), as aggregation and control platforms based on information and communication technologies, can coordinate and operate various types of DER resources across different geographical regions in a unified and market-oriented manner, becoming an important means to achieve flexible aggregation and optimized scheduling of distributed resources. In related research, VPPs primarily focus on static resource allocation, determining their participation capacity through methods such as full lifecycle assessment and resource adjustability assessment. However, in practical applications, the responsiveness of DERs is affected by various factors such as seasonality, load patterns, and equipment status, exhibiting periodic changes. Simultaneously, the electricity market trading mechanism and supply-demand structure are constantly evolving, making it difficult for fixed resource aggregation schemes to continuously adapt to complex environments.

[0004] Therefore, the virtual power plant resource aggregation scheme in related technologies suffers from a lack of flexibility. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for planning virtual power plant resource aggregation based on dynamic reconfiguration, which can improve the flexibility of virtual power plant resource aggregation schemes and address the aforementioned technical problems.

[0006] Firstly, this application provides a virtual power plant resource aggregation planning method based on dynamic reconfiguration, including:

[0007] For each distributed energy resource in the target area, the resource aggregation category to which each distributed energy resource belongs is determined based on the affiliation characteristics and response characteristics of each distributed energy resource; the affiliation characteristics are determined based on the structural attributes and output capacity of the distributed energy resources; the response characteristics are determined based on the response behavior parameters of the distributed energy resources.

[0008] The pre-trained franchise probability assessment model outputs the franchise probability assessment results for each of the resource aggregation categories, and determines the franchise capacity for each of the resource aggregation categories based on the franchise probability assessment results. The franchise probability assessment results are used to characterize the probability that distributed energy resources in the corresponding resource aggregation category will accept virtual power plant contracts. The franchise probability assessment results are determined by the pre-trained franchise probability assessment model based on a pre-built virtual power plant franchise reward mechanism.

[0009] In each reconfiguration phase of the resource operation cycle in the target region, the resource aggregation categories are combined to construct all reconfiguration time sequence combinations;

[0010] Through a dual-layer optimization model of virtual power plant resource aggregation and operation, the resource aggregation scheme and operation strategy are jointly optimized. In each of the reconstruction stages, the reconstruction sequence combination with the optimal return on investment is selected as the virtual power plant resource dynamic aggregation planning scheme. The dual-layer optimization model of virtual power plant resource aggregation and operation is constrained by at least the franchise capacity and franchise reward resource amount corresponding to the resource aggregation category. The upper-layer model aims to maximize the return on investment of the virtual power plant, and the lower-layer model aims to maximize the operating income.

[0011] In one embodiment, the method further includes:

[0012] For any distributed energy resource, obtain reward resource element information; the reward resource element information includes the basic franchise reward resources of the virtual power plant, the franchise capacity of the distributed energy resource, the franchise contract validity period, and the demand information of the virtual power plant for the distributed energy resource;

[0013] Input the reward resource element information into the pre-built reward resource model corresponding to the virtual power plant franchise reward mechanism, and output the franchise reward resource amount corresponding to any distributed energy resource;

[0014] The amount of franchise reward resources corresponding to each of the distributed energy resources and the resource aggregation category to which they belong is determined.

[0015] In one embodiment, determining the resource aggregation category of each distributed energy resource in the target area based on its associated characteristics and response characteristics includes:

[0016] Based on the membership characteristics corresponding to each of the distributed energy resources, the distributed energy resources are clustered to obtain the first clustering result;

[0017] Based on the response characteristics of the distributed energy resources in each of the first clustering results, the distributed energy resources in the first clustering results are clustered to obtain the second clustering results;

[0018] Based on the second clustering results, the resource aggregation category to which each of the distributed energy resources belongs is determined.

[0019] In one embodiment, the step of outputting the franchise probability assessment results corresponding to each of the resource aggregation categories through a pre-trained franchise probability assessment model includes:

[0020] The expression for the pre-trained franchise probability evaluation model is:

[0021]

[0022] in, For the first The probability that a distributed energy resource will accept a virtual power plant contract; For the first The utility value of a franchise contract for a distributed energy resource; Indicates the first The willingness to join a distributed energy resource is expressed as follows: a value of 1 indicates joining, and a value of 0 indicates not joining.

[0023]

[0024]

[0025] In the formula, For the first The self-preference coefficient of a distributed energy resource; , For the corresponding number Weighting coefficients of influencing factors of distributed energy resources; , The first The result is the normalized sum of the reward resources for joining a distributed energy resource and the validity period of the joining contract.

[0026] In one embodiment, the upper-level model performs dynamic aggregation planning on the virtual power plant with an annual resource operation cycle and a monthly time scale; the objective function of the upper-level model is shown below:

[0027]

[0028]

[0029]

[0030] in, Indicates the first of all the reconfiguration timing combinations. One reconstruction sequence; Cost of virtual power plant resource aggregation; For revenue from virtual power plant operations; This includes the resource cost of the membership incentive paid by the virtual power plant to the distributed energy resources. The costs associated with the modification of terminal equipment and communication, control, and metering involved in the access of the aforementioned distributed energy resources. ; This represents the amount of franchise reward resources corresponding to the nth type of resource aggregation category under the mth reconstruction phase. The resource access cost is the resource cost for the nth type of resource aggregation category. The resource access cost is the same for the same type of resource aggregation category. Let n be the number of member affiliations included in the nth resource aggregation category during the mth reconstruction phase. Let n be the membership status variable for the nth type of resource aggregation category under the mth reconstruction stage, where 1 represents membership and 0 represents non-membership.

[0031] The constraints of the upper-level model include:

[0032]

[0033]

[0034]

[0035]

[0036] in, , These are the upper and lower limits of the amount of franchise reward resources, respectively; Let n be the franchise capacity corresponding to the nth type of resource aggregation category under the mth reconstruction stage; , These represent the operating revenue of the virtual power plant and the resource aggregation cost of the virtual power plant in the m-th reconstruction stage, respectively. Let $\franchise$ be the utility value of the $n$-th resource aggregation category under the $m$-th reconstruction phase.

[0037] In one embodiment, the lower-level model calculates total revenue and operational risk by jointly optimizing the virtual power plant's electricity purchase and sale transactions in the energy market and its peak-shaving and frequency regulation services in the ancillary services market. The objective function is:

[0038]

[0039]

[0040]

[0041] in, Indicates the first of all the reconfiguration timing combinations. One reconstruction sequence; For revenue from virtual power plant operations; , These represent the number of months in the m-th reconstruction phase and the number of months in the m-th reconstruction phase. Number of typical scenarios per month; For the m-th reconstruction stage, the first... The number of days included in a month; For the first The first reconstruction phase Monthly scene The probability of occurrence; , They are respectively the m-th reconstruction stage and the th Monthly scene The virtual power plant operating revenue and virtual power plant resource aggregation cost function are defined below. For the risk function of virtual power plant operation; This represents the risk preference coefficient for virtual power plants. Value at Risk (VaR); Confidence level; For the m-th reconstruction stage, the first... Monthly scene The loss function takes the negative value of the virtual power plant's operating revenue:

[0042]

[0043] The constraints of the lower-level model include power balance constraints, distributed generation constraints, energy storage leasing constraints, load price parameter constraints, distributed energy resource regulation and response constraints, and conditional value of risk constraints.

[0044] Secondly, this application also provides a virtual power plant resource aggregation planning device based on dynamic reconfiguration, comprising:

[0045] The classification module is used to determine the resource aggregation category of each distributed energy resource in the target area based on the associated characteristics and response characteristics of each distributed energy resource; the associated characteristics are determined based on the structural attributes and output capacity of the distributed energy resources; the response characteristics are determined based on the response behavior parameters of the distributed energy resources.

[0046] The evaluation module is used to output the franchise probability evaluation results corresponding to each of the resource aggregation categories through a pre-trained franchise probability evaluation model, and to determine the franchise capacity corresponding to each of the resource aggregation categories based on the franchise probability evaluation results; the franchise probability evaluation results are used to characterize the probability of distributed energy resources in the corresponding resource aggregation category accepting virtual power plant contracts; the franchise probability evaluation results are determined by the pre-trained franchise probability evaluation model based on a pre-constructed virtual power plant franchise reward mechanism;

[0047] The combination module is used to combine the resource aggregation categories in each reconstruction stage of the resource operation cycle in the target region to construct all reconstruction sequence combinations;

[0048] The screening module is used to jointly optimize resource aggregation schemes and operational strategies through a dual-layer optimization model of virtual power plant resource aggregation and operation. In each of the reconstruction stages, it selects the reconstruction sequence combination with the optimal return on investment as the virtual power plant resource dynamic aggregation planning scheme. The dual-layer optimization model of virtual power plant resource aggregation and operation is constrained by at least the franchise capacity and franchise reward resource amount corresponding to the resource aggregation category. The upper-layer model aims to maximize the return on investment of the virtual power plant, while the lower-layer model aims to maximize operational revenue.

[0049] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program that, when executed by the processor, implements the steps of the method described above.

[0050] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, implements the steps of the above-described method.

[0051] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, implements the steps of the above-described method.

[0052] The aforementioned method, apparatus, computer equipment, computer-readable storage medium, and computer program product for resource aggregation planning of virtual power plants based on dynamic reconfiguration determine the resource aggregation category of each distributed energy resource in a target area based on its corresponding affiliation and response characteristics. Affiliation characteristics are determined based on the structural attributes and output capacity of the distributed energy resources; response characteristics are determined based on the response behavior parameters of the distributed energy resources. A pre-trained affiliation probability assessment model outputs the affiliation probability assessment results for each resource aggregation category, and the affiliation capacity for each resource aggregation category is determined based on these results. The affiliation probability assessment results characterize the acceptance of virtual power plants by distributed energy resources within the corresponding resource aggregation category. The probability of a power plant contract; the franchise probability assessment result is determined by a pre-trained franchise probability assessment model based on a pre-built virtual power plant franchise reward mechanism; in each reconstruction stage of the resource operation cycle in the target region, resource aggregation categories are combined to construct all reconstruction time sequence combinations. Through a virtual power plant resource aggregation and operation dual-layer optimization model, the resource aggregation scheme and operation strategy are jointly optimized. In each reconstruction stage, the reconstruction time sequence combination with the optimal return on investment is selected as the virtual power plant resource dynamic aggregation planning scheme; the virtual power plant resource aggregation and operation dual-layer optimization model is constrained at least by the franchise capacity and franchise reward resource amount corresponding to the resource aggregation category. The upper-layer model aims to maximize the return on investment of the virtual power plant, and the lower-layer model aims to maximize operating revenue.

[0053] Thus, by leveraging the membership and response characteristics of each distributed energy resource, the distributed energy resources can be more accurately classified into corresponding resource aggregation categories. A pre-trained membership probability assessment model outputs the membership probability assessment results for each resource aggregation category, and based on these results, the membership capacity for each resource aggregation category is determined, providing data support for aggregation planning. Building upon this, a reconstructed time-series combination is constructed. Through a dual-layer optimization model of virtual power plant resource aggregation and operation, the resource aggregation scheme and operational strategy are jointly optimized. This allows for the selection of the virtual power plant resource dynamic aggregation planning scheme with the optimal return on investment, ensuring that the output virtual power plant resource dynamic aggregation planning scheme possesses good market responsiveness and operational efficiency. This solves the problem of mismatch between the static configuration of virtual power plant resources and the evolution of market demand, effectively improving the flexibility of the virtual power plant resource aggregation scheme. Attached Figure Description

[0054] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0055] Figure 1 This is a flowchart illustrating a virtual power plant resource aggregation planning method based on dynamic reconfiguration in one embodiment.

[0056] Figure 2 This is a decision block diagram of a virtual power plant resource aggregation planning method based on dynamic reconfiguration in one embodiment;

[0057] Figure 3 This is a schematic diagram illustrating the optimal reconstruction timing under different reconstruction stages in one embodiment;

[0058] Figure 4 This is a schematic diagram illustrating the virtual power plant market transaction results at each reconstruction stage under optimal reconstruction timing in one embodiment.

[0059] Figure 5 This is a structural block diagram of a virtual power plant resource aggregation planning device based on dynamic reconfiguration in one embodiment;

[0060] Figure 6 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0061] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0062] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0063] In one embodiment, such as Figure 1As shown, a virtual power plant resource aggregation planning method based on dynamic reconfiguration is provided, applied to distributed energy resource aggregation planning scenarios. This embodiment illustrates the method using a computer device. The computer device can be a terminal or a server. The reward resource amount in this application can refer to a bonus amount.

[0064] In this embodiment, the method includes the following steps:

[0065] Step S110: For each distributed energy resource in the target area, determine the resource aggregation category to which each distributed energy resource belongs based on the corresponding affiliation characteristics and response characteristics.

[0066] Among them, the joining characteristics are determined based on the structural attributes and output capacity of distributed energy resources (DER); the response characteristics are determined based on the response behavior parameters of distributed energy resources.

[0067] The response behavior parameters include at least one of response time, duration, and capacity.

[0068] Specifically, computer equipment can extract affiliate features from the structural attributes and output capabilities of the DER, and then extract response features from response behavior parameters such as response time, duration, and capacity, so as to determine the resource aggregation category to which each distributed energy resource belongs based on the affiliate features and response features corresponding to each distributed energy resource.

[0069] In some embodiments, computer equipment can extract the membership and response features corresponding to each distributed energy resource in the target area, perform two-level clustering and label recognition (resource aggregation category division) to form a standardized feature representation. Specifically, primary and secondary clustering models can be constructed separately to achieve accurate division of DERs. Unsupervised methods such as K-means are used for clustering to ensure the comparability of resources of the same type, facilitating unified modeling and strategy formulation in subsequent models.

[0070] Step S120: Using the pre-trained franchise probability assessment model, output the franchise probability assessment results corresponding to each resource aggregation category, and determine the franchise capacity corresponding to each resource aggregation category based on the franchise probability assessment results.

[0071] Among them, the joining probability assessment result is used to characterize the probability (i.e., joining probability) of distributed energy resources in the corresponding resource aggregation category accepting Virtual Power Plant (VPP) contracts.

[0072] The franchise probability assessment result is determined by the pre-trained franchise probability assessment model based on the pre-built virtual power plant franchise reward mechanism.

[0073] In practice, a pre-trained franchise probability assessment model (which can also be named "franchise intention determination model") can be built based on the franchise agreement content. The franchise probability assessment model uses the Logit (Logistic regression) model to estimate its franchise probability, and combines DER historical data and classification results to evaluate the franchise capacity of DER in various resource aggregation categories.

[0074] It should be noted that, considering DER's autonomous choice when faced with a franchise invitation, this application constructs a Logit selection model based on the utility of the franchise contract to predict whether distributed energy resources are willing to join a virtual power plant. This model comprehensively considers factors such as the franchise bonus amount and the franchise contract utility value, establishes a franchise utility function, and normalizes its franchise probability model. Through maximum likelihood training on historical data, model parameters are obtained. Under the conditions of the franchise bonus amount and the franchise contract utility value, the franchise probability of different resource aggregation categories can be estimated. Furthermore, combined with the declared capacity of distributed energy resources, the available capacity for each resource aggregation category is derived, providing data support for aggregation planning.

[0075] In some embodiments, the expression for the pre-trained affiliation probability evaluation model is:

[0076]

[0077] in, For the first The probability that a distributed energy resource will accept a virtual power plant contract; For the first The utility value of a franchise contract for a distributed energy resource; Indicates the first The willingness to join a distributed energy resource is expressed as follows: a value of 1 indicates joining, and a value of 0 indicates not joining.

[0078]

[0079]

[0080] In the formula, For the first The self-preference coefficient of a distributed energy resource; , For the corresponding number Weighting coefficients of influencing factors of distributed energy resources; , The first The result is the normalized sum of the franchise bonus amount and the franchise contract validity period for each distributed energy resource.

[0081] Normalization refers to dividing the parameter value by the maximum value of the corresponding parameter in historical data.

[0082] If the probability of joining a resource aggregation category is greater than a preset probability threshold, then the distributed energy resources in that resource aggregation category are determined to be willing to join the virtual power plant; otherwise, the distributed energy resources in that resource aggregation category are determined to be unwilling to join the virtual power plant.

[0083] Step S130: In each reconstruction phase of the resource operation cycle in the target region, resource aggregation categories are combined to construct all reconstruction sequence combinations.

[0084] In practice, computer equipment can combine resource aggregation categories to construct all reconfiguration time sequence combinations based on the dynamic changes in market supply and demand and the response capabilities of distributed energy resources at each reconfiguration stage of the resource operation cycle in the target area.

[0085] It should be noted that DER response capabilities and electricity market demand are typically driven by factors such as seasonality, weather, and market mechanisms, exhibiting significant cyclical changes. This application divides the annual resource operation cycle into multiple reconfiguration phases. Based on the dynamic changes in market supply and demand and the response capabilities of distributed energy resources, it combines various resource aggregation categories to construct a set of all possible reconfiguration time series for screening by the virtual power plant resource aggregation and operation dual-layer optimization model.

[0086] Step S140: Through the dual-layer optimization model of virtual power plant resource aggregation and operation, the resource aggregation scheme and operation strategy are jointly optimized. In each reconstruction stage, the reconstruction sequence combination with the best return on investment is selected as the virtual power plant resource dynamic aggregation planning scheme.

[0087] Among them, the virtual power plant resource aggregation and operation dual-layer optimization model takes at least the franchise capacity and franchise bonus amount corresponding to the resource aggregation category as constraints. The upper-layer model aims to maximize the return on investment of the virtual power plant, while the lower-layer model aims to maximize the operating income.

[0088] In its implementation, the virtual power plant resource aggregation and operation dual-layer optimization model comprises an upper-layer model and a lower-layer model. The upper-layer model optimizes resource aggregation schemes, aiming to maximize the return on investment (ROI) of the VPP. Decision variables include the membership status of DERs (Delegates in Resource Allocation) in various resource aggregation categories, membership bonus amounts, and membership contract utility values. The lower-layer model simulates the operation of the VPP at each stage, aiming to maximize operational revenue. It covers strategies for energy market power purchase and sale, and participation in ancillary services (such as frequency regulation and peak shaving). Simultaneously, it introduces CVaR (Conditional Value-at-Risk) to constrain the DER output and market price fluctuations, ensuring revenue stability. Through interactive iterative solutions between the upper and lower-layer models, the upper layer continuously adjusts incentive and resource combination strategies based on feedback from the lower layer, ultimately outputting the optimal resource aggregation scheme (virtual power plant resource dynamic aggregation planning scheme) for each reconfiguration stage. In each refactoring phase, the one with the best ROI is selected from all refactoring sequence combinations and used as the final output of the VPP dynamic refactoring schedule and resource allocation (i.e., the refactoring sequence combination with the best return on investment is selected and used as the output of the virtual power plant resource dynamic aggregation planning scheme), thereby improving the economy, stability and market adaptability of the virtual power plant in long-term operation.

[0089] In the aforementioned virtual power plant resource aggregation planning method based on dynamic reconfiguration, the resource aggregation category of each distributed energy resource in the target area is determined according to its corresponding affiliation and response characteristics. Affiliation characteristics are determined based on the structural attributes and output capacity of the distributed energy resources; response characteristics are determined based on the response behavior parameters of the distributed energy resources. A pre-trained affiliation probability assessment model outputs the affiliation probability assessment results for each resource aggregation category, and the affiliation capacity corresponding to each resource aggregation category is determined based on these results. The affiliation probability assessment results characterize the probability that a distributed energy resource in the corresponding resource aggregation category will accept a virtual power plant contract. The evaluation results are obtained by the pre-trained franchise probability evaluation model based on the pre-constructed virtual power plant franchise reward mechanism. In each reconstruction stage of the resource operation cycle in the target region, resource aggregation categories are combined to construct all reconstruction time sequence combinations. Through the virtual power plant resource aggregation and operation two-layer optimization model, the resource aggregation scheme and operation strategy are jointly optimized. In each reconstruction stage, the reconstruction time sequence combination with the best return on investment is selected as the virtual power plant resource dynamic aggregation planning scheme. The virtual power plant resource aggregation and operation two-layer optimization model is constrained by at least the franchise capacity and franchise bonus amount corresponding to the resource aggregation category. The upper-layer model aims to maximize the return on investment of the virtual power plant, and the lower-layer model aims to maximize the operating income.

[0090] Thus, by leveraging the membership and response characteristics of each distributed energy resource, the distributed energy resources can be more accurately classified into corresponding resource aggregation categories. A pre-trained membership probability assessment model outputs the membership probability assessment results for each resource aggregation category, and based on these results, the membership capacity for each resource aggregation category is determined, providing data support for aggregation planning. Building upon this, a reconstructed time-series combination is constructed. Through a dual-layer optimization model of virtual power plant resource aggregation and operation, the resource aggregation scheme and operational strategy are jointly optimized. This allows for the selection of the virtual power plant resource dynamic aggregation planning scheme with the optimal return on investment, ensuring that the output virtual power plant resource dynamic aggregation planning scheme possesses good market responsiveness and operational efficiency. This solves the problem of mismatch between the static configuration of virtual power plant resources and the evolution of market demand, effectively improving the flexibility of the virtual power plant resource aggregation scheme.

[0091] In some embodiments, the method further includes: for any distributed energy resource, obtaining bonus element information; the bonus element information includes the basic franchise bonus of the virtual power plant, the franchise capacity of any distributed energy resource, the franchise contract validity period, and the demand information of the virtual power plant for any distributed energy resource; inputting the bonus element information into a pre-built bonus model corresponding to the virtual power plant franchise reward mechanism, and outputting the franchise bonus amount corresponding to any distributed energy resource; determining the franchise bonus amount corresponding to each resource aggregation category based on the franchise bonus amount corresponding to each distributed energy resource and the resource aggregation category to which it belongs.

[0092] In practice, for any distributed energy resource, the computer equipment can obtain bonus element information. The bonus element information includes the basic franchise bonus of the virtual power plant, the franchise capacity of the distributed energy resource, the validity period of the franchise contract, and the degree of demand of the virtual power plant for the distributed energy resource. The bonus element information is input into the pre-built bonus model corresponding to the virtual power plant franchise reward mechanism, and the franchise bonus amount corresponding to any distributed energy resource is output. In this way, the franchise bonus amount corresponding to each resource aggregation category can be determined based on the franchise bonus amount corresponding to each distributed energy resource and the resource aggregation category to which it belongs.

[0093] It should be noted that VPP, as the operating entity for resource aggregation, incentivizes high-quality resources (distributed energy resources with response capabilities meeting preset conditions) to participate by issuing franchise invitations and providing differentiated franchise bonuses to participating DERs. The franchise bonus amount is calculated based on franchise capacity, franchise contract validity period, the virtual power plant's demand for distributed energy resources, and the virtual power plant's basic franchise bonus, ensuring that the incentive mechanism matches resource capabilities and improves overall control efficiency.

[0094] The pre-built bonus model is shown below:

[0095]

[0096] In the formula, For the first The amount of the franchise bonus for each distributed energy resource; The basic franchise bonus set for VPP; For the first The capacity of a distributed energy resource to join; For distributed energy resources The validity period of the franchise agreement; To distinguish the first The bonus gain coefficient of the response performance of the first distributed energy resource characterizes the effect of VPP on the first... The demand level for a distributed energy resource is expressed as follows:

[0097]

[0098] In the formula, The basic incentive coefficient; For the first The response characteristic gain coefficient of each distributed energy resource is set differently according to the aggregated external characteristic requirements of VPP; To ensure the correlation between franchise capacity and bonuses, if the VPP has a high demand for the distributed energy resource, this value can be adjusted appropriately.

[0099] In some embodiments, for each distributed energy resource in the target area, the resource aggregation category to which each distributed energy resource belongs is determined based on the affiliation characteristics and response characteristics corresponding to each distributed energy resource. This includes: clustering each distributed energy resource according to the affiliation characteristics corresponding to each distributed energy resource to obtain a first clustering result; clustering the distributed energy resources in the first clustering result according to the response characteristics corresponding to each distributed energy resource in the first clustering result to obtain a second clustering result; and determining the resource aggregation category to which each distributed energy resource belongs based on the second clustering result.

[0100] In specific implementation, during the process of two-layer clustering and label identification of distributed energy resources, the computer equipment can use the k-means clustering algorithm to classify the extracted features into categories based on resource type, rated capacity, and quarterly output characteristics, thus obtaining the first clustering result. For the response features corresponding to the distributed energy resources in each first clustering result, a second classification is performed based on response type, advance notice time, response adjustment time, duration, response capacity, and response period, ultimately forming a DER multidimensional label data structure. The various DER features and label results can be represented as follows:

[0101]

[0102] In the formula, This is the dataset after the i-th DER classification; For the nth type of DER feature data set; For the first Franchise-related feature data set; For the first DER-like response feature data set; The label is for the nth type of DER.

[0103] In some embodiments, the process of outputting a dynamic aggregation planning scheme for virtual power plant resources transforms the resource aggregation and operation optimization problem of the virtual power plant into a two-layered dynamic programming problem. First, by extracting the joining characteristics, response characteristics, response capability parameters, and joining intentions of the DER (Distributed Energy Provider), the heterogeneity and dynamism of distributed energy resources are comprehensively characterized. Based on this, according to the phased changes in electricity market supply and demand, a set of reconfiguration time series for multiple reconfiguration stages is constructed, establishing aggregation configuration models under different time windows. Subsequently, using a two-layer optimization strategy, modeling and solving are performed simultaneously at both the resource selection and market operation levels, thereby obtaining a VPP (Virtual Power Plant) resource dynamic aggregation scheme with globally optimal returns.

[0104] Specifically, the upper-layer model aims to maximize the return on investment of the virtual power plant, providing resource selection, incentive mechanisms, and contract setup schemes for each stage. The lower-layer model, based on the aggregation results provided by the upper layer, simulates the operation of the VPP in the energy and ancillary services markets, considering factors such as electricity trading, frequency regulation and peak shaving participation revenue, and output volatility risk, dynamically adjusting operational strategies to ensure maximum returns. Through the iterative alternation of the upper and lower-layer models, the VPP aggregation strategy will be continuously optimized until resource combinations and operational returns tend to stabilize.

[0105] The method provided in this embodiment particularly emphasizes fine-grained modeling of resource response risk in the lower-level model, and further introduces financial risk indicators such as CVaR to assess the impact of market price volatility and DER uncertainty on operating returns. For example, for DER resources with high volatility and high uncertainty in return prediction, their membership ratio can be appropriately limited or their membership bonus threshold can be increased during the aggregation phase. Conversely, for DER resources with strong responsiveness and stable output, they can be prioritized for inclusion in the main aggregation queue to ensure that the overall VPP has high controllability and high response efficiency. Through this method, phased and robust return optimization under dynamic restructuring of VPP resources can be achieved, providing a feasible and sustainable strategic decision-making tool for virtual power plants oriented towards market-based operations.

[0106] In some embodiments, such as Figure 2As shown, a decision-making flowchart for a virtual power plant resource aggregation planning method based on dynamic reconfiguration is presented. The method includes the following steps:

[0107] a) At each refactoring stage, construct all possible refactoring timing combinations Ω;

[0108] b) For each combination, establish a two-layer optimization model (virtual power plant resource aggregation and operation two-layer optimization model) with the VPP return on investment as the objective, and optimize the franchise bonus amount, contract duration and resource status;

[0109] c) The upper-level model is a resource aggregation planning model, and the lower-level model is a VPP operation and transaction model. Typical daily scenarios and the CVaR model are used to evaluate returns and risks.

[0110] The upper-level model uses an annual resource operation cycle and a monthly time scale to perform dynamic aggregation planning for virtual power plants. Its objective function is to maximize the aggregated ROI of VPP resources under a single reconfiguration time series combination, as shown below:

[0111]

[0112]

[0113]

[0114] in, Indicates the first of all the reconfiguration timing combinations. One reconstruction sequence; Cost of virtual power plant resource aggregation; For revenue from virtual power plant operations; This includes the affiliate bonus cost paid by the virtual power plant to the distributed energy resource. The costs associated with the modification of terminal equipment and communication, control, and metering involved in the access of the aforementioned distributed energy resources. ; This refers to the franchise bonus amount corresponding to the nth resource aggregation category under the mth reconstruction stage; The resource access cost is the resource cost for the nth type of resource aggregation category. The resource access cost is the same for the same type of resource aggregation category. Let n be the number of member affiliations included in the nth resource aggregation category during the mth reconstruction phase. Let n be the membership status variable for the nth type of resource aggregation category under the mth reconstruction stage, where 1 represents membership and 0 represents non-membership.

[0115] The constraints of the upper-level model include:

[0116]

[0117]

[0118]

[0119]

[0120] in, , These are the upper and lower limits of the franchise bonus amount, respectively; Let n be the franchise capacity corresponding to the nth type of resource aggregation category under the mth reconstruction stage; , These represent the operating revenue of the virtual power plant and the resource aggregation cost of the virtual power plant in the m-th reconstruction stage, respectively. Let $\franchise$ be the utility value of the $n$-th resource aggregation category under the $m$-th reconstruction phase.

[0121] The lower-level model calculates total revenue and operational risk by jointly optimizing the virtual power plant's electricity purchase and sale transactions in the energy market and its peak-shaving and frequency regulation services in the ancillary services market. The objective function is:

[0122]

[0123]

[0124]

[0125] in, Indicates the first of all the reconfiguration timing combinations. One reconstruction sequence; For revenue from virtual power plant operations; , These represent the number of months in the m-th reconstruction phase and the number of months in the m-th reconstruction phase. Number of typical scenarios per month; For the m-th reconstruction stage, the first... The number of days included in a month; For the first The first reconstruction phase Monthly scene The probability of occurrence; , They are respectively the m-th reconstruction stage and the th Monthly scene The virtual power plant operating revenue and virtual power plant resource aggregation cost function are defined below. For the risk function of virtual power plant operation; This represents the risk preference coefficient for virtual power plants. Value at Risk (VaR); Confidence level; For the m-th reconstruction stage, the first... Monthly scene The loss function takes the negative value of the virtual power plant's operating revenue:

[0126]

[0127] The constraints of the lower-level model include power balance constraints, distributed generation constraints, energy storage leasing constraints, load price parameter constraints, distributed energy resource regulation and response constraints, and conditional value of risk constraints.

[0128] In this embodiment, both the upper and lower level models of the two-level optimization model are mixed-integer linear programming models, and they are coupled. This embodiment first constructs a Lagrangian function for the lower level model, and then transforms the lower level model into constraints for the upper level model based on the KKT (Karush-Kuhn-Tucker conditions), resulting in a single-level mixed-integer linear programming model. The transformed single-level mixed-integer linear programming model is then modeled using the modeling toolbox and solved using the solver.

[0129] Taking a distribution network in a certain area of ​​the power grid as an example, a total of 4,866 DERs (Distributed Photovoltaic Power, Wind Power, Cogeneration Units, and Various Controllable Loads) in the power grid of this area are used as VPP (Virtual Power Provider) aggregation objects for case analysis. The VPP resource operation cycle is set to 1 year, and it is divided into 4 reconfiguration stages.

[0130] Figure 3This diagram illustrates the optimal reconfiguration sequence (dynamic aggregation planning scheme for virtual power plant resources) of the VPP under different reconfiguration stages derived by the method of this application. The resource aggregation categories include 20 categories from c1 to c20. Analysis shows that the VPP contracts with generation resources c1 to c5 in each stage to meet load power supply needs. In stage 1, the VPP contracts with peak-shaving resources c6, c13, and c16, frequency regulation resources c5, c11, and c19, and the electricity market response resource c7. These resources all have good responsiveness in this stage. In stage 2, the peak-shaving market service period shifts, and electricity prices increase. The peak-shaving resource c6 contracted in stage 1 is no longer responsive in this stage, so the VPP re-contracts with c9, c13, and c16. Compared to stage 1, frequency regulation market demand further increases, and c11 is no longer responsive in this stage. The VPP re-contracts with c5, c12, c15, c18, and c19, increasing the frequency regulation capacity by 11.17MW. In the electricity market, electricity prices fell, and VPPs primarily consisted of peak-shaving and frequency regulation resources during this phase. In Phase 3, the peak-shaving market experienced negative peak-shaving demand. Based on the response characteristics of various DERs in Table 1, VPPs participated in the negative peak-shaving market by signing contracts for C19 and C20. The positive peak-shaving periods were largely consistent with Phase 2, and C9 lacked responsiveness in this phase; therefore, VPPs renewed contracts for C13 and C16. In Phase 4, peak-shaving market demand periods decreased, and C16 lacked responsiveness in this phase. VPPs renegotiated contracts for C6 and C10 to adapt to changes in market demand. In the frequency regulation market, prices decreased compared to Phase 3, and VPPs renegotiated contracts for C11, C14, and C20, resulting in a 45.21MW reduction in frequency regulation capacity. During peak hours, electricity prices rose in the electricity market. In this phase, C8 and C17 demonstrated good responsiveness, and VPPs reduced peak-hour power shortages by signing contracts for C8 and C17. As the above analysis shows, the method in this embodiment can perform dynamic aggregation planning of VPP based on changes in market demand and resource responsiveness. The details of various DER franchise bonus amounts under the optimal reconstruction sequence are shown in Table 1:

[0131] Table 1

[0132]

[0133] As shown in Table 1, the unit price of DER franchise bonuses varies among different types; the signing capacity of the same type of DER at each stage is not entirely the same as the franchise application capacity, and the signing capacity also differs across stages. This is because the VPP franchise reward target established in this embodiment not only increases the enthusiasm of DER franchisees but also allows the VPP to select high-quality resources that match the current market demand by adjusting the bonus amount. Therefore, the VPP franchise reward mechanism is an important way to identify high-quality resources and an efficient way to obtain higher economic benefits at a lower cost.

[0134] like Figure 4 The diagram illustrates the VPP market trading results at each stage under the optimal reconfiguration timing (the combination of reconfiguration timings with the best return on investment). In Stage 1, from 09:00 to 11:00, the peak-shaving market price is high, and VPPs prioritize participation in the peak-shaving market. From 05:00 to 08:00 and from 18:00 to 21:00, the frequency regulation market price is high, and VPPs prioritize participation in the frequency regulation market. From 03:00 to 07:00 and from 11:00 to 13:00, the electricity market price is low, and VPPs charge their energy storage. From 08:00 to 10:00 and from 18:00 to 22:00, VPPs utilize energy storage discharge to reduce electricity purchase costs. From 08:00 to 13:00, VPPs participate in the energy market by adjusting DER power reduction. Compared to Phase 1, Phase 2 sees an increase in peak-shaving and frequency regulation market service periods and higher electricity prices. Peak-hour electricity prices in the power market further increase. Through resource restructuring, the VPP increases its trading capacity in the peak-shaving market by 43.77 MW·h and in the frequency regulation market by 43.59 MW·h, while reducing its electricity purchases in the power market by 128.87 MW·h. In Phase 3, compared to the previous two phases, peak-shaving market service demand periods increase and electricity prices further rise. The VPP improves its operating revenue by aggregating more peak-shaving resources. In Phase 4, peak-shaving and frequency regulation market demand decreases and electricity prices fall. The VPP participates in the power market by aggregating low-cost resources, reducing electricity purchase costs while increasing electricity sales revenue. In summary, the method in this embodiment enables the VPP to continuously optimize its internal resource composition to adapt to various market demands, thereby improving its operational efficiency.

[0135] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0136] Based on the same inventive concept, this application also provides a device for implementing the above-described method for virtual power plant resource aggregation planning based on dynamic reconfiguration. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more embodiments of the device for virtual power plant resource aggregation planning based on dynamic reconfiguration provided below can be found in the limitations of the method for virtual power plant resource aggregation planning based on dynamic reconfiguration described above, and will not be repeated here.

[0137] In one exemplary embodiment, such as Figure 5 As shown, a virtual power plant resource aggregation planning device based on dynamic reconfiguration is provided, including: a classification module 510, an evaluation module 520, a combination module 530, and a screening module 540, wherein:

[0138] The classification module 510 is used to determine the resource aggregation category of each distributed energy resource in the target area based on the affiliation characteristics and response characteristics of each distributed energy resource; the affiliation characteristics are determined based on the structural attributes and output capabilities of the distributed energy resources; and the response characteristics are determined based on the response behavior parameters of the distributed energy resources.

[0139] The evaluation module 520 is used to output the franchise probability evaluation results corresponding to each of the resource aggregation categories through a pre-trained franchise probability evaluation model, and to determine the franchise capacity corresponding to each of the resource aggregation categories based on the franchise probability evaluation results; the franchise probability evaluation results are used to characterize the probability of distributed energy resources in the corresponding resource aggregation category accepting virtual power plant contracts; the franchise probability evaluation results are determined by the pre-trained franchise probability evaluation model based on a pre-constructed virtual power plant franchise reward mechanism.

[0140] The combination module 530 is used to combine the resource aggregation categories to construct all reconstruction sequence combinations in each reconstruction stage of the resource operation cycle in the target region.

[0141] The screening module 540 is used to jointly optimize resource aggregation schemes and operational strategies through a dual-layer optimization model of virtual power plant resource aggregation and operation, and to select the optimal combination of reconstruction time sequence with the best return on investment in each reconstruction stage as a dynamic aggregation planning scheme for virtual power plant resources. The dual-layer optimization model of virtual power plant resource aggregation and operation is constrained by at least the franchise capacity and franchise bonus amount corresponding to the resource aggregation category. The upper-layer model aims to maximize the return on investment of the virtual power plant, and the lower-layer model aims to maximize operational revenue.

[0142] In one embodiment, the device further includes: an amount determination module, configured to acquire bonus element information for any distributed energy resource; the bonus element information includes the basic franchise bonus of the virtual power plant, the franchise capacity of the any distributed energy resource, the franchise contract validity period, and the demand information of the virtual power plant for the any distributed energy resource; inputting the bonus element information into a pre-built bonus model corresponding to the virtual power plant franchise reward mechanism, and outputting the franchise bonus amount corresponding to the any distributed energy resource; and determining the franchise bonus amount corresponding to each resource aggregation category based on the franchise bonus amount corresponding to each distributed energy resource and the resource aggregation category to which it belongs.

[0143] In one embodiment, the classification module 510 is specifically used to cluster each of the distributed energy resources according to the affiliation characteristics corresponding to each of the distributed energy resources to obtain a first clustering result; to cluster the distributed energy resources in the first clustering result according to the response characteristics corresponding to each of the distributed energy resources in the first clustering result to obtain a second clustering result; and to determine the resource aggregation category to which each of the distributed energy resources belongs according to the second clustering result.

[0144] In one embodiment, the expression for the pre-trained affiliation probability evaluation model is:

[0145]

[0146] in, For the first The probability that a distributed energy resource will accept a virtual power plant contract; For the first The utility value of a franchise contract for a distributed energy resource; Indicates the first The willingness to join a distributed energy resource is expressed as follows: a value of 1 indicates joining, and a value of 0 indicates not joining.

[0147]

[0148]

[0149] In the formula, For the first The self-preference coefficient of a distributed energy resource; , For the corresponding number Weighting coefficients of influencing factors of distributed energy resources; , The first The result is the normalized sum of the franchise bonus amount and the franchise contract validity period for each distributed energy resource.

[0150] In one embodiment, the upper-level model performs dynamic aggregation planning on the virtual power plant with an annual resource operation cycle and a monthly time scale; the objective function of the upper-level model is shown below:

[0151]

[0152]

[0153]

[0154] in, Indicates the first of all the reconfiguration timing combinations. One reconstruction sequence; Cost of virtual power plant resource aggregation; For revenue from virtual power plant operations; This includes the affiliate bonus cost paid by the virtual power plant to the distributed energy resource. The costs associated with the modification of terminal equipment and communication, control, and metering involved in the access of the aforementioned distributed energy resources. ; This refers to the franchise bonus amount corresponding to the nth resource aggregation category under the mth reconstruction stage; The resource access cost is the resource cost for the nth type of resource aggregation category. The resource access cost is the same for the same type of resource aggregation category. Let n be the number of member affiliations included in the nth resource aggregation category during the mth reconstruction phase. Let n be the membership status variable for the nth type of resource aggregation category under the mth reconstruction stage, where 1 represents membership and 0 represents non-membership.

[0155] The constraints of the upper-level model include:

[0156]

[0157]

[0158]

[0159]

[0160] in, , These are the upper and lower limits of the franchise bonus amount, respectively; Let n be the franchise capacity corresponding to the nth type of resource aggregation category under the mth reconstruction stage; , These represent the operating revenue of the virtual power plant and the resource aggregation cost of the virtual power plant in the m-th reconstruction stage, respectively. Let $\franchise$ be the utility value of the $n$-th resource aggregation category under the $m$-th reconstruction phase.

[0161] In one embodiment, the lower-level model calculates total revenue and operational risk by jointly optimizing the virtual power plant's electricity purchase and sale transactions in the energy market and its peak-shaving and frequency regulation services in the ancillary services market. The objective function is:

[0162]

[0163]

[0164]

[0165] in, Indicates the first of all the reconfiguration timing combinations. One reconstruction sequence; For revenue from virtual power plant operations; , These represent the number of months in the m-th reconstruction phase and the number of months in the m-th reconstruction phase. Number of typical scenarios per month; For the m-th reconstruction stage, the first... The number of days included in a month; For the first The first reconstruction phase Monthly scene The probability of occurrence; , They are respectively the m-th reconstruction stage and the th Monthly scene The virtual power plant operating revenue and virtual power plant resource aggregation cost function are defined below. For the risk function of virtual power plant operation; This represents the risk preference coefficient for virtual power plants. Value at Risk (VaR); Confidence level; For the m-th reconstruction stage, the first... Monthly scene The loss function takes the negative value of the virtual power plant's operating revenue:

[0166]

[0167] The constraints of the lower-level model include power balance constraints, distributed generation constraints, energy storage leasing constraints, load price parameter constraints, distributed energy resource regulation and response constraints, and conditional value of risk constraints.

[0168] The modules in the aforementioned virtual power plant resource aggregation and planning device based on dynamic reconfiguration can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0169] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 6 As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides the environment for the operation of the operating system and computer programs in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a virtual power plant resource aggregation planning method based on dynamic reconfiguration. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0170] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0171] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0172] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0173] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0174] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0175] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0176] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0177] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A virtual power plant resource aggregation planning method based on dynamic reconfiguration, characterized in that, The method includes: For each distributed energy resource in the target area, the resource aggregation category to which each distributed energy resource belongs is determined based on the affiliation characteristics and response characteristics of each distributed energy resource; the affiliation characteristics are determined based on the structural attributes and output capacity of the distributed energy resources; the response characteristics are determined based on the response behavior parameters of the distributed energy resources. The pre-trained franchise probability assessment model outputs the franchise probability assessment results for each of the resource aggregation categories, and determines the franchise capacity for each of the resource aggregation categories based on the franchise probability assessment results. The franchise probability assessment results are used to characterize the probability that distributed energy resources in the corresponding resource aggregation category will accept virtual power plant contracts. The franchise probability assessment results are determined by the pre-trained franchise probability assessment model based on a pre-built virtual power plant franchise reward mechanism. In each reconfiguration phase of the resource operation cycle in the target region, the resource aggregation categories are combined to construct all reconfiguration time sequence combinations; Through a dual-layer optimization model of virtual power plant resource aggregation and operation, the resource aggregation scheme and operation strategy are jointly optimized. In each of the reconstruction stages, the reconstruction sequence combination with the optimal return on investment is selected, and the dynamic aggregation planning scheme of virtual power plant resources is displayed. The dual-layer optimization model of virtual power plant resource aggregation and operation is constrained by at least the franchise capacity and franchise reward resource amount corresponding to the resource aggregation category. The upper-layer model aims to maximize the return on investment of the virtual power plant, and the lower-layer model aims to maximize the operating income.

2. The method according to claim 1, characterized in that, The method further includes: For any distributed energy resource, obtain reward resource element information; the reward resource element information includes the basic franchise reward resource amount of the virtual power plant, the franchise capacity of the distributed energy resource, the franchise contract validity period, and the demand information of the virtual power plant for the distributed energy resource. Input the reward resource element information into the pre-built reward resource amount model corresponding to the virtual power plant franchise reward mechanism, and output the franchise reward resource amount corresponding to any distributed energy resource; The amount of franchise reward resources corresponding to each of the distributed energy resources and the resource aggregation category to which they belong is determined.

3. The method according to claim 1, characterized in that, The method involves determining the resource aggregation category of each distributed energy resource in the target area based on its associated characteristics and response characteristics, including: Based on the membership characteristics corresponding to each of the distributed energy resources, the distributed energy resources are clustered to obtain the first clustering result; Based on the response characteristics of the distributed energy resources in each of the first clustering results, the distributed energy resources in the first clustering results are clustered to obtain the second clustering results; Based on the second clustering results, the resource aggregation category to which each of the distributed energy resources belongs is determined.

4. The method according to claim 1, characterized in that, The pre-trained franchise probability assessment model outputs franchise probability assessment results corresponding to each of the resource aggregation categories, including: The expression for the pre-trained franchise probability evaluation model is: in, For the first The probability that a distributed energy resource will accept a virtual power plant contract; For the first The utility value of a franchise contract for a distributed energy resource; Indicates the first The willingness to join a distributed energy resource is expressed as follows: a value of 1 indicates joining, and a value of 0 indicates not joining. In the formula, For the first The self-preference coefficient of a distributed energy resource; , For the corresponding number Weighting coefficients of influencing factors of distributed energy resources; , The first The result is the normalized sum of the reward resources for joining a distributed energy resource and the validity period of the joining contract.

5. The method according to claim 1, characterized in that, The upper-level model performs dynamic aggregation planning on the virtual power plant with an annual resource operation cycle and a monthly time scale; the objective function of the upper-level model is as follows: in, Indicates the first of all the reconfiguration timing combinations. One reconstruction sequence; Cost of virtual power plant resource aggregation; For revenue from virtual power plant operations; This includes the resource cost of the membership incentive paid by the virtual power plant to the distributed energy resources. The costs associated with the modification of terminal equipment and communication, control, and metering involved in the access of the aforementioned distributed energy resources. ; This represents the amount of franchise reward resources corresponding to the nth type of resource aggregation category under the mth reconstruction phase. The resource access cost is the resource cost for the nth type of resource aggregation category. The resource access cost is the same for the same type of resource aggregation category. Let n be the number of member affiliations included in the nth resource aggregation category during the mth reconstruction phase. Let n be the membership status variable for the nth type of resource aggregation category under the mth reconstruction stage, where 1 represents membership and 0 represents non-membership. The constraints of the upper-level model include: in, , These are the upper and lower limits of the amount of franchise reward resources, respectively; Let n be the franchise capacity corresponding to the nth type of resource aggregation category under the mth reconstruction stage; The total franchise capacity declared for the nth type of resource; , These represent the operating revenue of the virtual power plant and the resource aggregation cost of the virtual power plant in the m-th reconstruction stage, respectively. Let $\franchise$ be the utility value of the $n$-th resource aggregation category under the $m$-th reconstruction phase.

6. The method according to claim 1, characterized in that, The lower-level model calculates total revenue and operational risk by jointly optimizing the virtual power plant's electricity purchase and sale transactions in the energy market and its peak-shaving and frequency regulation services in the ancillary services market. The objective function is: in, Indicates the first of all the reconfiguration timing combinations. One reconstruction sequence; For revenue from virtual power plant operations; , These represent the number of months in the m-th reconstruction phase and the number of months in the m-th reconstruction phase. Number of typical scenarios per month; For the m-th reconstruction stage, the first... The number of days included in a month; For the first The first reconstruction phase Monthly scene The probability of occurrence; , They are respectively the m-th reconstruction stage and the th Monthly scene The virtual power plant operating revenue and virtual power plant resource aggregation cost function are defined below. For the risk function of virtual power plant operation; This represents the risk preference coefficient for virtual power plants. Value at Risk (VaR); Confidence level; For the m-th reconstruction stage, the first... Monthly scene The loss function takes the negative value of the virtual power plant's operating revenue: The constraints of the lower-level model include power balance constraints, distributed generation constraints, energy storage leasing constraints, load price parameter constraints, distributed energy resource regulation and response constraints, and conditional value of risk constraints.

7. A virtual power plant resource aggregation planning device based on dynamic reconfiguration, characterized in that, The device includes: The classification module is used to determine the resource aggregation category of each distributed energy resource in the target area based on the associated characteristics and response characteristics of each distributed energy resource; the associated characteristics are determined based on the structural attributes and output capacity of the distributed energy resources; the response characteristics are determined based on the response behavior parameters of the distributed energy resources. The evaluation module is used to output the franchise probability evaluation results corresponding to each of the resource aggregation categories through a pre-trained franchise probability evaluation model, and to determine the franchise capacity corresponding to each of the resource aggregation categories based on the franchise probability evaluation results; the franchise probability evaluation results are used to characterize the probability of distributed energy resources in the corresponding resource aggregation category accepting virtual power plant contracts; the franchise probability evaluation results are determined by the pre-trained franchise probability evaluation model based on a pre-constructed virtual power plant franchise reward mechanism; The combination module is used to combine the resource aggregation categories in each reconstruction stage of the resource operation cycle in the target region to construct all reconstruction sequence combinations; The screening module is used to jointly optimize resource aggregation schemes and operational strategies through a dual-layer optimization model of virtual power plant resource aggregation and operation. In each of the reconstruction stages, it selects the reconstruction sequence combination with the optimal return on investment as the virtual power plant resource dynamic aggregation planning scheme. The dual-layer optimization model of virtual power plant resource aggregation and operation is constrained by at least the franchise capacity and franchise reward resource amount corresponding to the resource aggregation category. The upper-layer model aims to maximize the return on investment of the virtual power plant, while the lower-layer model aims to maximize operational revenue.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images