A virtual power plant construction method, device, equipment and medium

Abstract

This invention discloses a method, apparatus, equipment, and medium for constructing a virtual power plant. The method includes: generating several initial resource combinations based on preset combination generation constraint rules and a standardized resource component library; calling up operational scenario data to simulate the operation of the virtual power plant and obtaining time-series operational data for each initial resource combination; performing multi-dimensional coupling evaluation based on the time-series operational data to obtain evaluation index vectors for each initial resource combination; calculating the relative closeness of each initial resource combination to the ideal solution using the TOPSIS method to obtain the comprehensive coupling degree of each initial resource combination; and determining the final resource combination scheme of the target virtual power plant based on the comprehensive coupling degree to construct the target virtual power plant. This invention can improve the coupling degree of resource component combinations by performing multi-dimensional coupling relationship quantitative analysis of source-storage-load resources during the virtual power plant construction process, thereby enhancing the final collaborative operation effect of the constructed virtual power plant.

Description

Technical Field

[0001] This invention relates to the field of power grid collaborative management technology, and in particular to a method, apparatus, equipment and medium for constructing a virtual power plant. Background Technology

[0002] With the widespread integration of distributed energy resources, energy storage systems, and diversified loads, virtual power plants, as an integrated management model, can aggregate various heterogeneous resources to participate in the operation of the electricity market, thereby improving energy utilization efficiency and system regulation capabilities. During the planning and construction of virtual power plants, the rational allocation of resource components on the source side, energy storage side, and load side directly affects the operational synergy and overall economic benefits of the completed virtual power plant.

[0003] Currently, the resource combination schemes for virtual power plants mainly rely on the experience and judgment of planners or simple rule matching to determine them. Existing methods typically select resources based on single-dimensional technical parameters or economic indicators, such as only considering the matching relationship between renewable energy installed capacity and load scale, or only focusing on the peak-valley arbitrage capability of energy storage systems. This construction approach lacks a systematic quantitative analysis of the synergistic effects of various resources in power balance, time-series distribution, and economic benefits, making it difficult to accurately assess the comprehensive operational effects of different resource combination schemes. As a result, the final construction scheme often fails to achieve optimal resource allocation and coordinated operation. Summary of the Invention

[0004] This invention provides a method, apparatus, equipment, and medium for constructing a virtual power plant. During the construction process of a virtual power plant, it can improve the coupling degree of the resource component combination by performing multi-dimensional quantitative analysis of the coupling relationship between source, storage, and load resources, thereby enhancing the final collaborative operation effect of the constructed virtual power plant.

[0005] In a first aspect, embodiments of the present invention provide a method for constructing a virtual power plant, comprising: Based on preset combination generation constraint rules and a standardized resource component library, several initial resource combinations are generated, and preset operation scenario data are called to perform virtual power plant operation simulation for each initial resource combination, thereby obtaining time-series operation data for each initial resource combination; wherein, the standardized resource component library includes quantitative attribute data of resource components of various dimensions of the virtual power plant; the resource components of each dimension include source-side resource components, energy storage-side resource components, and load-side resource components; Based on the time-series operation data, a multi-dimensional coupling evaluation is performed on each initial resource combination to obtain an evaluation index vector for each initial resource combination. Then, based on the TOPSIS method and the evaluation index vector, the relative closeness between each initial resource combination and the pre-acquired ideal solution is calculated to obtain the comprehensive coupling degree of each initial resource combination. The multi-dimensional coupling evaluation includes power coupling evaluation, time-series coupling evaluation, and economic coupling evaluation. Based on the comprehensive coupling degree, the optimal resource combination is selected from the initial resource combination, and the optimal resource combination is determined as the final resource combination scheme of the target virtual power plant, so as to construct the target virtual power plant according to the final resource combination scheme.

[0006] This invention constructs a pool of solutions to be evaluated, providing diverse candidate objects for subsequent evaluation. Through virtual power plant operation simulation, static resource configuration is transformed into dynamic operational data, ensuring that subsequent evaluations are based on real-world operational scenarios. By acquiring evaluation index vectors, the complex operational process is decomposed into quantifiable multi-dimensional evaluation indicators, achieving a quantitative expression of coupling relationships. Furthermore, through a multi-indicator comprehensive evaluation method, these multi-dimensional indicators are integrated into a single comprehensive coupling degree, facilitating horizontal comparisons between solutions. Finally, the comprehensive coupling degree is used to select the final combined solution, ensuring that the ultimately constructed virtual power plant exhibits superior collaborative operation performance.

[0007] In some preferred embodiments of the first aspect, the step of generating several initial resource combinations based on preset combination generation constraint rules and a standardized resource component library specifically includes: According to the preset heterogeneity coverage strategy, resource components of different dimensions are extracted from the standardized resource component library to form candidate resource combinations; wherein, the heterogeneity coverage strategy is used to ensure that the generated candidate resource combinations cover different source-side capacity gradients and load-side type gradients. According to the preset combination generation constraint rules, the candidate resource combinations are screened to obtain several initial resource combinations; wherein, the combination generation constraint rules include power supply and demand balance constraints and resource coordination constraints.

[0008] The embodiments of the present invention ensure that the generated initial combination covers diverse scenarios with different capacity scales and load types, avoiding the distortion of evaluation results caused by the simplification of the scheme; and ensure that the selected schemes all meet the basic requirements of power supply and demand balance and resource coordination, thus guaranteeing the feasibility of the candidate schemes in engineering.

[0009] In some preferred embodiments of the first aspect, the step of calling preset operating scenario data to perform virtual power plant operation simulation for each of the initial resource combinations, and obtaining time-series operating data for each initial resource combination, specifically includes: Acquire preset operation scenario data; wherein, the operation scenario data includes per-unit value curves of new energy output under different climatic conditions and typical daily load curves of various loads; Based on the initial resource combination, source-load time-series basic data corresponding to the initial resource combination within the scheduling cycle are obtained by matching and combining from the operation scenario data. Based on the source-load time-series basic data, virtual power plant operation simulation is performed to generate time-series operation data corresponding to the initial resource combination. The source-load time-series basic data includes new energy output sequence and load demand sequence. The time-series operation data includes new energy output sequence, energy storage charging and discharging sequence, actual load power sequence, and market-traded electricity.

[0010] This invention, through obtaining source-load time-series basic data, transforms abstract "environmental conditions" into expected output and load curves with specific values ​​specific to each scheme, and uses simulation to recreate the collaborative operation process between resources, ensuring the scientific nature and accuracy of the final time-series operation data.

[0011] In some preferred embodiments of the first aspect, based on the time-series operational data, a multi-dimensional coupled evaluation is performed on each initial resource combination to obtain an evaluation index vector for each initial resource combination, specifically as follows: Based on the time-series operation data, the balance between power supply and demand within the virtual power plant and the effect of mitigating fluctuations in renewable energy output are evaluated to obtain the power coupling evaluation results for each initial resource combination; wherein, the power coupling evaluation results include power balance degree and fluctuation mitigation rate; Based on the time-series operational data, the complementary characteristics of various resources in terms of time distribution and their ability to guarantee load demand during different time periods are evaluated to obtain the time-series coupling evaluation results of each initial resource combination; wherein, the time-series coupling evaluation results include the time-series complementarity rate and full-time coverage. The investment cost data of each resource component is obtained, and combined with the market transaction electricity in the time-series operation data, the comprehensive economic benefits of coordinated operation are evaluated to obtain the economic coupling evaluation results of each initial resource combination; wherein, the economic coupling evaluation results include cost amortization rate and revenue improvement rate; The power coupling assessment results, timing coupling assessment results, and economic coupling assessment results are integrated to form an evaluation index vector for each initial resource combination.

[0012] This invention decomposes the abstract "coupling relationship" into three quantifiable dimensions: power, timing, and economy. Each dimension produces specific evaluation results, making the synergistic effect between resources clear, visible, and quantifiable, thus laying a data foundation for subsequent comprehensive evaluation.

[0013] In some preferred embodiments of the first aspect, the step of calculating the relative closeness between each initial resource combination and the pre-acquired ideal solution based on the TOPSIS method and the evaluation index vector, and obtaining the comprehensive coupling degree of each initial resource combination, specifically involves: The objective weights of each evaluation index in the evaluation index vector are determined by the entropy weight method, and the positive ideal solution and negative ideal solution of each evaluation index in the evaluation index vector are determined according to the objective weights. Based on the objective weights, the positive ideal solution, and the negative ideal solution, calculate the first distance between each initial resource combination and the positive ideal solution, and the second distance between each initial resource combination and the negative ideal solution. By combining the first distance and the second distance, the overall coupling degree of the corresponding initial resource combination is calculated.

[0014] This invention, through determining the objective weights of various evaluation indicators, avoids the subjectivity of manually setting weights, making the evaluation results more objective and fair. Furthermore, by determining the positive and negative ideal solutions of each evaluation indicator, an evaluation benchmark based on the data itself is established, making the evaluation results more scientific and credible. By calculating the first and second distances, the differences between multi-dimensional indicators are transformed into calculable Euclidean distances, achieving a quantitative expression of the differences between schemes. Finally, by calculating the comprehensive coupling degree, complex multi-dimensional information is integrated into an intuitive numerical value, enabling decision-makers to clearly judge the comprehensive advantages and disadvantages of each scheme.

[0015] In some preferred embodiments of the first aspect, the optimal resource combination is selected from the initial resource combination based on the overall coupling degree, specifically as follows: The initial resource combinations are sorted in descending order according to the comprehensive coupling degree. Each initial resource combination with a comprehensive coupling degree higher than the preset comprehensive coupling degree threshold is selected to obtain the optimal combination sequence. The initial resource combination with the highest comprehensive coupling degree in the optimal combination sequence is determined as the candidate optimal combination. Extract the evaluation index vector of the candidate optimal combination and compare it with the preset evaluation index threshold to determine whether there are any weak indicators that are lower than the corresponding evaluation index threshold. If there is no bottleneck indicator, the candidate optimal combination is determined as the optimal resource combination; if there is a bottleneck indicator, the next in line initial resource combination in the optimal combination sequence is determined as the candidate optimal combination, and the bottleneck indicator is judged on the current candidate optimal combination until an initial resource combination without a bottleneck indicator is selected from the optimal combination sequence and determined as the optimal resource combination.

[0016] This invention introduces a dual screening mechanism of comprehensive coupling degree ranking and weakness index verification to ensure that the final selected solution not only has good overall synergy, but also has balanced development in all dimensions without significant defects, thus avoiding the risk of poor actual operation due to poor performance of a single indicator.

[0017] Among the preferred options in the first aspect are: If each resource combination in the optimal combination sequence has a weak link indicator, then the initial resource combination with the highest comprehensive coupling degree in the optimal combination sequence is determined as the candidate optimal combination. Extract the types of the bottleneck indicators of the candidate optimal combination, and adjust the corresponding resource components in the candidate optimal combination according to the types of the bottleneck indicators until the optimal resource combination with preset combination conditions is obtained; wherein, the component adjustment includes component parameter adjustment and component type replacement; the preset combination conditions are that the overall coupling degree is higher than the preset overall coupling degree threshold and each evaluation indicator is higher than the corresponding evaluation indicator threshold.

[0018] This invention, when all solutions are imperfect, selects the solution closest to the target as the starting point for optimization, avoiding blind adjustments and improving adjustment efficiency; iterative optimization continuously improves the originally flawed solutions, ultimately obtaining a combination that meets the requirements, ensuring that the optimal combination that meets the requirements can be output under any circumstances.

[0019] Secondly, embodiments of the present invention provide a virtual power plant construction device, including a power plant operation simulation module, a coupling degree calculation module, and a virtual power plant construction module, wherein... The power plant operation simulation module is used to generate several initial resource combinations based on preset combination generation constraint rules and a standardized resource component library, and to call preset operation scenario data to perform virtual power plant operation simulation for each initial resource combination, thereby obtaining time-series operation data for each initial resource combination; wherein, the standardized resource component library includes quantitative attribute data of resource components of various dimensions of the virtual power plant; the resource components of each dimension include source-side resource components, energy storage-side resource components, and load-side resource components; The coupling degree calculation module is used to perform multi-dimensional coupling evaluation on each initial resource combination based on the time-series running data, obtain the evaluation index vector of each initial resource combination, and calculate the relative closeness of each initial resource combination to the pre-acquired ideal solution according to the TOPSIS method and the evaluation index vector, so as to obtain the comprehensive coupling degree of each initial resource combination; wherein, the multi-dimensional coupling evaluation includes power coupling evaluation, time-series coupling evaluation and economic coupling evaluation. The virtual power plant construction module is used to select the optimal resource combination from the initial resource combination based on the comprehensive coupling degree, and determine the optimal resource combination as the final resource combination scheme of the target virtual power plant, so as to construct the target virtual power plant according to the final resource combination scheme.

[0020] This invention employs a power plant operation simulation module to construct a pool of schemes to be evaluated, providing diverse candidate objects for subsequent evaluation. Through virtual power plant operation simulation, static resource configuration is transformed into dynamic operational data, ensuring that subsequent evaluations are based on realistic operational scenarios. A coupling degree calculation module obtains evaluation index vectors, breaking down the complex operational process into quantifiable multi-dimensional evaluation indicators, achieving a quantitative expression of coupling relationships. A multi-indicator comprehensive evaluation method integrates these multi-dimensional indicators into a single comprehensive coupling degree, facilitating horizontal comparisons between schemes. Finally, a virtual power plant construction module selects the final combination scheme based on the comprehensive coupling degree, ensuring that the ultimately constructed virtual power plant exhibits superior collaborative operation performance.

[0021] Thirdly, embodiments of the present invention provide a terminal device, including: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other through the communication bus; The memory is used to store at least one executable instruction that causes the processor to perform operations as described in any of the above-described methods for constructing a virtual power plant.

[0022] Fourthly, embodiments of the present invention provide a computer-readable storage medium comprising a stored computer program, wherein the computer program, when running, controls the device or apparatus containing the computer-readable storage medium to execute the virtual power plant construction method as described in any of the preceding claims.

[0023] The above description is merely an overview of the technical solutions of the embodiments of the present invention. In order to better understand the technical means of the embodiments of the present invention and to implement them in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the embodiments of the present invention more apparent and understandable, specific embodiments of the present invention are described below. Attached Figure Description

[0024] Figure 1 This is a schematic diagram of a virtual power plant construction method provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the initial resource combination acquisition process provided in an embodiment of the present invention; Figure 3 This is a structural diagram of a virtual power plant construction device provided in an embodiment of the present invention. Detailed Implementation

[0025] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0026] Example 1: like Figure 1 As shown, an embodiment of the present invention provides a method for constructing a virtual power plant, comprising: S101, based on preset combination generation constraint rules and a standardized resource component library, generate several initial resource combinations, and call preset operation scenario data to perform virtual power plant operation simulation for each initial resource combination, thereby obtaining time-series operation data for each initial resource combination; wherein, the standardized resource component library includes quantitative attribute data of resource components of various dimensions of the virtual power plant; the resource components of each dimension include source-side resource components, energy storage-side resource components, and load-side resource components; In this embodiment, generating several initial resource combinations according to preset combination generation constraint rules and a standardized resource component library specifically involves: extracting resource components of different dimensions from the standardized resource component library according to a preset heterogeneity coverage strategy to form candidate resource combinations; wherein, the heterogeneity coverage strategy is used to ensure that the generated candidate resource combinations cover different source-side capacity gradients and load-side type gradients; and filtering the candidate resource combinations according to preset combination generation constraint rules to obtain several initial resource combinations; wherein, the combination generation constraint rules include power supply and demand balance constraints and resource coordination constraints.

[0027] Optionally, the constraint rules generated according to the preset combination include capacity matching constraints, technology matching constraints, and heterogeneity coverage constraints.

[0028] Optionally, the capacity matching constraint is: Total source-side capacity = Storage-side power capacity + Load-side total capacity ±10% (to avoid severe power imbalance); Storage-side energy capacity ≥ Source-side maximum daily output fluctuation × 4h (to ensure smoothing of fluctuations).

[0029] Optionally, the technology matching constraint is: Total source-side capacity = Storage-side power capacity + Load-side total capacity ±10% (to avoid severe power imbalance); Storage-side energy capacity ≥ Source-side maximum daily output fluctuation × 4h (to ensure smoothing of fluctuations).

[0030] Optionally, the heterogeneity coverage constraint is: Total source-side capacity = Storage-side power capacity + Load-side total capacity ±10% (to avoid severe power imbalance); Storage-side energy capacity ≥ Source-side maximum daily output fluctuation × 4h (to ensure smoothing of fluctuations).

[0031] In one specific embodiment, the process of constructing a standardized resource original configuration component library is as follows: A three-dimensional standardized resource original configuration component library of "source-storage-load" is pre-constructed, engineering constraint rules are set, and an initial resource combination covering "capacity gradient, type gradient, and scenario gradient" is automatically generated through a computer-based stratified sampling and constraint verification algorithm, avoiding the randomness of manual selection. The library is then split according to the core resource dimensions of the virtual power plant, with each dimension further divided into basic component types, each assigned a unique identifier and quantifiable attributes. Table 1 shows an excerpt of the standardized resource original configuration component library.

[0032] Table 1. Excerpt from the Standardized Resource Original Configuration Component Library In one specific embodiment, the process of screening based on the heterogeneity coverage strategy is as follows: A stratified sampling + constraint verification algorithm is used to automatically generate initial combinations. The core process is as follows: The differences between heterogeneous resource combinations are concentrated in two dimensions: "source-side capacity scale" and "load-side type attribute". Stratified sampling can ensure that there are representative combinations for each core dimension. The sampling definition execution logic is as follows: (1) Layer definition: Five core layers are defined in the algorithm in advance (corresponding to the five combinations to be output in the end) to ensure full gradient coverage: Layer 1 is small capacity source side + commercial / residential load; Layer 2 is medium capacity source side + residential load; Layer 3 is large capacity source side + industrial load; Layer 4 is medium capacity source side + fixed industrial load (no adjustment capability, supplementing special scenarios); Layer 5 is medium and large capacity source side + agricultural / commercial mixed load.

[0033] (2) Component extraction: For each layer, the algorithm randomly extracts matching “source side + storage side + load side” components from the standardized component library: the source side is selected according to the capacity gradient of the layer (e.g., only photovoltaic / wind power with >300MW is extracted for layer 3); the storage side is adapted according to the load side type (e.g., large-capacity energy storage is selected first for industrial load layer, and small-capacity energy storage is selected for residential load layer); the load side is extracted according to the type gradient of the layer (e.g., commercial + agricultural load is extracted for layer 5).

[0034] For example, as shown in Table 2, Table 2 is the basis for dividing the two dimensions of "source-side capacity scale" and "load-side type attribute".

[0035] Table 2. Basis for Heterogeneity Dimension Classification It should be noted that stratified sampling only addresses "heterogeneous coverage," but may result in invalid combinations such as "capacity imbalance" and "technological incompatibility" (e.g., wind power + small-scale energy storage, source-side capacity far exceeding the total capacity of storage + load). Constraint verification uses three layers of rules for filtering to ensure that the combination conforms to the actual engineering situation.

[0036] For example, the constraint verification logic for resource combinations can be found in Table 3.

[0037] Table 3. Constraint Verification Logic for Resource Combinations Optionally, if the number of valid combinations after constraint verification is less than the preset number (e.g., 5), the algorithm repeats the "stratified sampling → constraint verification" process until a sufficient number of valid combinations are generated.

[0038] Optionally, the algorithm generates a unique identifier for valid combinations based on "source-side type + storage-side capacity + load-side type" and eliminates duplicate combinations (such as generating "300MW PV + medium energy storage + commercial load" in both samplings).

[0039] To more clearly illustrate the process and implementation principle of obtaining the initial resource combination in this invention, the specific implementation flow can be found as follows: Figure 2 The diagram shows the initial resource combination acquisition process.

[0040] In this embodiment, the step of calling preset operation scenario data to perform virtual power plant operation simulation for each of the initial resource combinations and obtaining time-series operation data for each initial resource combination specifically involves: acquiring preset operation scenario data; wherein, the operation scenario data includes per-unit curves of renewable energy output under different climatic conditions and typical daily load curves of various types of loads; matching and combining source-load time-series basic data for the corresponding initial resource combination within the scheduling cycle from the operation scenario data according to the initial resource combination, and performing virtual power plant operation simulation based on the source-load time-series basic data to generate time-series operation data for the corresponding initial resource combination; wherein, the source-load time-series basic data includes renewable energy output sequences and load demand sequences; the time-series operation data includes renewable energy output sequences, energy storage charging and discharging sequences, actual load power sequences, and market-traded electricity.

[0041] S102, based on the time-series operation data, perform multi-dimensional coupling evaluation on each initial resource combination to obtain the evaluation index vector of each initial resource combination, and calculate the relative closeness of each initial resource combination to the pre-acquired ideal solution according to the TOPSIS method and the evaluation index vector to obtain the comprehensive coupling degree of each initial resource combination; wherein, the multi-dimensional coupling evaluation includes power coupling evaluation, time-series coupling evaluation and economic coupling evaluation. In this embodiment, based on the time-series operational data, a multi-dimensional coupling evaluation is performed on each initial resource combination to obtain an evaluation index vector for each initial resource combination. Specifically, based on the time-series operational data, the balance between power supply and demand within the virtual power plant and the effect of mitigating fluctuations in renewable energy output are evaluated to obtain the power coupling evaluation results for each initial resource combination; wherein, the power coupling evaluation results include power balance degree and fluctuation mitigation rate; based on the time-series operational data, the complementary characteristics of various resources in time distribution and their ability to guarantee load demand during specific periods are evaluated to obtain the time-series coupling evaluation results for each initial resource combination; wherein, the time-series coupling evaluation results include time-series complementarity rate and full-time coverage; investment cost data for each resource component is obtained, and combined with market transaction electricity in the time-series operational data, the comprehensive economic benefits of coordinated operation are evaluated to obtain the economic coupling evaluation results for each initial resource combination; wherein, the economic coupling evaluation results include cost amortization rate and revenue improvement rate; the power coupling evaluation results, time-series coupling evaluation results, and economic coupling evaluation results are integrated to form the evaluation index vector for each initial resource combination.

[0042] For example, the evaluation index system of power coupling, timing coupling and economic coupling in the embodiments of the present invention is shown in Table 4.

[0043] Table 4. Evaluation index system for coupling degree in each dimension In one specific embodiment, the power coupling degree is calculated as follows: the evaluation index of power coupling is the power balance degree (… ), volatility reduction rate ( ).

[0044] Power balance ( The value represents the degree of power supply and demand matching within the virtual power plant; the closer to 1, the better the matching. (Power balance) The formula for calculating the positive indicator is as follows: in, The number of time-series sampling points within the scheduling period (e.g., 15-minute sampling per day). ); for The total output of the virtual power plant at any given time (kW) includes photovoltaic, wind power, energy storage discharge, and grid interaction power (purchases are positive, sales are negative). for The total load (kW) of the virtual power plant at any given time includes both fixed and adjustable loads; To avoid distortion of the deviation ratio in low-power scenarios, the maximum values ​​on both the supply and demand sides are used as the benchmark.

[0045] It should be noted that power balance ( The calculation logic is as follows: first calculate the relative supply and demand deviation at each time point, then take the average value within the period. The closer X1 is to 1, the more stable the supply and demand matching is throughout the period, and there is no significant imbalance.

[0046] Volatility reduction rate ( ) represents the effect of energy storage on mitigating fluctuations in the output of new energy sources (photovoltaics + wind power), with the fluctuation mitigation rate ( The formula for calculating the positive indicator is as follows: in, To smooth out the standard deviation (kW) of power output from previous renewable energy sources; The standard deviation (kW) of new energy output after the level suppression of energy storage charging and discharging.

[0047] It should be noted that the volatility smoothing rate ( The calculation logic is as follows: the smaller the standard deviation, the smoother the fluctuation, and the better the index value.

[0048] In one specific embodiment, the temporal coupling degree is calculated as follows: the evaluation index of temporal coupling is the temporal complementarity rate (…). ), full-time coverage ( ).

[0049] Temporal complementarity ( To quantify the degree to which diverse resources "offset peaks and complement troughs" over time, and to avoid the limitation of the original correlation coefficient mean being unable to distinguish between "no correlation" and "negative correlation," the time-series complementarity rate (TSR) is used. The formula for calculating the positive indicator is as follows: in, The number of resource types participating in time-series coupling (e.g., solar, wind, energy storage, adjustable load), ); For the first Class resources and the first Pearson correlation coefficient of intraday time-series output (or load) of resource type (values ​​[-1, 1]); This represents the total number of pairs of resource types (ensuring full coverage of coupling relationships).

[0050] It should be noted that the temporal complementarity rate ( The calculation logic for ) is as follows: like (Perfectly negative correlation, optimal peak-shifting and complementary), then the contribution of this item is ; like (Perfectly positive correlation, no complementarity), then the contribution of this item is ; like (Unrelated), contribution level is This reflects the potential for basic complementarity; final The value is [0,1]. The closer it is to 1, the stronger the temporal complementarity between resources and the more stable the output throughout the entire cycle.

[0051] Full-time coverage ( ) is the ability to guarantee load throughout all times for resource collaborative operation, and the coverage throughout all times ( The formula for calculating the positive indicator is as follows: in, The number of time periods to meet load demand (e.g., 96 15-minute time periods per day, if 80 are met, then count as 80). This represents the total number of scheduling periods (e.g., T=96 for daily scheduling); the constraint is that the load must meet the standard of actual power supply ≥ 95% of the load power.

[0052] In one specific embodiment, the economic coupling degree is calculated as follows: the evaluation index of economic coupling is the cost sharing rate ( ), Profitability Improvement Rate ) Cost allocation rate ( The percentage of unit investment cost reduced for collaborative operation, cost sharing rate ( The formula for calculating the positive indicator is as follows: in, Total investment cost (in ten thousand yuan) for each type of resource separately; Total investment cost for resource synergy (including shared equipment and integration costs, in RMB 10,000).

[0053] For example, if the investment in photovoltaics alone is 5 million, energy storage alone is 3 million, and the combined investment is 7.5 million, then... .

[0054] Profitability improvement rate ( ) represents the revenue increase rate compared to operating independently, with the revenue improvement rate being ( The formula for calculating the positive indicator is as follows: in, Total revenue from the separate operation of various resources (new energy grid connection + energy storage arbitrage + load response, in ten thousand yuan). The total revenue from resource synergy (including the added value from multi-resource complementarity, in ten thousand yuan).

[0055] Preferably, for all evaluation indicators, the range standardization method is used to eliminate the influence of dimensions: in, This is the standardized value of the j-th indicator for the i-th evaluation object (e.g., a virtual power plant resource combination scheme) (values ​​[0,1]). Let be the original value of the j-th indicator for the i-th evaluation object; : The maximum value of the j-th indicator (the optimal value in the sample); It is the minimum value of the j-th indicator (the worst value in the sample).

[0056] Optionally, the rules for handling anomalies in evaluation indicators are as follows: If (If there is no difference in the indicators), then (Default is medium level); if the original data is missing, the mean of the same indicator for similar evaluation objects will be used to fill the gap; if the original data exceeds... The range is truncated by boundary values ​​(to avoid interference from outliers).

[0057] In one specific embodiment, the initial combination evaluation process is as follows: Following the detailed data collection guidelines for each combination described above, data on six core indicators—power, timing, and economic dimensions—are collected for each combination. Noise is removed using a filtering algorithm, and dimensional differences are eliminated using range standardization. The weights of each indicator are objectively determined using the entropy weight method. The Euclidean distance between each initial combination and the same ideal combination is calculated based on the TOPSIS method, yielding the overall coupling degree C (value [0,1]). According to the coupling degree grading standard (C≥0.8 for high coupling, 0.5≤C<0.8 for medium coupling, and C<0.5 for low coupling), the shortcomings of each combination (such as insufficient power balance, low timing complementarity, etc.) are identified, providing a targeted basis for fine-tuning.

[0058] In this embodiment, the step of calculating the relative proximity between each initial resource combination and the pre-obtained ideal solution based on the TOPSIS method and the evaluation index vector to obtain the comprehensive coupling degree of each initial resource combination specifically involves: determining the objective weights of each evaluation index in the evaluation index vector using the entropy weight method, and determining the positive and negative ideal solutions of each evaluation index in the evaluation index vector based on the objective weights; calculating the first distance between each initial resource combination and the positive ideal solution, and the second distance between each initial resource combination and the negative ideal solution based on the objective weights, the positive ideal solution, and the negative ideal solution; and calculating the comprehensive coupling degree of the corresponding initial resource combination by combining the first and second distances.

[0059] In one specific embodiment, the weights of each indicator are objectively determined using the entropy weight method to avoid subjective bias. The steps are as follows: Calculate the weight of the i-th evaluation object under the j-th indicator: Wherein, the constraint is if ,but (To avoid meaningless logarithmic operations); The number of evaluation objects (e.g., the number of different resource combination schemes); Furthermore, calculate the entropy value of the j-th index: It should be noted that entropy has the following meaning: The closer an indicator is to 0, the higher its dispersion, the greater the amount of information it contains, and the higher its weight should be. Furthermore, calculate the difference coefficient for the j-th indicator: It should be noted that the larger the difference coefficient, the stronger the indicator's ability to distinguish the evaluation objects; Furthermore, calculate the weight of the j-th indicator: It should be noted that, ( (i.e., 6 evaluation indicators), the final output weight vector W=[ ].

[0060] In one specific embodiment, the process of calculating the overall coupling degree using the TOPSIS method involves: solving for the preconditions; collecting... One evaluation object (e.g.) The original data of 6 indicators for a virtual power plant resource combination scheme were used to form... Data Matrix Scheduling period (e.g., 96 15-minute intervals per day), Pearson correlation coefficient confidence level (95%), outlier truncation threshold (±10%); calculate the weighted standardized matrix. ( ); Furthermore, determine the ideal solution. With negative ideal solution : Furthermore, the Euclidean distance between the evaluation object and the ideal solution is calculated: , Furthermore, calculate the overall coupling degree. : ( (The closer to 1, the higher the coupling degree) S103, based on the comprehensive coupling degree, select the optimal resource combination from the initial resource combination, and determine the optimal resource combination as the final resource combination scheme of the target virtual power plant, so as to construct the target virtual power plant according to the final resource combination scheme.

[0061] In this embodiment, the optimal resource combination is selected from the initial resource combinations based on the comprehensive coupling degree. Specifically, the initial resource combinations are sorted in descending order according to the comprehensive coupling degree, and the initial resource combinations with a comprehensive coupling degree higher than a preset threshold are selected to obtain an optimal combination sequence. The initial resource combination with the highest comprehensive coupling degree in the optimal combination sequence is determined as a candidate optimal combination. The evaluation index vector of the candidate optimal combination is extracted and compared with the preset evaluation index thresholds to determine whether there are any shortcomings in the corresponding evaluation index thresholds. If there are no shortcomings in the indicators, the candidate optimal combination is determined as the optimal resource combination. If there are shortcomings in the indicators, the next-ranked initial resource combination in the optimal combination sequence is determined as a candidate optimal combination, and the current candidate optimal combination is judged for its shortcomings in the indicators. This process continues until an initial resource combination without any shortcomings in the optimal combination sequence is selected and determined as the optimal resource combination.

[0062] For example, the application scenarios for coupling degree calculation are as follows: Coupling degree It is in a highly coupled state, with excellent resource coordination effect, and can be directly used for scheduling optimization; In a state of medium coupling, the weakest link indicators need to be optimized in a targeted manner; The system is in a loosely coupled state, and the resource composition needs to be restructured.

[0063] In this embodiment, the method further includes: if each resource combination in the optimal combination sequence has a bottleneck indicator, then the initial resource combination with the highest comprehensive coupling degree in the optimal combination sequence is determined as a candidate optimal combination; the type of bottleneck indicator of the candidate optimal combination is extracted, and the corresponding resource components in the candidate optimal combination are adjusted according to the type of bottleneck indicator until the optimal resource combination with preset combination conditions is obtained; wherein, the component adjustment includes component parameter adjustment and component type replacement; the preset combination condition is that the comprehensive coupling degree is higher than the preset comprehensive coupling degree threshold and each evaluation indicator is higher than the corresponding evaluation indicator threshold.

[0064] In one specific embodiment, the fine-tuning constraints are as follows: (1) Capacity boundary constraints: After fine-tuning, the capacity of each resource must strictly fall within the range of the standardized component library (e.g., photovoltaic 200-350MW, energy storage 30-200MW), and it is strictly forbidden to exceed the upper limit of the actual capacity of the project; (2) Gradient preservation constraint: The source-side capacity gradient (small / medium / large) and the load-side type gradient do not change due to fine-tuning, ensuring heterogeneity coverage; (3) Secondary verification threshold: After fine-tuning, constraint verification needs to be re-executed. Capacity matching deviation ≤ ±10%, technical adaptation compliance, and single-category indicators must reach the above-mentioned compliance thresholds to avoid new collaborative failures caused by fine-tuning. (4) Iterative fine-tuning constraint: If the indicator fails to meet the standard after a single fine-tuning, iterative fine-tuning can be carried out (up to 2 times), with the cumulative increase not exceeding 30% of the initial capacity, to control the increase in investment.

[0065] In one specific embodiment, for all the fine-tuned combinations, a comprehensive coupling degree evaluation is performed again, and the final preferred combination is selected according to the following criteria: (1) Core indicators meet the standards: The overall coupling degree C≥0.8 (high coupling), all 6 core indicators are better than the initial combination, and there are no obvious shortcomings; (2) Heterogeneity preservation: The preferred combination should cover the initial 5 hierarchical gradients to avoid clustering of single-type combinations; (3) Economic efficiency of the project: The total investment increase after the fine adjustment is ≤10%, and the profit improvement rate is ≥0.15, which meets the cost control requirements.

[0066] The final output is the optimal combination, which is the recommended optimal combination.

[0067] This invention constructs a pool of solutions to be evaluated, providing diverse candidate objects for subsequent evaluation. Through virtual power plant operation simulation, static resource configuration is transformed into dynamic operational data, ensuring that subsequent evaluations are based on real-world operational scenarios. By acquiring evaluation index vectors, the complex operational process is decomposed into quantifiable multi-dimensional evaluation indicators, achieving a quantitative expression of coupling relationships. Furthermore, through a multi-indicator comprehensive evaluation method, these multi-dimensional indicators are integrated into a single comprehensive coupling degree, facilitating horizontal comparisons between solutions. Finally, the comprehensive coupling degree is used to select the final combined solution, ensuring that the ultimately constructed virtual power plant exhibits superior collaborative operation performance.

[0068] Example 2: like Figure 3 As shown, this embodiment provides a virtual power plant construction device, including a power plant operation simulation module 201, a coupling degree calculation module 202, and a virtual power plant construction module 203, wherein... The power plant operation simulation module 201 is used to generate several initial resource combinations according to preset combination generation constraint rules and a standardized resource component library, and to call preset operation scenario data to perform virtual power plant operation simulation for each initial resource combination, thereby obtaining time-series operation data for each initial resource combination; wherein, the standardized resource component library includes quantitative attribute data of resource components of various dimensions of the virtual power plant; the resource components of each dimension include source-side resource components, energy storage-side resource components, and load-side resource components; In this embodiment, the power plant operation simulation module 201 generates several initial resource combinations according to preset combination generation constraint rules and a standardized resource component library. Specifically, the power plant operation simulation module 201 extracts resource components of different dimensions from the standardized resource component library according to a preset heterogeneity coverage strategy to form candidate resource combinations. The heterogeneity coverage strategy is used to ensure that the generated candidate resource combinations cover different source-side capacity gradients and load-side type gradients. The candidate resource combinations are screened according to the preset combination generation constraint rules to obtain several initial resource combinations. The combination generation constraint rules include power supply and demand balance constraints and resource coordination constraints.

[0069] In this embodiment, the power plant operation simulation module 201 calls preset operation scenario data to perform virtual power plant operation simulation for each of the initial resource combinations, obtaining time-series operation data for each initial resource combination. Specifically, the power plant operation simulation module 201 acquires preset operation scenario data; wherein, the operation scenario data includes per-unit curves of renewable energy output under different climatic conditions and typical daily load curves of various types of loads; according to the initial resource combination, it matches and combines the source-load time-series basic data of the corresponding initial resource combination within the scheduling cycle from the operation scenario data, and performs virtual power plant operation simulation based on the source-load time-series basic data to generate time-series operation data for the corresponding initial resource combination; wherein, the source-load time-series basic data includes renewable energy output sequence and load demand sequence; the time-series operation data includes renewable energy output sequence, energy storage charging and discharging sequence, actual load power sequence, and market-traded electricity.

[0070] The coupling degree calculation module 202 is used to perform multi-dimensional coupling evaluation on each initial resource combination based on the time-series operation data, obtain the evaluation index vector of each initial resource combination, and calculate the relative closeness of each initial resource combination to the pre-acquired ideal solution according to the TOPSIS method and the evaluation index vector, so as to obtain the comprehensive coupling degree of each initial resource combination; wherein, the multi-dimensional coupling evaluation includes power coupling evaluation, time-series coupling evaluation and economic coupling evaluation; In this embodiment, the coupling degree calculation module 202 performs multi-dimensional coupling evaluation on each initial resource combination based on the time-series operation data to obtain an evaluation index vector for each initial resource combination. Specifically, the coupling degree calculation module 202 evaluates the balance between power supply and demand within the virtual power plant and the effect of smoothing out fluctuations in new energy output based on the time-series operation data to obtain the power coupling evaluation result for each initial resource combination; wherein, the power coupling evaluation result includes power balance degree and fluctuation smoothing rate; based on the time-series operation data, it evaluates the complementary characteristics of various resources in time distribution and their ability to guarantee load demand during specific periods to obtain the time-series coupling evaluation result for each initial resource combination; wherein, the time-series coupling evaluation result includes time-series complementarity rate and full-time coverage; it acquires the investment cost data of each resource component and, combined with the market transaction electricity in the time-series operation data, evaluates the comprehensive economic benefits of coordinated operation to obtain the economic coupling evaluation result for each initial resource combination; wherein, the economic coupling evaluation result includes cost amortization rate and revenue improvement rate; and integrates the power coupling evaluation result, the time-series coupling evaluation result, and the economic coupling evaluation result to form the evaluation index vector for each initial resource combination.

[0071] In this embodiment, the coupling degree calculation module 202 calculates the relative proximity between each initial resource combination and the pre-acquired ideal solution based on the TOPSIS method and the evaluation index vector, thereby obtaining the comprehensive coupling degree of each initial resource combination. Specifically, the coupling degree calculation module 202 determines the objective weights of each evaluation index using the entropy weight method based on the evaluation index vector, and determines the positive and negative ideal solutions for each evaluation index based on the evaluation index vector and the objective weights. Based on the evaluation index vector, the objective weights of each evaluation index, the positive and negative ideal solutions, the module calculates the first distance between each initial resource combination and the positive ideal solution and the second distance between each initial resource combination and the negative ideal solution. Combining the first and second distances, the module calculates the comprehensive coupling degree of the corresponding initial resource combination.

[0072] The virtual power plant construction module 203 is used to select the optimal resource combination from the initial resource combination according to the comprehensive coupling degree, and determine the optimal resource combination as the final resource combination scheme of the target virtual power plant, so as to construct the target virtual power plant according to the final resource combination scheme.

[0073] In this embodiment, the virtual power plant construction module 203 selects the optimal resource combination from the initial resource combinations based on the comprehensive coupling degree. Specifically, the virtual power plant construction module 203 sorts each initial resource combination in descending order according to the comprehensive coupling degree, selects each initial resource combination with a comprehensive coupling degree higher than a preset threshold, obtains the optimal combination sequence, and determines the initial resource combination with the highest comprehensive coupling degree in the optimal combination sequence as the candidate optimal combination; extracts the evaluation index vector of the candidate optimal combination, and compares it with each preset evaluation index threshold to determine whether there is a shortcoming index lower than the corresponding evaluation index threshold; if there is no shortcoming index, the candidate optimal combination is determined as the optimal resource combination; if there is a shortcoming index, the next-ranked initial resource combination in the optimal combination sequence is determined as the candidate optimal combination, and the current candidate optimal combination is judged for shortcoming index until an initial resource combination without shortcoming index is selected from the optimal combination sequence and determined as the optimal resource combination.

[0074] For a more detailed explanation of the working principle and procedures of this embodiment, please refer to the relevant description in Embodiment 1.

[0075] In this embodiment of the invention, a power plant operation simulation module 201 constructs a pool of schemes to be evaluated, providing diverse candidate objects for subsequent evaluation. Through virtual power plant operation simulation, static resource configuration is transformed into dynamic operation data, enabling subsequent evaluation to be based on real operation scenarios. Through the coupling degree calculation module 202, evaluation index vectors are obtained, decomposing the complex operation process into quantifiable multi-dimensional evaluation indicators, realizing the quantitative expression of coupling relationships. Through a multi-index comprehensive evaluation method, multi-dimensional indicators are integrated into a single comprehensive coupling degree, facilitating horizontal comparison between schemes. Through the virtual power plant construction module 203, the final combination scheme is selected based on the comprehensive coupling degree to ensure that the finally constructed virtual power plant has a better collaborative operation effect.

[0076] Example 3: This embodiment provides a terminal device, including: a processor, a memory, a communication interface, and a communication bus, wherein the processor, the memory, and the communication interface communicate with each other through the communication bus; The memory is used to store at least one executable instruction that causes the processor to perform operations as described in any of the above-described methods for constructing a virtual power plant.

[0077] Example 4: This invention provides a computer-readable storage medium including a stored computer program, wherein the computer program, when running, controls the device or apparatus containing the computer-readable storage medium to execute the virtual power plant construction method as described in any of the preceding claims.

[0078] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0079] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.

Claims

1. A method for constructing a virtual power plant, characterized in that, include: Based on preset combination generation constraint rules and a standardized resource component library, several initial resource combinations are generated, and preset operation scenario data are called to perform virtual power plant operation simulation for each initial resource combination, thereby obtaining time-series operation data for each initial resource combination; wherein, the standardized resource component library includes quantitative attribute data of resource components of various dimensions of the virtual power plant; the resource components of each dimension include source-side resource components, energy storage-side resource components, and load-side resource components; Based on the time-series operation data, a multi-dimensional coupling evaluation is performed on each initial resource combination to obtain an evaluation index vector for each initial resource combination. Then, based on the TOPSIS method and the evaluation index vector, the relative closeness between each initial resource combination and the pre-acquired ideal solution is calculated to obtain the comprehensive coupling degree of each initial resource combination. The multi-dimensional coupling evaluation includes power coupling evaluation, time-series coupling evaluation, and economic coupling evaluation. Based on the comprehensive coupling degree, the optimal resource combination is selected from the initial resource combination, and the optimal resource combination is determined as the final resource combination scheme of the target virtual power plant, so as to construct the target virtual power plant according to the final resource combination scheme.

2. The virtual power plant construction method as described in claim 1, characterized in that, The process of generating several initial resource combinations based on preset combination generation constraint rules and a standardized resource component library is as follows: According to the preset heterogeneity coverage strategy, resource components of different dimensions are extracted from the standardized resource component library to form candidate resource combinations; wherein, the heterogeneity coverage strategy is used to ensure that the generated candidate resource combinations cover different source-side capacity gradients and load-side type gradients. According to the preset combination generation constraint rules, the candidate resource combinations are screened to obtain several initial resource combinations; wherein, the combination generation constraint rules include power supply and demand balance constraints and resource coordination constraints.

3. The virtual power plant construction method as described in claim 1, characterized in that, The process of calling preset operational scenario data to simulate the operation of a virtual power plant for each of the initial resource combinations, and obtaining time-series operational data for each initial resource combination, specifically involves: Acquire preset operation scenario data; wherein, the operation scenario data includes per-unit value curves of new energy output under different climatic conditions and typical daily load curves of various loads; Based on the initial resource combination, source-load time-series basic data corresponding to the initial resource combination within the scheduling cycle are obtained by matching and combining from the operation scenario data. Based on the source-load time-series basic data, virtual power plant operation simulation is performed to generate time-series operation data corresponding to the initial resource combination. The source-load time-series basic data includes new energy output sequence and load demand sequence. The time-series operation data includes new energy output sequence, energy storage charging and discharging sequence, actual load power sequence, and market-traded electricity.

4. The virtual power plant construction method as described in claim 3, characterized in that, Based on the aforementioned time-series operational data, a multi-dimensional coupled evaluation is performed on each initial resource combination to obtain an evaluation index vector for each initial resource combination, specifically: Based on the time-series operation data, the balance between power supply and demand within the virtual power plant and the effect of mitigating fluctuations in renewable energy output are evaluated to obtain the power coupling evaluation results for each initial resource combination; wherein, the power coupling evaluation results include power balance degree and fluctuation mitigation rate; Based on the time-series operational data, the complementary characteristics of various resources in terms of time distribution and their ability to guarantee load demand during different time periods are evaluated to obtain the time-series coupling evaluation results of each initial resource combination; wherein, the time-series coupling evaluation results include the time-series complementarity rate and full-time coverage. The investment cost data of each resource component is obtained, and combined with the market transaction electricity in the time-series operation data, the comprehensive economic benefits of coordinated operation are evaluated to obtain the economic coupling evaluation results of each initial resource combination; wherein, the economic coupling evaluation results include cost amortization rate and revenue improvement rate; The power coupling assessment results, timing coupling assessment results, and economic coupling assessment results are integrated to form an evaluation index vector for each initial resource combination.

5. The virtual power plant construction method as described in claim 4, characterized in that, The relative closeness between each initial resource combination and the pre-acquired ideal solution is calculated based on the TOPSIS method and the evaluation index vector, resulting in the comprehensive coupling degree of each initial resource combination. Specifically: The objective weights of each evaluation index in the evaluation index vector are determined using the entropy weight method, and the positive ideal solution and negative ideal solution of each evaluation index in the evaluation index vector are determined based on the objective weights. Based on the objective weights, the positive ideal solution, and the negative ideal solution, calculate the first distance between each initial resource combination and the positive ideal solution, and the second distance between each initial resource combination and the negative ideal solution. By combining the first distance and the second distance, the overall coupling degree of the corresponding initial resource combination is calculated.

6. The virtual power plant construction method as described in claim 1, characterized in that, Based on the overall coupling degree, the optimal resource combination is selected from the initial resource combination, specifically as follows: The initial resource combinations are sorted in descending order according to the comprehensive coupling degree. The initial resource combinations with a comprehensive coupling degree higher than the preset comprehensive coupling degree threshold are selected to obtain the optimal combination sequence. The initial resource combination with the highest comprehensive coupling degree in the optimal combination sequence is determined as the candidate optimal combination. Extract the evaluation index vector of the candidate optimal combination and compare it with the preset evaluation index threshold to determine whether there are any weak indicators that are lower than the corresponding evaluation index threshold. If there is no bottleneck indicator, the candidate optimal combination is determined as the optimal resource combination; if there is a bottleneck indicator, the next in line initial resource combination in the optimal combination sequence is determined as the candidate optimal combination, and the bottleneck indicator is judged on the current candidate optimal combination until an initial resource combination without a bottleneck indicator is selected from the optimal combination sequence and determined as the optimal resource combination.

7. The virtual power plant construction method as described in claim 6, characterized in that, Also includes: If each resource combination in the optimal combination sequence has a weak link indicator, then the initial resource combination with the highest comprehensive coupling degree in the optimal combination sequence is determined as the candidate optimal combination. Extract the types of the bottleneck indicators of the candidate optimal combination, and adjust the corresponding resource components in the candidate optimal combination according to the types of the bottleneck indicators until the optimal resource combination with preset combination conditions is obtained; wherein, the component adjustment includes component parameter adjustment and component type replacement; the preset combination conditions are that the overall coupling degree is higher than the preset overall coupling degree threshold and each evaluation indicator is higher than the corresponding evaluation indicator threshold.

8. A virtual power plant construction device, characterized in that, It includes a power plant operation simulation module, a coupling degree calculation module, and a virtual power plant construction module, among which, The power plant operation simulation module is used to generate several initial resource combinations based on preset combination generation constraint rules and a standardized resource component library, and to call preset operation scenario data to perform virtual power plant operation simulation for each initial resource combination, thereby obtaining time-series operation data for each initial resource combination; wherein, the standardized resource component library includes quantitative attribute data of resource components of various dimensions of the virtual power plant; the resource components of each dimension include source-side resource components, energy storage-side resource components, and load-side resource components; The coupling degree calculation module is used to perform multi-dimensional coupling evaluation on each initial resource combination based on the time-series running data, obtain the evaluation index vector of each initial resource combination, and calculate the relative closeness of each initial resource combination to the pre-acquired ideal solution according to the TOPSIS method and the evaluation index vector, so as to obtain the comprehensive coupling degree of each initial resource combination; wherein, the multi-dimensional coupling evaluation includes power coupling evaluation, time-series coupling evaluation and economic coupling evaluation. The virtual power plant construction module is used to select the optimal resource combination from the initial resource combination based on the comprehensive coupling degree, and determine the optimal resource combination as the final resource combination scheme of the target virtual power plant, so as to construct the target virtual power plant according to the final resource combination scheme.

9. A terminal device, characterized in that, include: The processor, memory, communication interface, and communication bus are provided, wherein the processor, memory, and communication interface communicate with each other via the communication bus. The memory is used to store at least one executable instruction that causes the processor to perform the operation of the virtual power plant construction method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device or apparatus containing the computer-readable storage medium to perform the virtual power plant construction method as described in any one of claims 1 to 7.

Images