A multi-distributed resource aggregation operation optimization method and system

Abstract

The present invention discloses a multi-distributed resource aggregate operation optimization method and system, which is applied to the field of energy storage resource allocation technology. First, by obtaining member structure change data in the energy storage aggregate, information is extracted from the member structure change data to obtain the final value of the impact parameter of the structure change on the energy storage ownership; then, based on the final value of the impact parameter, a usage right allocation scheme is obtained, and according to the current status data and historical operation data of each member in the usage right allocation scheme, the energy storage operation plan of each member with a high priority is obtained; the energy storage operation plan of each member with a high priority is adjusted using the actual real-time charging and discharging data and usage rate data of the corresponding member to obtain the final operation strategy. Through this method, the energy storage usage priority and charging and discharging strategy are adjusted in real time according to the changes in the member structure, providing flexible and efficient energy storage services for members within the aggregate.

Description

Technical Field

[0001] The present invention relates to the technical field of energy storage resource allocation, and in particular to a method and system for optimizing the operation of a multi-distributed resource aggregate. Background Art

[0002] The impact of energy storage ownership structure on shared benefits in the operational optimization of multi-distributed resource aggregates is a complex technical issue. Changes in the aggregate's internal membership structure may involve restructuring equity distribution ratios, redefining shared boundary conditions, and reshaping the benefit distribution matrix. These changes directly impact the allocation mechanism for energy storage asset usage rights, and thus the dynamic adjustment strategy of the aggregate management system.

[0003] In a fully shared model, all members have equal access to energy storage assets. The system needs to dynamically adjust charging and discharging strategies based on real-time energy demand and storage status. However, when the equity distribution ratio is restructured, some members may receive higher usage priority. This can lead to deviations in the system's allocation of energy storage resources, impacting overall economic efficiency and energy storage asset utilization. In a partially shared model, access to energy storage assets is exclusively reserved for some members, while other members can only use them under specific conditions. When sharing boundary conditions are redefined, the exclusive use scope of members may expand or contract, directly impacting the system's energy storage resource scheduling strategy. The system needs to recalculate each member's usage priority based on the new boundary conditions to ensure a balanced allocation of energy storage resources. In a time-sharing sharing model, access to energy storage assets is allocated to different members based on time periods. When the revenue distribution coefficient matrix is ​​restructured, the value of usage rights in certain time periods may change, requiring the system to fully account for revenue differences across time periods when adjusting charging and discharging strategies. The system needs to optimize the order of energy storage resource usage based on the new revenue distribution coefficients to maximize overall economic efficiency. These changes in energy storage ownership structure place higher demands on the dynamic adjustment strategies of the aggregate management system. Therefore, how to adjust the energy storage usage priority and charging and discharging strategies in real time according to changes in the member structure to ensure the rational allocation of energy storage resources and maximize the overall economic benefits has become an urgent problem to be solved. Summary of the Invention

[0004] In order to solve the above technical problems, an embodiment of the present invention provides a multi-distributed resource aggregate operation optimization method and system to solve the problem of how to adjust the energy storage usage priority and charging and discharging strategy in real time according to changes in the member structure in the existing energy storage resource allocation technology.

[0005] A first aspect of an embodiment of the present invention provides a method for optimizing the operation of a multi-distributed resource aggregate, including:

[0006] Obtain member structure change data in the energy storage aggregate, extract information from the member structure change data to obtain preliminary reconstruction data, and obtain the final value of the impact parameter of the structure change on energy storage ownership based on the preliminary reconstruction data and benefit distribution information;

[0007] The ownership ratio of members in the energy storage aggregate is adjusted based on the final value of the influencing parameter to obtain the adjusted energy storage ownership. According to the adjusted energy storage ownership, a new structural change characteristic is obtained. According to the new structural change characteristic, a usage right allocation plan is obtained.

[0008] Obtaining current status data and historical operating data of each member in the usage rights allocation plan, determining an adjusted priority sequence based on the current status data and the historical operating data, extracting energy storage demand characteristics of high-priority members based on the adjusted priority sequence to obtain a demand characteristic data set, and obtaining an energy storage operation plan for each high-priority member based on the demand characteristic data set;

[0009] The actual real-time charge and discharge data and usage rate data of the corresponding members are used to adjust the energy storage operation plan of each high-priority member to obtain the final operation strategy.

[0010] In a possible implementation of the first aspect, obtaining a final value of a parameter affecting the structural change on energy storage ownership based on the preliminary reconstruction data and the revenue distribution information includes:

[0011] Based on the preliminary reconstruction data, proportional reconstruction information is obtained;

[0012] Based on the preliminary reconstructed data, the shared boundaries and boundary conditions are analyzed to obtain the adjusted feature set. According to the adjusted feature set and the income distribution information, the coefficient matrix is ​​constructed. The coefficient matrix is ​​reshaped using the principal component analysis algorithm to obtain the reshaped matrix data.

[0013] The reshaped matrix data is extracted to obtain the initial structural change characteristics. If the initial structural change characteristics are greater than the first preset threshold, the impact of the initial structural change characteristics on energy storage ownership is analyzed through a logistic regression algorithm to obtain the initial value of the influencing parameter. The final value of the influencing parameter is determined based on the combination of the initial value of the influencing parameter and the adjusted feature set.

[0014] In a possible implementation of the first aspect, obtaining a usage rights allocation plan based on new structural change characteristics includes:

[0015] Determine the set of influencing parameters based on the new structural change characteristics;

[0016] Determine whether the new structural change feature exceeds a second preset threshold; if so, extract key factors from the influencing parameter set to obtain an initial weight for the usage right allocation;

[0017] According to the initial weights, the allocation rules of each sharing mode are obtained;

[0018] According to the allocation rules, the usage rights ratio of each member in the energy storage aggregate under each sharing mode is calculated to obtain a ratio matrix, and based on the ratio matrix, a usage rights allocation plan is obtained.

[0019] In a possible implementation of the first aspect, obtaining a usage rights allocation scheme according to the ratio matrix includes:

[0020] If the usage right ratio of any member in the ratio matrix is ​​lower than the preset equilibrium value, the allocation rule is adjusted to obtain a new ratio matrix, and based on the new ratio matrix, a usage right allocation plan is obtained.

[0021] In a possible implementation of the first aspect, determining an adjusted priority sequence based on current state data and historical operation data includes:

[0022] Perform data cleaning on current status data and historical operation data to obtain standardized data sets;

[0023] Extract the charge and discharge frequencies from the standardized data set, and process them using time series analysis to obtain frequency eigenvalues.

[0024] Determine whether the frequency characteristic value is the same as the historical operation data. If different, calculate the offset between the frequency characteristic value and the historical operation data. If the offset exceeds the preset offset range, generate an adjustment signal, reallocate the usage priority, and obtain the adjusted priority sequence.

[0025] In a possible implementation of the first aspect, obtaining, according to the demand characteristic dataset, an energy storage operation plan for each high-priority member includes:

[0026] Based on the demand feature dataset, the energy storage cost of each high-priority member is predicted. If the energy storage cost is greater than the preset cost threshold, the charging and discharging period of the corresponding member is adjusted to obtain a preliminary charging and discharging strategy.

[0027] Forecast the load of each member to obtain the load forecast result. Based on the load forecast result, optimize the preliminary charge and discharge strategy to obtain the optimized charge and discharge strategy.

[0028] According to the optimized charging and discharging strategy and the energy storage system capacity of each member, a task allocation plan is obtained, and according to the task allocation plan, an energy storage operation plan of each member is obtained.

[0029] In a possible implementation of the first aspect, adjusting the energy storage operation plan of each high-priority member using actual real-time charge and discharge data and usage rate data of the corresponding member to obtain a final operation strategy includes:

[0030] Obtaining real-time charge and discharge data and usage rate data of high-priority members, comparing the charge and discharge data and usage rate data with the corresponding data in the energy storage operation plan, obtaining deviation results, and optimizing the energy storage operation plan based on the deviation results to obtain an optimized energy storage operation plan;

[0031] Based on the optimized energy storage operation plan, the operation status data is obtained, the operation status data is analyzed to obtain trend characteristics, and based on the trend characteristics, an optimized profit distribution plan is obtained;

[0032] According to the benefits of each member in the optimized benefit distribution plan, the usage priority and charging and discharging strategy are adjusted to obtain the final operation strategy.

[0033] In a possible implementation of the first aspect, obtaining an optimized profit distribution plan based on trend characteristics includes:

[0034] According to the trend characteristics, a new coefficient matrix is ​​obtained, and the new coefficient matrix is ​​reshaped to obtain the reshaped result data;

[0035] The distribution coefficient is adjusted according to the reshaping result data to obtain the adjusted distribution coefficient, and the optimized profit distribution plan is obtained according to the adjusted distribution coefficient.

[0036] In order to solve the same technical problem, a second aspect of an embodiment of the present invention provides a multi-distributed resource aggregation operation optimization system, including:

[0037] An acquisition module is used to obtain member structure change data in the energy storage aggregate, extract information from the member structure change data, obtain preliminary reconstruction data, and obtain the final value of the impact parameter of the structure change on the energy storage ownership based on the preliminary reconstruction data and the benefit distribution information;

[0038] A first adjustment module is configured to adjust the ownership ratios of members in the energy storage aggregate based on the final values ​​of the influencing parameters to obtain adjusted energy storage ownership, obtain new structural change characteristics based on the adjusted energy storage ownership, and obtain a usage rights allocation plan based on the new structural change characteristics;

[0039] An energy storage operation plan generation module is configured to obtain current status data and historical operation data of each member in the usage rights allocation plan, determine an adjusted priority sequence based on the current status data and historical operation data, extract energy storage demand characteristics of high-priority members based on the adjusted priority sequence, obtain a demand characteristic data set, and obtain an energy storage operation plan for each high-priority member based on the demand characteristic data set;

[0040] The final strategy generation module is used to adjust the energy storage operation plan of each high-priority member by using the actual real-time charging and discharging data and usage rate data of the corresponding member to obtain the final operation strategy.

[0041] In a possible implementation manner of the second aspect, the acquisition module further includes a scale reconstruction information extraction unit, a reshaping unit, and an optimization unit, wherein:

[0042] A proportional reconstruction information extraction unit, configured to extract preliminary reconstruction data to obtain proportional reconstruction information;

[0043] A reshaping unit is used to analyze the shared boundaries and boundary conditions based on the preliminary reconstructed data to obtain an adjusted feature set, construct a coefficient matrix based on the adjusted feature set and the income distribution information, and reshape the coefficient matrix using the principal component analysis algorithm to obtain reshaped matrix data;

[0044] The optimization unit is used to extract the reshaped matrix data to obtain the initial structural change characteristics. If the initial structural change characteristics are greater than a first preset threshold, the impact of the initial structural change characteristics on energy storage ownership is analyzed through a logistic regression algorithm to obtain the initial value of the influencing parameter. The final value of the influencing parameter is determined based on the combination of the initial value of the influencing parameter and the adjusted feature set.

[0045] The technical solution of the present invention has the following advantages:

[0046] An embodiment of the present invention provides an operation optimization method for a multi-distributed resource aggregate. The method first obtains member structure change data in an energy storage aggregate, extracts information from the member structure change data, and obtains a final value of a parameter affecting the structure change on energy storage ownership. The method then adjusts the ownership ratio of the members in the energy storage aggregate based on the final value of the influencing parameter to obtain adjusted energy storage ownership. A new structure change characteristic is obtained based on the adjusted energy storage ownership. A usage rights allocation plan is obtained based on the new structure change characteristic. Current state data and historical operation data of each member in the usage rights allocation plan are obtained. An adjusted priority sequence is determined based on the current state data and historical operation data. Based on the adjusted priority sequence, energy storage demand characteristics of high-priority members are extracted to obtain a demand characteristic data set. An energy storage operation plan for each high-priority member is obtained based on the demand characteristic data set. The energy storage operation plan for each high-priority member is adjusted using the actual real-time charge and discharge data and usage rate data of the corresponding member to obtain a final operation strategy. This method achieves real-time adjustment of energy storage usage priority and charge and discharge strategies based on changes in member structure, providing flexible and efficient energy storage services for members within the aggregate. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific implementation methods or the description of the prior art. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0048] Figure 1 Flowchart of a method for optimizing the operation of a multi-distributed resource aggregate according to an embodiment of the present invention;

[0049] Figure 2 This is a system block diagram of a multi-distributed resource aggregation operation optimization system in an embodiment of the present invention.

[0050] Reference numerals: 200, multi-distributed resource aggregate operation optimization system; 201, acquisition module; 202, first adjustment module; 203, energy storage operation plan generation module; 204, final strategy generation module. DETAILED DESCRIPTION

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

[0052] In the description of the present invention, it should be noted that the terms "first", "second" and "third" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance.

[0053] The embodiment of the present invention provides a multi-distributed resource aggregation operation optimization method, such as Figure 1 FIG. 1 is a flow chart of a method for optimizing the operation of a multi-distributed resource aggregate, including steps S101 to S104. The details of each step are as follows:

[0054] S101: Obtain member structure change data in the energy storage aggregate, extract information from the member structure change data to obtain preliminary reconstruction data, and obtain final values ​​of parameters affecting the structure change on energy storage ownership based on the preliminary reconstruction data and benefit distribution information.

[0055] In this embodiment, structural change data for each member of the energy storage aggregate is obtained. Equity and revenue distribution information contained in the change data is parsed and extracted to obtain preliminary reconstruction data. Proportional reconstruction information is extracted from the preliminary reconstruction data. A linear regression algorithm is used to determine the mapping between equity distribution and proportional reconstruction, thereby obtaining equity distribution ratio adjustment coefficients. The relationship between shared boundaries and boundary conditions is analyzed using the preliminary reconstruction data to obtain boundary condition redefinition information and obtain a feature set after shared boundary adjustment. A coefficient matrix is ​​constructed based on the feature set and revenue distribution information. The revenue distribution coefficient matrix is ​​reshaped using a principal component analysis algorithm to obtain reshaped matrix data. Structural change features are extracted from the reshaped matrix data to obtain initial structural change features. If the initial structural change features exceed a preset threshold, a logistic regression algorithm is used to analyze the impact of the structural change on energy storage ownership and obtain initial values ​​of the influencing parameters. The initial values ​​of the influencing parameters and the adjusted feature set are obtained, and the final values ​​of the influencing parameters are determined by fusing the reshaped matrix data. Based on the final values ​​and the change data, information processing techniques are used to adjust the energy storage ownership distribution logic to obtain optimized parameter results.

[0056] In one embodiment, based on the preliminary reconstruction data and the revenue distribution information, the final values ​​of the parameters affecting the energy storage ownership due to the structural changes are obtained, including:

[0057] Based on the preliminary reconstruction data, proportional reconstruction information is obtained;

[0058] Based on the preliminary reconstructed data, the shared boundaries and boundary conditions are analyzed to obtain the adjusted feature set. According to the adjusted feature set and the income distribution information, the coefficient matrix is ​​constructed. The coefficient matrix is ​​reshaped using the principal component analysis algorithm to obtain the reshaped matrix data.

[0059] The reshaped matrix data is extracted to obtain the initial structural change characteristics. If the initial structural change characteristics are greater than the first preset threshold, the impact of the initial structural change characteristics on energy storage ownership is analyzed through a logistic regression algorithm to obtain the initial value of the influencing parameter. The final value of the influencing parameter is determined based on the combination of the initial value of the influencing parameter and the adjusted feature set.

[0060] In this embodiment, the acquisition of data on changes in the internal member structure of an aggregate can be understood as extracting key information from a dynamic system. For example, in an energy storage aggregate, members may include multiple energy storage device owners, and the structural change data may reflect situations such as the joining or exit of devices and capacity adjustments. For example, assume that an energy storage aggregate initially has 5 members, each with 10 kWh of energy storage capacity. At a certain moment, a member exits, and the data records this change. By parsing this data, it can be extracted that the equity distribution of the remaining members after the exit changes from 20% to 25%, and the profit distribution is also adjusted accordingly. This process can provide a basis for subsequent analysis and ensure that the data reflects real dynamics.

[0061] When extracting proportion reconstruction information from the preliminary reconstruction data, the proportion can be recalculated based on the member's capacity contribution. If one of the remaining four members adds 5 kWh of capacity, the total capacity becomes 45 kWh, and its proportion is adjusted from 25% to approximately 33%. When using a linear regression algorithm for analysis, the equity distribution and proportion changes in historical data can be used as input to determine the mapping relationship. For example, the past 10 changes show that for every 5% increase in proportion, the equity distribution increases by 3%, resulting in an adjustment coefficient of 0.6. This coefficient helps predict future change trends and improve distribution fairness.

[0062] Then, through preliminary reconstruction of the data, the relationship between shared boundaries and boundary conditions is analyzed. Information on boundary condition redefinition is obtained, resulting in an adjusted feature set. It is important to note that the adjusted feature set is the one with the shared boundaries adjusted. When analyzing shared boundaries and boundary conditions, the shared boundary may be a rule governing resource sharing between members, such as maximum output power. Suppose the initial boundary condition is that each member's output does not exceed 10 kilowatts. After a structural change, the capacity of a member increases, and the boundary needs to be adjusted to 12 kilowatts. By analyzing the preliminary reconstruction data and redefining the boundary conditions, an adjusted feature set is obtained, such as the upper limit on power allocation between members. This feature set can optimize resource utilization. When constructing a coefficient matrix based on the feature set and revenue distribution information, factors such as the power allocation upper limit and capacity ratio can be used as matrix elements. For example, rows represent members, columns represent features, and the values ​​reflect the weights of each feature. When reshaping the revenue distribution coefficient matrix using principal component analysis, assuming the analysis finds that the capacity ratio has the greatest impact on revenue, the weight is increased from 0.4 to 0.6. This reshaped matrix data focuses more on key factors, reduces redundant information, and improves computational efficiency.

[0063] When extracting initial structural change features from the reshaped matrix data, a threshold of 10% can be set. If a change causes a 15% fluctuation in the capacity ratio, exceeding the threshold, logistic regression is used to analyze its impact on energy storage ownership. For example, historical data shows that the ownership impact parameter is 0.3 for a 10% fluctuation in the ratio. Given the current larger fluctuation, an initial value of 0.4 is used. This initial value reflects the potential effect of the structural change.

[0064] When integrating the initial values ​​of the influencing parameters and the adjusted feature set, the final value can be determined by weighted averaging the reshaped matrix data. Assuming the initial value is 0.4 and the feature set weight is adjusted to 0.5, the final value is 0.45. This value guides adjustments to the energy storage ownership allocation logic, such as increasing the ownership ratio of members with significant capacity contributions.

[0065] The above method is used to optimize the distribution of energy storage ownership. For example, increasing the proportion of a member from 25% to 30% will increase the income by 5%. The optimization result improves the fairness of overall income, thereby more fairly reflecting the actual contribution of each member and ensuring the dynamic adaptability of energy storage ownership distribution.

[0066] S102: adjusting the ownership ratios of members in the energy storage aggregate based on the final values ​​of the influencing parameters to obtain adjusted energy storage ownership, obtaining new structural change characteristics based on the adjusted energy storage ownership, and obtaining a usage rights allocation plan based on the new structural change characteristics.

[0067] In this embodiment, the ownership ratios of members in the energy storage aggregate are adjusted based on the final values ​​of the influencing parameters to obtain the adjusted energy storage ownership. The adjusted energy storage ownership is then analyzed to obtain new structural change characteristics and determine a set of influencing parameters. A usage rights allocation plan is then determined based on the set of influencing parameters.

[0068] In one embodiment, a usage rights allocation plan is obtained based on the new structural change characteristics, including:

[0069] Determine the set of influencing parameters based on the new structural change characteristics;

[0070] Determine whether the new structural change feature exceeds a second preset threshold; if so, extract key factors from the influencing parameter set to obtain an initial weight for the usage right allocation;

[0071] According to the initial weights, the allocation rules of each sharing mode are obtained;

[0072] According to the allocation rules, the usage rights ratio of each member in the energy storage aggregate under each sharing mode is calculated to obtain a ratio matrix, and based on the ratio matrix, a usage rights allocation plan is obtained.

[0073] In this embodiment, the initial structural change characteristics can be extracted from multiple dimensions through the adjusted energy storage ownership to obtain new structural change characteristics. For example, assume that a certain energy storage aggregate contains 5 members, and the initial ownership data is allocated based on capacity contribution, where the capacities of members A, B, C, D, and E are 100kW, 150kW, 200kW, 50kW, and 100kW, respectively, with a total capacity of 600kW. The initial structural change characteristics may be manifested as the addition of 50kW of capacity to member C, resulting in a total capacity of 650kW. At this time, the data can be analyzed to obtain the changes in the proportion of each member. The characteristic value of C increases from 33.33% to 38.46%, exceeding the preset threshold of 5%, triggering further analysis. This method facilitates the rapid location of key change points.

[0074] Then, based on the new structural change characteristics, the influencing parameter set is determined. When determining the influencing parameter set, factors such as capacity change, participation time and usage frequency can be extracted. For example, assume that the energy storage capacity of member C has increased, and at the same time, its usage frequency has increased from 2 hours a day to 4 hours. In this case, first determine the key factors in the influencing parameter set: capacity factor and usage frequency factor. These two factors have weights of 0.6 and 0.3 respectively. Next, calculate the initial weight of the usage rights allocation based on member C's performance on these two key factors. For example, if the increase in member C's capacity significantly increases its relative importance in the aggregate, and the doubling of the usage frequency also has a positive contribution to its usage rights, then the initial weight of the usage rights allocation can be calculated by the following formula:

[0075] Usage right allocation weight = (capacity factor × capacity factor weight) + (usage frequency factor × usage frequency factor weight)

[0076] Taking member C as an example, assuming that the growth of its capacity and usage frequency results in a score of 1 on both factors (indicating maximum growth or highest demand), the initial weight of usage rights allocation is calculated as follows:

[0077] Usage rights allocation weight = (1 × 0.6) + (1 × 0.3) = 0.9

[0078] However, in practice, the actual scores of each factor may need to be adjusted according to specific circumstances. In this example, the usage rights allocation weight is 0.45, which indicates that by considering the increase in capacity and usage frequency, the usage rights of member C have been correspondingly improved.

[0079] After obtaining the initial weights for the allocation of usage rights. Based on the initial weights, the allocation rules for each classified sharing mode are generated. The classified sharing modes are full sharing, partial sharing, or time-sharing sharing. Based on the allocation rules, the usage rights ratio of each member in the energy storage aggregate under each sharing mode is calculated, the ratio matrix is ​​determined, and the usage rights allocation plan is obtained. For example, in the classified sharing mode, full sharing can be defined as all members using the energy storage resources equally, partial sharing is limited by capacity ratio, and time-sharing sharing is allocated by time period. For example, under full sharing, the five members share the usage rights equally, each getting 20%; under partial sharing, according to the new capacity ratio, A gets 15.38% and C gets 38.46%; under time-sharing sharing, C gets more night time periods due to high frequency of use. This classification can flexibly adapt to the needs of different scenarios.

[0080] In one embodiment, a usage rights allocation scheme is obtained based on the ratio matrix, including:

[0081] If the usage right ratio of any member in the ratio matrix is ​​lower than the preset equilibrium value, the allocation rule is adjusted to obtain a new ratio matrix, and based on the new ratio matrix, a usage right allocation plan is obtained.

[0082] In this embodiment, if the usage right ratio of a member in the ratio matrix is ​​lower than a preset equilibrium value, the allocation rule is adjusted, the ratio matrix is ​​updated, and a new allocation plan is generated based on the updated ratio matrix.

[0083] Specifically, when calculating usage rights, a ratio matrix can be constructed. For example, a new capacity ratio matrix shows that A, B, C, D, and E are 15.38%, 23.08%, 38.46%, 7.69%, and 15.38%, respectively. If the preset balance value is 10%, and D's ratio is lower than this value, the rules need to be adjusted. For example, by adding D's priority usage period, the updated matrix would be 15%, 22%, 37%, 11%, and 15%.

[0084] It should be noted that when generating a new allocation plan, resource scheduling can be optimized based on the updated matrix. For example, if D's usage rights increase from 7.69% to 11%, it can be prioritized for using energy storage during off-peak hours to reduce resource competition.

[0085] When allocating results, each member's actual usage period and capacity quota can be recorded. For example, C received 38% of the quota, mainly concentrated in the high-frequency nighttime period. This recording method facilitates subsequent tracing and optimization adjustments.

[0086] In one possible implementation, when updating the energy storage ownership and usage rights record, the new plan can be compared with historical data. For example, if C's usage rights increase from 33% to 38%, the system automatically updates its permissions to ensure data consistency.

[0087] S103: Obtain the current status data and historical operation data of each member in the usage rights allocation plan, determine an adjusted priority sequence based on the current status data and historical operation data, extract the energy storage demand characteristics of the members with high priority based on the adjusted priority sequence, obtain a demand characteristic data set, and obtain an energy storage operation plan for each member with high priority based on the demand characteristic data set.

[0088] In this embodiment, the current status data and historical energy storage operation data of each member of the usage rights allocation scheme are obtained, and the charging and discharging frequency and priority trends are analyzed. Based on the trend changes, the need for dynamic adjustment of usage priorities is identified to obtain an adjusted priority sequence. Based on this adjusted priority sequence, the energy storage demand characteristics of high-priority members are then extracted to obtain a demand characteristic dataset. Based on this demand characteristic dataset, an energy storage operation plan is derived for each high-priority member.

[0089] In one embodiment, determining an adjusted priority sequence based on current state data and historical operation data includes:

[0090] Perform data cleaning on current status data and historical operation data to obtain standardized data sets;

[0091] Extract the charge and discharge frequencies from the standardized data set, and process them using time series analysis to obtain frequency eigenvalues.

[0092] Determine whether the frequency characteristic value is the same as the historical operation data. If different, calculate the offset between the frequency characteristic value and the historical operation data. If the offset exceeds the preset offset range, generate an adjustment signal, reallocate the usage priority, and obtain the adjusted priority sequence.

[0093] In this implementation, the current status data and historical operating data of each member of the usage rights allocation scheme are obtained, and then outliers are removed through data cleaning to obtain a standardized data set. For example, in energy storage asset management, the process of obtaining current status data and historical operating data needs to ensure data integrity and accuracy. Therefore, the voltage, current, temperature and other status data of the energy storage system are collected in real time through sensors, and operating data such as the number of charge and discharge times and operating time are recorded. These data may contain outliers due to equipment failure or signal interference, so data cleaning is crucial. For example, assuming that abnormally high values ​​appear in the voltage data collected by a certain energy storage system, a reasonable range such as 3.0 to 4.2V can be set to remove data points that are out of range to obtain a standardized data set.

[0094] Time series analysis is a key tool for extracting charge and discharge frequency from standardized datasets. Specifically, a frequency distribution curve is generated by counting the number of charges and discharges per hour. For example, a storage system may have a high frequency during the day on weekdays, approximately 5 times per hour, but this decreases to 1 time per hour at night, exhibiting a clear periodic pattern. Based on this frequency distribution, characteristic values ​​(i.e., charge and discharge frequencies) can be calculated, such as the daily average or peak frequency.

[0095] Determine whether the frequency characteristic value is the same as the historical operation data. If different, calculate the offset between the frequency characteristic value and the historical operation data. If the offset exceeds the preset offset range, generate an adjustment signal, reallocate the usage priority of the members, and obtain the adjusted priority sequence. For example, the priority trend is determined by combining the frequency characteristic value and the historical operation data. Assuming that the historical operation data shows that the normal frequency range is 2 to 4 times, if the current frequency characteristic value rises to 5 times, the recorded offset is 1 time, and the trend is biased towards high-load operation. Specifically, this offset may be caused by increased electricity demand, such as an increase in air-conditioning load in summer. After recording the offset, the direction of trend change can be clarified, providing a basis for subsequent adjustments.

[0096] It should be noted that the offset is a key indicator when analyzing the dynamic adjustment trigger conditions. If the offset exceeds the preset threshold by 0.5 times, an adjustment signal is generated.

[0097] The adjustment signal triggers the power system to reallocate usage priorities, resulting in an adjusted priority sequence. For example, an industrial park's energy storage system may have an offset of 0.7 times, triggering an adjustment process to ensure that high-priority equipment has access to energy storage resources.

[0098] Specifically, when redistributing usage priorities, a clustering algorithm is used to divide priority groups. When using a clustering algorithm to divide priority groups, grouping is performed based on device type and power demand. For example, assuming there are three types of equipment in the park: servers, lighting, and production lines, they can be divided into high, medium, and low priority groups based on charging and discharging frequency and importance through a clustering algorithm. Servers are classified into the high priority group due to their high frequency and high importance, and a preliminary sequence is generated. This grouping method can clearly reflect resource allocation needs. When optimizing the preliminary priority sequence, the sorting needs to be adjusted in combination with the current status data. If the efficiency of a device decreases due to excessive temperature, its priority can be appropriately lowered to ensure the overall stability of the system. The adjusted priority sequence needs to be verified for consistency with the charging and discharging frequency. For example, if the frequency of the high priority group is concentrated in peak hours and the verification is passed, the final adjusted priority sequence can be used to guide the allocation of energy storage resources. This consistency verification can effectively improve resource utilization efficiency.

[0099] In one embodiment, obtaining an energy storage operation plan for each high-priority member based on a demand characteristic data set includes:

[0100] Based on the demand feature dataset, the energy storage cost of each high-priority member is predicted. If the energy storage cost is greater than the preset cost threshold, the charging and discharging period of the corresponding member is adjusted to obtain a preliminary charging and discharging strategy.

[0101] Forecast the load of each member to obtain the load forecast result. Based on the load forecast result, optimize the preliminary charge and discharge strategy to obtain the optimized charge and discharge strategy.

[0102] According to the optimized charging and discharging strategy and the energy storage system capacity of each member, a task allocation plan is obtained, and according to the task allocation plan, an energy storage operation plan of each member is obtained.

[0103] In this embodiment, based on the adjusted priority sequence, members with high priority are extracted, their energy storage demand characteristics are obtained, and a demand characteristic data set is generated. For example, the priority sequence in the energy storage system may be sorted based on device capacity and response speed, and the high-priority member may be a battery pack with large capacity and fast response. In practice, the charging and discharging frequency and capacity requirements of these members can be obtained through system logs. For example, if a battery pack needs to be charged 50kWh per day, a data set containing characteristics such as frequency and capacity can be generated. This data set provides a basis for subsequent analysis and ensures that cost forecasts are targeted at key equipment. By combining the demand characteristic data set with electricity price data, a linear regression algorithm is used to predict the energy storage cost of each member to obtain a cost forecast result.

[0104] The system then uses a linear regression algorithm to predict each member's energy storage cost by combining the demand profile dataset with electricity price data. If the energy storage cost exceeds a preset cost threshold, the charging and discharging period is adjusted to a period with lower electricity prices, generating a preliminary charging and discharging strategy. For example, assuming a threshold of 50 yuan / day, a battery pack with a predicted cost of 60 yuan / day would require adjustment. In implementation, charging tasks can be shifted from peak to off-peak hours, such as charging between 2:00 a.m. and 6:00 a.m., generating a strategy that includes these adjusted periods. This adjustment leverages electricity price differences to reduce operating costs.

[0105] It should be noted that electricity price data can be obtained from the real-time grid interface, such as a peak price of 1.2 yuan / kWh and an off-peak price of 0.5 yuan / kWh. Linear regression analysis of the relationship between demand characteristics and electricity prices predicts that the cost of operating a battery pack during peak hours may be 60 yuan / day. This prediction helps identify high-cost operating scenarios and provides a basis for adjusting strategies. If the cost prediction exceeds a preset threshold, the charging and discharging period is adjusted to a period with lower electricity prices, generating a preliminary charging and discharging strategy.

[0106] Based on the load forecast results, the system then determines the predicted peak and valley load periods. A greedy algorithm is then used to optimize the initial charge and discharge strategy, resulting in an optimized strategy. For example, the load forecast indicates a peak period between 12:00 PM and 3:00 PM. The greedy algorithm prioritizes charging high-priority battery packs during valley periods and discharging during peak periods to ensure system stability. Finally, the optimized plan specifies charging a battery pack in the early morning hours and discharging 30 kWh at noon, achieving a balanced approach between cost and load demand.

[0107] Based on the optimized charging and discharging strategy and the capacity of each member's energy storage system, specific charging and discharging tasks are assigned to generate a task allocation plan. For example, a battery pack with a capacity of 100kWh is scheduled to discharge 30kWh. During implementation, the task allocation plan specifies the specific time and amount of discharge during peak periods for this battery pack to ensure that the task is executable. This allocation improves system operational efficiency. The task allocation plan is used to obtain the operating parameters of each member's energy storage system and generate the final energy storage operation plan.

[0108] It should be noted that operating parameters include the voltage and temperature of the battery pack. A battery pack may need to maintain a voltage of around 400V and a temperature below 35°C. The plan will set the operating mode accordingly to ensure equipment safety. This refinement improves the operability of the plan. If the state of the energy storage system deviates from the predicted results after the operation plan is executed, the charging and discharging strategy will be adjusted based on real-time electricity price data, and the operation plan will be updated. If a battery pack actually discharges only 20kWh instead of the planned 30kWh, the discharge can be rearranged for the off-peak period based on the real-time electricity price of 0.8 yuan / kWh. The updated energy storage operation plan can quickly respond to deviations and maintain efficient system operation.

[0109] S104: adjusting the energy storage operation plan of each high-priority member using the actual real-time charge and discharge data and usage rate data of the corresponding member to obtain a final operation strategy.

[0110] In this embodiment, real-time charge / discharge data and usage data are collected for high-priority members of the energy storage cluster. This real-time data is recorded by a data acquisition system. By comparing the planned data in the operation plan with the collected real-time data, deviations in the charge / discharge data and usage data are determined, resulting in a deviation result. Based on the deviation result, the energy storage operation plan for each high-priority member is adjusted to produce a final operation strategy.

[0111] In one embodiment, the energy storage operation plan of each high-priority member is adjusted using the actual real-time charge and discharge data and usage rate data of the corresponding member to obtain a final operation strategy, including:

[0112] Obtaining real-time charge and discharge data and usage rate data of high-priority members, comparing the charge and discharge data and usage rate data with the corresponding data in the energy storage operation plan, obtaining deviation results, and optimizing the energy storage operation plan based on the deviation results to obtain an optimized energy storage operation plan;

[0113] Based on the optimized energy storage operation plan, the operation status data is obtained, the operation status data is analyzed to obtain trend characteristics, and based on the trend characteristics, an optimized profit distribution plan is obtained;

[0114] According to the benefits of each member in the optimized benefit distribution plan, the usage priority and charging and discharging strategy are adjusted to obtain the final operation strategy.

[0115] In this embodiment, real-time data acquisition of energy storage assets involves using a data acquisition system to record key information about the operating status of each energy storage asset. For example, in an energy storage power station, the data acquisition system can record the battery's charge and discharge power, usage rate, and voltage status every five minutes, generating continuous time series data that reflects the asset's actual operating status.

[0116] It is worth noting that the real-time data includes but is not limited to actual real-time charging and discharging data and usage rate data. The actual real-time charging and discharging data includes but is not limited to charging power and discharging power, and the usage rate data includes but is not limited to usage rate.

[0117] By comparing the planned data in the operation plan with the collected real-time data, the deviation results are determined. The key is to identify the difference between actual operation and expectations. Specifically, if the charging power in the operation plan is 100 kilowatts for a certain period, but the real-time data shows that the actual power is only 80 kilowatts, the deviation is 20 kilowatts. In terms of utilization rate, if the planned utilization rate is 70% and the actual utilization rate is 50%, the deviation result is 20%. This deviation result provides the basis for subsequent analysis.

[0118] When analyzing economic benefit trends using deviation results, preset thresholds are used to determine whether adjustments are necessary. For example, if the economic benefit decline threshold is set at 5%, an adjustment is triggered if the deviation causes electricity costs to increase by more than 5%. For example, if a storage asset's charging period doesn't avoid peak electricity prices, costs will increase by 8%, exceeding the threshold, indicating that strategy optimization is needed to reduce costs.

[0119] In response to adjustment needs, operating status features are extracted from real-time data, and optimized charging and discharging instructions are generated based on asset usage. For example, if real-time data shows that battery utilization is low, the charging task can be adjusted to the early morning hours when electricity prices are low, while the discharging task can be increased to the evening peak hours. This adjustment can fully utilize the price difference and increase profits. The operation plan is updated and the operation tasks are assigned through the optimized charging and discharging instructions to obtain an optimized energy storage operation plan. For example, if the capacity of an energy storage asset is 500 kWh, the optimization instruction may assign 200 kWh of charging from 1:00 to 4:00 in the morning and 150 kWh of discharging from 6:00 to 8:00 in the evening. This solution not only matches the real-time status but also optimizes economic efficiency.

[0120] Then, the operating status data of the optimized energy storage operation plan is obtained, and the updated plan data is compared with the real-time data to determine the changing trend of the energy storage operation plan in terms of economic benefit value and asset utilization rate, and obtain the trend characteristics. It should be noted that if the actual charging power after adjustment is stable near the optimized value, such as fluctuating between 198 kW and 202 kWh, the trend is stable; if the power frequently jumps below 180 kWh, further adjustment is required. If the change trend deviates from expectations, the charging and discharging instructions are adjusted through real-time data, and the task execution plan is updated. For example, when the real-time electricity price suddenly rises by 10%, the charging task volume can be temporarily reduced from 200 kWh to 150 kWh, and the excess capacity can be reserved for periods with lower electricity prices. This dynamic adjustment can effectively respond to external changes.

[0121] The final operation plan might be reflected in a full-day task list: charging in the early morning accounts for 40% of the total capacity, standby during the day, and discharging in the evening accounts for 30%. Through flexible adjustments, the energy storage assets are ensured to operate efficiently and maximize economic benefits. Ideally, this approach also extends battery life and reduces equipment loss caused by frequent deviations. It is understandable that the above process, through real-time data-driven decision-making, ensures that the operation plan is closely aligned with actual needs. For example, a pattern of charging during off-peak electricity prices and discharging during peak hours can significantly improve the utilization rate and revenue stability of energy storage assets.

[0122] Based on the trend characteristics, an optimized profit distribution plan is obtained. Then, based on the profits of each member in the optimized profit distribution plan and combined with the historical feedback data of the dynamic adjustment mechanism, the usage priority and charging and discharging strategy are adjusted to obtain the final operation strategy. Specifically, the profit change data of internal members is extracted through the optimized profit distribution plan. Combined with the historical feedback data, regression analysis is used to determine the key factors affecting the profit. For example, assuming there are multiple member units in the aggregate, the profit change data may show that some members have increased their profits by 10% in a specific time period, while others have decreased by 5%. Combined with historical feedback data such as equipment operating time and market price fluctuations, regression analysis may reveal that equipment utilization rate and electricity price changes are key factors.

[0123] If device utilization falls below the 80% threshold, revenue declines significantly, necessitating adjustments to energy storage priorities. For example, prioritization can prioritize energy storage devices during high-revenue periods, such as shifting nighttime off-peak charging to daytime peak discharge, to improve overall revenue. Based on the new energy storage priority ranking, the charging and discharging strategy is adjusted, and the operational results are predicted through time series analysis. Assuming that the adjustment results in an additional two hours of peak discharge per day, time series analysis might predict an 8% increase in revenue. This prediction can intuitively reflect the potential value of the strategy adjustment and provide support for preliminary plans.

[0124] Long-term trend data on aggregate structural changes is obtained, and Monte Carlo simulation is used to analyze future operating conditions for the preliminary plan for the target operating strategy. For example, trend data may show that the number of member units will increase by 20% over the next two years. Monte Carlo simulation uses randomly sampled operating conditions to determine whether the strategy can adapt to this expansion. The simulation results may show that the strategy remains stable in 80% of scenarios, demonstrating its strong adaptability. Key status indicators, such as revenue stability or equipment load rate, are extracted through simulation analysis to determine whether the preset conditions are met. If the revenue stability exceeds 90%, the current strategy is retained, and the final operating strategy is obtained. This judgment can provide an optimization basis for the dynamic adjustment mechanism and avoid frequent and ineffective adjustments. Adjustment parameters are extracted from the optimization basis, and iterative updates are performed on the energy storage priority and charging and discharging strategies. The results are verified using historical feedback data.

[0125] It's important to note that, assuming a parameter adjustment increases the peak discharge ratio by 5%, the validation results might show a 3% increase in revenue, indicating the update was effective. This iteration continuously improves the strategy's applicability. By operating the strategy based on the ultimate goal and combining it with long-term trend data, we can predict future revenue changes and structural adjustment needs. For example, a forecast suggests a 15% revenue increase over the next three years, but this requires 10% additional energy storage capacity. This forecast provides direction for the continuous optimization of the dynamic adjustment mechanism to ensure long-term profit maximization.

[0126] In one embodiment, an optimized profit distribution plan is obtained based on trend characteristics, including:

[0127] According to the trend characteristics, a new coefficient matrix is ​​obtained, and the new coefficient matrix is ​​reshaped to obtain the reshaped result data;

[0128] The distribution coefficient is adjusted according to the reshaping result data to obtain the adjusted distribution coefficient, and the optimized profit distribution plan is obtained according to the adjusted distribution coefficient.

[0129] In this embodiment, the collection and analysis of energy storage asset operating status data typically relies on the integration of real-time monitoring systems and data interfaces. For example, consider an energy storage power station that uses sensors and smart meters to record battery charge and discharge power, voltage, and operating time every minute. This data forms an aggregated dataset. For example, a power station's daily operating data may show a planned charging power of 1000kW, but the actual average charging power collected is only 900kW. This data collection method can comprehensively reflect the operating status of energy storage assets and provide a foundation for subsequent analysis.

[0130] When analyzing economic benefits and asset utilization trends from operational data, trend characteristics can be extracted by comparing planned and actual data. For example, suppose a storage asset is scheduled to perform two charge and discharge cycles per day, but actual data shows an average of only 1.8 cycles. Analysis reveals that the reduction in cycles may be due to changes in grid dispatch requirements or fluctuations in equipment efficiency. Trend characteristics may manifest as slightly lower-than-expected asset utilization and lower economic benefits due to inability to fully utilize peak-to-valley price differences. This analysis helps identify key optimization areas.

[0131] By applying an iterative calculation method to the profit coefficient based on trend characteristics and obtaining a new coefficient matrix, a profit model can be constructed based on the statistical patterns of historical data. For example, the profit coefficient may be related to factors such as charging and discharging timing and grid price fluctuations. Suppose, through iterative calculations, it is found that the profit coefficient can be increased by 10% when charging time is concentrated during off-peak electricity price periods. This method repeatedly adjusts parameters to gradually approach the optimal solution, ensuring that the analysis results are more closely aligned with actual operating scenarios.

[0132] When performing a reshape operation based on the new coefficient matrix, the profit coefficients can be combined with the asset operating parameters to form a new data structure, the reshape result data. For example, a reshape operation for a storage power station might regroup daily operating data by hourly segment, generating a data table containing dimensions such as profit coefficient, charge and discharge power, and utilization rate. The reshape result data can more intuitively demonstrate which operating periods are most profitable, providing a basis for optimization.

[0133] When adjusting the allocation coefficient based on the reshaped data, the optimization direction can be determined by comparing the effects of different operating strategies. This results in an adjusted allocation coefficient, which can then be used to determine the optimized revenue distribution plan. For example, assuming the adjusted allocation coefficient allocates more charging and discharging tasks to periods with high electricity prices, simulated operating data shows an 8% increase in economic benefits. If this result meets the preset threshold, the optimization direction is feasible. This data-driven approach ensures the scientific nature of the adjustments. For example, after implementing an optimization plan at a storage power station, actual operating data showed that daily revenue increased from 100,000 yuan to 110,000 yuan, validating the plan's effectiveness. The resulting allocation may manifest as more reasonable charging and discharging schedules and higher asset utilization.

[0134] After obtaining the final allocation results, the energy storage power station may prioritize discharging tasks during the daily peak electricity price period based on the optimized profit distribution plan, while supplementing charging during the off-peak period.

[0135] The embodiment of the present invention provides a multi-distributed resource aggregation operation optimization system, such as Figure 2 As shown, Figure 2 A system block diagram of a system 200 for optimizing the operation of a multi-distributed resource aggregation includes:

[0136] An acquisition module 201 is configured to acquire member structure change data in the energy storage aggregate, extract information from the member structure change data to obtain preliminary reconstruction data, and obtain final values ​​of parameters affecting the energy storage ownership based on the preliminary reconstruction data and the revenue distribution information.

[0137] A first adjustment module 202 is configured to adjust the ownership ratios of members in the energy storage aggregate based on the final values ​​of the influencing parameters to obtain adjusted energy storage ownership, obtain new structural change characteristics based on the adjusted energy storage ownership, and obtain a usage rights allocation plan based on the new structural change characteristics;

[0138] Energy storage operation plan generation module 203 is configured to obtain current status data and historical operation data of each member in the usage rights allocation plan, determine an adjusted priority sequence based on the current status data and historical operation data, extract energy storage demand characteristics of high-priority members based on the adjusted priority sequence, obtain a demand characteristic data set, and obtain an energy storage operation plan for each high-priority member based on the demand characteristic data set;

[0139] The final strategy generating module 204 is configured to adjust the energy storage operation plan of each high-priority member by using the actual real-time charge and discharge data and usage rate data of the corresponding member to obtain a final operation strategy.

[0140] In one embodiment, the acquisition module 201 further includes a scale reconstruction information extraction unit, a reshaping unit, and an optimization unit, wherein:

[0141] A proportional reconstruction information extraction unit, configured to extract preliminary reconstruction data to obtain proportional reconstruction information;

[0142] A reshaping unit is used to analyze the shared boundaries and boundary conditions based on the preliminary reconstructed data to obtain an adjusted feature set, construct a coefficient matrix based on the adjusted feature set and the income distribution information, and reshape the coefficient matrix using the principal component analysis algorithm to obtain reshaped matrix data;

[0143] The optimization unit is used to extract the reshaped matrix data to obtain the initial structural change characteristics. If the initial structural change characteristics are greater than a first preset threshold, the impact of the initial structural change characteristics on energy storage ownership is analyzed through a logistic regression algorithm to obtain the initial value of the influencing parameter. The final value of the influencing parameter is determined based on the combination of the initial value of the influencing parameter and the adjusted feature set.

[0144] The specific implementation of the system for optimizing the operation of multiple distributed resource aggregates is basically the same as the specific embodiment of the above-mentioned method for optimizing the operation of multiple distributed resource aggregates, and will not be repeated here.

[0145] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, 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 specification.

[0146] The specific embodiments described above further illustrate the objectives, technical solutions, 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 optimizing the operation of a multi-distributed resource aggregate, characterized in that: include: Obtaining member structure change data in the energy storage aggregate, performing information extraction on the member structure change data to obtain preliminary reconstruction data, and obtaining final values ​​of parameters affecting the energy storage ownership based on the preliminary reconstruction data and the income distribution information; Adjusting the ownership ratios of members in the energy storage aggregate based on the final values ​​of the influencing parameters to obtain adjusted energy storage ownership, obtaining new structural change characteristics based on the adjusted energy storage ownership, and obtaining a usage rights allocation plan based on the new structural change characteristics; Obtaining current status data and historical operation data of each member in the usage rights allocation scheme, determining an adjusted priority sequence based on the current status data and historical operation data, extracting energy storage demand characteristics of members with high priority based on the adjusted priority sequence to obtain a demand characteristic data set, and obtaining an energy storage operation plan for each member with high priority based on the demand characteristic data set; The energy storage operation plan of each high-priority member is adjusted using the actual real-time charge and discharge data and usage rate data corresponding to the member to obtain a final operation strategy.

2. The multi-distributed resource aggregation operation optimization method according to claim 1, characterized in that: The method of obtaining a final value of a parameter affecting energy storage ownership due to structural changes based on the preliminary reconstruction data and the income distribution information includes: Based on the preliminary reconstruction data, obtaining proportional reconstruction information; Based on the preliminary reconstructed data, analyzing the shared boundaries and boundary conditions to obtain an adjusted feature set, constructing a coefficient matrix based on the adjusted feature set and the revenue distribution information, and reshaping the coefficient matrix using a principal component analysis algorithm to obtain reshaped matrix data; The reshaped matrix data is extracted to obtain initial structural change characteristics. If the initial structural change characteristics are greater than a first preset threshold, the impact of the initial structural change characteristics on energy storage ownership is analyzed using a logistic regression algorithm to obtain initial values ​​of influencing parameters. The final values ​​of the influencing parameters are determined based on the initial values ​​of the influencing parameters and the adjusted feature set.

3. The multi-distributed resource aggregation operation optimization method according to claim 1, characterized in that: The method of obtaining a usage rights allocation plan based on the new structural change characteristics includes: Determining a set of influencing parameters based on the new structural change characteristics; Determining whether the new structural change feature exceeds a second preset threshold; if so, extracting key factors from the influencing parameter set to obtain an initial weight for allocation of usage rights; According to the initial weights, allocation rules for each sharing mode are obtained; According to the allocation rule, the usage right ratio of each member in the energy storage aggregate under each sharing mode is calculated to obtain a ratio matrix, and based on the ratio matrix, a usage right allocation plan is obtained.

4. The multi-distributed resource aggregation operation optimization method according to claim 3, characterized in that: The method of obtaining a usage rights allocation scheme based on the ratio matrix includes: If the usage right ratio of any member in the ratio matrix is ​​lower than a preset equilibrium value, the allocation rule is adjusted to obtain a new ratio matrix, and a usage right allocation plan is obtained based on the new ratio matrix.

5. The multi-distributed resource aggregation operation optimization method according to claim 1, characterized in that: The step of determining an adjusted priority sequence based on the current state data and the historical operation data includes: Performing data cleaning on the current state data and historical operation data to obtain a standardized data set; Extract the charge and discharge frequencies from the standardized data set, and process them using time series analysis to obtain frequency eigenvalues. Determine whether the frequency characteristic value is the same as the historical operation data. If different, calculate the offset between the frequency characteristic value and the historical operation data. If the offset exceeds the preset offset range, generate an adjustment signal, reallocate the usage priority, and obtain an adjusted priority sequence.

6. The multi-distributed resource aggregation operation optimization method according to claim 1, characterized in that: Obtaining the energy storage operation plan for each member with a high priority according to the demand characteristic data set includes: Predicting the energy storage cost of each member with a high priority based on the demand characteristic data set, and if the energy storage cost is greater than a preset cost threshold, adjusting the charging and discharging time period of the corresponding member to obtain a preliminary charging and discharging strategy; Predicting the load of each member to obtain a load prediction result, and optimizing the preliminary charge and discharge strategy based on the load prediction result to obtain an optimized charge and discharge strategy; A task allocation plan is obtained based on the optimized charging and discharging strategy and the energy storage system capacity of each member, and an energy storage operation plan of each member is obtained based on the task allocation plan.

7. The multi-distributed resource aggregation operation optimization method according to claim 5, characterized in that: The method of adjusting the energy storage operation plan of each high-priority member by using the actual real-time charge and discharge data and usage rate data corresponding to the member to obtain a final operation strategy includes: obtaining real-time charge and discharge data and usage rate data of the member with a high priority, comparing the charge and discharge data and the usage rate data with corresponding data in the energy storage operation plan, respectively, to obtain deviation results, and optimizing the energy storage operation plan according to the deviation results to obtain an optimized energy storage operation plan; Based on the optimized energy storage operation plan, operating status data is obtained, the operating status data is analyzed to obtain trend characteristics, and an optimized profit distribution plan is obtained according to the trend characteristics; According to the income of each member in the optimized income distribution plan, the usage priority and charging and discharging strategy are adjusted to obtain a final operation strategy.

8. The multi-distributed resource aggregation operation optimization method according to claim 7, characterized in that: The optimized profit distribution plan obtained according to the trend characteristics includes: According to the trend characteristics, a new coefficient matrix is ​​obtained, and the new coefficient matrix is ​​reshaped to obtain reshaped result data; The distribution coefficient is adjusted according to the remodeling result data to obtain an adjusted distribution coefficient, and an optimized profit distribution plan is obtained according to the adjusted distribution coefficient.

9. A multi-distributed resource aggregation operation optimization system, characterized in that: include: an acquisition module, configured to acquire member structure change data in the energy storage aggregate, extract information from the member structure change data to obtain preliminary reconstruction data, and obtain a final value of a parameter affecting the structure change on energy storage ownership based on the preliminary reconstruction data and the revenue distribution information; a first adjustment module, configured to adjust the ownership ratio of members in the energy storage aggregate based on the final value of the influencing parameter to obtain adjusted energy storage ownership, obtain new structural change characteristics based on the adjusted energy storage ownership, and obtain a usage rights allocation plan based on the new structural change characteristics; an energy storage operation plan generation module, configured to obtain current state data and historical operation data of each member in the usage rights allocation scheme, determine an adjusted priority sequence based on the current state data and historical operation data, extract energy storage demand characteristics of members with high priority based on the adjusted priority sequence, obtain a demand characteristic data set, and obtain an energy storage operation plan for each member with high priority based on the demand characteristic data set; The final strategy generating module is used to adjust the energy storage operation plan of each high-priority member by using the actual real-time charge and discharge data and usage rate data corresponding to the member to obtain the final operation strategy.

10. The multi-distributed resource aggregation operation optimization system according to claim 9, characterized in that: The acquisition module further includes a scale reconstruction information extraction unit, a reshaping unit and an optimization unit, wherein: a proportional reconstruction information extraction unit, configured to extract the preliminary reconstruction data to obtain proportional reconstruction information; a reshaping unit configured to analyze the shared boundaries and boundary conditions based on the preliminary reconstructed data to obtain an adjusted feature set, construct a coefficient matrix based on the adjusted feature set and the revenue distribution information, and reshape the coefficient matrix using a principal component analysis algorithm to obtain reshaped matrix data; The optimization unit is configured to extract the reshaped matrix data to obtain initial structural change characteristics. If the initial structural change characteristics are greater than a first preset threshold, the optimization unit is configured to analyze the impact of the initial structural change characteristics on energy storage ownership through a logistic regression algorithm to obtain initial values ​​of influencing parameters. The final values ​​of the influencing parameters are determined based on a combination of the initial values ​​of the influencing parameters and the adjusted feature set.

Images