Method, device and equipment for evaluating cooperative capability of power distribution network and micro-grid

Abstract

The invention provides a power distribution network and micro-grid cooperative capability evaluation method, device and equipment, and relates to the technical field of power distribution network and micro-grid cooperative control. The method comprises the following steps: acquiring current load data in a target power distribution network and a target micro-grid and current operation data of each flexible resource, and acquiring current topological information and current environment data of the target power distribution network and the target micro-grid to form a current data set; according to the current data set, a first scene matching model about the response capability and a second scene matching model about the availability, obtaining a current response capability scene and a current availability scene of the target power distribution network and the target micro-grid; and performing similarity evaluation on the current data set, the current response capability scene and the current availability scene, and determining the cooperative capability of the target power distribution network and the target micro-grid according to an evaluation result. The method can comprehensively and accurately evaluate the power distribution and micro-grid cooperation capability, thereby improving the power distribution and micro-grid cooperation operation capability, and promoting the development of the power distribution and micro-grid cooperation technology.

Description

Technical Field

[0001] This invention relates to the field of distribution network and microgrid coordinated control technology, and in particular to a method, apparatus and equipment for evaluating the coordinated capability of distribution networks and microgrids. Background Technology

[0002] With the deepening of the new energy revolution, the power system is undergoing unprecedented changes. The large-scale integration of distributed energy resources (DERs), the rapid popularization of electric vehicles, and the increasing maturity of energy storage technologies have fundamentally changed the structure and operation mode of traditional distribution networks. As the "last mile" connecting the transmission network and users, the stability, economy, and reliability of the distribution network directly affect users' electricity experience and energy efficiency.

[0003] Against this backdrop, microgrids, as autonomous systems encompassing distributed power sources, energy storage devices, and loads, can flexibly connect to the grid or operate in islanded mode, and have become an important technical means to solve the problem of distributed energy consumption. The coordinated operation of distribution networks and microgrids can effectively improve the overall operating efficiency of the system, enhance power supply reliability, and promote the consumption of clean energy, making it a key technical path for building new power systems.

[0004] However, current research on the coordinated operation of distribution networks and microgrids largely remains at the level of theoretical discussions and simplified models, exhibiting numerous limitations. Existing methods are often overly simplistic, failing to fully reflect the dynamic characteristics of flexibility resources in distribution-microgrid systems, and unable to reflect resource availability and responsiveness in real time, thus lacking a comprehensive assessment system for coordinated operation capabilities. Furthermore, the coordinated operation between distribution networks and microgrids requires consideration of various factors, such as grid topology, the type and scale of flexibility resources, and grid load characteristics. The interaction of these factors complicates the design and optimization of the coordinated operation mechanism.

[0005] This situation makes it impossible to accurately predict and respond to resource changes during the distribution microgrid scheduling optimization process, thus limiting the grid's scheduling optimization capabilities and affecting the system's flexibility in responding to load fluctuations and resource changes. Therefore, establishing a comprehensive, accurate, and operable method for evaluating the collaborative capabilities of distribution networks and microgrids is of significant theoretical and practical value for promoting the development and engineering application of distribution microgrid collaborative technology. Summary of the Invention

[0006] This invention provides a method, apparatus, and equipment for evaluating the collaborative capability of distribution networks and microgrids, in order to solve the problem that traditional research on the collaborative operation of distribution networks and microgrids cannot comprehensively and accurately evaluate their collaborative capability.

[0007] In a first aspect, embodiments of the present invention provide a method for evaluating the coordination capability of a distribution network and a microgrid, including: Acquire current load data and current operating data of various flexibility resources in the target distribution network and target microgrid, and acquire current topology information and current environmental data of the target distribution network and target microgrid to form the current dataset; Based on the current dataset, the first scenario matching model regarding response capability, and the second scenario matching model regarding availability, the current response capability scenario and the current availability scenario of the target distribution network and the target microgrid are obtained. A similarity assessment is performed on the current dataset with the current response capability scenario and the current availability scenario. Based on the assessment results, the coordination capability of the target distribution network and the target microgrid is determined.

[0008] Secondly, embodiments of the present invention provide a device for evaluating the coordination capability of distribution networks and microgrids, comprising: The acquisition module is used to acquire the current load data and current operating data of each flexibility resource in the target distribution network and target microgrid, and to acquire the current topology information and current environmental data of the target distribution network and target microgrid to form the current dataset; The scenario matching module is used to obtain the current response capability scenario and the current availability scenario of the target distribution network and the target microgrid based on the current dataset, the first scenario matching model about response capability, and the second scenario matching model about availability. The collaborative capability assessment module is used to evaluate the similarity between the current dataset and the current response capability scenario and the current availability scenario, and to determine the collaborative capability between the target distribution network and the target microgrid based on the assessment results.

[0009] Thirdly, embodiments of the present invention provide an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method described in the first aspect or any possible implementation thereof.

[0010] In this embodiment of the invention, current load data and current operating data of various flexibility resources in the target distribution network and target microgrid are acquired, along with current topology information and current environmental data, to form a current dataset. Then, based on the current dataset, a first scenario matching model regarding response capability, and a second scenario matching model regarding availability, the current response capability scenario and current availability scenario of the target distribution network and target microgrid are obtained. Furthermore, a similarity assessment is performed between the current dataset and the current response capability scenario and current availability scenario. Based on the assessment results, the collaborative capability of the target distribution network and target microgrid is determined. The current dataset ensures the real-time nature of the distribution network and microgrid collaborative capability assessment. By using the first and second scenario matching models to measure the current dataset based on real historical data, a more accurate assessment of the current response capability scenario and current availability scenario is obtained, thus helping to improve the collaborative operation capability of the distribution network and microgrid and promoting the development of distribution network-microgrid collaborative technology. Attached Figure Description

[0011] Figure 1 This is a flowchart illustrating the implementation of the method for assessing the coordination capability between power distribution networks and microgrids provided in this embodiment of the invention. Figure 2 This is a schematic diagram of the structure of the power distribution network and microgrid coordination capability assessment device provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0012] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0013] See Figure 1 The document illustrates a flowchart of the implementation of the distribution network and microgrid coordination capability assessment method provided in this embodiment of the invention, detailed below: Step 101: Obtain the current load data and current operating data of each flexibility resource in the target distribution network and target microgrid, and obtain the current topology information and current environmental data of the target distribution network and target microgrid to form the current dataset.

[0014] For example, the target distribution network can be a regional distribution network, and the target microgrid can be a microgrid connected to the target distribution network. Flexible resources refer to power resources with "adjustable, dispatchable, and responsive" characteristics, and can include proactive response power sources, energy storage systems, and adjustable loads. Examples include photovoltaics, wind power, micro gas turbines, electrochemical energy storage, flywheel energy storage, virtual power plant aggregation energy storage, industrial flexible loads, commercial building air conditioning / lighting, and electric vehicle orderly charging lights. The target distribution network can include various types of loads and several flexible resources, such as factory parks, residential areas, data centers, electric vehicle charging piles, and energy storage devices. The target microgrid can be various park microgrids, such as park microgrids with distributed power sources, energy storage equipment, and factory and user loads.

[0015] In this embodiment, considering the operational complexity caused by microgrids connecting to the distribution network under different circumstances, data is obtained from four aspects: load, flexibility resources, topology, and environment to distinguish the collaborative scenarios between the microgrid and the distribution network, so as to accurately evaluate the collaborative capabilities between the microgrid and the distribution network based on different collaborative scenarios.

[0016] Step 102: Based on the current dataset, the first scenario matching model regarding response capability, and the second scenario matching model regarding availability, obtain the current response capability scenario and the current availability scenario of the target distribution network and the target microgrid.

[0017] In this embodiment, the coordination capability between the microgrid and the distribution network is evaluated from the perspective of the response capability and availability between the microgrid and the distribution network. Therefore, a first scenario matching model for response capability and a second scenario matching model for availability are trained in advance based on real coordination data between the microgrid and the distribution network.

[0018] In one embodiment, the training process of the first scene matching model includes: Acquire multiple sets of historical coordination data for the target distribution network and the target microgrid, and acquire the historical load data and historical operation data of each flexibility resource in the target distribution network and the target microgrid at the historical coordination time corresponding to each set of historical coordination data, as well as the historical topology information and historical environmental data of the target distribution network and the target microgrid at that historical coordination time.

[0019] Based on each set of historical coordination data, calculate the historical response speed, historical regulation accuracy, and historical continuous response capability of the target distribution network and the target microgrid at the corresponding historical coordination time.

[0020] Based on historical response speed, historical regulation accuracy, and historical continuous response capability, calculate the comprehensive index of historical response capability for the target distribution network and the target microgrid.

[0021] The first dataset is constructed by taking a set of historical collaborative data corresponding to historical response speed, historical adjustment accuracy, historical continuous response capability, historical response capability comprehensive index, historical load data, various historical operation data, historical topology information and historical environmental data as a single data point.

[0022] Cluster the first dataset and obtain the first scene matching model based on the clustering results.

[0023] Among them, historical response speed can characterize the time delay from receiving the instruction to reaching the target response state in historical collaborative data, historical adjustment accuracy can characterize the degree of deviation between the actual response output and the target instruction in historical collaborative data, and historical continuous response capability can characterize the longest time to maintain the target response state in historical collaborative data.

[0024] For example, different methods can be used to calculate the historical response speed, historical regulation accuracy, and historical sustained response capability for different flexible resources. For distributed power sources, the ramp rate can be obtained by calculating the power change per unit time, and this ramp rate is used as the corresponding historical response speed. The historical regulation accuracy is obtained by calculating the difference between the actual output power and the power corresponding to the dispatch command. The time period where the power fluctuation is less than a set range is determined by calculating the standard deviation of power fluctuation during the response period, and this period is used as the corresponding historical sustained response capability. For energy storage systems, the active power response time can be obtained by calculating the time from the issuance of the command to the active power reaching the target value, and this active power response time is used as the corresponding historical response speed. The historical regulation accuracy is obtained by calculating the difference between the actual output power and the power corresponding to the dispatch command. The sustained response time is obtained by calculating the time for the energy storage system to charge and discharge at the power corresponding to the dispatch command, considering charging and discharging efficiency, and this sustained response time is used as the corresponding historical sustained response capability. For adjustable loads, the load response delay can be obtained by calculating the time from the issuance of the command to the start of load change, and this load response delay is used as the corresponding historical response speed. The historical regulation accuracy is obtained by calculating the difference between the actual load adjustment and the target load adjustment. The historical continuous response capability is obtained by calculating the longest time that the load can maintain a regulated state (constrained by process / user requirements).

[0025] For example, after obtaining the historical response speed, historical adjustment accuracy, and historical continuous response capability, the corresponding historical response capability comprehensive index can be obtained by weighting and summing them according to their importance under different operating conditions.

[0026] Based on this, by clustering the first dataset consisting of historical response speed, historical adjustment accuracy, historical continuous response capability, historical response capability comprehensive index, historical load data, various historical operating data, historical topology information, and historical environmental data, different scenarios regarding response capability can be obtained, and thus a first scenario matching model regarding response capability can be obtained.

[0027] For example, due to the complex operating conditions of the coordinated operation of microgrids and distribution networks, clustering of the first dataset can be achieved using methods that do not require a predetermined number of clusters, such as density-based clustering of applications with noise (DBSCAN) or clustering methods based on kernel density estimation (KDE).

[0028] In one embodiment, the training process of the second scene matching model includes: Acquire multiple sets of historical coordination data for the target distribution network and the target microgrid, and acquire the historical load data and historical operation data of each flexibility resource in the target distribution network and the target microgrid at the historical coordination time corresponding to each set of historical coordination data, as well as the historical topology information and historical environmental data of the target distribution network and the target microgrid at that historical coordination time.

[0029] Based on each set of historical collaborative data, calculate the historical spatiotemporal available capacity and historical constraint adaptability of the target distribution network and the target microgrid at the corresponding historical collaborative moment.

[0030] Based on historical available capacity and historical constraint adaptability, calculate the comprehensive historical availability index of the target distribution network and the target microgrid.

[0031] A second dataset is constructed by taking a set of historical collaborative data corresponding to historical spatiotemporal available capacity, historical constraint adaptability, historical availability comprehensive index, historical load data, various historical operation data, historical topology information and historical environmental data as a single data point.

[0032] Cluster the second dataset and obtain the second scene matching model based on the clustering results.

[0033] Among them, historical spatiotemporal available capacity can characterize the stable adjustment capacity (upward / downward) that can be provided in a specific time / region in historical collaborative data, and historical constraint adaptability can characterize the degree of matching between resource operation constraints and scheduling requirements in historical collaborative data (such as time windows and process limitations).

[0034] Similarly, different methods can be used to calculate the historical spatiotemporal available capacity and historical constraint adaptability for different flexible resources. For example, for distributed generation, the effective adjustable capacity can be calculated as (actual photovoltaic output - minimum technical output + available energy storage capacity) / rated total capacity × 100% as its corresponding historical spatiotemporal available capacity. The historical constraint adaptability can be calculated using ramp-up adaptability rate and weather adaptability rate calculators. The ramp-up adaptability rate can be obtained by calculating the percentage of time when the dispatch demand ramp-up rate is less than or equal to the maximum ramp-up rate, and the weather adaptability rate can be obtained by calculating the percentage of events where the irradiance is greater than or equal to the photovoltaic output irradiance. For energy storage systems, the historical spatiotemporal available capacity can be obtained by calculating the SOC available range or available capacity, and the historical constraint adaptability can be obtained by calculating the temperature adaptability rate (e.g., the percentage of time when the actual temperature is within the allowable temperature range). For adjustable loads, taking industrial flexible loads as an example, the availability of the time window of the adjustable load can be obtained by calculating the proportion of the overlap between the scheduling demand time and the load adjustable window to the total demand time. The effective adjustable capacity of the adjustable load can be calculated by calculating the proportion of the actual adjustable capacity to the rated adjustable capacity. Based on the availability of the time window and the effective adjustable capacity, the corresponding historical spatiotemporal available capacity can be obtained. The corresponding historical constraint adaptability can be obtained by calculating the process adaptability rate of the adjustable load. For example, the process adaptability rate can be obtained by calculating the proportion of the number of times the adjustment process meets the process requirements to the total number of adjustments.

[0035] Similarly, after obtaining the historical available capacity and historical constraint adaptability, the corresponding historical availability comprehensive index can be obtained by weighting and summing the historical available capacity and historical constraint adaptability under different operating conditions according to their importance.

[0036] Based on this, by clustering the second dataset, which consists of historical spatiotemporal available capacity, historical constraint adaptability, historical availability comprehensive index, historical load data, various historical operation data, historical topology information and historical environmental data, we can obtain different scenarios regarding availability, and thus obtain a second scenario matching model for availability.

[0037] For example, methods such as DBSCAN and KDE can also be used to cluster the second dataset without needing to determine the number of clusters in advance.

[0038] In one embodiment, step 102 includes: Calculate the distance between the current dataset and each cluster center in the first scenario matching model, and determine the scenario with the smallest distance as the current response capability scenario of the target distribution network and the target microgrid.

[0039] Calculate the distance between the current dataset and each cluster center in the second scenario matching model, and determine the scenario with the smallest distance as the current availability scenario of the target distribution network and the target microgrid.

[0040] Since both the first and second scenario matching models are obtained through clustering, each of them includes clusters with multiple cluster centers. Each cluster corresponds to a scenario related to response capability or a scenario related to availability. Therefore, the current response capability scenario and the current availability scenario of the target distribution network and the target microgrid can be determined by calculating the distance between the current dataset and each cluster center in the first scenario matching model, as well as the distance between the current dataset and each cluster center in the second scenario matching model.

[0041] For example, the load data, operational data, and environmental data of the current dataset and each cluster center can be calculated using Euclidean distance. The topological information of the current dataset and each cluster center can be calculated using graph similarity identification. Then, the calculated distances are weighted and summed to obtain the distance between the current dataset and each cluster center.

[0042] Step 103: Perform a similarity assessment between the current dataset and the current response capability scenario and the current availability scenario, and determine the collaborative capability of the target distribution network and the target microgrid based on the assessment results.

[0043] In this embodiment, considering the uncertainty of microgrid access to the distribution network, after determining the current response capability scenario and the current availability scenario corresponding to the current dataset, a similarity assessment is also performed on the current dataset and the current response capability scenario and the current availability scenario, so as to more comprehensively and accurately determine the collaborative capability of the target distribution network and the target microgrid based on the assessment results.

[0044] In one embodiment, step 103 includes: Obtain the first standard dataset corresponding to the current response capability scenario and the second standard dataset corresponding to the current availability scenario.

[0045] Calculate the similarity between the current dataset and the first standard dataset, denoted as the first similarity. Calculate the similarity between the current dataset and the second standard dataset, denoted as the second similarity.

[0046] Determine whether the first similarity is greater than the first threshold, and whether the second similarity is greater than the second threshold.

[0047] If the first similarity is greater than the first threshold and the second similarity is greater than the second threshold, the coordination capability of the target distribution network and the target microgrid is determined based on the historical comprehensive index of response capability corresponding to the current response capability scenario, the historical comprehensive index of availability corresponding to the current availability scenario, the first similarity and the second similarity.

[0048] If the first similarity is less than or equal to the first threshold, and / or the second similarity is less than or equal to the second threshold, the uncertainty impact coefficient is calculated based on the current dataset, and the coordination capability of the target distribution network and the target microgrid is determined based on the historical comprehensive index of the current response capability scenario, the historical comprehensive index of the current availability scenario, the first similarity, the second similarity, and the uncertainty impact coefficient.

[0049] In one embodiment, the coordination capability of the target distribution network and the target microgrid is determined based on the historical comprehensive index of response capability corresponding to the current response capability scenario, the historical comprehensive index of availability corresponding to the current availability scenario, a first similarity, and a second similarity, including: Based on the first similarity, the historical comprehensive index of response capability corresponding to the current response capability scenario is corrected to obtain the current comprehensive index of response capability for the target distribution network and the target microgrid.

[0050] The historical availability composite index corresponding to the current availability scenario is corrected based on the second similarity to obtain the current availability composite index of the target distribution network and the target microgrid.

[0051] The coordination capability of the target distribution network and the target microgrid is determined based on the current comprehensive response capability index and the current comprehensive availability index.

[0052] The current response capability scenario corresponds to the first standard dataset, which includes historical load data, historical operational data, historical topology information, and historical environmental data corresponding to the cluster centers of the current response capability scenario. The current availability scenario corresponds to the second standard dataset, which includes historical load data, historical operational data, historical topology information, and historical environmental data corresponding to the cluster centers of the current availability scenario.

[0053] The method for calculating the distance between the current dataset and the first and second standard datasets can be the same as the method for calculating the distance between the current dataset and the cluster center in step 102, and will not be repeated here.

[0054] After calculating the first similarity and the second similarity, these scores can be compared with the first threshold and the second threshold, respectively. Based on the comparison results, the coordination capability between the target distribution network and the target microgrid can be determined in different ways. The first threshold and the second threshold can be determined according to actual needs and can be the same or different.

[0055] For example, if the first similarity is greater than the first threshold and the second similarity is greater than the second threshold, it means that the scenario corresponding to the current dataset is similar to the historical operating conditions. Therefore, the coordination capability of the target distribution network and the target microgrid can be determined directly based on the historical comprehensive index of the current response capability scenario, the historical comprehensive index of the current availability scenario, the first similarity and the second similarity.

[0056] For example, if the first similarity is less than or equal to the first threshold, and / or the second similarity is less than or equal to the second threshold, it means that the scenario corresponding to the current dataset has at least one significant difference from the historical operating conditions in terms of response capability and availability. Therefore, it is necessary to first calculate the uncertainty impact coefficient based on the current dataset, and then determine the coordination capability of the target distribution network and the target microgrid based on the historical response capability comprehensive index corresponding to the current response capability scenario, the historical availability comprehensive index corresponding to the current availability scenario, the first similarity, the second similarity, and the uncertainty impact coefficient.

[0057] In one embodiment, calculating the uncertainty impact coefficient based on the current dataset includes: Calculate the distance between the current dataset and the target standard dataset, which is the dataset in the first and second standard datasets whose similarity is less than or equal to the corresponding first or second threshold; calculate the uncertainty influence coefficient based on the distance.

[0058] In one embodiment, if the target standard dataset is a first standard dataset and a second standard dataset, calculating the distance between the current dataset and the target standard dataset includes: Calculate the distance between the current dataset and the first standard dataset, and denote it as the first distance.

[0059] Calculate the distance between the current dataset and the second standard dataset, and denote it as the second distance.

[0060] The uncertainty impact coefficient is calculated based on distance, including: The first uncertainty influence coefficient is calculated based on the first distance.

[0061] The second uncertainty influence coefficient is calculated based on the second distance.

[0062] In this embodiment, the target standard dataset may include only the first standard dataset, only the second standard dataset, or both. If only the first standard dataset is included, the distance between the current dataset and the first standard dataset is calculated, and an uncertainty impact coefficient for correcting the historical comprehensive index of the current response capability scenario is determined solely based on the distance between the previous dataset and the first standard dataset. If only the second standard dataset is included, the distance between the current dataset and the second standard dataset is calculated, and an uncertainty impact coefficient for correcting the historical comprehensive index of the current availability scenario is determined solely based on the distance between the previous dataset and the second standard dataset. If both the first and second standard datasets are included, the distance between the current dataset and the first standard dataset is calculated and denoted as the first distance, and the distance between the current dataset and the second standard dataset is calculated and denoted as the second distance. Then, the first uncertainty impact coefficient is calculated based on the first distance, and the second uncertainty impact coefficient is calculated based on the second distance.

[0063] For example, when calculating the uncertainty impact coefficient based on distance, the relationship between distance and uncertainty impact can be fitted using real historical data, and the uncertainty impact coefficient corresponding to the calculated distance can be determined based on the fitting result.

[0064] In this embodiment, when the first similarity is less than or equal to the first threshold and / or the second similarity is less than or equal to the second threshold, the uncertainty impact coefficient is first calculated based on the current dataset. Then, the coordination capability of the target distribution network and the target microgrid is determined based on the historical comprehensive index of the current response capability scenario, the historical comprehensive index of the current availability scenario, the first similarity, the second similarity, and the uncertainty impact coefficient. This allows for the evaluation of the uncertainty impact coefficient of the current dataset in real time, and further, the coordination capability of the target distribution network and the target microgrid can be determined more accurately based on the uncertainty impact coefficient.

[0065] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0066] The following are device embodiments of the present invention. For details not described in detail, please refer to the corresponding method embodiments described above.

[0067] Figure 2 A schematic diagram of the structure of the distribution network and microgrid coordination capability assessment device provided in an embodiment of the present invention is shown. For ease of explanation, only the parts related to the embodiment of the present invention are shown, and are described in detail below: like Figure 2As shown, the device for assessing the coordination capability between distribution networks and microgrids includes: The acquisition module 21 is used to acquire the current load data and the current operating data of each flexibility resource in the target distribution network and the target microgrid, and to acquire the current topology information and current environmental data of the target distribution network and the target microgrid to form the current dataset.

[0068] The scenario matching module 22 is used to obtain the current response capability scenario and the current availability scenario of the target distribution network and the target microgrid based on the current dataset, the first scenario matching model about response capability and the second scenario matching model about availability.

[0069] The collaborative capability assessment module 23 is used to assess the similarity between the current dataset and the current response capability scenario and the current availability scenario, and to determine the collaborative capability between the target distribution network and the target microgrid based on the assessment results.

[0070] This invention, through its embodiments, acquires current load data and current operational data of various flexibility resources in the target distribution network and target microgrid, and obtains current topology information and current environmental data of the target distribution network and target microgrid to form a current dataset. Then, based on the current dataset, a first scenario matching model regarding response capability, and a second scenario matching model regarding availability, it obtains the current response capability scenario and the current availability scenario of the target distribution network and target microgrid. Furthermore, it performs a similarity assessment between the current dataset and the current response capability scenario and current availability scenario, and determines the collaborative capability of the target distribution network and target microgrid based on the assessment results. The current dataset ensures the real-time nature of the distribution network and microgrid collaborative capability assessment, and the first and second scenario matching models measure the current dataset based on real historical data. This results in a more accurate assessment of the current response capability scenario and current availability scenario, thereby improving the collaborative operation capability of the distribution network and microgrid and promoting the development of distribution network-microgrid collaborative technology.

[0071] In one possible implementation, the training process of the first scene matching model includes: Acquire multiple sets of historical coordination data for the target distribution network and the target microgrid, and acquire the historical load data and historical operation data of each flexibility resource in the target distribution network and the target microgrid at the historical coordination time corresponding to each set of historical coordination data, as well as the historical topology information and historical environmental data of the target distribution network and the target microgrid at that historical coordination time.

[0072] Based on each set of historical coordination data, calculate the historical response speed, historical regulation accuracy, and historical continuous response capability of the target distribution network and the target microgrid at the corresponding historical coordination time.

[0073] Based on historical response speed, historical regulation accuracy, and historical continuous response capability, calculate the comprehensive index of historical response capability for the target distribution network and the target microgrid.

[0074] The first dataset is constructed by taking a set of historical collaborative data corresponding to historical response speed, historical adjustment accuracy, historical continuous response capability, historical response capability comprehensive index, historical load data, various historical operation data, historical topology information and historical environmental data as a single data point.

[0075] Cluster the first dataset and obtain the first scene matching model based on the clustering results.

[0076] In one possible implementation, the training process of the second scene matching model includes: Acquire multiple sets of historical coordination data for the target distribution network and the target microgrid, and acquire the historical load data and historical operation data of each flexibility resource in the target distribution network and the target microgrid at the historical coordination time corresponding to each set of historical coordination data, as well as the historical topology information and historical environmental data of the target distribution network and the target microgrid at that historical coordination time.

[0077] Based on each set of historical collaborative data, calculate the historical spatiotemporal available capacity and historical constraint adaptability of the target distribution network and the target microgrid at the corresponding historical collaborative moment.

[0078] Based on historical available capacity and historical constraint adaptability, calculate the comprehensive historical availability index of the target distribution network and the target microgrid.

[0079] A second dataset is constructed by taking a set of historical collaborative data corresponding to historical spatiotemporal available capacity, historical constraint adaptability, historical availability comprehensive index, historical load data, various historical operation data, historical topology information and historical environmental data as a single data point.

[0080] Cluster the second dataset and obtain the second scene matching model based on the clustering results.

[0081] In one possible implementation, the scene matching module 22 is specifically used for: Calculate the distance between the current dataset and each cluster center in the first scenario matching model, and determine the scenario with the smallest distance as the current response capability scenario of the target distribution network and the target microgrid.

[0082] Calculate the distance between the current dataset and each cluster center in the second scenario matching model, and determine the scenario with the smallest distance as the current availability scenario of the target distribution network and the target microgrid.

[0083] In one possible implementation, the collaborative capability assessment module 23 is specifically used for: Obtain the first standard dataset corresponding to the current response capability scenario and the second standard dataset corresponding to the current availability scenario.

[0084] Calculate the similarity between the current dataset and the first standard dataset, denoted as the first similarity. Calculate the similarity between the current dataset and the second standard dataset, denoted as the second similarity.

[0085] Determine whether the first similarity is greater than the first threshold, and whether the second similarity is greater than the second threshold.

[0086] If the first similarity is greater than the first threshold and the second similarity is greater than the second threshold, the coordination capability of the target distribution network and the target microgrid is determined based on the historical comprehensive index of response capability corresponding to the current response capability scenario, the historical comprehensive index of availability corresponding to the current availability scenario, the first similarity and the second similarity.

[0087] If the first similarity is less than or equal to the first threshold, and / or the second similarity is less than or equal to the second threshold, the uncertainty impact coefficient is calculated based on the current dataset, and the coordination capability of the target distribution network and the target microgrid is determined based on the historical comprehensive index of the current response capability scenario, the historical comprehensive index of the current availability scenario, the first similarity, the second similarity, and the uncertainty impact coefficient.

[0088] In one possible implementation, the collaborative capability assessment module 23 is specifically used for: Based on the first similarity, the historical comprehensive index of response capability corresponding to the current response capability scenario is corrected to obtain the current comprehensive index of response capability for the target distribution network and the target microgrid.

[0089] The historical availability composite index corresponding to the current availability scenario is corrected based on the second similarity to obtain the current availability composite index of the target distribution network and the target microgrid.

[0090] The coordination capability of the target distribution network and the target microgrid is determined based on the current comprehensive response capability index and the current comprehensive availability index.

[0091] In one possible implementation, the collaborative capability assessment module 23 is specifically used for: Calculate the distance between the current dataset and the target standard dataset, which is the dataset in the first and second standard datasets whose similarity is less than or equal to the corresponding first or second threshold; calculate the uncertainty influence coefficient based on the distance.

[0092] In one possible implementation, if the target standard dataset is a first standard dataset and a second standard dataset, the collaborative capability assessment module 23 is specifically used for: Calculate the distance between the current dataset and the first standard dataset, and denote it as the first distance.

[0093] Calculate the distance between the current dataset and the second standard dataset, and denote it as the second distance.

[0094] The first uncertainty influence coefficient is calculated based on the first distance.

[0095] The second uncertainty influence coefficient is calculated based on the second distance.

[0096] Figure 3 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. For example... Figure 3 As shown, the electronic device 3 of this embodiment includes a processor 30 and a memory 31. The memory 31 stores a computer program 32. When the processor 30 executes the computer program 32, it implements the steps in the various method embodiments described above. Alternatively, when the processor 30 executes the computer program 32, it implements the functions of each module / unit in the various device embodiments described above.

[0097] For example, computer program 32 may be divided into one or more modules / units, which are stored in memory 31 and executed by processor 30 to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of computer program 32 in electronic device 3.

[0098] Electronic device 3 may include, but is not limited to, processor 30 and memory 31. Those skilled in the art will understand that... Figure 3 This is merely an example of electronic device 3 and does not constitute a limitation on electronic device 3. It may include more or fewer components than shown, or combine certain components, or different components. For example, electronic device 3 may also include input / output devices, network access devices, buses, etc.

[0099] For the sake of simplicity and clarity, only the above-described functional modules / units are used as examples. In practical applications, the functions described above can be assigned to different functional modules / units as needed. These modules / units can be implemented in hardware, software, or a combination of both.

[0100] In the above embodiments, the descriptions of each embodiment have their own emphasis. Parts not detailed or described in a particular embodiment can be referred to in the relevant descriptions of other embodiments. Unless otherwise specified or in conflict with logic, the terminology and / or descriptions between different embodiments are consistent and can be referenced interchangeably. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0101] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for evaluating the coordination capability between distribution networks and microgrids, characterized in that, include: Acquire current load data and current operating data of various flexibility resources in the target distribution network and target microgrid, and acquire current topology information and current environmental data of the target distribution network and target microgrid to form the current dataset; Based on the current dataset, the first scenario matching model regarding response capability, and the second scenario matching model regarding availability, the current response capability scenario and the current availability scenario of the target distribution network and the target microgrid are obtained. A similarity assessment is performed on the current dataset with the current response capability scenario and the current availability scenario. Based on the assessment results, the coordination capability of the target distribution network and the target microgrid is determined.

2. The method for evaluating the coordination capability of distribution networks and microgrids according to claim 1, characterized in that, The training process of the first scene matching model includes: Acquire multiple sets of historical coordination data for the target distribution network and the target microgrid, and acquire the historical load data and historical operation data of each flexibility resource in the target distribution network and the target microgrid at the historical coordination time corresponding to each set of historical coordination data, as well as the historical topology information and historical environmental data of the target distribution network and the target microgrid at that historical coordination time; Based on the historical coordination data of each group, calculate the historical response speed, historical regulation accuracy and historical continuous response capability of the target distribution network and the target microgrid at the corresponding historical coordination time. Based on the historical response speed, the historical regulation accuracy, and the historical continuous response capability, calculate the comprehensive index of the historical response capability of the target distribution network and the target microgrid; A first dataset is constructed by taking the historical response speed, historical adjustment accuracy, historical continuous response capability, historical response capability comprehensive index, historical load data, each of the historical operating data, historical topology information, and historical environmental data corresponding to a set of the historical collaborative data as a single data entry. Cluster the first dataset and obtain the first scene matching model based on the clustering results.

3. The method for evaluating the coordination capability of distribution networks and microgrids according to claim 1, characterized in that, The training process of the second scene matching model includes: Acquire multiple sets of historical coordination data for the target distribution network and the target microgrid, and acquire the historical load data and historical operation data of each flexibility resource in the target distribution network and the target microgrid at the historical coordination time corresponding to each set of historical coordination data, as well as the historical topology information and historical environmental data of the target distribution network and the target microgrid at that historical coordination time; Based on the historical collaborative data of each group, calculate the historical spatiotemporal available capacity and historical constraint adaptability of the target distribution network and the target microgrid at the corresponding historical collaborative moment; Based on the historical available capacity and historical constraint adaptability, calculate the comprehensive historical availability index of the target distribution network and the target microgrid; A second dataset is constructed by taking the historical spatiotemporal available capacity, historical constraint adaptability, historical availability comprehensive index, historical load data, each of the historical operational data, historical topology information, and historical environmental data corresponding to a set of the historical collaborative data as a single data entry. The second dataset is clustered, and the second scene matching model is obtained based on the clustering results.

4. The method for evaluating the coordination capability of distribution networks and microgrids according to claim 1, characterized in that, The process of obtaining the current response capability scenario and current availability scenario of the target distribution network and target microgrid based on the current dataset, a first scenario matching model regarding response capability, and a second scenario matching model regarding availability includes: Calculate the distance between the current dataset and each cluster center in the first scenario matching model, and determine the scenario with the smallest distance as the current response capability scenario of the target distribution network and the target microgrid; Calculate the distance between the current dataset and each cluster center in the second scenario matching model, and determine the scenario with the smallest distance as the current availability scenario of the target distribution network and the target microgrid.

5. The method for evaluating the coordination capability of distribution networks and microgrids according to claim 1, characterized in that, The process of evaluating the similarity between the current dataset and the current response capability and availability scenarios, and determining the coordination capability of the target distribution network and the target microgrid based on the evaluation results, includes: Obtain the first standard dataset corresponding to the current response capability scenario and the second standard dataset corresponding to the current availability scenario; Calculate the similarity between the current dataset and the first standard dataset, denoted as the first similarity; calculate the similarity between the current dataset and the second standard dataset, denoted as the second similarity. Determine whether the first similarity is greater than a first threshold, and whether the second similarity is greater than a second threshold; If the first similarity is greater than the first threshold and the second similarity is greater than the second threshold, the coordination capability of the target distribution network and the target microgrid is determined based on the historical comprehensive index of response capability corresponding to the current response capability scenario, the historical comprehensive index of availability corresponding to the current availability scenario, the first similarity, and the second similarity. If the first similarity is less than or equal to the first threshold, and / or the second similarity is less than or equal to the second threshold, the uncertainty impact coefficient is calculated based on the current dataset, and the coordination capability of the target distribution network and the target microgrid is determined based on the historical comprehensive index of response capability corresponding to the current response capability scenario, the historical comprehensive index of availability corresponding to the current availability scenario, the first similarity, the second similarity, and the uncertainty impact coefficient.

6. The method for evaluating the coordination capability of distribution networks and microgrids according to claim 5, characterized in that, The step of determining the coordination capability of the target distribution network and the target microgrid based on the historical comprehensive index of response capability corresponding to the current response capability scenario, the historical comprehensive index of availability corresponding to the current availability scenario, the first similarity, and the second similarity includes: Based on the first similarity, the historical comprehensive index of response capability corresponding to the current response capability scenario is corrected to obtain the current comprehensive index of response capability of the target distribution network and the target microgrid. Based on the second similarity, the historical availability composite index corresponding to the current availability scenario is corrected to obtain the current availability composite index of the target distribution network and the target microgrid; The coordination capability of the target distribution network and the target microgrid is determined based on the current comprehensive response capability index and the current comprehensive availability index.

7. The method for evaluating the coordination capability of distribution networks and microgrids according to claim 5, characterized in that, The calculation of the uncertainty impact coefficient based on the current dataset includes: Calculate the distance between the current dataset and the target standard dataset, wherein the target standard dataset is the dataset in the first standard dataset and the second standard dataset whose similarity is less than or equal to the corresponding first threshold or second threshold; The uncertainty impact coefficient is calculated based on the distance.

8. The method for evaluating the coordination capability of distribution networks and microgrids according to claim 7, characterized in that, If the target standard dataset is the first standard dataset and the second standard dataset, calculate the distance between the current dataset and the target standard dataset, including: Calculate the distance between the current dataset and the first standard dataset, and denote it as the first distance; Calculate the distance between the current dataset and the second standard dataset, and denote it as the second distance; The uncertainty impact coefficient is calculated based on the distance, including: Calculate the first uncertainty influence coefficient based on the first distance; The second uncertainty influence coefficient is calculated based on the second distance.

9. A device for evaluating the coordination capability of distribution networks and microgrids, characterized in that, include: The acquisition module is used to acquire the current load data and current operating data of each flexibility resource in the target distribution network and target microgrid, and to acquire the current topology information and current environmental data of the target distribution network and target microgrid to form the current dataset; The scenario matching module is used to obtain the current response capability scenario and the current availability scenario of the target distribution network and the target microgrid based on the current dataset, the first scenario matching model about response capability, and the second scenario matching model about availability. The collaborative capability assessment module is used to evaluate the similarity between the current dataset and the current response capability scenario and the current availability scenario, and to determine the collaborative capability between the target distribution network and the target microgrid based on the assessment results.

10. An electronic device, characterized in that, It includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method as described in any one of claims 1 to 8.

Images